CN118334594A - Target area security monitoring method and device, electronic equipment and readable medium - Google Patents

Abstract

The embodiments of the present disclosure disclose a method, device, electronic device and readable medium for security monitoring of a target area. A specific implementation of the method includes: for every two frames of coded monitoring video frame images in a sequence of coded monitoring video frame images, image change detection is performed on the two frames of coded monitoring video frame images to obtain a frame image change detection result; for every two frames of coded monitoring video frame images, the following processing steps are performed: determining whether the frame image change detection results corresponding to the two frames of coded monitoring video frame images meet a preset change condition; in response to determining that the frame image change detection result meets the preset change condition, retaining the latter frame of the two frames of coded monitoring video frame images; inputting each coded monitoring video frame image to be detected into an image abnormal object detection model to obtain an image abnormal object detection result group. This implementation improves the efficiency of video image detection and can detect abnormal targets in the area in a timely manner.

Description

Target area security monitoring method, device, electronic device and readable medium

Technical Field

Embodiments of the present disclosure relate to the field of video surveillance, and in particular to a method, device, electronic device, and readable medium for securely monitoring a target area.

Background technique

In order to ensure the safety of the target area (for example, a factory/workshop), the target area is usually monitored by video. At present, the method of monitoring the target area by video is usually: the monitoring personnel always check the monitoring video to determine whether there is any abnormal target in the target area.

However, when the above method is used to monitor the target area, the following technical problems often occur: the monitoring video needs to be observed all the time, which is inefficient.

The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.

Summary of the invention

The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

Some embodiments of the present disclosure propose a target area security monitoring method, device, electronic device and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

In a first aspect, some embodiments of the present disclosure provide a method for security monitoring of a target area, the method comprising: controlling an associated camera device to collect monitoring video data of a target area; encoding the monitoring video data to generate encoded monitoring video data; performing frame processing on the encoded monitoring video data to obtain a sequence of encoded monitoring video frame images; for every two frames of encoded monitoring video frame images in the sequence of encoded monitoring video frame images, performing image change detection on the two frames of encoded monitoring video frame images to obtain a frame image change detection result, wherein the frame image change detection result represents a degree of change between two frames of encoded monitoring video frame images; for every two frames of encoded monitoring video frame images The image is processed as follows: determining whether the frame image change detection results corresponding to the above two frames of coded surveillance video frame images meet the preset change conditions; in response to determining that the above frame image change detection results meet the preset change conditions, retaining the latter frame of the above two frames of coded surveillance video frame images as the coded surveillance video frame image to be detected; inputting each coded surveillance video frame image to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one coded surveillance video frame image to be detected corresponds to one image abnormal object detection result; and according to the above image abnormal object detection result group, controlling the associated alarm device to perform alarm processing.

In a second aspect, some embodiments of the present disclosure provide a target area security monitoring device, comprising: a control unit, configured to control an associated camera device to collect monitoring video data of a target area; an encoding unit, configured to perform encoding processing on the monitoring video data to generate encoded monitoring video data; a framing unit, configured to perform framing processing on the encoded monitoring video data to obtain a sequence of encoded monitoring video frame images; a detection unit, configured to perform image change detection on each two frames of encoded monitoring video frame images in the sequence of encoded monitoring video frame images to obtain a frame image change detection result, wherein the frame image change detection result indicates a degree of change between two frames of encoded monitoring video frame images; a determination unit, configured to perform image change detection on each two frames of encoded monitoring video frame images in the sequence of encoded monitoring video frame images to obtain a frame image change detection result, wherein the frame image change detection result indicates a degree of change between two frames of encoded monitoring video frame images; and a determination unit, configured to perform image change detection on each two frames of encoded monitoring video frame images in the sequence of encoded monitoring video frame images to obtain a frame image change detection result. The following processing steps are performed for every two frames of coded surveillance video frame images: determining whether the frame image change detection results corresponding to the above two frames of coded surveillance video frame images meet the preset change conditions; in response to determining that the above frame image change detection results meet the preset change conditions, retaining the latter frame of the above two frames of coded surveillance video frame images as the coded surveillance video frame image to be detected; an input unit is configured to input each coded surveillance video frame image to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one coded surveillance video frame image to be detected corresponds to one image abnormal object detection result; an alarm unit is configured to control the associated alarm device to perform alarm processing according to the above image abnormal object detection result group.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the target area security monitoring method of some embodiments of the present disclosure, the efficiency of video image detection is improved, and abnormal targets in the area can be detected in time. Specifically, it is necessary to observe the monitoring video at all times, and the reason for the low efficiency is that the monitoring personnel check the monitoring video at all times to determine whether there are abnormal targets in the target area. Based on this, the target area security monitoring method of some embodiments of the present disclosure, first, controls the associated camera device to collect the monitoring video data of the target area. Secondly, the above-mentioned monitoring video data is encoded to generate encoded monitoring video data. In this way, the compression of the above-mentioned monitoring video can be achieved, and the video monitoring data can be better transmitted. Then, the above-mentioned encoded monitoring video data is frame-by-frame processed to obtain a sequence of encoded monitoring video frame images. In this way, it is convenient to detect images frame by frame. Afterwards, for every two frames of encoded monitoring video frame images in the above-mentioned sequence of encoded monitoring video frame images, image change detection is performed on the above-mentioned two frames of encoded monitoring video frame images to obtain a frame image change detection result. Among them, the above-mentioned frame image change detection result represents the degree of change between the two frames of encoded monitoring video frame images. In this way, the pixel change between the two frames of images can be determined. Then, for every two frames of coded surveillance video frame images, the following processing steps are performed: determine whether the frame image change detection results corresponding to the above two frames of coded surveillance video frame images meet the preset change conditions; in response to determining that the above frame image change detection results meet the preset change conditions, retain the latter frame of the above two frames of coded surveillance video frame images as the coded surveillance video frame image to be detected. Thus, the image with pixel changes can be determined to avoid detecting each frame image to improve the detection efficiency. Then, each coded surveillance video frame image to be detected is input into the pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one coded surveillance video frame image to be detected corresponds to one image abnormal object detection result. Finally, according to the above image abnormal object detection result group, the associated alarm device is controlled to perform alarm processing. Thus, the efficiency of video image detection is improved, and abnormal targets in the area can be detected in a timely manner.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

FIG1 is a flow chart of some embodiments of a target area security monitoring method according to the present disclosure;

FIG2 is a schematic diagram of the structure of some embodiments of the target area security monitoring device according to the present disclosure;

FIG. 3 is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure.

Detailed ways

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

FIG1 is a flow chart of some embodiments of the target area security monitoring method according to the present disclosure. A flow chart 100 of some embodiments of the target area security monitoring method according to the present disclosure is shown. The target area security monitoring method comprises the following steps:

Step 101: Control the associated camera device to collect monitoring video data of the target area.

In some embodiments, the execution subject (e.g., computing device) of the target area security monitoring method may control the associated camera device to collect monitoring video data of the target area. The camera device may be a monitoring camera set in the target area. The target area may refer to an area that needs to be monitored at all times. For example, the target area may refer to an industrial park, a production workshop, or a warehouse.

Step 102: Encode the monitoring video data to generate encoded monitoring video data.

In some embodiments, the execution entity may encode the surveillance video data to generate encoded surveillance video data.

In practice, the execution subject may encode the surveillance video data by the following steps:

The first step is to pre-process the monitoring video data to obtain pre-processed monitoring video data. The monitoring video data may be denoised, resolution adjusted, and color space converted to obtain pre-processed monitoring video data.

In the second step, each frame of the surveillance video image in the preprocessed surveillance video data is divided into macroblocks to obtain a set of image pixel macroblock groups. Each image pixel macroblock in the image pixel macroblock group corresponds to one frame of the surveillance video image. The surveillance video image can be pixel-divided at a preset size to obtain an image pixel macroblock group. The preset size can be an image size used to divide the surveillance video image into each image pixel macroblock group. For example, the preset size can be 32*32. Here, there is no limitation on the specific setting of the preset size. The image pixel macroblocks in the image pixel macroblock group can be image blocks of the surveillance video image.

In the third step, for each image pixel macroblock group in the above image pixel macroblock group set, the following processing steps are performed:

The first processing step is to perform prediction coding processing on each image pixel macroblock in the above-mentioned image pixel macroblock group to generate a prediction coding image information group. The prediction coding image information in the above-mentioned prediction coding image information group includes prediction macroblocks and prediction image information. Inter-frame prediction processing and intra-frame prediction processing can be performed on each image pixel macroblock in the above-mentioned image pixel macroblock group to obtain a prediction coding image information group. The above-mentioned prediction macroblock can be an image block after the image pixel macroblock is predicted and coded. The above-mentioned prediction image information may include: a global motion vector, an inter-frame prediction mode, and a coding mode of the prediction macroblock. The above-mentioned inter-frame prediction mode may be an inter-frame prediction method used when predicting and coding the image pixel macroblock. For example, motion compensated prediction. The above-mentioned coding mode may be compression coding.

In the second processing step, for each image pixel macroblock in the above image pixel macroblock group, the following steps are performed:

1. Determine the predicted coded image information corresponding to the above-mentioned image pixel macroblock in the above-mentioned predicted coded image information group as the target predicted coded image information.

2. Determine the predicted macroblock included in the above target predicted coded image information as the target predicted macroblock.

3. Determine the pixel difference block between the above image pixel macroblock and the above target prediction macroblock as a residual block. Each pixel difference between the above image pixel macroblock and the above target prediction macroblock can be determined as a residual block.

The third processing step is to transform each determined residual block to obtain a frequency coefficient group. Each residual block can be subjected to discrete cosine transform processing to obtain a frequency coefficient group. The frequency coefficient can be a discrete cosine transform coefficient obtained after the residual block is subjected to discrete cosine transform coding processing.

The fourth processing step is to perform quantization processing on each frequency coefficient in the above frequency coefficient group to obtain a quantized frequency coefficient group. Each frequency coefficient can be subjected to scalar quantization processing to obtain a quantized frequency coefficient.

The fifth processing step is to encode each quantized frequency coefficient in the quantized frequency coefficient group to obtain a residual coefficient code stream group. Each quantized frequency coefficient may be entropy encoded.

In the fourth step, video encoding is performed on each residual coefficient bitstream group obtained, each predicted image information in each predicted coded image information group, and video image parameter information to obtain encoded monitoring video data. The video parameter information may include the width, height, and encoding parameter information of each frame of monitoring video image. The encoded monitoring video data may be the encoded monitoring video data. The encoding parameter information may be a parameter set during video encoding. For example, the video frame rate is 25 frames. In practice, the execution subject may perform high-efficiency video coding (HEVC) processing on each residual coefficient bitstream group obtained, each predicted image information in each predicted coded image information group, and video parameter information to obtain encoded monitoring video data.

In this way, the monitoring video data can be compressed and the transmission efficiency of the monitoring video data can be improved.

Step 103: perform frame processing on the above-mentioned coded monitoring video data to obtain a coded monitoring video frame image sequence.

In some embodiments, the execution subject may perform frame processing on the coded surveillance video data to obtain a coded surveillance video frame image sequence. For example, the execution subject may perform frame processing on the coded surveillance video data according to a preset frame duration to obtain a coded surveillance video frame image sequence.

Step 104 : for every two frames of coded surveillance video frame images in the coded surveillance video frame image sequence, image change detection is performed on the two frames of coded surveillance video frame images to obtain a frame image change detection result.

In some embodiments, the execution subject may perform image change detection on every two frames of the encoded surveillance video frame image in the encoded surveillance video frame image sequence to obtain a frame image change detection result, wherein the frame image change detection result indicates the degree of change between the two frames of the encoded surveillance video frame image.

For example, the pixel change value can be determined as the frame image change detection result by comparing the pixel change between two frames of coded surveillance video frames. That is, the frame image change detection result can represent the pixel change value between two frames of coded surveillance video frames.

In practice, the execution entity may input the two encoded surveillance video frame images into a pre-trained image change detection model to obtain a frame image change detection result.

The image change detection model can be trained by the following steps:

The first step is to obtain a monitoring video frame image sample set, wherein the monitoring video frame image sample includes: two consecutive monitoring video frame images.

The second step is to select a target surveillance video frame image sample set from the surveillance video frame image sample set. For example, a surveillance video frame image sample can be randomly selected from the surveillance video frame image sample set as the target surveillance video frame image sample.

In the third step, the two consecutive surveillance video frames included in the target surveillance video frame image sample set are input into the initial image change detection model to obtain the initial image change detection result. The initial image change detection model can be a pre-trained neural network model for detecting pixel changes between two consecutive video frames. For example, the initial image change detection model can be an untrained convolutional neural network model or a deep neural network model.

The fourth step is to determine the image change loss value between the above-mentioned initial image change detection result and the corresponding image change sample label. The image change loss value between the above-mentioned initial image change detection result and the corresponding image change sample label can be determined by a preset loss function. For example, the preset loss function can be a cosine similarity loss function/cross entropy loss function.

In a fifth step, in response to determining that the image change loss value is less than or equal to a preset image change loss value, the initial image change detection model is determined as a trained image change detection model.

Step 105: for every two frames of encoded surveillance video frame images, perform the following processing steps:

Step 1051 , determining whether the frame image change detection results corresponding to the above two frames of encoded surveillance video frame images meet a preset change condition.

In some embodiments, the execution subject may determine whether the frame image change detection results corresponding to the two frames of encoded surveillance video frame images meet a preset change condition. The preset change condition may be: the pixel change value represented by the frame image change detection result is greater than or equal to a preset pixel change value.

Step 1052, in response to determining that the above frame image change detection result meets the preset change condition, retaining the latter frame of the above two frames of encoded surveillance video frame image as the encoded surveillance video frame image to be detected.

In some embodiments, the execution subject may, in response to determining that the frame image change detection result satisfies a preset change condition, retain the latter of the two encoded surveillance video frame images as the encoded surveillance video frame image to be detected.

Optionally, a surveillance video image training sample set is obtained. Each surveillance video image training sample set corresponds to a surveillance scene. The surveillance scene may represent different surveillance environments. For example, the surveillance scene may include but is not limited to: an indoor scene, an outdoor scene, a rainy day, a cloudy day, a sunny day scene, or a dim scene.

Optionally, determine an initial image abnormal object detection model. The initial image abnormal object detection model includes: an initial image abnormal object detection network group, each initial image abnormal object detection network corresponds to a monitoring scene. The initial image abnormal object detection model may refer to an untrained target detection model. For example, the initial image abnormal object detection model may be an untrained R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, etc. model. The initial image abnormal object detection network may be an untrained R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD (SingleShot MultiBox Detector) or other network.

Optionally, for each initial image abnormal object detection network in the above initial image abnormal object detection network group, perform the following training steps:

The first training step is to determine a surveillance video image training sample group corresponding to the above-mentioned initial image abnormal object detection network, that is, to determine a surveillance video image training sample group with the same surveillance scene as that corresponding to the above-mentioned initial image abnormal object detection network.

The second training step is to select a target surveillance video image training sample from the surveillance video image training sample group. A surveillance video image training sample can be randomly selected from the surveillance video image training sample group as the target surveillance video image training sample.

In the third training step, the monitoring video sample images included in the target monitoring video image training samples are input into the initial image abnormal object detection network to obtain the initial image abnormal object detection results. The initial image abnormal object detection results may refer to the abnormal object detection results for the monitoring video sample images.

The fourth training step is to determine the loss value between the above-mentioned initial image abnormal object detection result and the corresponding sample label. The loss value between the above-mentioned initial image abnormal object detection result and the corresponding sample label can be determined by a preset loss function. For example, the loss function can be a hinge loss function or a cross entropy loss function.

In a fifth training step, in response to determining that the loss value is less than or equal to a preset loss value, the initial image abnormal object detection network is determined as a trained image abnormal object detection network.

Optionally, each determined image abnormal object detection network is determined as an image abnormal object detection model.

Optionally, the training step may also include: in response to determining that the above-mentioned loss value is greater than the above-mentioned preset loss value, adjusting the model parameters of the initial image abnormal object detection network, and selecting the target surveillance video image training sample from each unselected surveillance video image training sample, using the adjusted initial image abnormal object detection network as the initial image abnormal object detection network, and retraining the initial image abnormal object detection network. For example, the loss value and the preset loss value can be subtracted to obtain the loss difference. On this basis, the loss difference is passed forward from the last layer of the model using back propagation, stochastic gradient descent and other methods to adjust the parameters of each layer. Of course, according to needs, the network freezing (dropout) method can also be used to keep the network parameters of some layers unchanged and not adjust them. There is no limitation on this.

In this way, the accuracy of video image detection for different monitoring scenarios can be improved, and the robustness of the image abnormal object detection model can be improved.

Step 106: input each of the encoded surveillance video frame images to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group.

In some embodiments, the above-mentioned execution subject can input each coded surveillance video frame image to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group. Among them, one coded surveillance video frame image to be detected corresponds to one image abnormal object detection result. The image abnormal object detection model can be a pre-trained neural network model for detecting whether an abnormal target appears in a surveillance video frame image. For example, the image abnormal object detection model can be a pre-trained target detection model. Abnormal targets can include but are not limited to: animals, fire, water leaks and other abnormal targets.

Step 107: Control the associated alarm device to perform alarm processing according to the above-mentioned image abnormal object detection result group.

In some embodiments, the execution subject may control the associated alarm device to perform alarm processing according to the abnormal image object detection result group.

In practice, the execution subject may perform the following processing steps for each abnormal image object detection result in the abnormal image object detection result group:

The first step is to determine whether the above image abnormal object detection result meets a preset abnormal condition. The preset abnormal condition may be: the image abnormal object detection result indicates that an abnormal target appears in the surveillance video frame image.

The second step is to generate a warning tone corresponding to the abnormal object detection result in response to determining that the abnormal object detection result meets the preset abnormal condition. For example, a prompt tone indicating that an abnormal object has appeared can be generated.

The third step is to control the alarm device to play the alarm tone. The alarm device may be a voice playing device connected to the execution subject for communication.

Further referring to FIG. 2 , as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a target area security monitoring device, which correspond to the method embodiments shown in FIG. 1 , and the target area security monitoring device can be specifically applied to various electronic devices.

As shown in FIG2 , the target area security monitoring device 200 of some embodiments includes: a control unit 201, an encoding unit 202, a framing unit 203, a detection unit 204, a determination unit 205, an input unit 206, and an alarm unit 207. The control unit 201 is configured to control the associated camera device to collect monitoring video data of the target area; the encoding unit 202 is configured to perform encoding processing on the above monitoring video data to generate encoded monitoring video data; the framing unit 203 is configured to perform framing processing on the above encoded monitoring video data to obtain an encoded monitoring video frame image sequence; the detection unit 204 is configured to perform image change detection on each two frames of the encoded monitoring video frame image in the above encoded monitoring video frame image sequence to obtain a frame image change detection result, wherein the frame image change detection result represents the degree of change between the two frames of the encoded monitoring video frame image; the determination unit 205 is configured to perform image change detection on each two frames of the encoded monitoring video frame image in the above encoded monitoring video frame image sequence to obtain a frame image change detection result, wherein the frame image change detection result represents the degree of change between the two frames of the encoded monitoring video frame image; the determination unit 205 is configured to perform image change detection on each two frames of the encoded monitoring video frame image Image, perform the following processing steps: determine whether the frame image change detection results corresponding to the above two frames of coded surveillance video frame images meet the preset change conditions; in response to determining that the above frame image change detection results meet the preset change conditions, retain the latter frame of the above two frames of coded surveillance video frame images as the coded surveillance video frame image to be detected; the input unit 206 is configured to input each coded surveillance video frame image to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one coded surveillance video frame image to be detected corresponds to one image abnormal object detection result; the alarm unit 207 is configured to control the associated alarm device to perform alarm processing according to the above image abnormal object detection result group.

It is understandable that the units recorded in the target area security monitoring device 200 correspond to the steps in the method described with reference to Figure 1. Therefore, the operations, features and beneficial effects described above for the method are also applicable to the target area security monitoring device 200 and the units contained therein, and will not be repeated here.

Referring to FIG. 3 below, a schematic diagram of the structure of an electronic device (e.g., a computing device) 300 suitable for implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG. 3 is only an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG3 , the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and task data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to the bus 304.

Typically, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication device 309 may allow the electronic device 300 to communicate wirelessly or wired with other devices to exchange task data. Although FIG. 3 shows an electronic device 300 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively. Each box shown in FIG. 3 may represent one device, or may represent multiple devices as needed.

In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a mission data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such a propagated mission data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital task data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: controls the associated camera device to collect monitoring video data of the target area; encodes the above-mentioned monitoring video data to generate encoded monitoring video data; performs frame processing on the above-mentioned encoded monitoring video data to obtain a sequence of encoded monitoring video frame images; for every two frames of encoded monitoring video frame images in the above-mentioned sequence of encoded monitoring video frame images, performs image change detection on the above-mentioned two frames of encoded monitoring video frame images to obtain a frame image change detection result, wherein the above-mentioned frame image change detection result represents the degree of change between the two frames of encoded monitoring video frame images; for every two frames of encoded monitoring video frame images, The coded surveillance video frame images are processed as follows: determining whether the frame image change detection results corresponding to the above two frames of coded surveillance video frame images meet the preset change conditions; in response to determining that the above frame image change detection results meet the preset change conditions, retaining the latter frame of the above two frames of coded surveillance video frame images as the coded surveillance video frame image to be detected; inputting each of the coded surveillance video frame images to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one coded surveillance video frame image to be detected corresponds to one image abnormal object detection result; and according to the above image abnormal object detection result group, controlling the associated alarm device to perform alarm processing.

Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including product-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor comprising: a control unit, an encoding unit, a framing unit, a detection unit, a determination unit, an input unit, and an alarm unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, an alarm unit may also be described as "a unit that controls the associated alarm device to perform alarm processing according to the above-mentioned image abnormal object detection result group".

The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims (8)

1. A target area security monitoring method, comprising: Controlling the associated camera device to collect monitoring video data of the target area; Encoding the surveillance video data to generate encoded surveillance video data; Performing frame processing on the encoded surveillance video data to obtain an encoded surveillance video frame image sequence; For every two frames of coded surveillance video frame images in the coded surveillance video frame image sequence, image change detection is performed on the two frames of coded surveillance video frame images to obtain a frame image change detection result, wherein the frame image change detection result represents a degree of change between the two frames of coded surveillance video frame images; For every two frames of encoded surveillance video frames, the following processing steps are performed: Determine whether the frame image change detection results corresponding to the two frames of encoded surveillance video frame images meet a preset change condition; In response to determining that the frame image change detection result meets the preset change condition, retaining the latter frame of the two frames of coded surveillance video frame image as the coded surveillance video frame image to be detected; Input each of the to-be-detected coded surveillance video frame images into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one to-be-detected coded surveillance video frame image corresponds to one image abnormal object detection result; According to the image abnormal object detection result group, the associated alarm device is controlled to perform alarm processing. 2. The method according to claim 1, wherein the step of controlling the associated alarm device to perform alarm processing according to the image abnormal object detection result group comprises: For each abnormal image object detection result in the abnormal image object detection result group, the following processing steps are performed: Determining whether the abnormal object detection result of the image meets a preset abnormal condition; In response to determining that the image abnormal object detection result meets a preset abnormal condition, generating an alarm prompt sound corresponding to the image abnormal object detection result; Control the alarm device to play the alarm prompt tone. 3. The method according to claim 1, wherein, before inputting each of the encoded surveillance video frame images to be detected into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, the method further comprises: Obtaining a surveillance video image training sample group set, wherein each surveillance video image training sample group corresponds to a surveillance scene; Determine an initial image abnormal object detection model, wherein the initial image abnormal object detection model includes: an initial image abnormal object detection network group, each initial image abnormal object detection network corresponds to a monitoring scene; For each initial image abnormal object detection network in the initial image abnormal object detection network group, the following training steps are performed: Determine a surveillance video image training sample group corresponding to the initial image abnormal object detection network; Selecting a target surveillance video image training sample from the surveillance video image training sample group; Inputting the surveillance video sample images included in the target surveillance video image training samples into the initial image abnormal object detection network to obtain the initial image abnormal object detection results; Determine a loss value between the initial image abnormal object detection result and the corresponding sample label; In response to determining that the loss value is less than or equal to a preset loss value, determining the initial image abnormal object detection network as a trained image abnormal object detection network; The determined respective image abnormal object detection networks are determined as image abnormal object detection models. 4. The method according to claim 3, wherein the training step further comprises: In response to determining that the loss value is greater than the preset loss value, the model parameters of the initial image abnormal object detection network are adjusted, and a target surveillance video image training sample is selected from each unselected surveillance video image training sample, and the adjusted initial image abnormal object detection network is used as the initial image abnormal object detection network, and the initial image abnormal object detection network is retrained. 5. The method according to claim 1, wherein the performing image change detection on the two frames of encoded surveillance video frame images to obtain the frame image change detection result comprises: The two frames of encoded surveillance video frame images are input into a pre-trained image change detection model to obtain a frame image change detection result. 6. A target area security monitoring device, comprising: A control unit configured to control an associated camera device to collect monitoring video data of a target area; An encoding unit, configured to perform encoding processing on the monitoring video data to generate encoded monitoring video data; A frame division unit is configured to perform frame division processing on the coded monitoring video data to obtain a coded monitoring video frame image sequence; a detection unit configured to perform image change detection on every two frames of coded surveillance video frame images in the coded surveillance video frame image sequence, and obtain a frame image change detection result, wherein the frame image change detection result indicates a degree of change between the two frames of coded surveillance video frame images; The determination unit is configured to perform the following processing steps for every two frames of coded surveillance video frame images: determining whether the frame image change detection results corresponding to the two frames of coded surveillance video frame images meet a preset change condition; in response to determining that the frame image change detection result meets the preset change condition, retaining the latter frame of the two frames of coded surveillance video frame images as the coded surveillance video frame image to be detected; An input unit is configured to input each of the to-be-detected coded surveillance video frame images into a pre-trained image abnormal object detection model to obtain an image abnormal object detection result group, wherein one to-be-detected coded surveillance video frame image corresponds to one image abnormal object detection result; The alarm unit is configured to control the associated alarm device to perform alarm processing according to the image abnormal object detection result group. 7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5. 8. A computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.