CN107105207A - Target monitoring method, target monitoring device and video camera - Google Patents
Target monitoring method, target monitoring device and video camera Download PDFInfo
- Publication number
- CN107105207A CN107105207A CN201710435936.0A CN201710435936A CN107105207A CN 107105207 A CN107105207 A CN 107105207A CN 201710435936 A CN201710435936 A CN 201710435936A CN 107105207 A CN107105207 A CN 107105207A
- Authority
- CN
- China
- Prior art keywords
- target
- monitoring
- control
- monitored
- deploying
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a kind of target monitoring method, target monitoring device and video camera, this method is applied to video camera, including：Obtain the current frame image of the camera collection of video camera；Object in current frame image is classified, the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are obtained；The target to be monitored in current frame image is determined from the suspect objects got according to target of currently deploying to ensure effective monitoring and control of illegal activities；Control camera treats monitoring objective and is tracked shooting, obtains the close-up image of target to be monitored；Feature recognition is carried out to close-up image according to current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, judges whether target to be monitored belongs to current target of deploying to ensure effective monitoring and control of illegal activities；If it is, target to be monitored is defined as into monitoring objective, and the tracing and monitoring monitoring objective.Target monitoring method, target monitoring device and video camera that the present invention is provided, can reduce the cost input during target monitoring, lift the ageing and reliability of target monitoring.
Description
Technical field
The present invention relates to safety monitoring technical field, more particularly, to a kind of target monitoring method, target monitoring device and
Video camera.
Background technology
With the fast development of " safe city " system Construction, the demand to video monitoring camera is sharply increased.Tradition
Protection and monitor field generally carries out video monitoring, PTZ shootings using PTZ (Pan Tilt Zoom translate tilt zoom) video camera
Machine carries head function, it is possible to achieve head comprehensive (left and right/up and down) is mobile and camera lens zoom, Zoom control.
In each security protection application scenarios, the control of Pan/Tilt/Zoom camera is typically according to Pan/Tilt/Zoom camera by back-end operations personnel
The video file of transmission is manually completed by console, to realize the feature monitoring to specifically monitored target and track, works as behaviour
Make personnel to find that when the target of monitoring tracking is alert target really corresponding action can be taken, such as alarm.But people is meeting
Fatigue, can occur leaking anti-problem because of absent minded.There is the regular hour during additionally, due to transmission video file
Difference, therefore manually control the problem of Pan/Tilt/Zoom camera has poor real when carrying out target monitoring.
In summary, there is waste of manpower cost, poor real, the anti-skill of leakage easily occur in existing target monitoring method
Art problem.
The content of the invention
In view of this, it is an object of the invention to provide a kind of target monitoring method, target monitoring device and video camera, with
The cost input during target monitoring is reduced, the ageing and reliability of target monitoring is lifted.
In a first aspect, the embodiments of the invention provide a kind of target monitoring method, methods described is applied to video camera, bag
Include：
Obtain the current frame image of the camera collection of the video camera；
Object in the current frame image is classified, the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are obtained；
Treating in the current frame image is determined from the suspect objects got according to the current target of deploying to ensure effective monitoring and control of illegal activities
Monitoring objective；
Control the camera to be tracked shooting to the target to be monitored, obtain the close up view of the target to be monitored
Picture；
Feature recognition is carried out to the close-up image according to the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, the mesh to be monitored is judged
Whether mark belongs to the current target of deploying to ensure effective monitoring and control of illegal activities；
If it is, the target to be monitored is defined as into monitoring objective, and monitoring objective described in tracing and monitoring.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the first of first aspect, wherein, institute
State and the object in the current frame image is classified, obtain the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities, including：
The object in the current frame image is classified according to default classifying rules, the default classifying rules includes
By object according to personage, vehicle and animal classification；
The suspect objects of the current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are extracted from the sorted object.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of second of first aspect, wherein, institute
State the mesh to be monitored determined according to the current target of deploying to ensure effective monitoring and control of illegal activities from the suspect objects got in the current frame image
Mark, including：
According to the current target of deploying to ensure effective monitoring and control of illegal activities, the similarity of the suspect objects is determined using video structural algorithm；
Suspect objects described in similarity highest are defined as the target to be monitored.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the third of first aspect, wherein, institute
State the control camera and shooting is tracked to the target to be monitored, obtain the close-up image of the target to be monitored, wrap
Include：
The focal length of the camera is adjusted, and the mesh to be monitored is determined using target tracking algorism and image compensation algorithm
The position in the video image of track up is marked on, turning for the camera is controlled using cradle head control algorithm according to the position
Dynamic angle and velocity of rotation, obtain the close-up image of the target to be monitored.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the 4th of first aspect kind, wherein, institute
State and feature recognition is carried out to the close-up image according to the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, whether judge the target to be monitored
Belong to the current target of deploying to ensure effective monitoring and control of illegal activities, including：
Extract the clarification of objective to be monitored in the close-up image；
The clarification of objective to be monitored is contrasted with the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, comparing result is obtained；
According to the comparing result, judge whether the target to be monitored belongs to the current target of deploying to ensure effective monitoring and control of illegal activities.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the 5th of first aspect kind, wherein, institute
Stating method also includes：
When judge the target to be monitored for it is described it is current deploy to ensure effective monitoring and control of illegal activities target when, send warning message to monitor terminal.
With reference in a first aspect, the embodiments of the invention provide the possible embodiment of the 6th of first aspect kind, wherein, institute
Stating method also includes：
When receiving the alert target information of monitor terminal transmission, the object in the alert target information is defined as
The current target of deploying to ensure effective monitoring and control of illegal activities.
Second aspect, the embodiment of the present invention also provides a kind of target monitoring device, including：
Image collection module, for obtaining the current frame image that the camera of the video camera is gathered；
Object acquisition module, for classifying to the object in the current frame image, obtains current target pair of deploying to ensure effective monitoring and control of illegal activities
Answer the suspect objects of classification；
Target determination module, described in being determined according to the current target of deploying to ensure effective monitoring and control of illegal activities from the suspect objects got
Target to be monitored in current frame image；
Track up module, for controlling the camera to be tracked shooting to the target to be monitored, obtains described
The close-up image of target to be monitored；
Judge module, for carrying out feature recognition to the close-up image according to the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, sentences
Whether the target to be monitored of breaking belongs to the current target of deploying to ensure effective monitoring and control of illegal activities；
Monitoring module, for when the judged result of the judge module is is, the target to be monitored to be defined as into prison
Control target, and monitoring objective described in tracing and monitoring.
The third aspect, the embodiment of the present invention also provides a kind of video camera, including head, the head electricity that is connected with the head
Machine, the camera being arranged on the head, memory, processor and it is stored on the memory and can be in the processor
The computer program of upper operation；
The horizontal stage electric machine, the camera are electrically connected with the processor respectively, are calculated described in the computing device
The step of method described in above-mentioned first aspect is realized during machine program, wherein, the processor is by controlling the horizontal stage electric machine
The camera is driven to rotate.
Fourth aspect, the embodiment of the present invention also provides a kind of meter for the non-volatile program code that can perform with processor
Calculation machine computer-readable recording medium, described program code makes the computing device first aspect methods described.
The embodiment of the present invention brings following beneficial effect：
In the embodiment of the present invention, target monitoring method is applied to video camera, including：Obtain the camera collection of video camera
Current frame image；Object in current frame image is classified, the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are obtained；Root
The target to be monitored in current frame image is determined from the suspect objects got according to target of currently deploying to ensure effective monitoring and control of illegal activities；Control the camera pair
Target to be monitored is tracked shooting, obtains the close-up image of target to be monitored；According to currently deploying to ensure effective monitoring and control of illegal activities clarification of objective to the spy
Write image and carry out feature recognition, judge whether target to be monitored belongs to current target of deploying to ensure effective monitoring and control of illegal activities；If it is, target to be monitored is true
It is set to monitoring objective, and the tracing and monitoring monitoring objective.During using the target monitoring method, it can be adopted from the camera of video camera
Automatic sieve selects target to be monitored in the current frame image of collection, and whether the automatic decision target to be monitored belongs to current mesh of deploying to ensure effective monitoring and control of illegal activities
Mark, therefore independent of rear end control platform, human cost has been saved, and be not easy to occur leaking anti-problem.Simultaneously as this method
Applied to video camera, the video file of the camera acquisition is directly handled in shooting generator terminal, it is no longer necessary to transmit video file extremely
Back-end processing, thus it is real-time.In summary, target monitoring method provided in an embodiment of the present invention, target monitoring device and
Video camera reduces the cost input during target monitoring, and improves the ageing and reliability of target monitoring.
Other features and advantages of the present invention will be illustrated in the following description, also, partly be become from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages are in specification, claims
And specifically noted structure is realized and obtained in accompanying drawing.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art
The accompanying drawing used required in embodiment or description of the prior art is briefly described, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paid
Put, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is the first schematic flow sheet of target monitoring method provided in an embodiment of the present invention；
Fig. 2 is second of schematic flow sheet of target monitoring method provided in an embodiment of the present invention；
Fig. 3 is the third schematic flow sheet of target monitoring method provided in an embodiment of the present invention；
Fig. 4 is the module composition schematic diagram of target monitoring device provided in an embodiment of the present invention；
Fig. 5 is the structural representation of video camera provided in an embodiment of the present invention.
Icon：
10- image collection modules；20- object acquisition modules；30- target determination modules；40- track up modules；50- sentences
Disconnected module；60- monitoring modules；100- heads；200- horizontal stage electric machines；300- cameras；400- processors；500- memories；
600- buses；700- communication interfaces.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with accompanying drawing to the present invention
Technical scheme be clearly and completely described, it is clear that described embodiment is a part of embodiment of the invention, rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
The video file transmitted at present generally according to video camera, target monitoring is carried out using artificial control Pan/Tilt/Zoom camera, because
There is waste of manpower cost, poor real, the anti-technical problem of leakage easily occur in this.It is provided in an embodiment of the present invention based on this
A kind of target monitoring method, target monitoring device and video camera, have saved human cost, and are not easy to occur leaking anti-problem；Directly
The video file that shooting generator terminal handles the camera acquisition is connected on, it is real-time.
For ease of understanding the present embodiment, a kind of target monitoring method disclosed in the embodiment of the present invention is entered first
Row is discussed in detail.
Embodiment one：
Target monitoring method provided in an embodiment of the present invention is applied to video camera, and the video camera may be mounted at each video
Monitor the private sites such as place, the public place such as bank, market, station and traffic intersection, and personal family, below with
Illustrated exemplified by monitoring traffic intersection.
General traffic intersection is fitted with video camera, is taken pictures for violating the regulations, or is public security organ's strike street for recording a video
Face crime provides evidence and clue.The camera for the video camera that the embodiment of the present invention is used should have zoom lock function, and
The camera can be rotated to track target in all directions, the video camera can with but be not limited to Pan/Tilt/Zoom camera.Simultaneously should
Target of deploying to ensure effective monitoring and control of illegal activities is pre-stored with video camera, the target of deploying to ensure effective monitoring and control of illegal activities can be to be multiple, such as multiple personages, many cars, when being supervised
During control, the target of deploying to ensure effective monitoring and control of illegal activities of a certain classification can be regard as current target of deploying to ensure effective monitoring and control of illegal activities according to actual needs.
Fig. 1 is the first schematic flow sheet of target monitoring method provided in an embodiment of the present invention, as shown in figure 1, the party
Method includes following steps：
Step S101, obtains the current frame image of the camera collection of video camera.
Specifically, the video file of the camera captured in real-time traffic intersection of above-mentioned video camera, obtains the video file, and
The video file is decoded, current frame image can be obtained.
Step S102, classifies to the object in current frame image, obtains current the doubtful of target correspondence classification of deploying to ensure effective monitoring and control of illegal activities
Object.
One or more objects are there may be in current frame image, object here does not consider fixed object, first roughing
Go out the object with target identical category of currently deploying to ensure effective monitoring and control of illegal activities, i.e. suspect objects.Specifically, according to default classifying rules to current frame image
Interior object is classified, and the default classifying rules is included object according to personage, vehicle and animal classification, from sorted right
As the suspect objects of the current corresponding classification of target of deploying to ensure effective monitoring and control of illegal activities of middle extraction.If for example, current target of deploying to ensure effective monitoring and control of illegal activities is pedestrian, by present frame figure
As each interior pedestrian is used as suspect objects；If current target of deploying to ensure effective monitoring and control of illegal activities makees each car in current frame image for car
For suspect objects.Here the specific algorithm that performs is not restricted.
The smaller and slow object of movement is not easy to be detected in usual video image, it is preferable that step S102 is used
Video structural algorithm performs based on deep neural network, the algorithm is responsible for the analysis of the object in full-view video image, energy
Enough identify many class objects, including pedestrian, bicycle, motorcycle, car, tricycle, bus, minibus and truck etc., energy
Enough realize the accurate detection to the object with categorical attribute.The algorithm can be with the class of the object in Accurate Calibration current frame image
Not, guarantee in advance is provided for the automatic selected and tracking of target to be monitored.Further, in order to lift treatment effeciency, this is regarded
Frequency structuring algorithm is stored in embedded processing chip, and the chip is arranged in video camera.Using Embedded video structure
Change algorithm, processing speed is fast, efficiency high.
Step S103, is determined to be monitored in current frame image according to target of currently deploying to ensure effective monitoring and control of illegal activities from the suspect objects got
Target.
Specifically, the feature of suspect objects is extracted, and is contrasted with current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, by similarity highest
Suspect objects be defined as target to be monitored.Current target of deploying to ensure effective monitoring and control of illegal activities can be multiple, and suspect objects can also be multiple, need here
The similarity of each suspect objects and each target of currently deploying to ensure effective monitoring and control of illegal activities is determined, and wherein similarity highest suspect objects will be determined
For target to be monitored.Here the specific algorithm that performs is not restricted.
Table 1 is suspect objects and the similarity result schematic table of target of currently deploying to ensure effective monitoring and control of illegal activities, and any occurrence in table 1 is only
It is exemplary, not as limitation.As shown in table 1, suspect objects include A, B, C, and target of currently deploying to ensure effective monitoring and control of illegal activities includes X, Y, its
Middle C and X similarity highest, are 50%, then C are defined as into target to be monitored.
Table 1
Preferably, according to current target of deploying to ensure effective monitoring and control of illegal activities, the similarity of above-mentioned suspect objects is determined using video structural algorithm, will
Similarity highest suspect objects are defined as target to be monitored.The video structural algorithm is identical with the algorithm in step S102,
Here repeat no more.
Step S104, controls above-mentioned camera to treat monitoring objective and is tracked shooting, obtain the spy of the target to be monitored
Write image.
Because in scene of deploying to ensure effective monitoring and control of illegal activities, in overall view monitoring, target to be monitored shared pixel in current frame image is all less, difficult
To judge whether target to be monitored belongs to current target of deploying to ensure effective monitoring and control of illegal activities according to current frame image.Enter accordingly, it would be desirable to treat monitoring objective
Row feature is tracked.
Specifically, the focal length of camera is adjusted, and mesh to be monitored is determined using target tracking algorism and image compensation algorithm
The position in the video image of track up is marked on, the angle of rotation of the camera is controlled using cradle head control algorithm according to the position
Degree and velocity of rotation, obtain the close-up image of target to be monitored.Wherein, target tracking algorism be responsible for determining target to be monitored regarding
Position in frequency image；Image compensation algorithm can prevent from the motion of video camera and shake to bring influence to target tracking algorism；
Cradle head control algorithm can realize the control to horizontal stage electric machine, the position that head is provided according to target tracking algorism is carried out
Respective angles, angular speed, the control of angular acceleration, treat monitoring objective and realize real-time tracking.
Target tracking algorism includes：Frame difference method, kinect video frequency trackings algorithm, mineshift target tracking algorisms,
Kalman filtering algorithms, OAB (Online Adaptive Boosting Tracking, online adaptive enhancing) track algorithm,
IVT (Incremental Learning for Robust Visual Tracing, incremental learning) track algorithm, MIL
(Multiple instance learning, multi-instance learning) track algorithm, CT (Fast Compressive Tracking,
High speed compression) track algorithm, TLD (Tracking-Learning-Detection), Struck track algorithms etc..Here to tool
Target tracking algorism, image compensation algorithm and the cradle head control algorithm of body are not restricted.
In one embodiment, above-mentioned video camera is Pan/Tilt/Zoom camera, and its camera is arranged on head, passes through head control
Algorithm processed controls the rotational angle and velocity of rotation of head to control shooting head-turned angle and velocity of rotation.Pan/Tilt/Zoom camera
With zoom function, it can realize that treating monitoring objective carries out feature tracking, makes target to be monitored at video by the camera lens that furthers
Enough pixel quantities are occupied in image, are conducive to the practical application of target tracking algorism, can to greatest extent optimization aim with
Track algorithm.During tracking, regulation in real time images head-turned angle and focal length, so that target to be monitored is maintained at camera
The center of the video image of shooting simultaneously occupies most of image and realizes feature.
Step S105, carries out feature recognition to above-mentioned close-up image according to current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, judges to be monitored
Whether target belongs to the current target of deploying to ensure effective monitoring and control of illegal activities.
Specifically, the clarification of objective to be monitored in close-up image is extracted, by clarification of objective to be monitored with currently deploying to ensure effective monitoring and control of illegal activities
Clarification of objective is contrasted, and obtains comparing result, according to the comparing result, judges whether target to be monitored belongs to the current cloth
Control target.
It is possible to further perform step S105 using plurality of target recognizer, such as face recognition algorithms, car face are known
Other algorithm, tailstock recognizer etc., obtain the matching degree of target to be monitored and target of currently deploying to ensure effective monitoring and control of illegal activities, so as to accurately judge to be monitored
Whether target belongs to the current target of deploying to ensure effective monitoring and control of illegal activities.Above-mentioned comparing result includes the matching degree, is matched according to the matching degree with default
Magnitude relationship between threshold value judges whether target to be monitored belongs to the current target of deploying to ensure effective monitoring and control of illegal activities, wherein, matching threshold can root
According to being actually needed setting.If the matching degree is more than default matching threshold, judge that target to be monitored belongs to the current mesh of deploying to ensure effective monitoring and control of illegal activities
Mark, it is on the contrary then judge that target to be monitored is not belonging to this and currently deployed to ensure effective monitoring and control of illegal activities target.
For example, default matching threshold is 0.7, if target C to be monitored and currently deploy to ensure effective monitoring and control of illegal activities target X or Y matching degree are more than
0.7, then judge that target C to be monitored belongs to the current target of deploying to ensure effective monitoring and control of illegal activities；If target C to be monitored is matched with target X, Y of currently deploying to ensure effective monitoring and control of illegal activities
Degree, which is respectively less than, is equal to 0.7, then judges that target C to be monitored is not belonging to the current target of deploying to ensure effective monitoring and control of illegal activities.
If the determination result is YES, then step S106 is performed；If judged result is no, control camera zoom to panorama mould
Formula, re-executes above-mentioned steps S101.
Step S106, if it is, above-mentioned target to be monitored is defined as into monitoring objective, and the tracing and monitoring monitoring mesh
Mark.
When judge target to be monitored belong to this it is current deploy to ensure effective monitoring and control of illegal activities target when, it is monitoring objective to determine the target to be monitored, and is adopted
With target tracking algorism, image compensation algorithm and cradle head control algorithm continuation the tracing and monitoring monitoring objective.
Target monitoring method provided in an embodiment of the present invention is independent of rear end control platform, using the processing utensil of this method
There is efficient local video disposal ability, mobility strong, bandwidth occupancy is few, and Tracking Recognition effect is good.
In the embodiment of the present invention, target monitoring method is applied to video camera, including：Obtain the camera collection of video camera
Current frame image；Object in current frame image is classified, the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are obtained；Root
The target to be monitored in current frame image is determined from the suspect objects got according to target of currently deploying to ensure effective monitoring and control of illegal activities；Control the camera pair
Target to be monitored is tracked shooting, obtains the close-up image of target to be monitored；According to currently deploying to ensure effective monitoring and control of illegal activities clarification of objective to the spy
Write image and carry out feature recognition, judge whether target to be monitored belongs to current target of deploying to ensure effective monitoring and control of illegal activities；If it is, target to be monitored is true
It is set to monitoring objective, and the tracing and monitoring monitoring objective.During using the target monitoring method, it can be adopted from the camera of video camera
Automatic sieve selects target to be monitored in the current frame image of collection, and whether the automatic decision target to be monitored belongs to current mesh of deploying to ensure effective monitoring and control of illegal activities
Mark, therefore independent of rear end control platform, human cost has been saved, and be not easy to occur leaking anti-problem.Simultaneously as this method
Applied to video camera, the video file of the camera acquisition is directly handled in shooting generator terminal, it is no longer necessary to transmit video file extremely
Back-end processing, thus it is real-time.In summary, target monitoring method provided in an embodiment of the present invention reduces target monitoring mistake
Cost input in journey, and improve the ageing and reliability of target monitoring.
In order to accelerate processing speed of the monitoring personnel to target of deploying to ensure effective monitoring and control of illegal activities, treatment effeciency is improved, when judging that target to be monitored is
During target of currently deploying to ensure effective monitoring and control of illegal activities, warning message is sent to monitor terminal.Monitor terminal includes mobile phone, computer, tablet personal computer etc., monitor
Member can timely receive warning message by monitor terminal, consequently facilitating arresting the target of deploying to ensure effective monitoring and control of illegal activities monitored in time.
Fig. 2 is second of schematic flow sheet of target monitoring method provided in an embodiment of the present invention, as shown in Fig. 2 the mesh
Marking monitoring method includes following steps：
Step S201, when receiving the alert target information of monitor terminal transmission, by the object in alert target information
It is defined as target of currently deploying to ensure effective monitoring and control of illegal activities.
In view of when find it is a certain deploy to ensure effective monitoring and control of illegal activities target to specified range when, monitor terminal can be to the shooting in the specified range
Machine sends alert target information, based on this, when receiving the alert target information of monitor terminal transmission, by alert target information
In object be defined as currently deploying to ensure effective monitoring and control of illegal activities target, so as to improve the monitoring efficiency to the target of deploying to ensure effective monitoring and control of illegal activities.
Step S202, obtains the current frame image of the camera collection of video camera.
Step S203, classifies to the object in current frame image, obtains current the doubtful of target correspondence classification of deploying to ensure effective monitoring and control of illegal activities
Object.
Step S204, is determined to be monitored in current frame image according to target of currently deploying to ensure effective monitoring and control of illegal activities from the suspect objects got
Target.
Step S205, controls above-mentioned camera to treat monitoring objective and is tracked shooting, obtain the spy of the target to be monitored
Write image.
Step S206, carries out feature recognition to above-mentioned close-up image according to current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, judges to be monitored
Whether target belongs to the current target of deploying to ensure effective monitoring and control of illegal activities.
Step S207, if it is, above-mentioned target to be monitored is defined as into monitoring objective, and the tracing and monitoring monitoring mesh
Mark.
Step S202 to step S207 is identical to step S106 with step S101 respectively, repeats no more here.
Fig. 3 is the third schematic flow sheet of target monitoring method provided in an embodiment of the present invention, as shown in figure 3, one
In individual embodiment, this method includes following steps：
Step S301, obtains current frame image.
Step S302, Classification and Identification is carried out using video structural algorithm.
Step S303, determines target to be monitored.
Step S304, treats monitoring objective and is tracked, and adjusts focal length and the rotation of camera, obtains the target to be monitored
Close-up image.
Step S305, judges whether target to be monitored matches with target of deploying to ensure effective monitoring and control of illegal activities.
If so, then performing step S306；If it is not, then zoom re-executes step S301 to panoramic picture.
Step S306, sends warning message to monitor terminal.
Step S307, continues to track.
Each step in Fig. 3 is identical with the content of preceding method, repeats no more here.
In a kind of all examples for showing and describing of embodiment, any occurrence should be construed as merely exemplary
, not as limitation, therefore, other examples of exemplary embodiment can have different values.
Embodiment two：
Fig. 4 is the module composition schematic diagram of target monitoring device provided in an embodiment of the present invention, as shown in figure 4, the target
Supervising device includes：
Image collection module 10, for obtaining the current frame image that the camera of video camera is gathered；
Object acquisition module 20, for classifying to the object in current frame image, obtains current target correspondence of deploying to ensure effective monitoring and control of illegal activities
The suspect objects of classification；
Target determination module 30, for determining current frame image from the suspect objects got according to target of currently deploying to ensure effective monitoring and control of illegal activities
In target to be monitored；
Track up module 40, is tracked shooting for controlling camera to treat monitoring objective, obtains the mesh to be monitored
Target close-up image；
Judge module 50, for carrying out feature recognition to close-up image according to current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, judges to wait to supervise
Whether control target belongs to current target of deploying to ensure effective monitoring and control of illegal activities；
Monitoring module 60, for when the judged result of judge module 50 is is, target to be monitored being defined as to monitor mesh
Mark, and the tracing and monitoring monitoring objective.
In the embodiment of the present invention, image collection module 10 obtains the current frame image of the camera collection of video camera；Object
Acquisition module 20 is classified to the object in current frame image, obtains the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities；Mesh
Mark determining module 30 determines the target to be monitored in current frame image according to target of currently deploying to ensure effective monitoring and control of illegal activities from the suspect objects got；
Track up module 40 controls the camera to treat monitoring objective and is tracked shooting, obtains the close-up image of target to be monitored；
Judge module 50 carries out feature recognition according to current clarification of objective of deploying to ensure effective monitoring and control of illegal activities to the close-up image, judges whether target to be monitored belongs to
In current target of deploying to ensure effective monitoring and control of illegal activities；If it is, target to be monitored is defined as monitoring objective by monitoring module 60, and the tracing and monitoring monitoring
Target.Automatic sieve selects mesh to be monitored in the current frame image that the target monitoring device can be gathered from the camera of video camera
Mark, and whether the automatic decision target to be monitored belongs to current target of deploying to ensure effective monitoring and control of illegal activities, therefore independent of rear end control platform, saved people
Power cost, and be not easy to occur leaking anti-problem.Simultaneously as the device is applied to video camera, directly should in shooting generator terminal processing
The video file of camera acquisition, it is no longer necessary to transmit video file to back-end processing, thus it is real-time.In summary, originally
The target monitoring device that inventive embodiments are provided reduces the cost input during target monitoring, and improves target monitoring
Ageing and reliability.
The technique effect and preceding method embodiment phase of the device that the embodiment of the present invention is provided, its realization principle and generation
Together, to briefly describe, device embodiment part does not refer to part, refers to corresponding contents in preceding method embodiment.
Flow chart and block diagram in accompanying drawing show system, method and the computer journey of multiple embodiments according to the present invention
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code a, part for the module, program segment or code is used comprising one or more
In the executable instruction for realizing defined logic function.It should also be noted that in some realizations as replacement, being marked in square frame
The function of note can also be with different from the order marked in accompanying drawing generation.For example, two continuous square frames can essentially base
Originally it is performed in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.It is also noted that
It is, the combination of each square frame in block diagram and/or flow chart and the square frame in block diagram and/or flow chart that can use and perform rule
Fixed function or the special hardware based system of action realize, or can use the group of specialized hardware and computer instruction
Close to realize.
Embodiment three：
Fig. 5 is the structural representation of video camera provided in an embodiment of the present invention, and referring to Fig. 5, the embodiment of the present invention is also provided
A kind of video camera, including：Head 100, the horizontal stage electric machine 200 being connected with head 100, the camera being arranged on head 100
300th, memory 500, processor 400 and it is stored in the computer program that can be run on memory 500 and on processor 400.
Horizontal stage electric machine 200, camera 300 are electrically connected with processor 400 respectively, and processor 400 is realized when performing the computer program
The step of stating the method for embodiment one, wherein, processor 400 is by controlling horizontal stage electric machine 200 to drive camera 300 to rotate.
Preferably, memory 500, processor 400 are integrated in embedded processing chip.
Above-mentioned video camera also includes bus 600 and communication interface 700, processor 400, communication interface 700 and memory 500
Connected by bus 600.
Wherein, memory 500 may include high-speed random access memory (RAM, Random Access Memory),
Non-labile memory (non-volatile memory), for example, at least one magnetic disk storage may also be included.By extremely
A few communication interface 700 (can be wired or wireless) is realized logical between the system network element and at least one other network element
Letter connection, can use internet, wide area network, LAN, Metropolitan Area Network (MAN) etc..
Bus 600 can be isa bus, pci bus or eisa bus etc..Bus 600 can be divided into address bus, data
Bus, controlling bus etc..Only represented for ease of representing, in Fig. 5 with a four-headed arrow, it is not intended that only one bus or
A type of bus.
Wherein, memory 500 is used to store computer program, and the processor 400 is performed after execute instruction is received
The computer program, the method performed by device that the stream process that foregoing any embodiment of the embodiment of the present invention is disclosed is defined can
To be realized applied in processor 400, or by processor 400.
Processor 400 is probably a kind of IC chip, the disposal ability with signal.It is above-mentioned in implementation process
Each step of method can be completed by the integrated logic circuit of the hardware in processor 400 or the instruction of software form.On
The processor 400 stated can be general processor, including central processing unit (Central Processing Unit, referred to as
CPU), network processing unit (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (Digital
Signal Processing, abbreviation DSP), application specific integrated circuit (Application Specific Integrated
Circuit, abbreviation ASIC), ready-made programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or
Person other PLDs, discrete gate or transistor logic, discrete hardware components.It can realize or perform sheet
Disclosed each method, step and logic diagram in inventive embodiments.General processor can be microprocessor or the processing
Device can also be any conventional processor etc..The step of method with reference to disclosed in the embodiment of the present invention, can be embodied directly in
Hardware decoding processor performs completion, or performs completion with the hardware in decoding processor and software module combination.Software mould
Block can be located at random access memory, flash memory, read-only storage, programmable read only memory or electrically erasable programmable storage
In the ripe storage medium in this areas such as device, register.The storage medium is located at memory 500, and processor 400 reads memory
Information in 500, the step of completing the above method with reference to its hardware.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the shooting of foregoing description
The specific work process of machine, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
Target monitoring device and video camera provided in an embodiment of the present invention, the target monitoring method provided with above-described embodiment
With identical technical characteristic, so can also solve identical technical problem, identical technique effect is reached.
Example IV：
The embodiment of the present invention additionally provides a kind of computer for the non-volatile program code that can perform with processor can
Medium is read, the instruction that described program code includes can be used for performing the method described in previous methods embodiment, and implementing can
Referring to embodiment of the method, it will not be repeated here.
If the function is realized using in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in the executable non-volatile computer read/write memory medium of a processor.Understood based on such, the present invention
The part that is substantially contributed in other words to prior art of technical scheme or the part of the technical scheme can be with software
The form of product is embodied, and the computer software product is stored in a storage medium, including some instructions are to cause
One computer equipment (can be personal computer, server, or network equipment etc.) performs each embodiment institute of the invention
State all or part of step of method.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-
Only Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with
The medium of store program codes.
, can in several embodiments provided herein, it should be understood that disclosed method, device and video camera
To realize by another way.Device embodiment described above is only schematical, for example, stroke of the unit
Point, only a kind of division of logic function can have other dividing mode when actually realizing, in another example, multiple units or group
Part can combine or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown
Or the coupling each other discussed or direct-coupling or communication connection can be by some communication interfaces, device or unit
INDIRECT COUPLING or communication connection, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.
Finally it should be noted that：Embodiment described above, is only the embodiment of the present invention, to illustrate the present invention
Technical scheme, rather than its limitations, protection scope of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, it will be understood by those within the art that：Any one skilled in the art
The invention discloses technical scope in, it can still modify to the technical scheme described in previous embodiment or can be light
Change is readily conceivable that, or equivalent substitution is carried out to which part technical characteristic；And these modifications, change or replacement, do not make
The essence of appropriate technical solution departs from the spirit and scope of technical scheme of the embodiment of the present invention, should all cover the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention described should be defined by scope of the claims.
Claims (10)
1. a kind of target monitoring method, it is characterised in that methods described is applied to video camera, including：
Obtain the current frame image of the camera collection of the video camera；
Object in the current frame image is classified, the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are obtained；
Determined according to the current target of deploying to ensure effective monitoring and control of illegal activities from the suspect objects got to be monitored in the current frame image
Target；
Control the camera to be tracked shooting to the target to be monitored, obtain the close-up image of the target to be monitored；
Feature recognition is carried out to the close-up image according to the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, judges that the target to be monitored is
It is no to belong to the current target of deploying to ensure effective monitoring and control of illegal activities；
If it is, the target to be monitored is defined as into monitoring objective, and monitoring objective described in tracing and monitoring.
2. according to the method described in claim 1, it is characterised in that the object in the current frame image is divided
Class, obtains the suspect objects of current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities, including：
The object in the current frame image is classified according to default classifying rules, the default classifying rules includes will be right
As according to personage, vehicle and animal classification；
The suspect objects of the current target correspondence classification of deploying to ensure effective monitoring and control of illegal activities are extracted from the sorted object.
3. according to the method described in claim 1, it is characterised in that it is described according to the current target of deploying to ensure effective monitoring and control of illegal activities from the institute got
The target to be monitored determined in suspect objects in the current frame image is stated, including：
According to the current target of deploying to ensure effective monitoring and control of illegal activities, the similarity of the suspect objects is determined using video structural algorithm；
Suspect objects described in similarity highest are defined as the target to be monitored.
4. according to the method described in claim 1, it is characterised in that the control camera enters to the target to be monitored
Line trace is shot, and obtains the close-up image of the target to be monitored, including：
The focal length of the camera is adjusted, and determines that the target to be monitored exists using target tracking algorism and image compensation algorithm
Position in the video image of track up, the angle of rotation of the camera is controlled according to the position using cradle head control algorithm
Degree and velocity of rotation, obtain the close-up image of the target to be monitored.
5. according to the method described in claim 1, it is characterised in that described currently to deploy to ensure effective monitoring and control of illegal activities clarification of objective to described according to described
Close-up image carries out feature recognition, judges whether the target to be monitored belongs to the current target of deploying to ensure effective monitoring and control of illegal activities, including：
Extract the clarification of objective to be monitored in the close-up image；
The clarification of objective to be monitored is contrasted with the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, comparing result is obtained；
According to the comparing result, judge whether the target to be monitored belongs to the current target of deploying to ensure effective monitoring and control of illegal activities.
6. according to the method described in claim 1, it is characterised in that methods described also includes：
When judge the target to be monitored for it is described it is current deploy to ensure effective monitoring and control of illegal activities target when, send warning message to monitor terminal.
7. according to the method described in claim 1, it is characterised in that methods described also includes：
When receiving the alert target information of monitor terminal transmission, the object in the alert target information is defined as described
Current target of deploying to ensure effective monitoring and control of illegal activities.
8. a kind of target monitoring device, it is characterised in that including：
Image collection module, for obtaining the current frame image that the camera of the video camera is gathered；
Object acquisition module, for classifying to the object in the current frame image, obtains current target correspondence class of deploying to ensure effective monitoring and control of illegal activities
Other suspect objects；
Target determination module, it is described current for being determined according to the current target of deploying to ensure effective monitoring and control of illegal activities from the suspect objects got
Target to be monitored in two field picture；
Track up module, for controlling the camera to be tracked shooting to the target to be monitored, obtains described waiting to supervise
Control the close-up image of target；
Judge module, for carrying out feature recognition to the close-up image according to the current clarification of objective of deploying to ensure effective monitoring and control of illegal activities, judges institute
State whether target to be monitored belongs to the current target of deploying to ensure effective monitoring and control of illegal activities；
Monitoring module, for when the judged result of the judge module is is, the target to be monitored being defined as to monitor mesh
Mark, and monitoring objective described in tracing and monitoring.
9. a kind of video camera, it is characterised in that the horizontal stage electric machine that is connected including head, with the head, be arranged on the head
On camera, memory, processor and be stored in the computer journey that can be run on the memory and on the processor
Sequence；
The horizontal stage electric machine, the camera are electrically connected with the processor respectively, computer journey described in the computing device
The step of method described in the claims any one of 1-7 is realized during sequence, wherein, the processor is by controlling the head
Motor drives the camera to rotate.
10. a kind of computer-readable medium for the non-volatile program code that can perform with processor, it is characterised in that described
Program code makes any methods describeds of claim 1-7 described in the computing device.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710435936.0A CN107105207A (en) | 2017-06-09 | 2017-06-09 | Target monitoring method, target monitoring device and video camera |
| PCT/CN2018/089945 WO2018223955A1 (en) | 2017-06-09 | 2018-06-05 | Target monitoring method, target monitoring device, camera and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710435936.0A CN107105207A (en) | 2017-06-09 | 2017-06-09 | Target monitoring method, target monitoring device and video camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107105207A true CN107105207A (en) | 2017-08-29 |
Family
ID=59660134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710435936.0A Pending CN107105207A (en) | 2017-06-09 | 2017-06-09 | Target monitoring method, target monitoring device and video camera |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107105207A (en) |
| WO (1) | WO2018223955A1 (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107569848A (en) * | 2017-08-30 | 2018-01-12 | 武汉斗鱼网络科技有限公司 | One kind game classification method, apparatus and electronic equipment |
| CN107742422A (en) * | 2017-10-11 | 2018-02-27 | 公安部第三研究所 | Road Vehicle Violation Monitoring System and Method |
| CN108038408A (en) * | 2017-10-13 | 2018-05-15 | 西安天和防务技术股份有限公司 | Intelligent-tracking method and device, storage medium and electric terminal |
| CN108174102A (en) * | 2018-01-05 | 2018-06-15 | 北京红云融通技术有限公司 | A kind of method and system of the image for obtaining dynamic object |
| CN108921001A (en) * | 2018-04-18 | 2018-11-30 | 特斯联（北京）科技有限公司 | A kind of video monitor holder and its method for tracing using artificial intelligence prediction tracking |
| WO2018223955A1 (en) * | 2017-06-09 | 2018-12-13 | 北京深瞐科技有限公司 | Target monitoring method, target monitoring device, camera and computer readable medium |
| CN109024370A (en) * | 2018-10-16 | 2018-12-18 | 青岛特锐德电气股份有限公司 | A kind of parking stall lock control method and system |
| CN109102531A (en) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | A kind of target trajectory method for tracing and device |
| CN110266984A (en) * | 2019-07-01 | 2019-09-20 | 浙江大学 | A pan-tilt camera intelligent analysis teaching recording and broadcasting all-in-one machine |
| CN110378189A (en) * | 2019-04-22 | 2019-10-25 | 北京旷视科技有限公司 | A kind of monitoring method for arranging, device, terminal and storage medium |
| CN110599721A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Monitoring method, device and system and monitoring equipment |
| WO2019242672A1 (en) * | 2018-06-22 | 2019-12-26 | 杭州海康威视数字技术股份有限公司 | Method, device and system for target tracking |
| CN111402297A (en) * | 2020-03-25 | 2020-07-10 | 杭州博雅鸿图视频技术有限公司 | Target tracking detection method, system, electronic device and storage medium |
| CN112085927A (en) * | 2019-06-15 | 2020-12-15 | 高雪亚 | Reliable target monitoring system |
| CN112132315A (en) * | 2020-08-18 | 2020-12-25 | 华为技术有限公司 | Target object escape route prediction method and deployment control platform |
| CN112180818A (en) * | 2019-07-05 | 2021-01-05 | 深圳市华创技术有限公司 | Intelligent AI device and control method |
| CN112861853A (en) * | 2021-01-21 | 2021-05-28 | 济南浪潮高新科技投资发展有限公司 | Knowledge graph-based vehicle identification method and device |
| CN113507577A (en) * | 2021-07-07 | 2021-10-15 | 杭州海康威视系统技术有限公司 | Target object detection method, device, equipment and storage medium |
| CN113665495A (en) * | 2021-09-23 | 2021-11-19 | 温州大学大数据与信息技术研究院 | Vehicle-mounted target tracker convenient to install and based on computer vision |
| CN113724324A (en) * | 2021-08-30 | 2021-11-30 | 杭州华橙软件技术有限公司 | Control method and device of holder, storage medium and electronic device |
| CN114040115A (en) * | 2021-11-29 | 2022-02-11 | 海南哦课教育科技有限公司 | Method, device, medium and electronic equipment for capturing abnormal action of target object |
| CN114419555A (en) * | 2022-01-19 | 2022-04-29 | 广东飞达交通工程有限公司 | Road traffic target tracking method based on deep convolutional neural network |
| CN114900648A (en) * | 2022-03-28 | 2022-08-12 | 安克创新科技股份有限公司 | Pet monitoring method based on camera device with holder and camera device |
| CN116883297A (en) * | 2023-06-30 | 2023-10-13 | 中国舰船研究设计中心 | Multi-target automatic verification method based on infrared and visible light fusion |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739054B (en) * | 2019-03-25 | 2025-06-17 | 北京京东尚科信息技术有限公司 | Target tracking and marking method, system, electronic device and readable storage medium |
| CN111860063B (en) * | 2019-04-30 | 2023-08-11 | 杭州海康威视数字技术股份有限公司 | Gait data construction system, method and device |
| CN112241649B (en) * | 2019-07-16 | 2025-01-10 | 浙江宇视科技有限公司 | A target identification method and device |
| CN113111685B (en) * | 2020-01-10 | 2024-08-13 | 杭州海康威视数字技术股份有限公司 | Tracking system, tracking data acquisition/processing method and device |
| CN111460977B (en) * | 2020-03-30 | 2024-02-20 | 广东电网有限责任公司电力科学研究院 | Cross-view personnel re-identification method, device, terminal and storage medium |
| CN111626165B (en) * | 2020-05-15 | 2024-02-02 | 安徽江淮汽车集团股份有限公司 | Pedestrian recognition method and device, electronic equipment and storage medium |
| CN112580469A (en) * | 2020-12-10 | 2021-03-30 | 上海慈航建设发展有限公司 | System, method, equipment and storage medium for auditing and managing illegal videos |
| CN112883815B (en) * | 2021-01-26 | 2022-11-29 | 首都师范大学 | A method, system and server for automatic monitoring of agricultural machinery |
| CN113485465B (en) * | 2021-06-01 | 2024-08-02 | 浙江大华技术股份有限公司 | Camera holder control method, device, equipment and storage medium |
| CN113421431B (en) * | 2021-06-17 | 2022-12-02 | 京东方科技集团股份有限公司 | Emergency channel monitoring method and device |
| CN113487727B (en) * | 2021-07-14 | 2022-09-02 | 广西民族大学 | Three-dimensional modeling system, device and method |
| CN116311873A (en) * | 2021-12-20 | 2023-06-23 | 上海三思电子工程有限公司 | Traffic information content distribution confirmation system, method, terminal and storage medium |
| CN114549876A (en) * | 2022-01-10 | 2022-05-27 | 上海明胜品智人工智能科技有限公司 | Image processing method, device and system |
| CN115278162B (en) * | 2022-06-23 | 2025-07-08 | 浙江大华技术股份有限公司 | Monitoring system scheduling method, device, computer equipment and readable storage medium |
| CN115082836B (en) * | 2022-07-23 | 2022-11-11 | 深圳神目信息技术有限公司 | Behavior recognition-assisted target object detection method and device |
| CN115311620A (en) * | 2022-08-08 | 2022-11-08 | 深圳市权志信息技术有限公司 | A humanoid movement monitoring method, system, terminal and storage medium |
| CN115883780A (en) * | 2022-10-21 | 2023-03-31 | 国网河北省电力有限公司保定供电分公司 | A monitoring system and method |
| CN115690155A (en) * | 2022-10-28 | 2023-02-03 | 武汉中海庭数据技术有限公司 | Signboard tracking method, signboard tracking system, electronic equipment and storage medium |
| CN115457449B (en) * | 2022-11-11 | 2023-03-24 | 深圳市马博士网络科技有限公司 | Early warning system based on AI video analysis and monitoring security protection |
| CN117255180B (en) * | 2023-11-20 | 2024-02-09 | 山东通广电子股份有限公司 | Intelligent safety monitoring equipment and monitoring method |
| CN118764706B (en) * | 2024-09-04 | 2024-12-13 | 航天宏图信息技术股份有限公司 | Pan/tilt control method, device, equipment and medium for monitoring camera center composition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201278180Y (en) * | 2008-05-28 | 2009-07-22 | 丁国锋 | Automatic tracking recognition system |
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracking and identifying system controlled by nerve |
| CN102968802A (en) * | 2012-11-28 | 2013-03-13 | 无锡港湾网络科技有限公司 | Moving target analyzing and tracking method and system based on video monitoring |
| CN103679156A (en) * | 2013-12-31 | 2014-03-26 | 武汉理工大学 | Automatic identification and tracking method for various kinds of moving objects |
| CN104506819A (en) * | 2015-01-06 | 2015-04-08 | 成都新舟锐视科技有限公司 | Multi-camera real-time linkage mutual feedback tracing system and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050104958A1 (en) * | 2003-11-13 | 2005-05-19 | Geoffrey Egnal | Active camera video-based surveillance systems and methods |
| CN101626489B (en) * | 2008-07-10 | 2011-11-02 | 苏国政 | Method and system for intelligently identifying and automatically tracking objects under unattended condition |
| WO2010090621A1 (en) * | 2009-02-09 | 2010-08-12 | Vitamin D, Inc. | Systems and methods for video monitoring |
| CN106600977B (en) * | 2017-02-13 | 2020-09-15 | 深圳英飞拓科技股份有限公司 | Multi-feature recognition-based illegal parking detection method and system |
| CN107105207A (en) * | 2017-06-09 | 2017-08-29 | 北京深瞐科技有限公司 | Target monitoring method, target monitoring device and video camera |
-
2017
- 2017-06-09 CN CN201710435936.0A patent/CN107105207A/en active Pending
-
2018
- 2018-06-05 WO PCT/CN2018/089945 patent/WO2018223955A1/en not_active Ceased
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201278180Y (en) * | 2008-05-28 | 2009-07-22 | 丁国锋 | Automatic tracking recognition system |
| CN101635834A (en) * | 2008-07-21 | 2010-01-27 | 侯荣琴 | Automatic tracking and identifying system controlled by nerve |
| CN102968802A (en) * | 2012-11-28 | 2013-03-13 | 无锡港湾网络科技有限公司 | Moving target analyzing and tracking method and system based on video monitoring |
| CN103679156A (en) * | 2013-12-31 | 2014-03-26 | 武汉理工大学 | Automatic identification and tracking method for various kinds of moving objects |
| CN104506819A (en) * | 2015-01-06 | 2015-04-08 | 成都新舟锐视科技有限公司 | Multi-camera real-time linkage mutual feedback tracing system and method |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018223955A1 (en) * | 2017-06-09 | 2018-12-13 | 北京深瞐科技有限公司 | Target monitoring method, target monitoring device, camera and computer readable medium |
| CN107569848A (en) * | 2017-08-30 | 2018-01-12 | 武汉斗鱼网络科技有限公司 | One kind game classification method, apparatus and electronic equipment |
| CN107742422A (en) * | 2017-10-11 | 2018-02-27 | 公安部第三研究所 | Road Vehicle Violation Monitoring System and Method |
| CN108038408A (en) * | 2017-10-13 | 2018-05-15 | 西安天和防务技术股份有限公司 | Intelligent-tracking method and device, storage medium and electric terminal |
| CN108174102A (en) * | 2018-01-05 | 2018-06-15 | 北京红云融通技术有限公司 | A kind of method and system of the image for obtaining dynamic object |
| CN108921001A (en) * | 2018-04-18 | 2018-11-30 | 特斯联（北京）科技有限公司 | A kind of video monitor holder and its method for tracing using artificial intelligence prediction tracking |
| CN110599721A (en) * | 2018-06-13 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | Monitoring method, device and system and monitoring equipment |
| WO2019242672A1 (en) * | 2018-06-22 | 2019-12-26 | 杭州海康威视数字技术股份有限公司 | Method, device and system for target tracking |
| CN109102531A (en) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | A kind of target trajectory method for tracing and device |
| CN109024370A (en) * | 2018-10-16 | 2018-12-18 | 青岛特锐德电气股份有限公司 | A kind of parking stall lock control method and system |
| CN110378189A (en) * | 2019-04-22 | 2019-10-25 | 北京旷视科技有限公司 | A kind of monitoring method for arranging, device, terminal and storage medium |
| CN112085927A (en) * | 2019-06-15 | 2020-12-15 | 高雪亚 | Reliable target monitoring system |
| CN112085927B (en) * | 2019-06-15 | 2022-09-27 | 湖北讯泰通信电子有限公司 | Reliable target monitoring system |
| CN110266984A (en) * | 2019-07-01 | 2019-09-20 | 浙江大学 | A pan-tilt camera intelligent analysis teaching recording and broadcasting all-in-one machine |
| CN110266984B (en) * | 2019-07-01 | 2020-12-18 | 浙江大学 | A PTZ camera intelligent analysis teaching recording and broadcasting integrated machine |
| CN112180818A (en) * | 2019-07-05 | 2021-01-05 | 深圳市华创技术有限公司 | Intelligent AI device and control method |
| CN111402297A (en) * | 2020-03-25 | 2020-07-10 | 杭州博雅鸿图视频技术有限公司 | Target tracking detection method, system, electronic device and storage medium |
| CN112132315A (en) * | 2020-08-18 | 2020-12-25 | 华为技术有限公司 | Target object escape route prediction method and deployment control platform |
| CN112861853A (en) * | 2021-01-21 | 2021-05-28 | 济南浪潮高新科技投资发展有限公司 | Knowledge graph-based vehicle identification method and device |
| CN113507577A (en) * | 2021-07-07 | 2021-10-15 | 杭州海康威视系统技术有限公司 | Target object detection method, device, equipment and storage medium |
| CN113724324A (en) * | 2021-08-30 | 2021-11-30 | 杭州华橙软件技术有限公司 | Control method and device of holder, storage medium and electronic device |
| CN113724324B (en) * | 2021-08-30 | 2023-12-19 | 杭州华橙软件技术有限公司 | Control method and device of cradle head, storage medium and electronic device |
| CN113665495A (en) * | 2021-09-23 | 2021-11-19 | 温州大学大数据与信息技术研究院 | Vehicle-mounted target tracker convenient to install and based on computer vision |
| CN114040115A (en) * | 2021-11-29 | 2022-02-11 | 海南哦课教育科技有限公司 | Method, device, medium and electronic equipment for capturing abnormal action of target object |
| CN114419555A (en) * | 2022-01-19 | 2022-04-29 | 广东飞达交通工程有限公司 | Road traffic target tracking method based on deep convolutional neural network |
| CN114900648A (en) * | 2022-03-28 | 2022-08-12 | 安克创新科技股份有限公司 | Pet monitoring method based on camera device with holder and camera device |
| CN116883297A (en) * | 2023-06-30 | 2023-10-13 | 中国舰船研究设计中心 | Multi-target automatic verification method based on infrared and visible light fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018223955A1 (en) | 2018-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107105207A (en) | Target monitoring method, target monitoring device and video camera | |
| KR102051829B1 (en) | Bigdata Previewport Multi-resolution video transmission CCTV using License plate detection and Bigdata Previewport Multi-resolution video transmission traffic control method using License plate detection | |
| KR102122859B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| KR101824446B1 (en) | A reinforcement learning based vehicle number recognition method for CCTV | |
| KR102122850B1 (en) | Solution for analysis road and recognition vehicle license plate employing deep-learning | |
| Kulkarni et al. | Real time vehicle detection, tracking and counting using Raspberry-Pi | |
| CN106339657B (en) | Crop straw burning monitoring method based on monitor video, device | |
| CN106878670A (en) | A kind of method for processing video frequency and device | |
| CN109672863A (en) | A kind of construction personnel's safety equipment intelligent monitoring method based on image recognition | |
| CN112084928B (en) | Road traffic accident detection method based on visual attention mechanism and ConvLSTM network | |
| CN107169458A (en) | Data processing method, device and storage medium | |
| CN109413411A (en) | A kind of blank screen recognition methods, device and the server of monitoring circuit | |
| CN114140745A (en) | Method, system, device and medium for detecting personnel attributes of construction site | |
| CN117636241B (en) | Multimodal pedestrian detection and tracking method in low-light scenes based on decision-level fusion | |
| KR101337554B1 (en) | Apparatus for trace of wanted criminal and missing person using image recognition and method thereof | |
| CN104715264A (en) | Method and system for recognizing video images of motion states of vehicles in expressway tunnel | |
| Jin et al. | A deep-learning-based scheme for detecting driver cell-phone use | |
| CN115294519A (en) | An abnormal event detection and early warning method based on lightweight network | |
| CN118097580A (en) | A dangerous behavior protection method and system based on Yolov4 network | |
| Bedruz et al. | Philippine vehicle plate localization using image thresholding and genetic algorithm | |
| CN111062319B (en) | Driver call detection method based on active infrared image | |
| CN119992463A (en) | Track worker safety wear detection method, device, equipment and storage medium | |
| Zhou | Traffic accident detection based on YOLOv11 | |
| CN114155472A (en) | Method, device and equipment for detecting abnormal state of factory scene empty face protection equipment | |
| CN107609498A (en) | A kind of data processing method of computer supervisory control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170829 |