+

WO2018191421A1 - Procédé de détermination d'endommagement de véhicule fondé sur une image, appareil et dispositif électronique - Google Patents

Procédé de détermination d'endommagement de véhicule fondé sur une image, appareil et dispositif électronique Download PDF

Info

Publication number
WO2018191421A1
WO2018191421A1 PCT/US2018/027174 US2018027174W WO2018191421A1 WO 2018191421 A1 WO2018191421 A1 WO 2018191421A1 US 2018027174 W US2018027174 W US 2018027174W WO 2018191421 A1 WO2018191421 A1 WO 2018191421A1
Authority
WO
WIPO (PCT)
Prior art keywords
damage
auto part
image
repair
auto
Prior art date
Application number
PCT/US2018/027174
Other languages
English (en)
Other versions
WO2018191421A8 (fr
Inventor
Haitao Zhang
Juan Xu
Jinlong HOU
Jian Wang
Xin Guo
Danni Cheng
Yue Hu
Bokun Wu
Yanqing Chen
Original Assignee
Alibaba Group Holding Limited
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN201710233657.6A external-priority patent/CN107392218B/zh
Application filed by Alibaba Group Holding Limited filed Critical Alibaba Group Holding Limited
Priority to JP2019523649A priority Critical patent/JP6859505B2/ja
Priority to SG11201903836QA priority patent/SG11201903836QA/en
Priority to EP18722299.7A priority patent/EP3520051A1/fr
Priority to KR1020197012653A priority patent/KR102270499B1/ko
Publication of WO2018191421A1 publication Critical patent/WO2018191421A1/fr
Publication of WO2018191421A8 publication Critical patent/WO2018191421A8/fr
Priority to PH12019500977A priority patent/PH12019500977A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance

Definitions

  • the present application relates to the field of computer image data processing technologies, and in particular, to an image-based vehicle damage determining method, apparatus, and an electronic device.
  • the alert information of the identified damaged area is mainly used by the insurance company staff to compare with damage determined by human, and serves as reference information to help the insurance company staff with damage determination and calculation.
  • the algorithm uses only an object identification algorithm commonly used in the CNN. A final determination of vehicle damage is still made by a human being. Consequently, labor and time costs are relatively high.
  • a vehicle damage determination result can vary greatly, and reliability can be relatively low.
  • the present application aims to provide an image-based vehicle damage determination method, apparatus, and an electronic device, so as to quickly, accurately and reliably detect specific information such as the part that is damaged area and degree of damage of an auto part, to provide a more accurate and reliable damage determination result, maintenance plan information for a user, and quickly and efficiently processing vehicle damage determination, thereby greatly improving user service experience.
  • An image-based vehicle damage determining method includes: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • An image-based vehicle damage determination apparatus includes: an image acquisition module, configured to obtain an auto part image corresponding to an auto part; a check module, configured to: store a constructed component damage identification model, and check the auto part image by using the component damage identification model, to determine a damaged area and a damage type of the auto part; and a damage determination processing module, configured to generate a repair plan for the auto part based on information, including the damaged area and the damage type of the auto part.
  • An image-based vehicle damage determination apparatus includes a processor and a memory configured to store an instruction that can be executed by the processor, wherein when executing the instruction, the processor implements the following operations: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information, including the damaged area and the damage type of the auto part.
  • a computer readable storage medium stores a computer instruction, and when the instruction is executed, the following steps are implemented: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • An electronic device includes a processor and a memory configured to store an instruction that can be executed by the processor, where when executing the instruction, the processor implements the following operations: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • a training model identifying information such as a damaged area and a damage type more comprehensively and reliably can be constructed, and a damaged area and a damage type corresponding to the damaged area of an auto part can be detected by using the model, so as to obtain information required for accurate and comprehensive damage determination of the auto part.
  • a repair plan for the auto part is generated by using information including the identified damaged area and the damage type, so as to provide more accurate and reliable damage determination information with a practical reference value for an insurance staff and a vehicle owner.
  • a repair plan can be automatically generated based on specific vehicle damage information, an auto part price library, and a maintenance processing method, so as to satisfy a requirement of an insurance company or a vehicle owner for quick, comprehensive, accurate, and reliable vehicle damage determination processing, improve accuracy and reliability of a vehicle damage determination processing results, and improve user service experience.
  • FIG 1 is a flowchart of an image-based vehicle damage determination method, according to an implementation of the present application.
  • FIG 2 is a schematic flowchart of an image-based vehicle damage determination method according to another implementation of the present application.
  • FIG. 3 is a schematic diagram of a network structure of a neural network for identifying an auto part image according to an implementation of the present application
  • FIG 4 is a schematic structural diagram of modules of an image-based vehicle damage determination apparatus according to an implementation of the present application.
  • FIG 5 is a schematic structural diagram of an electronic device according to an implementation of the present application.
  • FIG. 6 is a schematic diagram of a processing scenario of vehicle damage determination according to an implementation of the present application.
  • FIG. 7 is a flowchart illustrating an example of a computer-implemented method for planning vehicle repair, according to an implementation of the present disclosure.
  • FIG 1 is a flowchart of an image-based vehicle damage determination method according to an implementation of the present application.
  • the present application provides a method operation step or an apparatus structure shown in the following implementations or the accompanying drawings, the method or apparatus can include more or, after combination, fewer operation steps or module units based on a conventional or non-creative effort.
  • steps or a structure without a necessary causal relationship in logic an execution sequence of these steps or a module structure of the apparatus is not limited to the execution sequence or the module structure shown in the implementations of the present application or the accompanying drawings.
  • the method or the module structure can be performed sequentially or in parallel based on the method or the module structure shown in the implementations or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed processing implementation environment and a server cluster implementation environment).
  • the vehicle owner can take a picture of the damaged location of the vehicle by using a mobile device (such as a mobile phone) on a traffic accident scene, and then upload the picture (or image) by using the APP.
  • a mobile device such as a mobile phone
  • the vehicle owner can select or input information about an auto part such as a front bumper, a left front door, or a taillight of the vehicle.
  • a cloud server can identify a damaged area location and a damage type of the auto part in the picture based on a machine learning algorithm.
  • the cloud server can then develop a rule engine, invoke different pricing scheme databases based on repair strategy information such as vehicle model, location, and repair shop, and generate at least one repair plan for the auto part.
  • the repair plan can be returned to the vehicle owner, and the vehicle owner can quickly obtain a vehicle damage determination result.
  • the repair plan can be returned directly to the insurance company, or a repair plan can be directly displayed.
  • a person skilled in the art can understand that the spirit of the present solution can be applied to other implementation scenarios of vehicle damage determination, for example, automatic vehicle damage determination of an insurance company or a repair shop, or self-service vehicle damage determination services provided by 4S stores or other service providers.
  • FIG. 1 an implementation is shown in FIG. 1.
  • the method can include the following steps.
  • a server can obtain an auto part image of a single auto part from a client or a third-party server (such as a server of an insurance company).
  • the previous auto part images can be considered as an image of the auto part.
  • the auto part image in this implementation can be a general name of various graphics and images, generally refers to a picture having a visual effect, and can usually include a picture on a medium such as a paper, a negative, a photo, a television, a projector, or a computer screen.
  • the vehicle owner when uploading the auto part image, the vehicle owner can specify component information of the auto part image, for example, an auto part image of a front bumper, a left front door, or a taillight.
  • the client or the server side can tag information of a corresponding auto part for the obtained auto part image.
  • the auto part is usually a component on a vehicle, for example, a front bumper, a left front door, or a taillight.
  • image quality of the auto part image reaches a predetermined processing requirement. If the image quality is relatively poor, for example, the picture is obscure and cannot be identified, the auto part image can be discarded, and feedback can be returned to the mobile APP to prompt the user to consider factors such as focusing and illumination that affect definition when the user takes a picture.
  • S2. Determine a damaged area and a damage type of the auto part by parsing the auto part image using a pre-constructed auto part damage identification model.
  • the cloud server side can parse the auto part image by using the pre-constructed auto part damage identification model, to identify the damaged area and the damage type of the auto part in the image.
  • the damaged area in this implementation is usually a part that is damaged on the vehicle.
  • a damaged auto part may include a plurality of damaged areas, and each damaged area corresponds to a damage type (for example, severe scratching or mild deformation).
  • a location region of a damaged area in an image to be processed can be parsed to identify a damage type.
  • the damage type in this implementation can include types such as mild scratching, severe scratching, mild deformation, moderate deformation, severe deformation, damage, and disassembling-required check, etc.
  • a designed machine learning algorithm can be used in advance to construct a component damage identification model used to identify the damaged area and the damage type of the auto part in the image.
  • the component damage identification model can identify the damaged area and the damage type of the auto part in the auto part image.
  • the component damage identification model can use network models or transformed network models of a deep neural network, and is constructed after sample image training.
  • the component damage identification model can be constructed based on a convolutional neural network (CNN) and a region proposal network (RPN) with reference to a pooling layer, a fully connected layer, etc. Therefore, in another implementation of the method of the present application, the component damage identification model includes:
  • S201 A deep neural network constructed after sample data training and based on network models of a convolutional layer and a region proposal layer.
  • the convolutional neural network is usually a neural network mainly including a convolutional layer (CNN) with reference to other layers such as an activation layer, and is mainly used for image identification.
  • the deep neural network in this implementation can include a convolutional layer and other important layers (such as a pooling layer, a data normalization layer, and an activation layer), and is constructed with reference to a region proposal network (RPN).
  • RNN region proposal network
  • the convolution neural network usually combines a two-dimensional discrete convolution operation with an artificial neural network in image processing. The convolution operation can be used to automatically extract a feature.
  • the region proposal network can use a feature extracted from an image (of any size) as an input (a two-dimensional feature extracted by the convolutional neural network can be used), and output a set of rectangular target proposal boxes. Each box has an object score.
  • the convolutional neural network (CNN) used can be referred to as a convolutional layer (CNN)
  • a region proposal network (RPN) can be referred to as a region proposal layer (RPN).
  • the component damage identification model can further include the deep CNN constructed after sample data training and based on a transformed network model obtained after the CNN network or the RPN has been improved.
  • the model and algorithm used in the previous implementation can select the same model or algorithm.
  • a plurality of models and transformations based on the convolutional neural network and the region proposal network can be used, for example, Faster R-CNN, YOLO, and Mask-FCN.
  • the convolutional neural network (CNN) can use any CNN model, for example, ResNet, Inception, VGQ and their transformations.
  • a convolutional network (CNN) part in a neural network can use a developed network structure having a relatively good capability in object identification, for example, an Inception or ResNet network.
  • the output can be a plurality of picture regions with damaged areas, corresponding damage categories (the damage categories are used to determine damage types), and confidence (confidence is a parameter indicating a degree of authenticity of the damage type).
  • Faster R-CN , YOLO, Mask-FCN, etc. are deep neural networks that include the convolutional layer and can be used in this implementation.
  • the deep neural network used in this implementation can detect a damaged area, a damage type, and a location region of the damaged area in the auto part image with reference to the region proposal layer and the CNN layer.
  • the auto part image can be parsed by using an individual algorithm server to identify the damaged area and the damage type of the auto part in the auto part image.
  • a service server is configured to obtain the auto part image of the auto part and output a repair plan.
  • An algorithm server can also be configured to store the constructed component damage identification model, parse and identify the auto part image on the service server, and determine the damaged area and the damage type of the auto part. Certainly, the previous processing can also be done by the same server.
  • the algorithm server can generate the repair plan for the auto part based on the previous information and a predetermined processing rule. For example, a left front panel of a Bl -model vehicle of a manufacturer Al in 2016 is mildly deformed and requires metal beating processing; a left front door of a B2-model vehicle of a manufacturer A2 in 2010 is severely scratched and severely deformed and requires replacement processing; a front bumper of a B3-model vehicle of a manufacturer A3 in 2013 is mildly scratched and requires spray painting, and a left headlight needs to be disassembled for inspection, etc.
  • the repair plan can further include information about an estimated price for auto part repair, so that the user can learn repair price information, select a more suitable repair option, satisfy user requirement, and improve user experience. Therefore, in another implementation of the method in the present application, the method can further include the following step:
  • the repair plan can further include an estimated repair price corresponding to the repair strategy, and the estimated repair price is an estimated repair price of the auto part that is calculated based on the information including the damaged area, the damage type, and the repair strategy of the auto part, price of auto parts included in the repair strategy and the cost of the repair service.
  • FIG 2 is a schematic flowchart of another implementation of the method in the present application.
  • a calculation rule can be designed, to invoke different price libraries based on the information about the repair strategy such as a model of the auto part, a selected repair location of the auto part, a repair shop (4S store or a common integrated repair shop), and generate the repair plan for the auto part that includes a preliminary repair processing method and a corresponding estimated repair price.
  • the information about the repair strategy can be selected by the user. For example, the user can select a repair location (for example, based on a city-level or district-level division), select a 4S store or an integrated repair shop, and input a vehicle brand and model.
  • the algorithm server can obtain the following repair plan based on information about the repair strategy of the auto part and the identified damaged area and damage type:
  • a front bumper of a B3-model vehicle of the manufacturer A3 in 2013 is mildly scratched and requires spray painting, and estimated repair cost at a local 4S store is 600 yuan RMB.
  • information such as a damaged auto part, a damage type, and a degree of damage of the vehicle on an accident scene can also be obtained based on claim experience of a conventional vehicle insurance company, and an engine module is created with reference to information such as repair hours and costs at the 4S store.
  • an APP used for actual processing identifies the damaged area and the damage type of the auto part
  • the engine module can be invoked to output a damage determination result for the auto part.
  • the information about the repair strategy can be modified or replaced. For example, if the user can select the 4S store for repair, there is a corresponding repair strategy and a corresponding repair plan. If the user selects the integrated repair shop for repair, there is another corresponding repair strategy, and another repair plan is generated accordingly.
  • damage determination can usually include two pieces of information: damage evaluation and price evaluation.
  • damage determination can be the damage evaluation. If the output repair plan for the auto part includes information about repair costs, both the damage evaluation and the price evaluation are performed. The two repair plans included in vehicle damage determination processing.
  • a training model more comprehensively and reliably identifying information such as a damaged area and a damage type can be constructed, and a damaged area and a damage type corresponding to the damaged area of an auto part can be detected by using the model, so as to obtain information needed for accurate and comprehensive damage determination of the auto part.
  • a repair plan for the auto part is generated by using information including the identified damaged area and the damage type, so as to provide more accurate and reliable damage determination information with a practical reference value for an insurance staff and a vehicle owner.
  • a repair plan and estimated repair costs can be automatically generated based on more specific vehicle damage information, an auto part price library, and a repair processing method, so as to satisfy a requirement of an insurance company or a vehicle owner for quick, comprehensive, accurate, and reliable vehicle damage determination processing, improve accuracy and reliability of a vehicle damage determination processing result, and improve user service experience.
  • the obtained auto part image can include a plurality of damaged areas.
  • the deep neural network model can be set to identify each damaged area and a damage degree (a damage type) of each damaged area.
  • the component damage identification model is configured to:
  • S200 Identify, based on the auto part image, the damaged areas of the auto part and one or more damage types corresponding to the damaged areas.
  • S210 Select a damaged area corresponding to a damage type of the one or more damage types that has a highest damage degree as the damaged area of the auto part. Correspondingly, the damage type with the highest damage degree is the determined damage type of the auto part.
  • Each damage type usually corresponds to a respective repair plan.
  • severe deformation corresponds to replacement
  • mild deformation requires metal beating
  • mild scratching requires spray painting.
  • one repair plan can be eventually output for one component.
  • a repair method for a part that is damaged the worst is used as a final processing method for the entire component.
  • an auto part of the vehicle can be considered as a whole.
  • one repair plan may be selected to repair all the damages. For example, a damage type of a damaged area is severe damage, and replacement is required; a damage type of another damaged area is moderate deformation and requires metal beating. In this case, replacement can be performed without the need of metal beating.
  • a plurality of damaged areas in a single auto part image can be identified during model training.
  • a picture is used as input, a plurality of picture regions and corresponding damage categories are output.
  • the marked data marks a region and an image of a corresponding type, and can be obtained by manually marking a real vehicle damage picture.
  • An input of the neural network is a picture, and the output region is related to the number of damaged areas in the picture. Specifically, for example, if there is one damaged area, one picture region can be the output; if there are K damaged areas, K picture regions can be the output; and if there is no damaged area, no picture region is output.
  • the auto part image is input to the neural network. If there are a plurality of damaged areas, a plurality of picture regions including the damaged areas are detected, the picture regions are parsed, damage types of the picture regions are determined, and damaged areas and damage types corresponding to the picture regions are separately output. Further, in this implementation, a damaged area corresponding to a damage type that is in the damage types and that indicates a highest damage degree can be selected as the damaged area of the auto part. Correspondingly, the damage type with the highest damage degree is the determined damage type of the auto part.
  • FIG 3 is a schematic diagram of a network structure of a neural network for checking an auto part image according to an implementation of the present application.
  • the parsing of the auto part image using a constructed component damage identification model to determine a damaged area and a damage type of the auto part includes the following steps:
  • S20 Separately check the auto part images by using the component damage identification model, to determine a damaged area and a damage type of each auto part image.
  • the parsing step of the method can be customized. For example, to determine the damaged area and the damage type of each auto part image, a damage type with the highest damage degree can be selected as an output damage type and a corresponding damaged area of the auto part. For example, assume that two pictures of a rear bumper are obtained, one taken from the side and the other taken from the front. A parsing result of identifying the picture taken from the front is that the rear bumper is mildly deformed on the right. However, a parsing result obtained by identifying the picture taken from the side is that the rear bumper is damaged with a damage type more severe than mild deformation. The picture shot from the front is not comprehensive, and the picture shot from the side shows a more real damage status of the rear bumper. Therefore, the parsing results of the two pictures can be combined by using the solution provided in this implementation, that the rear bumper is damaged, so that the output result is more reliable.
  • the present application further provides an image-based vehicle damage determination apparatus.
  • the apparatus can include a system (including a distributed system), software (an application), a module, a component, a server, a client, etc. that use the method according to the present application.
  • the apparatus can further include necessary implementation hardware.
  • the apparatus according to an implementation of the present application is described in the following descriptions. Implementation schemes of the apparatus for problem resolution are similar to that of the method. Therefore, for specific implementation of the apparatus in the present application, references can be made to the implementation of the method. Repetitive details are not separately described.
  • FIG. 4 is a schematic diagram of modules of an image-based vehicle damage determination apparatus, according to an implementation of the present application.
  • the apparatus can include: an image acquisition module 101, configured to obtain an auto part image corresponding to an auto part; a check module 102, configured to: store a constructed component damage identification model, and check the auto part image by using the component damage identification model, to determine a damaged area and a damage type of the auto part; and a damage determination processing module 103, configured to generate a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • the apparatus can be further implemented in another way.
  • the component damage identification model can be a deep neural network constructed after sample data training and based on network models of a convolutional layer and a region proposal layer.
  • the apparatus can further include a repair strategy acquisition module, or directly use the damage determination processing module 103, to obtain information about a repair strategy of the auto part and generate a repair plan including an estimated repair price.
  • a repair strategy acquisition module or directly use the damage determination processing module 103, to obtain information about a repair strategy of the auto part and generate a repair plan including an estimated repair price.
  • the method or apparatus in the present application can be implemented by using a computer program and necessary hardware, and can be configured in a device, so that an image-based vehicle damage determination result can be quickly and reliably output. Therefore, the present application can further provide an image-based vehicle damage determination apparatus that can be used on the server side, and can include a processor and a memory configured to store an instruction that can be executed by the processor. When executing the instruction, the processor implements the following operations: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • the apparatus can further include other processing hardware such as a GPU (Graphics Processing Unit).
  • the processor when executing the instruction, can further implement the following operation: obtaining information about a repair strategy of the auto part.
  • the repair plan can further include an estimated repair price corresponding to the repair strategy, and the estimated repair price is an estimated repair price of the auto part that is calculated based on the information including the damaged area, the damage type, and the repair strategy of the auto part and pricing information corresponding to a product and/or a repair service of the auto part in the repair strategy.
  • an instruction of the constructed component damage identification model can include an algorithm processing instruction of a deep neural network constructed after sample data training and based on network models of a convolutional layer and a region proposal layer.
  • the processor when executing the instruction, if confirming that the currently processed auto part image includes at least two damaged areas, the processor executes the instruction of the component damage identification model to implement the following operations: identifying, based on the auto part image, the damaged areas of the auto part and damage types corresponding to the damaged areas; and selecting a damaged area corresponding to a damage type that is in the damage types and that indicates a highest damage degree as the damaged area of the auto part, where correspondingly, the damage type with the highest damage degree is the determined damage type of the auto part.
  • the checking, by the processor, the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part includes: separately checking the auto part images by using the component damage identification model, to determine a damaged area and a damage type of each auto part image; and performing, based on a predetermined rule, combined selection on the damaged areas and the damage types corresponding to the auto part images, to determine a result of the damaged area and the damage type of the auto part.
  • a training model identifying information such as a damaged area and a damage type more comprehensively and reliably can be constructed, and a damaged area and a damage type corresponding to the damaged area of an auto part can be detected by using the model, so as to obtain information required for accurate and comprehensive damage determination of the auto part.
  • a repair plan for the auto part is generated by using information including the identified damaged area and the damage type, so as to provide more accurate and reliable damage determination information with a practical reference value for an insurance staff and a vehicle owner.
  • a repair plan and estimated repair costs can be automatically generated based on more specific vehicle damage information, an auto part price library, and a repair processing method, so as to satisfy a requirement of an insurance company or a vehicle owner for quick, comprehensive, accurate, and reliable vehicle damage determination processing, improve accuracy and reliability of a vehicle damage determination processing result, and improve user service experience.
  • the method or apparatus in the previous implementations of the present application can implement service logic by using a computer program and record the service logic in a storage medium, and the storage medium can be read and executed by a computer, so as to implement effects of the solutions described in the implementations of the present application. Therefore, the present application further provides a computer readable storage medium.
  • the computer readable storage medium stores a computer instruction, and when the instruction is executed, the following steps are implemented: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • the computer readable storage medium can include a physical apparatus configured to store information.
  • the apparatus usually stores the information in an electric, magnetic, optical, etc. way after the information is digitized.
  • the computer readable storage medium in this implementation can include an apparatus for storing information in an electric way, for example, various memories such as a RAM and a ROM; an apparatus for storing information in a magnetic way, for example, a hard disk, a floppy disk, a magnetic tape, a core memory, a bubble memory, and a USB flash disk; and an apparatus for storing information in an optical way, for example, a CD or a DVD.
  • a quantum memory and a graphene memory such as a quantum memory and a graphene memory.
  • the apparatus or method can be used in an electronic device for image processing, so as to implement quick image-based vehicle damage determination processing.
  • the electronic device can be a separate server, or can be a system cluster including a plurality of application servers, or can be a server in a distributed system.
  • FIG 5 is a schematic structural diagram of an electronic device, according to an implementation of the present application.
  • the electronic device can include a processor and a memory configured to store an instruction that can be executed by the processor.
  • the processor When executing the instruction, the processor implements the following operations: obtaining an auto part image corresponding to an auto part; checking the auto part image by using a constructed component damage identification model, to determine a damaged area and a damage type of the auto part; and generating a repair plan for the auto part based on information including the damaged area and the damage type of the auto part.
  • FIG 6 is a schematic diagram of a processing scenario of vehicle damage determination according to an implementation of the present application.
  • a client in FIG 6 is a mobile terminal of a user, and can be a PC or another terminal device in another implementation scenario.
  • the image-based vehicle damage determination method and apparatus, and the electronic device provided in the present application a damaged area and a damage type are detected by using a deep learning technology, the damaged area can be accurately located by using an image matching method, and damage determination accuracy can be improved by using a multi-image check result.
  • An image check technology, an auto part price library, and a repair rule are combined to automatically generate a repair plan and price evaluation.
  • a repair plan and estimated repair costs can be automatically generated based on more specific vehicle damage information, an auto part price library, and a repair processing method, so as to satisfy the requirement of an insurance company or a vehicle owner for quick, comprehensive, accurate, and reliable vehicle damage determination processing, improve accuracy and reliability of a vehicle damage determination, and improve user service experience.
  • the present application includes descriptions of data model construction and data acquisition, exchange, calculation, and determination such as image quality processing, a convolution neural network, a region proposal network, and a deep neural network generated by using a combination of the convolution neural network and the region proposal network, a calculation method of an estimated repair price, and a processing method of a plurality of auto part images of a same component
  • the present application is not limited to complying with an industry communications standard, a standard data model, a computer processing and storage rule, or a case described in the implementations of the present application.
  • Some industry standards or implementation solutions that are slightly modified in a self-defined way or based on implementations described in the implementations can also implement same, equivalent, similar, or deformed but expected implementation effects. Implementations obtained by using these modifications or transformed methods of data acquisition, storage, determination, and processing can still fall within the scope of the optional implementations of the present application.
  • a technology for example, improvement in hardware (for example, improvement in a circuit structure such as a diode, a transistor, or a switch) or improvement in software (improvement in a method procedure) can be clearly determined.
  • improvement in many methods today can be considered as direct improvement in a hardware circuit structure.
  • a designer often obtains a corresponding hardware circuit structure by programming an improved method into a hardware circuit. Therefore, it cannot be said that improvement in a method procedure cannot be implemented by using a hardware entity module.
  • a programmable logic device for example, a field programmable gate array (FPGA)
  • FPGA field programmable gate array
  • the designer "integrates" a digital system into a PLD by programming, and does not need a chip manufacturer to design and manufacture a dedicated integrated circuit chip.
  • an integrated circuit chip is not currently manually manufactured, and this programming is mostly implemented by using "logic compiler” software. It is similar to a software compiler used during program development and writing. Original code waiting to be compiled also needs to be written with a specific programming language. It is called a hardware description language (HDL).
  • HDL hardware description language
  • HDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog are most frequently used currently.
  • a person skilled in the art should also understand that a method procedure only needs to be logically programmed by using the previous hardware description languages and programmed into an integrated circuit, to obtain a hardware circuit that implements the logical method procedure.
  • the controller can be implemented in any suitable way.
  • the controller can be implemented in a form of a microprocessor, a processor, a computer readable medium storing computer readable program code (for example, hardware or firmware) that can be executed by the processor (microprocessor), a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller.
  • the controller includes but is not limited to the following microcontrollers: ARC 625D, Atmel AT91 SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320.
  • a memory controller can be implemented as a part of control logic of the memory.
  • the controller can be considered as a hardware component, and an apparatus that is included in the controller and configured to implement various functions can also be considered as a structure in the hardware component.
  • an apparatus configured to implement various functions can be considered as both a software module implementing the method and a structure in a hardware component.
  • the system, apparatus, module, or unit described in the previous implementations can be specifically implemented by a computer chip or an entity, or implemented by a product having a specific function.
  • a typical implementation device is a computer.
  • the computer can be a personal computer, a laptop computer, an in-vehicle human-computer interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an e-mail device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
  • step sequence listed in the implementations is merely one of a plurality of step execution sequences, and does not represent a unique execution sequence.
  • steps can be performed sequentially or in parallel based on the method shown in the implementations or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment).
  • the apparatus is described by dividing the apparatus into various modules in terms of functions.
  • the functions of the modules can be implemented in one or more pieces of software and/or hardware, or a plurality of submodules or subunits implementing a same function can be jointly implemented.
  • the described apparatus implementation is merely an example.
  • the unit division is merely logical function division and can be other division in actual implementation.
  • a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not performed.
  • the displayed or discussed mutual couplings or direct couplings or communication connections can be implemented by using some interfaces.
  • the indirect couplings or communication connections between the apparatus or units can be implemented in electronic, mechanical, or other forms.
  • the controller can be considered as a hardware component, and an apparatus that is included in the controller and configured to implement various functions can also be considered as a structure in the hardware component.
  • an apparatus configured to implement various functions can be considered as both a software module implementing the method and a structure in a hardware component.
  • These computer program instructions can be provided for a general-purpose computer, a dedicated computer, an embedded processor, or a processor of any other programmable data processing device to generate a machine, so that the instructions executed by the computer or the processor of any other programmable data processing device generate an apparatus for implementing a specific function in one or more processes in the flowcharts and/or in one or more blocks in the block diagrams.
  • These computer program instructions can be stored in a computer readable memory that can instruct the computer or any other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable memory generate an artifact that includes an instruction apparatus.
  • the instruction apparatus implements a specific function in one or more processes in the flowcharts and/or in one or more blocks in the block diagrams.
  • the computing device includes one or more central processing units (CPU), an input/output interface, a network interface, and a memory.
  • CPU central processing units
  • input/output interface input/output interface
  • network interface network interface
  • memory a memory
  • the memory can include a non-persistent memory, a random access memory (RAM), and/or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM) in a computer readable medium.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • the computer readable medium includes a persistent medium and a non-persistent medium, or a movable medium and an immovable medium that can store information by using any method or technology.
  • the information can be a computer readable instruction, a data structure, a program module, or other data.
  • the computer storage medium includes but is not limited to a phase change memory (PRAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a random access memory (RAM) of another type, a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or another memory technology, a compact disc read-only memory (CD-ROM), a digital versatile disc (DVD) or other optical storage, a cassette magnetic tape, a tape or disk storage device or another magnetic storage device or any other non-transmission medium that can be configured to store information that can be accessed by a computing device.
  • the computer readable medium does not include transitory media, for example, a modulated data signal and carrier.
  • the implementations of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can use a form of hardware only implementations, software only implementations, or implementations with a combination of software and hardware. Moreover, the present application can use a form of a computer program product that is implemented on one or more computer-usable storage media (including but not limited to a disk memory, a CD-ROM, an optical memory, and the like) that include computer-usable program code.
  • computer-usable storage media including but not limited to a disk memory, a CD-ROM, an optical memory, and the like
  • the present application can be described in a general context of a computer executable instruction executed by a computer, for example, a program module.
  • the program module includes a routine, a program, an object, a component, a data structure, etc. for executing a specific task or implementing a specific abstract data type.
  • the present application can also be practiced in a distributed computing environment that tasks are performed by remote processing devices that are connected by using a communications network.
  • the program module can be in both local and remote computer storage media including storage devices.
  • FIG. 7 is a flowchart illustrating an example of a computer-implemented method 700 for generating vehicle repair plan, according to an implementation of the present disclosure.
  • method 700 can be performed, for example, by any system, environment, software, and hardware, or a combination of systems, environments, software, and hardware, as appropriate.
  • various steps of method 700 can be run in parallel, in combination, in loops, or in any order.
  • vehicle damage data is received.
  • the vehicle can include any type of private or public vehicle, such as a car, a truck, a boat, a train, a helicopter, and/or an airplane.
  • the vehicle damage data is received from a user, such as a vehicle operator or a vehicle owner.
  • the vehicle operator can take one or more pictures (or images) of the damaged location of the vehicle by using a mobile device (such as a mobile phone) at an accident scene involving the damaged vehicle.
  • the vehicle operator can directly upload the pictures or transmit the pictures to the vehicle owner to upload them.
  • the user can access an application configured to support vehicle repair to upload the acquired pictures.
  • the application can be configured to automatically process the images to minimize the amount of transmitted data to minimize bandwidth requirements.
  • the image processing can include filtering the images to delete features (e.g., background features) that are irrelevant for damage identification.
  • the image processing can include conversion to gray scale images to minimize transmission bandwidth requirements.
  • the image processing can include compression to a predetermined file size to minimize transmission bandwidth requirements.
  • the user can provide a user identifier (e.g., name and a password) and data associated to the uploaded pictures.
  • the data can include indication of the damaged auto part (e.g., a front bumper, a left front door, or a taillight of the vehicle), the vehicle owner, insurance information, insurance information of other parties associated to the damaged vehicle, accident conditions, location and time of accident. From 702, method 700 proceeds to 704.
  • vehicle damage data is processed to determine whether the data quality is acceptable and sufficient. If the vehicle damage data is below a quality threshold or portions of the vehicle damage data are missing, from 704, method 700 proceeds to 706.
  • additional vehicle damage data are requested from the user.
  • the user can be instructed to provide additional pictures that conform to particular standards that enable image processing.
  • the user can be instructed to provide additional data associated to the uploaded pictures. From 706, method 700 returns to 702.
  • the received vehicle damage data is processed to retrieve user information based on the user identifier and to identify one or more damaged area locations respective one or more damage types of the auto parts based on a particular model.
  • the model can be configured to perform one or more image processing techniques to parse the vehicle image by using the pre-constructed vehicle part damage identification model to identify the damaged area and the damage type of the vehicle part in the image.
  • the damaged area includes a part that is damaged on the vehicle.
  • a damaged vehicle part may include a plurality of damaged areas, and each damaged area corresponds to a damage type (for example, severe scratching or mild deformation).
  • a location region of a damaged area in an image to be processed can be parsed to identify a damage type.
  • the damage type can include mild scratching, severe scratching, mild deformation, moderate deformation, severe deformation, damage, and disassembling-required check.
  • the damage type can be quantified using scores (e.g., 1, 2, 3) to differentiate between mild, moderate and severe damages.
  • the vehicle part damage identification model can include a machine-learning algorithm, a convolutional neural network (CNN), and a region proposal network (RPN), as described with reference to FIGS. 1-3.
  • damage identification can include generation of damage ranking based on severity of damage. For example, if the vehicle includes multiple damaged areas, the overall damage of the vehicle can be ranked using the damage scores of the damaged areas. From 708, method 700 proceeds to 710.
  • a repair plan is generated based on the identified damaged area locations and damage types.
  • the repair plan can be generated using a rule engine.
  • the rule engine can invoke different pricing scheme databases based on a repair strategy associated to the vehicle model, location, and available repair shops, to generate, based on a set of rules, at least one repair plan for the damaged vehicle part including the repair services that can remedy the identified damage.
  • the rules can include front-end rules and back-end rules.
  • the front-end rules can indicate contract requirements, such as a minimum type of information type necessary to determine a repair plan. These contract-based features may include labor rates, chargeable hours per particular task, or any other aspect of the work covered by the repair plan.
  • the back-end rules can indicate whether the repair plan aligns with the identified damage (e.g., in the case of a front-end collision, the system would flag a rear tail light assembly indicated as needing repair).
  • the repair plan can include cost estimates and time estimates corresponding to possible repair services and locations.
  • generating the repair plan includes transmitting assignment data one or more vehicle repair shops as part of the first notice of loss (FNOL) process to generate assignment estimates.
  • FNOL first notice of loss
  • Assignment data may include, but not be limited to, damage information, customer name, contact information, insurance claim number, assignment date, loss date, loss type, loss type detail, loss description, current vehicle location, location where vehicle may be sent, deductible amount, vehicle type, year/make/model, vehicle identification number (VIN), license plate number, towing company information, damage information, prior damage information, and vehicle safety status (drivable/non-drivable). From 710, method 700 proceeds to 712.
  • the repair plan is transmitted to the user and/or an insurer associated to the vehicle.
  • the repair plan transmission can include generating a repair plan code interpretable by the application configured to support the vehicle repair.
  • the plan code can be formatted to minimize the amount of transmitted data to minimize bandwidth requirements and to increase the speed of the visualization process.
  • the application can be configured to generate an alert for the user to indicate that the repair plan is ready to be reviewed.
  • the application can be configured to display the repair plan for the user of the mobile device on a graphical user interface of the application. From 712, method 700 proceeds to 714.
  • an approval of the repair plan can be received from the user and/or the insurer.
  • the approval of the repair plan can indicate if the financial responsibility is accepted by the user, the insurer, and/or a third party.
  • the approval of the repair plan can include a selection of a repair shop and at least a portion of the possible repair services listed in the proposed repair plan.
  • the approval of the repair plan can include a preferred timing to initiate the repair plan. From 714, method 700 proceeds to 716.
  • the repair plan in response to receiving the approval of the repair plan, the repair plan is initiated. Initiating the repair plan can include transmitting work assignment data a selected vehicle repair shop to conduct repair operations.
  • An advantage of communication with the vehicle repair shop is the ability to offer real-time updates when any of the information changes during the course of the claim and/or repair and may expedite the repair for the customer.
  • the implementations of the present disclosure can improve corresponding data sharing efficiency, while reducing computing resources by minimizing the amount of transmitted data to minimize bandwidth requirements and to increase the speed of vehicle repair plan generation process.
  • Embodiments and the operations described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification or in combinations of one or more of them.
  • the operations can be implemented as operations performed by a data processing apparatus on data stored on one or more computer-readable storage devices or received from other sources.
  • a data processing apparatus, computer, or computing device may encompass apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, a system on a chip, or multiple ones, or combinations, of the foregoing.
  • the apparatus can include special purpose logic circuitry, for example, a central processing unit (CPU), a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC).
  • CPU central processing unit
  • FPGA field programmable gate array
  • ASIC application-specific integrated circuit
  • the apparatus can also include code that creates an execution environment for the computer program in question, for example, code that constitutes processor firmware, a protocol stack, a database management system, an operating system (for example an operating system or a combination of operating systems), a cross-platform runtime environment, a virtual machine, or a combination of one or more of them.
  • the apparatus and execution environment can realize various different computing model infrastructures, such as web services, distributed computing and grid computing infrastructures.
  • a computer program (also known, for example, as a program, software, software application, software module, software unit, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment.
  • a program can be stored in a portion of a file that holds other programs or data (for example, one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (for example, files that store one or more modules, sub-programs, or portions of code).
  • a computer program can be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
  • Processors for execution of a computer program include, by way of example, both general- and special-purpose microprocessors, and any one or more processors of any kind of digital computer.
  • a processor will receive instructions and data from a read-only memory or a random-access memory or both.
  • the essential elements of a computer are a processor for performing actions in accordance with instructions and one or more memory devices for storing instructions and data.
  • a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data.
  • a computer can be embedded in another device, for example, a mobile device, a personal digital assistant (PDA), a game console, a Global Positioning System (GPS) receiver, or a portable storage device.
  • PDA personal digital assistant
  • GPS Global Positioning System
  • Devices suitable for storing computer program instructions and data include non-volatile memory, media and memory devices, including, by way of example, semiconductor memory devices, magnetic disks, and magneto-optical disks.
  • the processor and the memory can be supplemented by, or incorporated in, special-purpose logic circuitry.
  • Mobile devices can include handsets, user equipment (UE), mobile telephones (for example, smartphones), tablets, wearable devices (for example, smart watches and smart eyeglasses), implanted devices within the human body (for example, biosensors, cochlear implants), or other types of mobile devices.
  • the mobile devices can communicate wirelessly (for example, using radio frequency (RF) signals) to various communication networks (described below).
  • RF radio frequency
  • the mobile devices can include sensors for determining characteristics of the mobile device's current environment.
  • the sensors can include cameras, microphones, proximity sensors, GPS sensors, motion sensors, accelerometers, ambient light sensors, moisture sensors, gyroscopes, compasses, barometers, fingerprint sensors, facial recognition systems, RF sensors (for example, Wi-Fi and cellular radios), thermal sensors, or other types of sensors.
  • the cameras can include a forward- or rear-facing camera with movable or fixed lenses, a flash, an image sensor, and an image processor.
  • the camera can be a megapixel camera capable of capturing details for facial and/or iris recognition.
  • the camera along with a data processor and authentication information stored in memory or accessed remotely can form a facial recognition system.
  • the facial recognition system or one-or-more sensors for example, microphones, motion sensors, accelerometers, GPS sensors, or RF sensors, can be used for user authentication.
  • a computer having a display device and an input device, for example, a liquid crystal display (LCD) or organic light-emitting diode (OLED)/virtual-reality (VR)/augmented-reality (AR) display for displaying information to the user and a touchscreen, keyboard, and a pointing device by which the user can provide input to the computer.
  • LCD liquid crystal display
  • OLED organic light-emitting diode
  • VR virtual-reality
  • AR pointing device
  • Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, for example, visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input.
  • a computer can interact with a user by sending documents to and receiving documents from a device that is used by the user; for example, by sending web pages to a web browser on a user's client device in response to requests received from the web browser
  • Embodiments can be implemented using computing devices interconnected by any form or medium of wireline or wireless digital data communication (or combination thereof), for example, a communication network.
  • interconnected devices are a client and a server generally remote from each other that typically interact through a communication network.
  • a client for example, a mobile device, can carry out transactions itself, with a server, or through a server, for example, performing buy, sell, pay, give, send, or loan transactions, or authorizing the same.
  • Such transactions may be in real time such that an action and a response are temporally proximate; for example an individual perceives the action and the response occurring substantially simultaneously, the time difference for a response following the individual's action is less than 1 millisecond (ms) or less than 1 second (s), or the response is without intentional delay taking into account processing limitations of the system.
  • ms millisecond
  • s 1 second
  • Examples of communication networks include a local area network (LAN), a radio access network (RAN), a metropolitan area network (MAN), and a wide area network (WAN).
  • the communication network can include all or a portion of the Internet, another communication network, or a combination of communication networks.
  • Information can be transmitted on the communication network according to various protocols and standards, including Long Term Evolution (LTE), 5G, IEEE 802, Internet Protocol (IP), or other protocols or combinations of protocols.
  • LTE Long Term Evolution
  • 5G Fifth Generation
  • IEEE 802 Internet Protocol
  • IP Internet Protocol
  • the communication network can transmit voice, video, biometric, or authentication data, or other information between the connected computing devices.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Image Analysis (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)

Abstract

La présente invention concerne un procédé et un appareil de détermination d'endommagement de véhicule fondé sur une image, ainsi qu'un dispositif électronique. Le procédé consiste : à obtenir une image de pièce d'automobile correspondant à une pièce d'automobile ; à vérifier l'image de pièce d'automobile à l'aide d'un modèle d'identification de détérioration de composant construit, afin de déterminer une zone endommagée et un type de détérioration de la pièce d'automobile ; et à générer un plan de réparation de la pièce d'automobile en fonction d'informations comprenant la zone endommagée et le type de détérioration de la pièce d'automobile. Selon les modes de réalisation de la présente invention, un traitement de détermination d'endommagement de véhicule peut être exécuté rapidement, avec précision et de manière fiable, et un procédé de maintenance après la détermination de l'endommagement peut être rapidement fourni à un utilisateur, de façon à améliorer considérablement l'expérience d'entretien de l'utilisateur.
PCT/US2018/027174 2017-04-11 2018-04-11 Procédé de détermination d'endommagement de véhicule fondé sur une image, appareil et dispositif électronique WO2018191421A1 (fr)

Priority Applications (5)

Application Number Priority Date Filing Date Title
JP2019523649A JP6859505B2 (ja) 2017-04-11 2018-04-11 画像に基づく車両損傷判定方法、装置および電子デバイス
SG11201903836QA SG11201903836QA (en) 2017-04-11 2018-04-11 Image-based vehicle damage determining method, apparatus, and electronic device
EP18722299.7A EP3520051A1 (fr) 2017-04-11 2018-04-11 Procédé de détermination d'endommagement de véhicule fondé sur une image, appareil et dispositif électronique
KR1020197012653A KR102270499B1 (ko) 2017-04-11 2018-04-11 이미지 기반의 차량 손상 판정 방법과 장치, 및 전자기기
PH12019500977A PH12019500977A1 (en) 2017-04-11 2019-04-30 Image-based vehicle damage determining method, apparatus, and electronic device

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US15/950,660 2017-04-11
CN201710233657.6 2017-04-11
CN201710233657.6A CN107392218B (zh) 2017-04-11 2017-04-11 一种基于图像的车辆定损方法、装置及电子设备
US15/950,660 US20180293664A1 (en) 2017-04-11 2018-04-11 Image-based vehicle damage determining method and apparatus, and electronic device

Publications (2)

Publication Number Publication Date
WO2018191421A1 true WO2018191421A1 (fr) 2018-10-18
WO2018191421A8 WO2018191421A8 (fr) 2019-02-28

Family

ID=62111206

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2018/027174 WO2018191421A1 (fr) 2017-04-11 2018-04-11 Procédé de détermination d'endommagement de véhicule fondé sur une image, appareil et dispositif électronique

Country Status (1)

Country Link
WO (1) WO2018191421A1 (fr)

Cited By (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109697429A (zh) * 2018-12-27 2019-04-30 睿驰达新能源汽车科技（北京）有限公司 一种确定车损的方法及装置
CN109871770A (zh) * 2019-01-17 2019-06-11 平安城市建设科技(深圳)有限公司 房产证识别方法、装置、设备及存储介质
CN110428403A (zh) * 2019-07-22 2019-11-08 宝能汽车有限公司 验车方法及电子装置
CN110619279A (zh) * 2019-08-22 2019-12-27 天津大学 一种基于跟踪的路面交通标志实例分割方法
JP2020086762A (ja) * 2018-11-21 2020-06-04 本田技研工業株式会社 評価システム、評価方法、およびプログラム
WO2020140684A1 (fr) * 2019-01-02 2020-07-09 阿里巴巴集团控股有限公司 Procédé et dispositif d'évaluation de modèle d'identification de dommages de véhicule
CN112016710A (zh) * 2020-08-25 2020-12-01 中车青岛四方机车车辆股份有限公司 轨道车辆维修策略的确定方法、装置和轨道车辆
WO2021001337A1 (fr) * 2019-07-03 2021-01-07 Ocado Innovation Limited Appareil et procédé de détection de dommages
WO2021011898A1 (fr) * 2019-07-18 2021-01-21 Apkudo, Llc Inspection ou réparation de dispositifs physiques
CN113344478A (zh) * 2021-08-06 2021-09-03 捷尔杰（天津）设备有限公司 离散生产线连续配料方法、装置、电子设备及存储介质
CN114565474A (zh) * 2022-03-21 2022-05-31 邦邦汽车销售服务(北京)有限公司 一种汽车零件选取方法、终端设备和存储介质
CN114792273A (zh) * 2022-05-12 2022-07-26 中国平安财产保险股份有限公司 出险车定损方法、装置、计算机设备及可读存储介质
JP2022537857A (ja) * 2018-12-31 2022-08-31 アジャイルソーダ インコーポレイテッド ディープラーニングに基づいた自動車部位別の破損程度の自動判定システムおよび方法
CN115345331A (zh) * 2022-08-18 2022-11-15 浙江安易信科技有限公司 一种基于物联网的工单全过程分配跟踪管理系统
US11562570B2 (en) 2020-10-06 2023-01-24 Ford Global Technologies, Llc Vehicle damage identification and incident management systems and methods
US11631165B2 (en) * 2020-01-31 2023-04-18 Sachcontrol Gmbh Repair estimation based on images
US12002192B2 (en) 2021-11-16 2024-06-04 Solera Holdings, Llc Transfer of damage markers from images to 3D vehicle models for damage assessment
JP7670628B2 (ja) 2019-06-03 2025-04-30 イーストマン・パフォーマンス・フィルムズ・エルエルシー パターンを組み立て、窓用フィルムおよび塗装保護フィルムを切り取り貼り付けるためのシステムおよび方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005109263A1 (fr) * 2004-05-11 2005-11-17 Fausto Siri Procede et systeme permettant d'analyser des deformations dans des vehicules a moteur
CN105678622A (zh) 2016-01-07 2016-06-15 平安科技（深圳）有限公司 车险理赔照片的分析方法及系统

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005109263A1 (fr) * 2004-05-11 2005-11-17 Fausto Siri Procede et systeme permettant d'analyser des deformations dans des vehicules a moteur
CN105678622A (zh) 2016-01-07 2016-06-15 平安科技（深圳）有限公司 车险理赔照片的分析方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SHAOQING REN ET AL: "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 6 January 2016 (2016-01-06), pages 1 - 1, XP055480920, Retrieved from the Internet <URL:https://arxiv.org/pdf/1506.01497.pdf> [retrieved on 20180604], DOI: 10.1109/TPAMI.2016.2577031 *

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2020086762A (ja) * 2018-11-21 2020-06-04 本田技研工業株式会社 評価システム、評価方法、およびプログラム
CN109697429A (zh) * 2018-12-27 2019-04-30 睿驰达新能源汽车科技（北京）有限公司 一种确定车损的方法及装置
JP2022537857A (ja) * 2018-12-31 2022-08-31 アジャイルソーダ インコーポレイテッド ディープラーニングに基づいた自動車部位別の破損程度の自動判定システムおよび方法
JP7277997B2 (ja) 2018-12-31 2023-05-19 アジャイルソーダ インコーポレイテッド ディープラーニングに基づいた自動車部位別の破損程度の自動判定システムおよび方法
WO2020140684A1 (fr) * 2019-01-02 2020-07-09 阿里巴巴集团控股有限公司 Procédé et dispositif d'évaluation de modèle d'identification de dommages de véhicule
CN109871770A (zh) * 2019-01-17 2019-06-11 平安城市建设科技(深圳)有限公司 房产证识别方法、装置、设备及存储介质
JP7670628B2 (ja) 2019-06-03 2025-04-30 イーストマン・パフォーマンス・フィルムズ・エルエルシー パターンを組み立て、窓用フィルムおよび塗装保護フィルムを切り取り貼り付けるためのシステムおよび方法
WO2021001337A1 (fr) * 2019-07-03 2021-01-07 Ocado Innovation Limited Appareil et procédé de détection de dommages
US12236671B2 (en) 2019-07-03 2025-02-25 Ocado Innovation Limited Damage detection apparatus and method
WO2021011898A1 (fr) * 2019-07-18 2021-01-21 Apkudo, Llc Inspection ou réparation de dispositifs physiques
US11574182B2 (en) 2019-07-18 2023-02-07 Apkudo, Inc. Physical device inspection or repair
CN110428403B (zh) * 2019-07-22 2023-01-20 宝能汽车集团有限公司 验车方法及电子装置
CN110428403A (zh) * 2019-07-22 2019-11-08 宝能汽车有限公司 验车方法及电子装置
CN110619279A (zh) * 2019-08-22 2019-12-27 天津大学 一种基于跟踪的路面交通标志实例分割方法
US11631165B2 (en) * 2020-01-31 2023-04-18 Sachcontrol Gmbh Repair estimation based on images
CN112016710A (zh) * 2020-08-25 2020-12-01 中车青岛四方机车车辆股份有限公司 轨道车辆维修策略的确定方法、装置和轨道车辆
US11562570B2 (en) 2020-10-06 2023-01-24 Ford Global Technologies, Llc Vehicle damage identification and incident management systems and methods
CN113344478B (zh) * 2021-08-06 2022-01-04 捷尔杰（天津）设备有限公司 离散生产线连续配料方法、装置、电子设备及存储介质
CN113344478A (zh) * 2021-08-06 2021-09-03 捷尔杰（天津）设备有限公司 离散生产线连续配料方法、装置、电子设备及存储介质
US12002192B2 (en) 2021-11-16 2024-06-04 Solera Holdings, Llc Transfer of damage markers from images to 3D vehicle models for damage assessment
CN114565474B (zh) * 2022-03-21 2022-10-14 邦邦汽车销售服务(北京)有限公司 一种汽车零件选取方法、终端设备和存储介质
CN114565474A (zh) * 2022-03-21 2022-05-31 邦邦汽车销售服务(北京)有限公司 一种汽车零件选取方法、终端设备和存储介质
CN114792273A (zh) * 2022-05-12 2022-07-26 中国平安财产保险股份有限公司 出险车定损方法、装置、计算机设备及可读存储介质
CN115345331A (zh) * 2022-08-18 2022-11-15 浙江安易信科技有限公司 一种基于物联网的工单全过程分配跟踪管理系统

Also Published As

Publication number Publication date
WO2018191421A8 (fr) 2019-02-28

Similar Documents

Publication Publication Date Title
US10817956B2 (en) Image-based vehicle damage determining method and apparatus, and electronic device
US10789786B2 (en) Picture-based vehicle loss assessment
EP3520045B1 (fr) Procédé, appareil et système d&#39;évaluation de perte de véhicule à base d&#39;image, et dispositif électronique
WO2018191421A1 (fr) Procédé de détermination d&#39;endommagement de véhicule fondé sur une image, appareil et dispositif électronique
EP3637317A1 (fr) Procédé et appareil de génération d&#39;informations de dommages de véhicules
US11790632B2 (en) Method and apparatus for sample labeling, and method and apparatus for identifying damage classification
US11514526B1 (en) Systems and methods for property damage restoration predictions based upon processed digital images
CN110674788B (zh) 车辆定损方法和装置
US20200160748A1 (en) Cognitive snapshots for visually-impaired users
US10635940B1 (en) Systems and methods for updating image recognition models
US11455763B2 (en) Bounding box generation for object detection
CN118230426B (zh) 人体姿态识别方法、设备和存储介质
KR102795887B1 (ko) 블랙박스 영상을 활용한 인공지능 기반 과실판정 시스템
KR102803846B1 (ko) 블랙박스 영상을 활용한 인공지능 기반 과실판정 시스템
US20210095980A1 (en) Enhanced localization
CN117079253A (zh) 一种对象检测方法及装置
CN113129330A (zh) 一种可移动设备的轨迹预测方法及装置
CN117036050A (zh) 车险理赔处理方法、系统、计算机设备和存储介质
CN111814483A (zh) 用于分析情感的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18722299

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
ENP Entry into the national phase

Ref document number: 2019523649

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20197012653

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2018722299

Country of ref document: EP

Effective date: 20190429

NENP Non-entry into the national phase

Ref country code: DE

点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载