WO2019019943A1 - 跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统 - Google Patents

跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统 Download PDF

Info

Publication number
WO2019019943A1
WO2019019943A1 PCT/CN2018/096094 CN2018096094W WO2019019943A1 WO 2019019943 A1 WO2019019943 A1 WO 2019019943A1 CN 2018096094 W CN2018096094 W CN 2018096094W WO 2019019943 A1 WO2019019943 A1 WO 2019019943A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
monitoring
trajectory
monitoring area
action
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.)
Ceased
Application number
PCT/CN2018/096094
Other languages
English (en)
French (fr)
Inventor
陈伟
葛有功
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Publication of WO2019019943A1 publication Critical patent/WO2019019943A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

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
    • H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory

Definitions

  • the present application relates to the field of Internet technology applications, and in particular, to a method and a data processing method, apparatus and system for cross-region target trajectory tracking.
  • a face recognition camera needs to be continuously deployed in a monitoring area, and a face recognition camera is used to perform tracking shooting on the same target person on each floor.
  • the embodiment of the present application provides a cross-region target trajectory tracking method and a data processing method, device and system, so as to at least solve the facial features of the same target person on each layer through multiple face recognition cameras in the prior art. Identifying and monitoring the shooting results in a technical problem of complex deployment and low tracking of target people.
  • a data processing method including: acquiring at least two geo-fence data having an intersection area, wherein the intersection area is a common area, and the geo-fence data includes an action track of the object; Obtaining a first action track and a second action track in the two geofence data; determining the first action track and the second action track as matching tracks; displaying the first action track and the second action track.
  • a method for tracking cross-region target trajectory including: separately extracting motion trajectories of targets in at least two monitoring regions; and determining coincidence of motion trajectories of targets in at least two monitoring regions. Whether the degree is greater than a preset value; if the result of the determination is that the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value, the action track of the target in the at least two monitoring areas is generated.
  • the method before extracting the action track of the target in the at least two monitoring areas, the method further includes: when the at least two monitoring areas include the first monitoring area and the second monitoring area, when the target enters the first monitoring area At the time, the target device is marked by the monitoring device, and the action track of the corresponding target in the first monitoring area is generated in the first monitoring area according to the mark; when the target leaves the first monitoring area, the first part adjacent to the first monitoring area is called.
  • the monitoring device of the monitoring area determines whether the monitoring device of the second monitoring area captures at least one target; if the determination result is yes, marks at least one target in the second monitoring area, and generates a target in the second monitoring The trajectory of the area.
  • extracting the action track of the target in the at least two monitoring areas respectively includes: in the case that the at least two monitoring areas include the first monitoring area and the second monitoring area, respectively, in the first monitoring area, respectively, the first monitoring At least one target in the area is marked, and the action trajectory of the marked at least one target is extracted; in the second monitoring area, at least one target in the second monitored area is marked, and the action of the marked at least one target is extracted Track.
  • marking at least one target in the second monitoring area, and extracting the action track of the at least one target after the marking includes: dividing the second monitoring area by a preset cell, Obtaining a second position binning map of the second monitoring area in the form of a grid; marking the second position binning map according to the at least one target; generating according to the position change of the at least one target in the second position binning map a trajectory matrix; the trajectory matrix is determined as an action trajectory of the at least one target after the marking in the second monitoring area.
  • determining whether the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value includes: acquiring, in a case where the at least two monitoring areas include the first monitoring area and the second monitoring area, acquiring the first monitoring area An overlapping area with the second monitoring area; marking at least one target in the overlapping area, and generating an action trajectory according to the at least one target after the marking; determining whether the action trajectory of the at least one target in the overlapping area is related to at least one target in the first monitoring area The motion trajectory and the coincidence degree of the motion trajectory of at least one target in the second monitoring area are greater than a preset value.
  • the action track of the generating target in the at least two monitoring areas includes: the coincidence is greater than In the case of a preset value, determining that at least one of the overlapping areas is the same target as at least one of the first monitoring area and the second monitoring area; according to the time and the first monitoring area and the second monitoring area A position change of at least one target generates an action trajectory of at least one target.
  • a data processing apparatus including: a first obtaining module, configured to acquire at least two geo-fence data having an intersection area, where the intersection area is a common area, and the geo-fence data Include a motion trajectory of the object; a second acquiring module, configured to respectively acquire a first motion trajectory and a second motion trajectory of the two geofence data; and a trajectory determining module, configured to determine that the first motion trajectory and the second motion trajectory are matched a track; a display module for displaying the first action track and the second action track.
  • an apparatus for tracking cross-region target trajectory including: an extracting module, configured to respectively extract motion trajectories of targets in at least two monitoring regions; and a determining module, configured to determine at least two Whether the coincidence degree of the action track of the target in the monitoring area is greater than a preset value; the track generating module is configured to generate the target if the result of the determination is that the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value Action trajectories in at least two surveillance areas.
  • the extracting module includes: a first extracting unit, configured to: in the first monitoring area, at least the first monitoring area, where the at least two monitoring areas include the first monitoring area and the second monitoring area Marking a target and extracting a motion trajectory of the at least one target after the marking; the second extracting unit is configured to mark at least one target in the second monitoring area in the second monitoring area, and extract at least one of the marked objects The trajectory of a target's action.
  • the determining module includes: an acquiring unit, configured to acquire an overlapping area of the first monitoring area and the second monitoring area, where the at least two monitoring areas include the first monitoring area and the second monitoring area; And the at least one target in the overlapping area is used to generate an action trajectory according to the at least one target after the marking; the determining unit is configured to determine whether the action trajectory of the at least one target in the overlapping area and the action trajectory of the at least one target in the first monitoring area And the coincidence degree of the action track of the at least one target in the second monitoring area is greater than a preset value.
  • a system for cross-region target trajectory tracking comprising: at least two micro monitoring devices for marking at least one captured target and according to at least one target after marking Generating an action track of the at least one target, and reporting the action track of the at least one target to the server; the server is configured to acquire an action track of the at least one target uploaded by the at least two micro monitoring devices, and determine the shooting of the at least two micro monitoring devices Whether at least one target appears at the same time in the overlapping area, and calculates a coincidence degree of the monitoring area where the at least one target is located in at least two micro monitoring devices, and if the coincidence degree is greater than a preset value, determining at least two micro monitoring devices At least one target in the monitored area is the same target, and an action track of at least one target in the monitored area where the at least two micro monitoring devices are located is generated.
  • a storage medium including a stored program, wherein a method of controlling the cross-region target trajectory tracking by the device where the storage medium is located is controlled while the program is running.
  • a processor for executing a program, wherein the method for performing the above-described cross-region target trajectory tracking is executed while the program is running.
  • a storage medium includes a stored program, wherein the device in which the storage medium is located is controlled to execute the data processing method when the program is running.
  • a processor for executing a program, wherein the data processing method is executed when the program is running.
  • the action trajectory of the target in the at least two monitoring areas is separately extracted; determining whether the coincidence degree of the action trajectory of the target in the at least two monitoring areas is greater than a preset value; and the determining result is at least two monitoring areas. If the coincidence degree of the target trajectory is greater than the preset value, the action trajectory of the target in at least two monitoring areas is generated, which achieves the purpose of easy deployment of the target tracking system, thereby improving the tracking efficiency of the target task.
  • the technical effect further solves the technical problem that the prior art needs to identify and monitor the facial features of the same target person by using multiple face recognition cameras, resulting in complicated deployment and low target tracking efficiency.
  • FIG. 1 is a hardware structural block diagram of a computer terminal of a method for tracking a cross-region target trajectory according to an embodiment of the present application
  • FIG. 2 is a flowchart of a method for cross-region target trajectory tracking according to Embodiment 1 of the present application;
  • FIG. 3 is a schematic diagram of a method for tracking a cross-region target trajectory according to Embodiment 1 of the present application;
  • FIG. 4 is a schematic diagram of another method for tracking trajectory of a cross-region target according to Embodiment 1 of the present application.
  • FIG. 4a is a flowchart of a data processing method according to Embodiment 2 of the present application.
  • FIG. 5 is a schematic structural diagram of an apparatus for tracking a cross-region target trajectory according to Embodiment 3 of the present invention.
  • FIG. 5a is a schematic structural diagram of a data processing apparatus according to Embodiment 4 of the present invention.
  • FIG. 6 is a schematic diagram of interaction of a system for cross-region target trajectory tracking according to Embodiment 5 of the present invention.
  • FIG. 1 is a hardware structural block diagram of a computer terminal of a method for tracking a cross-region target trajectory according to an embodiment of the present application.
  • computer terminal 10 may include one or more (only one shown) processor 102 (processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA)
  • processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA)
  • a memory 104 for storing data
  • a transmission module 106 for communication functions.
  • computer terminal 10 may also include more or fewer components than those shown in FIG. 1, or have a different configuration than that shown in FIG.
  • the memory 104 can be used to store software programs and modules of the application software, such as program instructions/modules corresponding to the method of cross-region target trajectory tracking in the embodiment of the present application, and the processor 102 runs the software programs and modules stored in the memory 104. Thereby performing various functional applications and data processing, that is, a method of implementing cross-region target trajectory tracking of the above-described application.
  • Memory 104 may include high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory.
  • memory 104 may further include memory remotely located relative to processor 102, which may be coupled to computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the transmission module 106 is configured to receive or transmit data via a network.
  • the network specific examples described above may include a wireless network provided by a communication provider of the computer terminal 10.
  • the transport module 106 includes a Network Interface Controller (NIC) that can be connected to other network devices through a base station to communicate with the Internet.
  • the transmission module 106 can be a Radio Frequency (RF) module for communicating with the Internet wirelessly.
  • NIC Network Interface Controller
  • RF Radio Frequency
  • the present application provides a method for cross-region target trajectory tracking as shown in FIG. 2.
  • 2 is a flow chart of a method for cross-region target trajectory tracking according to Embodiment 1 of the present application.
  • a method for cross-region target trajectory tracking is provided, and the steps of the method include:
  • Step S202 respectively extracting motion trajectories of the targets in the at least two monitoring areas
  • the method for tracking the trajectory of the cross-region target provided by the present application can be applied to the field of indoor security monitoring, wherein the present invention is different from the prior art in that the mini-camera is substituted for the face recognition in the prior art.
  • the camera reduces the cost of security monitoring and increases the number of miniature cameras and the access compatibility of the miniature camera to the security monitoring system.
  • the area that each micro camera can monitor is called a monitoring area
  • the trajectory of each target person (ie, the target in the present application) moving in the monitoring area is called a motion trajectory
  • each micro camera is based on the distribution of the micro camera.
  • the monitoring area in which the target person is located will generate the action track of the target person in the monitored area after the target person appears in the monitoring area.
  • Step S204 determining whether the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value
  • step S204 of the present application when the action trajectory of the target A needs to be acquired, the action trajectory of the target A in the at least two monitoring areas is acquired in step S202, and the coincidence degree of the action trajectory of the target A in the at least two monitoring areas is determined. Whether it is greater than the preset value, if it is greater than the preset value, step S206 is performed; if it is less than the preset value, it indicates that the coincidence degree of the action track of the target in at least two monitoring areas is low, so the target A is not moved, or the target A is not Move to another monitoring area.
  • Step S206 in a case where the result of the determination is that the coincidence degree of the action trajectory of the target in the at least two monitoring areas is greater than a preset value, the action trajectory of the target in the at least two monitoring areas is generated.
  • step S206 of the present application based on the determination of step S204, when the coincidence degree is greater than the preset value, the target in the at least two monitoring areas is the same target, and then the target is generated according to the target in at least two monitoring.
  • the trajectory of action in the area is the same target, and then the target is generated according to the target in at least two monitoring.
  • the trajectory tracking of the cross-region target trajectory is taken as an example for the trajectory tracking of the cross-region target trajectory.
  • the embodiment provided by the present application does not need to be deployed for the face recognition camera, but needs to perform the human trajectory.
  • a miniature camera (hereinafter referred to as “camera”) is continuously deployed in the tracked area to ensure that the field of view between the cameras crosses or covers.
  • the camera in the cross-region target trajectory tracking method provided by the present application only collects the human body and the corresponding trajectory and time information appearing in the field of view and uses each low-speed wireless transmission technology to identify each coordinate information that can be recognized as human in the field of view.
  • the completion of the report does not involve face recognition of specific personnel, so it does not infringe the privacy of the user.
  • FIG. 3 is a schematic diagram of a cross-region target trajectory tracking method according to Embodiment 1 of the present application. As shown in FIG. 3, the method for tracking cross-region target trajectory provided by the present application is as follows:
  • the camera O identifies a person and its trajectory [mark the person as Idxo];
  • the background server commands the adjacent micro camera to capture
  • Camera A obtains the person appearing in the field of view and distinguishes the calibration, records the moment of occurrence and the trajectory of the journey and completes the report to the background server;
  • the background server matches the appearance track marked as Idxo in the camera O with the personnel track reported by A, searches for the person whose coincidence degree is greater than the set threshold, and calibrates the person to be in the scope of the camera A and inherits as Idxo;
  • the action trajectory of the target in the at least two monitoring areas is separately extracted; determining whether the coincidence degree of the action trajectory of the target in the at least two monitoring areas is greater than a preset value; and the determining result is at least two monitoring areas. If the coincidence degree of the target trajectory is greater than the preset value, the action trajectory of the target in at least two monitoring areas is generated, which achieves the purpose of easy deployment of the target tracking system, thereby improving the tracking efficiency of the target task.
  • the technical effect further solves the technical problem that the prior art needs to identify and monitor the facial features of the same target person by using multiple face recognition cameras, resulting in complicated deployment and low target tracking efficiency.
  • the method for tracking the cross-region target trajectory provided by the present application before the extracting the motion trajectory of the target in the at least two monitoring regions in the step S202 further includes:
  • Step S199 in a case where the at least two monitoring areas include the first monitoring area and the second monitoring area, when the target enters the first monitoring area, the target is marked by the monitoring device, and is generated in the first monitoring area according to the marking. Corresponding to the action track of the target in the first monitoring area;
  • Step S200 When the target leaves the first monitoring area, the monitoring device of the second monitoring area adjacent to the first monitoring area is called to determine whether the monitoring device of the second monitoring area captures at least one target;
  • Step S201 If the determination result is yes, at least one target in the second monitoring area is marked, and an action trajectory of the target in the second monitoring area is generated.
  • the two monitoring areas are taken as an example, that is, the first monitoring area and the second monitoring area, in combination with steps S199 to S201.
  • each monitoring area Before extracting the action trajectory of the target in the two monitoring areas, each monitoring area first marks the targets appearing in the monitoring area, and generates each marked target object in time sequence.
  • the action generated by the monitoring area a track, and when the target in the first monitoring area leaves the first monitoring area, the second monitoring area adjacent to the first monitoring area marks each target entering the monitoring area, and generates a mark each The trajectory of the target's action, so that it can provide data support in the process of the specificity.
  • step S202 the action track of the target in the at least two monitoring areas is respectively extracted in step S202, including:
  • Step 1 In a case that the at least two monitoring areas include the first monitoring area and the second monitoring area, in the first monitoring area, at least one target in the first monitoring area is marked, and the marked at least one target is extracted. Action track
  • Step 2 In the second monitoring area, mark at least one target in the second monitoring area, and extract the action track of the marked at least one target.
  • Step1 and Step2 in the process of extracting the action trajectory of at least one target of each monitoring area, the marked target is extracted first, and then the action trajectory of each target in the monitoring area is extracted according to the mark.
  • step S202 at least one target in the first monitoring area is marked, and the action track of the at least one target after the marking is extracted includes:
  • Step 1 dividing the first monitoring area by a preset cell, and obtaining a first position binning map of the first monitoring area in the form of a grid;
  • Step 2 marking according to at least one target in the first position binning map
  • Step 3 generating a trajectory matrix according to the position change of the at least one target after the marking in the first position grid map
  • Step 4 Determine the trajectory matrix as the action trajectory of the at least one target after the marking in the first monitoring area.
  • step S202 at least one target in the second monitoring area is marked, and the action track of the at least one target after the marking is extracted includes:
  • Step 1 dividing the second monitoring area by a preset cell to obtain a second position binning map of the second monitoring area in the form of a grid;
  • Step 2 marking according to at least one target in the second position binning map
  • Step 3 generating a trajectory matrix according to the position change of the at least one target after the marking in the second position grid map
  • Step 4 Determine the trajectory matrix as the action trajectory of the marked at least one target in the second monitoring area.
  • the first position frame and the second frame composed of cells are respectively arranged for each target.
  • the position change in the position grid map generates an action trajectory of each target in the first monitoring area and the second monitoring area.
  • determining whether the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value in step S204 includes:
  • Step 1 Acquire an overlapping area of the first monitoring area and the second monitoring area, where the at least two monitoring areas include the first monitoring area and the second monitoring area;
  • Step 2 marking at least one target in the overlapping area, and generating an action track according to at least one target after the marking;
  • Step 3 Determine whether the action track of the at least one target in the overlap region is equal to the action track of the at least one target in the first monitoring area, and the coincidence degree of the action track of the at least one target in the second monitoring area is greater than a preset value.
  • step S206 if the result of the determination is that the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value, the action track of the generated target in the at least two monitoring areas includes:
  • Step 1 where the coincidence degree is greater than a preset value, determining that at least one target in the overlapping area is at least one target in the first monitoring area and at least one target in the second monitoring area is the same target;
  • Step 2 Generate an action trajectory of the at least one target according to the time and the position change of the at least one target in the first monitoring area and the second monitoring area.
  • the action trajectory of the target of the two monitoring area overlapping areas by predicting the action trajectory of each target in the first monitoring area and the second monitoring area, if the target trajectory of the overlapping area is If the coincidence degree of the action track of the target of the first monitoring area and the second monitoring area is greater than a preset value, the target of the overlapping area is the same target as the target of the first monitoring area and the second monitoring area, and further according to the overlapping area.
  • the motion trajectory of the target in the first monitoring area and the second monitoring area generates a trajectory of the target in the entire monitoring area.
  • FIG. 4 is a schematic diagram of another method for tracking trajectory of a cross-region target according to the first embodiment of the present application. As shown in FIG. 4, the method for tracking trajectory of a cross-region target provided by the present application is as follows:
  • each size can accommodate no more than one person's physical features.
  • the grid position in the field of view in each camera is identified by a matrix, for example: ⁇ M, N ⁇ , which means that the grid range is M rows, N columns of matrix type (the actual field of view of the camera is not necessarily rectangular, need to match The industry's existing deformity correction technology).
  • ⁇ M,N ⁇ o *Z ⁇ N,N ⁇ ⁇ M,N ⁇ A .
  • Z is an N-dimensional matrix. For example, it can be seen that the position of the red star in the camera O is (2, 14), and after matrix conversion, its position in the camera A is (2, 2).
  • the traveling track in the area in the camera O can be represented by a matrix as Track O , and the traveling track in the area in the camera A is available.
  • the matrix is represented as Track A.
  • the visual map of the X personal trajectory of the overlapping area in the camera O in the camera A can be obtained: Track A, 1 ', Track A, 2 '... Track A, x ', and then with the Track in the camera A A performs similarity comparison. If the similarity is greater than the preset threshold, it means that the two tracks correspond to the same person.
  • the background server matches the fuzzy algorithm of the human trajectory recognition between the cameras to obtain the tracking of the continuous trajectory when the pedestrian moves between the cameras; and the camera of the pedestrian trajectory monitor only captures the trajectory of the pedestrian, The appearance of time and the marking of pedestrians will not capture the video stream for face recognition, and will not cause leakage of human privacy.
  • the method for tracking the trajectory of the cross-region target according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. But in many cases the former is a better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in various embodiments of the present application.
  • FIG. 4a is a flowchart of a data processing method according to Embodiment 2 of the present application. As shown in FIG. 4a, according to an aspect of the embodiments of the present application, a data processing method is provided.
  • the data processing method provided by the present application includes the following steps:
  • Step S402 acquiring at least two geofence data having an intersection area, where the intersection area is a public area, and the geofence data includes an action track of the object therein;
  • Step S404 respectively acquiring a first action track and a second action track in the two geofence data
  • Step S406 determining that the first motion trajectory and the second motion trajectory are matching trajectories
  • Step S408 displaying the first action track and the second action track.
  • the data processing method provided by the present application may be applicable to monitoring the security field, particularly for target trajectory tracking prediction.
  • each target is obtained.
  • the first action track and the second action track in the two geofence data determine whether the same target is by matching the two action tracks.
  • the geofence data includes an action track of the object; and acquiring the first action track in the two geofence data respectively And a second action trajectory; determining the first action trajectory and the second action trajectory as matching trajectories; displaying the first action trajectory and the second action trajectory, achieving the purpose of facilitating deployment of the target tracking system, thereby achieving the improvement of the target task
  • the technical effect of tracking efficiency further solves the problem that the prior art needs to identify and monitor the facial features of the same target person through each face recognition camera through multiple face recognition cameras, resulting in complicated deployment and low target tracking efficiency. problem.
  • the data processing method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases The former is a better implementation.
  • the technical solution of the present application which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM, disk,
  • the optical disc includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in various embodiments of the present application.
  • FIG. 5 is a schematic structural diagram of an apparatus for tracking the trajectory of the cross-region target according to the third embodiment of the present invention.
  • the apparatus for tracking the cross-region target trajectory includes: an extraction module 52, a determination module 54, and a trajectory generation module 56.
  • the extracting module 52 is configured to respectively extract the action trajectory of the target in the at least two monitoring areas; the determining module 54 is configured to determine whether the coincidence degree of the action trajectory of the target in the at least two monitoring areas is greater than a preset value; the trajectory generating module 56. For determining that the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value, generating an action track of the target in the at least two monitoring areas.
  • the action trajectory of the target in the at least two monitoring areas is separately extracted; determining whether the coincidence degree of the action trajectory of the target in the at least two monitoring areas is greater than a preset value; and the determining result is at least two monitoring areas. If the coincidence degree of the target trajectory is greater than the preset value, the action trajectory of the target in at least two monitoring areas is generated, which achieves the purpose of easy deployment of the target tracking system, thereby improving the tracking efficiency of the target task.
  • the technical effect further solves the technical problem that the prior art needs to identify and monitor the facial features of the same target person by using multiple face recognition cameras, resulting in complicated deployment and low target tracking efficiency.
  • the foregoing extraction module 52, the determination module 54 and the trajectory generation module 56 correspond to steps S202 to S206 in the first embodiment, and the three modules are the same as the examples and application scenarios implemented by the corresponding steps, but It is not limited to the contents disclosed in the above embodiment 1. It should be noted that the foregoing module may be implemented as a part of the device in the method for tracking the cross-region target trajectory provided in the first embodiment, and may be implemented by software or by hardware.
  • the extracting module 52 includes: a first extracting unit, configured to: in the first monitoring area, in the first monitoring area, where the at least two monitoring areas include the first monitoring area and the second monitoring area, respectively At least one target is marked, and the marked trajectory of the at least one target is extracted; and the second extracting unit is configured to mark at least one target in the second monitoring area in the second monitoring area, and extract the marked At least one target's action trajectory.
  • a first extracting unit configured to: in the first monitoring area, in the first monitoring area, where the at least two monitoring areas include the first monitoring area and the second monitoring area, respectively At least one target is marked, and the marked trajectory of the at least one target is extracted
  • the second extracting unit is configured to mark at least one target in the second monitoring area in the second monitoring area, and extract the marked At least one target's action trajectory.
  • first extraction unit and the second extraction unit correspond to Step 1 and Step 2 in step S202 in the first embodiment.
  • the two modules are the same as the examples and application scenarios implemented in the corresponding steps, but not It is limited to the content disclosed in the above embodiment 1.
  • the foregoing module may be implemented as a part of the device in the method for tracking the cross-region target trajectory provided in the first embodiment, and may be implemented by software or by hardware.
  • the determining module 54 includes: an acquiring unit, configured to acquire an overlapping area of the first monitoring area and the second monitoring area, where the at least two monitoring areas include the first monitoring area and the second monitoring area; And the at least one target in the overlapping area is marked, and the action trajectory is generated according to the at least one target after the marking; the determining unit is configured to determine whether the action trajectory of the at least one target in the overlapping area and the action of the at least one target in the first monitoring area The trajectory and the coincidence degree of the action trajectory of at least one target in the second monitoring area are greater than a preset value.
  • the foregoing acquiring unit, the marking unit, and the determining unit correspond to Step 1 to Step 3 in step S204 in the first embodiment, and the three modules are the same as the examples and application scenarios implemented by the corresponding steps, but are not limited thereto.
  • the foregoing module may be implemented as a part of the device in the method for tracking the cross-region target trajectory provided in the first embodiment, and may be implemented by software or by hardware.
  • FIG. 5a is a schematic structural diagram of a data processing apparatus according to Embodiment 4 of the present invention.
  • the data processing apparatus includes a first acquisition module 52a, a second acquisition module 54a, a track determination module 56a, and a display module 58a.
  • the first obtaining module 52a is configured to acquire at least two geo-fence data having an intersection area, wherein the intersection area is a common area, the geo-fence data includes an action track of the object, and the second obtaining module 54a is configured to acquire two a first action track and a second action track in the geofence data; a track determining module 56a, configured to determine the first action track and the second action track as matching tracks; and a display module 58a for displaying the first action track and the second action Track.
  • the geofence data includes an action trajectory of the object; and acquiring the first action trajectory of the two geofences respectively a second motion trajectory; determining the first motion trajectory and the second motion trajectory as matching trajectories; displaying the first motion trajectory and the second motion trajectory, achieving the purpose of facilitating deployment of the target tracking system, thereby improving tracking of the target task
  • the technical effect of efficiency further solves the technical problem that the prior art needs to identify and monitor the facial features of the same target person through each face recognition camera by multiple face recognition cameras, resulting in complicated deployment and low target tracking efficiency.
  • first acquiring module 52a, the second obtaining module 54a, the trajectory determining module 56a, and the displaying module 58a correspond to steps S402 to S408 in the second embodiment, and the four modules and corresponding steps are implemented.
  • the example is the same as the application scenario, but is not limited to the content disclosed in the second embodiment above.
  • the foregoing module may be implemented in the data processing method provided in the second embodiment as a part of the device, and may be implemented by software or by hardware.
  • a system for cross-region target trajectory tracking including:
  • At least two micro-monitoring devices for marking the captured at least one target, and generating an action trajectory of the at least one target according to the at least one target after the marking, and reporting the action trajectory of the at least one target to the server;
  • the server is configured to obtain And determining, by the at least two micro-monitoring devices, the action trajectory of the at least one target, determining whether at least one target occurs at the same time in the overlapping area captured by the at least two micro monitoring devices, and calculating at least one target in the at least two micro monitoring devices At a coincidence degree of the monitoring area, if the coincidence degree is greater than a preset value, determining that at least one target in the monitoring area where the at least two micro monitoring devices are located is the same target, and generating at least one target in at least two micro monitoring The action track of the monitored area where the device is located.
  • the server may be the background server in FIG. 3, and in the embodiment of the present application, as shown in FIG. 6, FIG. 6 is a cross-regional target according to Embodiment 5 of the present invention.
  • FIG. 6 is a cross-regional target according to Embodiment 5 of the present invention.
  • At least two micro monitoring devices mark at least one target captured
  • the at least two micro monitoring devices generate an action trajectory of the at least one target according to the at least one target after the marking;
  • At least two micro monitoring devices report the action track of the at least one target to the server;
  • the server acquires an action track of the at least one target uploaded by the at least two micro monitoring devices, and determines whether at least one target occurs at the same time in the overlapping area captured by the at least two micro monitoring devices;
  • the server calculates a coincidence degree of at least one target in a monitoring area where the at least two micro monitoring devices are located. If the coincidence degree is greater than a preset value, determining that at least one target in the monitoring area where the at least two micro monitoring devices are located is the same a goal;
  • the server generates an action track of at least one target in a monitored area where at least two micro monitoring devices are located.
  • a storage medium includes a stored program, wherein a method of controlling a cross-region target trajectory tracking in the first embodiment is performed by controlling a device where the storage medium is located when the program is running.
  • a processor for executing a program wherein the method for performing cross-region target trajectory tracking in the above-described Embodiment 1 is executed while the program is running.
  • a storage medium includes a stored program, wherein the device in which the storage medium is located is executed during the running of the program to execute the data processing method in Embodiment 2 above.
  • a processor for executing a program, wherein the data processing method in Embodiment 2 above is executed when the program is running.
  • Embodiments of the present application also provide a storage medium.
  • the foregoing storage medium may be used to save the program code executed by the method for tracking cross-region target trajectory provided by Embodiment 1 above.
  • the foregoing storage medium may be located in any one of the computer terminal groups in the computer network, or in any one of the mobile terminal groups.
  • the storage medium is configured to store program code for performing the following steps: respectively extracting motion trajectories of the targets in the at least two monitoring areas; determining motion trajectories of the targets in the at least two monitoring areas Whether the coincidence degree is greater than a preset value; if the result of the determination is that the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value, the action track of the target in the at least two monitoring areas is generated.
  • the storage medium is configured to store program code for performing the following steps: before extracting the action track of the target in the at least two monitoring areas, respectively, including the first monitoring in the at least two monitoring areas
  • the target is marked by the monitoring device, and the action track of the corresponding target in the first monitoring area is generated in the first monitoring area according to the mark;
  • the monitoring device of the second monitoring area adjacent to the first monitoring area is called to determine whether the monitoring device of the second monitoring area captures at least one target; if the determination result is yes, At least one target in the second monitoring area is marked, and an action trajectory of the target in the second monitoring area is generated.
  • the storage medium is configured to store program code for performing the following steps: respectively extracting the action track of the target in the at least two monitoring areas, comprising: including the first monitoring area in the at least two monitoring areas And in the case of the second monitoring area, in the first monitoring area, at least one target in the first monitoring area is marked, and the action trajectory of the marked at least one target is extracted; in the second monitoring area, respectively At least one target in the second monitoring area is marked, and the action trajectory of the marked at least one target is extracted.
  • the storage medium is configured to store program code for performing the following steps: in the first monitoring area, respectively marking at least one target in the first monitoring area, and extracting The action track of the at least one target after the marking comprises: dividing the first monitoring area by a predetermined cell, obtaining a first position binning map of the first monitoring area in the form of a grid; and dividing the first position according to the at least one target The grid map is marked; the trajectory matrix is generated according to the position change of the at least one target in the first position of the marker, and the trajectory matrix is determined as the motion trajectory of the at least one target in the first monitoring area.
  • the storage medium is configured to store program code for performing: in the second monitoring area, marking at least one target in the second monitoring area, and extracting the marked
  • the action track of the at least one target comprises: dividing the second monitoring area by a preset cell, obtaining a second position binning map of the second monitoring area in the form of a grid; performing the second position binning map according to the at least one target Marking; generating a trajectory matrix according to the position change of the at least one target after the marking in the second position; determining the trajectory matrix as the action trajectory of the at least one target after the marking in the second monitoring area.
  • the storage medium is configured to store program code for performing the following steps: determining whether the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value comprises: at least two If the monitoring area includes the first monitoring area and the second monitoring area, acquiring an overlapping area of the first monitoring area and the second monitoring area; marking at least one target in the overlapping area, and generating an action track according to the at least one target after the marking; Determining whether the action trajectory of the at least one target in the overlap region is equal to the action trajectory of the at least one target in the first monitoring region, and the motion trajectory of the at least one target in the second monitoring region is greater than a preset value.
  • the storage medium is configured to store program code for performing the following steps: the result of the determination is that the coincidence degree of the action track of the target in the at least two monitoring areas is greater than a preset value.
  • the action trajectory of the generating target in the at least two monitoring areas comprises: determining at least one target in the overlapping area and at least one target in the first monitoring area and the second monitoring area if the degree of coincidence is greater than a preset value At least one of the targets is the same target; and the action trajectory of the at least one target is generated according to the time and the position change of the at least one target in the first monitoring area and the second monitoring area.
  • the disclosed technical contents may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)
  • Alarm Systems (AREA)

Abstract

本申请公开了一种跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统。其中，该方法包括：分别提取至少两个监控区域中目标的行动轨迹；判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹。本申请解决了由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的技术问题。

Description

跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统
本申请要求2017年07月28日递交的申请号为201710632975.X、发明名称为“跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及互联网技术应用领域，具体而言，涉及一种跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统。
背景技术
在商业办公楼宇内，出于安防以及构建新型商业模式的目的，需要对进入楼宇内特定人员进行连续不间断的行进轨迹跟踪。业界现有的方案是可以实现一个摄像机枪机镜头视野内的人脸识别以及轨迹跟踪功能。但是对实现一个空间开阔的室内楼宇内人员轨迹的连续跟踪仍然缺失经济且有效的方案。
现有技术中需要在监控区域连续部署人脸识别摄像机，通过人脸识别摄像机对每层同一个目标人物进行跟踪拍摄。
但是一旦目标人物离开了一个摄像头的视野，再进入另一个摄像头的视野，除非第二个摄像头准确识别该人外，没有有效手段将两个摄像头获取到的两个认得特征有效标识起来，在室内开阔空间，难以确保所有摄像机都准确对准人的面部，并且在除了大厅入口进行人脸识别处部署摄像机外，其他开阔区域也部署摄像机进行人脸识别，容易引起个人隐私泄露。
针对上述由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低问题，目前尚未提出有效的解决方案。
发明内容
本申请实施例提供了一种跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统，以至少解决由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的技术问题。
根据本申请实施例的一个方面，提供了一种数据处理方法，包括：获取至少两个存 在交集区域的地理围栏数据，其中，交集区域为公共区域，地理围栏数据包括其中物体的行动轨迹；分别获取两个地理围栏数据中第一行动轨迹和第二行动轨迹；确定第一行动轨迹和第二行动轨迹为匹配轨迹；展示第一行动轨迹和第二行动轨迹。
根据本申请实施例的另一个方面，提供了一种跨区域目标轨迹跟踪的方法，包括：分别提取至少两个监控区域中目标的行动轨迹；判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹。
可选的，在分别提取至少两个监控区域中目标的行动轨迹之前，方法还包括：在至少两个监控区域包括第一监控区域和第二监控区域的情况下，当目标进入第一监控区域时，通过监控设备对目标进行标记，并依据标记在第一监控区域中生成对应目标在第一监控区域的行动轨迹；当目标离开第一监控区域时，调用与第一监控区域相邻的第二监控区域的监控设备，判断第二监控区域的监控设备是否拍摄到至少一个目标；在判断结果为是的情况下，对第二监控区域中至少一个目标进行标记，并生成目标在第二监控区域的行动轨迹。
可选的，分别提取至少两个监控区域中目标的行动轨迹包括：在至少两个监控区域包括第一监控区域和第二监控区域的情况下，在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹；在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹。
进一步地，可选的，在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹包括：对第一监控区域以预设单元格进行划分，得到栅格形式的第一监控区域的第一位置分格图；依据至少一个目标在第一位置分格图进行标记；依据标记后的至少一个目标在第一位置分格图的位置变化，生成轨迹矩阵；将轨迹矩阵确定为标记后的至少一个目标在第一监控区域的行动轨迹。
可选的，在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹包括：对第二监控区域以预设单元格进行划分，得到栅格形式的第二监控区域的第二位置分格图；依据至少一个目标在第二位置分格图进行标记；依据标记后的至少一个目标在第二位置分格图的位置变化，生成轨迹矩阵；将轨迹矩阵确定为标记后的至少一个目标在第二监控区域的行动轨迹。
可选的，判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值包括： 在至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取第一监控区域与第二监控区域的重叠区域；标记重叠区域中至少一个目标，并依据标记后的至少一个目标生成行动轨迹；判断重叠区域中至少一个目标的行动轨迹是否与第一监控区域中至少一个目标的行动轨迹，以及第二监控区域中至少一个目标的行动轨迹的重合度大于预设值。
进一步地，可选的，在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹包括：在重合度大于预设值的情况下，确定重叠区域中的至少一个目标与第一监控区域中至少一个目标以及第二监控区域中至少一个目标为同一目标；依据时间和第一监控区域与第二监控区域中至少一个目标的位置变化，生成至少一个目标的行动轨迹。
根据本申请实施例的又一个方面，提供了一种数据处理装置，包括：第一获取模块，用于获取至少两个存在交集区域的地理围栏数据，其中，交集区域为公共区域，地理围栏数据包括其中物体的行动轨迹；第二获取模块，用于分别获取两个地理围栏数据中第一行动轨迹和第二行动轨迹；轨迹确定模块，用于确定第一行动轨迹和第二行动轨迹为匹配轨迹；显示模块，用于展示第一行动轨迹和第二行动轨迹。
根据本申请实施例的再一个方面，提供了一种跨区域目标轨迹跟踪的装置，包括：提取模块，用于分别提取至少两个监控区域中目标的行动轨迹；判断模块，用于判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；轨迹生成模块，用于在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹。
可选的，提取模块包括：第一提取单元，用于在至少两个监控区域包括第一监控区域和第二监控区域的情况下，在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹；第二提取单元，用于在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹。
可选的，判断模块包括：获取单元，用于在至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取第一监控区域与第二监控区域的重叠区域；标记单元，用于标记重叠区域中至少一个目标，并依据标记后的至少一个目标生成行动轨迹；判断单元，用于判断重叠区域中至少一个目标的行动轨迹是否与第一监控区域中至少一个目标的行动轨迹，以及第二监控区域中至少一个目标的行动轨迹的重合度大于预设值。
根据本申请另一实施例的一个方面，提供了一种跨区域目标轨迹跟踪的系统，包括：至少两个微型监控设备，用于标记拍摄到的至少一个目标，并依据标记后的至少一个目标生成至少一个目标的行动轨迹，并将至少一个目标的行动轨迹上报至服务器；服务器，用于获取至少两个微型监控设备上传的至少一个目标的行动轨迹，判断在至少两个微型监控设备拍摄的重叠区域中是否在相同时间出现至少一个目标，并计算至少一个目标在至少两个微型监控设备所处监控区域的重合度，在重合度大于预设值的情况下，确定至少两个微型监控设备所处监控区域中至少一个目标是同一个目标，并生成至少一个目标的在至少两个微型监控设备所处监控区域的行动轨迹。
根据本申请另一实施例的另一个方面，提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述跨区域目标轨迹跟踪的方法。
根据本申请另一实施例的另一个方面，提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述跨区域目标轨迹跟踪的方法。
根据本申请另一实施例的又一个方面，提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述数据处理方法。
根据本申请另一实施例的又一个方面，提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述数据处理方法。
在本申请实施例中，通过分别提取至少两个监控区域中目标的行动轨迹；判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹，达到了对目标跟踪系统易部署的目的，从而实现了提升对目标任务的跟踪效率的技术效果，进而解决了由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的技术问题。
附图说明
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是本申请实施例的一种跨区域目标轨迹跟踪的方法的计算机终端的硬件结构框图；
图2是根据本申请实施例一的跨区域目标轨迹跟踪的方法的流程图；
图3是根据本申请实施例一的一种跨区域目标轨迹跟踪的方法的示意图；
图4是根据本申请实施例一的另一种跨区域目标轨迹跟踪的方法的示意图；
图4a是根据本申请实施例二的数据处理方法的流程图；
图5是根据本发明实施例三的跨区域目标轨迹跟踪的装置的结构示意图；
图5a是根据本发明实施例四的数据处理装置的结构示意图；
图6是根据本发明实施例五的跨区域目标轨迹跟踪的系统的交互示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
实施例1
根据本申请实施例，还提供了一种跨区域目标轨迹跟踪的方法实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
本申请实施例一所提供的方法实施例可以在移动终端、计算机终端或者类似的运算装置中执行。以运行在计算机终端上为例，图1是本申请实施例的一种跨区域目标轨迹跟踪的方法的计算机终端的硬件结构框图。如图1所示，计算机终端10可以包括一个或多个(图中仅示出一个)处理器102(处理器102可以包括但不限于微处理器MCU或可编程逻辑器件FPGA等的处理装置)、用于存储数据的存储器104、以及用于通信功能 的传输模块106。本领域普通技术人员可以理解，图1所示的结构仅为示意，其并不对上述电子装置的结构造成限定。例如，计算机终端10还可包括比图1中所示更多或者更少的组件，或者具有与图1所示不同的配置。
存储器104可用于存储应用软件的软件程序以及模块，如本申请实施例中的跨区域目标轨迹跟踪的方法对应的程序指令/模块，处理器102通过运行存储在存储器104内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现上述的应用程序的跨区域目标轨迹跟踪的方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储装置、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可进一步包括相对于处理器102远程设置的存储器，这些远程存储器可以通过网络连接至计算机终端10。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输模块106用于经由一个网络接收或者发送数据。上述的网络具体实例可包括计算机终端10的通信供应商提供的无线网络。在一个实例中，传输模块106包括一个网络适配器(Network Interface Controller，NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输模块106可以为射频(Radio Frequency，RF)模块，其用于通过无线方式与互联网进行通讯。
在上述运行环境下，本申请提供了如图2所示的跨区域目标轨迹跟踪的方法。图2是根据本申请实施例一的跨区域目标轨迹跟踪的方法的流程图。根据本申请实施例的一个方面，提供了一种跨区域目标轨迹跟踪的方法，该方法的步骤包括：
步骤S202，分别提取至少两个监控区域中目标的行动轨迹；
本申请上述步骤S202中，本申请提供的跨区域目标轨迹跟踪的方法可以适用于室内安防监控领域，其中，在本申请中区别于现有技术，以微型摄像头替代现有技术中的人脸识别摄像机，降低了安防监控成本，并且能够提升微型摄像头数量，以及微型摄像头与安防监控系统的接入兼容性。其中，每个微型摄像头所能够监控的区域称作监控区域，每个目标人物(即，本申请中的目标)在监控区域中移动的轨迹被称作行动轨迹，基于微型摄像头的分布每个微型摄像头所处的监控区域，均会在有目标人物出现在监控区域后，生成该目标人物在该监控区域的行动轨迹。
步骤S204，判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；
本申请上述步骤S204中，当需要获取目标A的行动轨迹时，通过步骤S202获取目标A在至少两个监控区域中的行动轨迹，判断在至少两个监控区域中目标A的行动轨迹 的重合度是否大于预设值，如果大于预设值则执行步骤S206，如果小于预设值则说明至少两个监控区域中的目标的行动轨迹的重合度很低，所以目标A未移动，或目标A未移动至其他监控区域。
步骤S206，在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹。
本申请上述步骤S206中，基于步骤S204的判断，当重合度大于预设值的情况下，说明至少两个监控区域中的目标为同一个目标，进而根据该目标生成该目标在至少两个监控区域中的行动轨迹。
综上，本申请提供的跨区域目标轨迹跟踪的方法中，以跨区域目标人物的轨迹跟踪为例进行说明，本申请提供的实施例中无需部署用于人脸识别摄像机，但需要进行人轨迹跟踪的区域内连续部署微型摄像头(后续简称：摄像头)，确保摄像头之间的视野交叉或覆盖。本申请提供的跨区域目标轨迹跟踪的方法中的摄像头仅采集视野内出现的人这个生物类以及对应出现的轨迹、时间信息并通过低速无线传输技术将视野内每一个可识别为人类的坐标信息完成上报，不涉及具体人员的人脸识别，因此不会侵犯用户的隐私。
图3是根据本申请实施例一的一种跨区域目标轨迹跟踪的方法的示意图，如图3所示，本申请提供的跨区域目标轨迹跟踪的方法如下：
1.摄像头O识别出一个人以及其行进轨迹【将该人标记为Idxo】；
2.当该标记的人即将离开摄像头O的视野，进入与摄像头A重叠覆盖区时，后台服务器命令相邻微型摄像头进行捕获；
3.摄像头A获取视野内出现的人并加以区分标定，记录出现的时刻以及行进的轨迹并完成上报给后台服务器；
4.后台服务器对摄像头O中标记为Idxo的出现轨迹与A上报的人员轨迹进行匹配，寻找重合度大于设定门限值的人员，并将该人员标定在摄像头A范围内继承为Idxo；
5.当行人移动至下一个微型摄像头覆盖范围是，重复上述的过程，获取标定为Idxo在行进过程中的连续轨迹。
在本申请实施例中，通过分别提取至少两个监控区域中目标的行动轨迹；判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹，达到了对目标跟踪系统易部署的目的，从而实现了提升对目标任务的跟踪 效率的技术效果，进而解决了由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的技术问题。
可选的，在步骤S202中分别提取至少两个监控区域中目标的行动轨迹之前，本申请提供的跨区域目标轨迹跟踪的方法还包括：
步骤S199,在至少两个监控区域包括第一监控区域和第二监控区域的情况下，当目标进入第一监控区域时，通过监控设备对目标进行标记，并依据标记在第一监控区域中生成对应目标在第一监控区域的行动轨迹；
步骤S200,当目标离开第一监控区域时，调用与第一监控区域相邻的第二监控区域的监控设备，判断第二监控区域的监控设备是否拍摄到至少一个目标；
步骤S201,在判断结果为是的情况下，对第二监控区域中至少一个目标进行标记，并生成目标在第二监控区域的行动轨迹。
具体的，在步骤S202中分别提取至少两个监控区域中目标的行动轨迹之前，结合步骤S199至步骤S201，以两个监控区域为例进行说明，即，第一监控区域和第二监控区域，在提取两个监控区域中目标的行动轨迹之前，每个监控区域先对自己监控区域内出现的目标进行标记，并随着时间的顺序生成每个标记后的目标子啊该监控区域生成的行动轨迹，并且当第一监控区域中的目标离开第一监控区域时，作为与第一监控区域相邻的第二监控区域将对每个进入该监控区域的目标进行标记，并生成标记后每个目标的行动轨迹，以便后续在对比重合度的过程中提供数据支持。
可选的，步骤S202中分别提取至少两个监控区域中目标的行动轨迹包括：
Step1,在至少两个监控区域包括第一监控区域和第二监控区域的情况下，在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹；
Step2,在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹。
具体的，结合Step1和Step2,提取每个监控区域的至少一个目标的行动轨迹的过程中，先提取标记过的目标，进而根据该标记提取各个目标在监控区域中的行动轨迹。
进一步地，可选的，步骤S202中Step1中的在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹包括：
步骤1，对第一监控区域以预设单元格进行划分，得到栅格形式的第一监控区域的 第一位置分格图；
步骤2，依据至少一个目标在第一位置分格图进行标记；
步骤3，依据标记后的至少一个目标在第一位置分格图的位置变化，生成轨迹矩阵；
步骤4，将轨迹矩阵确定为标记后的至少一个目标在第一监控区域的行动轨迹。
可选的，步骤S202中Step2中的在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹包括：
步骤1，对第二监控区域以预设单元格进行划分，得到栅格形式的第二监控区域的第二位置分格图；
步骤2，依据至少一个目标在第二位置分格图进行标记；
步骤3，依据标记后的至少一个目标在第二位置分格图的位置变化，生成轨迹矩阵；
步骤4，将轨迹矩阵确定为标记后的至少一个目标在第二监控区域的行动轨迹。
具体的，步骤S202中的Step1和步骤S202中的Step2中分别根据第一监控区域和第二监控区域划分单元格后，对每个目标在由单元格组成的第一位置分格图和第二位置分格图中的位置变化，生成每个目标在第一监控区域和第二监控区域的行动轨迹。
可选的，步骤S204中判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值包括：
Step1，在至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取第一监控区域与第二监控区域的重叠区域；
Step2，标记重叠区域中至少一个目标，并依据标记后的至少一个目标生成行动轨迹；
Step3，判断重叠区域中至少一个目标的行动轨迹是否与第一监控区域中至少一个目标的行动轨迹，以及第二监控区域中至少一个目标的行动轨迹的重合度大于预设值。
进一步地，可选的，步骤S206中在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹包括：
Step1，在重合度大于预设值的情况下，确定重叠区域中的至少一个目标与第一监控区域中至少一个目标以及第二监控区域中至少一个目标为同一目标；
Step2，依据时间和第一监控区域与第二监控区域中至少一个目标的位置变化，生成至少一个目标的行动轨迹。
具体的，在本申请中通过两个监控区域重叠区域的目标的行动轨迹，通过对第一监控区域和第二监控区域中各个目标的行动轨迹的预测，如果该重叠区域的目标的行动轨迹与第一监控区域和第二监控区域的目标的行动轨迹的重合度大于预设值，则说明该重 叠区域的目标与第一监控区域和第二监控区域的目标为同一个目标，进而根据重叠区域、第一监控区域和第二监控区域中目标的行动轨迹生成目标在整个监控区域的移动轨迹。
综上，图4是根据本申请实施例一的另一种跨区域目标轨迹跟踪的方法的示意图，如图4所示，本申请提供的跨区域目标轨迹跟踪的方法具体如下：
1.将每一个摄像头的视野内位置划分为栅格，每格大小可以容纳不超过一个人的形体特征。
2.每一个摄像头内的视野中栅格位置使用矩阵进行标识，比如为：{M,N}，表示栅格范围为M行，N列的矩阵型(摄像头实际视野不一定是矩形，需匹配业界已有的畸形矫正技术)。则相邻摄像头重叠区域在各自摄像头视野范围内的栅格位置存在固定的逻辑转换关系，我们定义为{M,N} o*Z{N,N}＝{M,N} A。Z是一个N维矩阵。举例可以看出红星在摄像头O中的位置为(2,14)，经过矩阵转换后，其在摄像头A中的位置就是(2,2)。
3.一个人进入一个摄像头后，将该摄像头矩阵中出现该人的位置上的值标成1，其他位置都标成0，则该矩阵上所有值为1的点串起来就是这个人在该摄像头视野中的行进轨迹。举例，如
Figure PCTCN2018096094-appb-000001
4.当一个人从摄像头O进入摄像头O与A的重叠区域，直至离开该区域，在摄像头O中该区域内的行进轨迹可用矩阵表示为Track O，在摄像头A中该区域内的行进轨迹可用矩阵表示为Track A。
5.使用转换矩阵，将摄像头O中重叠区域里的行人轨迹转换为其在摄像头A内的轨迹：Track A’＝Track O*Z{N,N}。
6.通过上述计算可以获取摄像头O中重叠区域的X个人轨迹在摄像头A中的视野映射：Track A,1’、Track A,2’……Track A,x’，然后与摄像头A中的Track A进行相似度比较，相似度大于预设门限的则表示这两个轨迹对应的是同一个人。
本申请提供的跨区域目标轨迹跟踪的方法中后台服务器通过摄像头之间人轨迹识别的模糊算法匹配，获取行人在摄像头间移动时连续轨迹的跟踪；并且行人轨迹监控的摄像头仅捕获行人的轨迹、出现时间并对行人进行标号，不会捕获视频流去进行人脸识别， 不会造成人隐私的泄露。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的跨区域目标轨迹跟踪的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
实施例2
图4a是根据本申请实施例二的数据处理方法的流程图。如图4a所示，根据本申请实施例的一个方面，提供了一种数据处理方法，实现本申请提供的该数据处理方法包括如下步骤：
步骤S402，获取至少两个存在交集区域的地理围栏数据，其中，交集区域为公共区域，地理围栏数据包括其中物体的行动轨迹；
步骤S404，分别获取两个地理围栏数据中第一行动轨迹和第二行动轨迹；
步骤S406，确定第一行动轨迹和第二行动轨迹为匹配轨迹；
步骤S408，展示第一行动轨迹和第二行动轨迹。
具体的，本申请提供的数据处理方法可以适用于监控安防领域，特别是用于目标轨迹跟踪预测，在本实施例中，通过获取至少两个存在交局区域的地理围栏数据，得到各个目标在两个地理围栏数据中的第一行动轨迹和第二行动轨迹，通过匹配两个行动轨迹判断是否为同一目标。
在本申请实施例中，通过获取至少两个存在交集区域的地理围栏数据，其中，交集区域为公共区域，地理围栏数据包括其中物体的行动轨迹；分别获取两个地理围栏数据中第一行动轨迹和第二行动轨迹；确定第一行动轨迹和第二行动轨迹为匹配轨迹；展示第一行动轨迹和第二行动轨迹，达到了对目标跟踪系统易部署的目的，从而实现了提升 对目标任务的跟踪效率的技术效果，进而解决了由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的技术问题。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到根据上述实施例的数据处理方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本申请各个实施例所述的方法。
实施例3
根据本申请实施例，还提供了一种用于实施上述跨区域目标轨迹跟踪的方法的装置，图5是根据本发明实施例三的跨区域目标轨迹跟踪的装置的结构示意图。
如图5所示，该跨区域目标轨迹跟踪的装置，包括：提取模块52、判断模块54和轨迹生成模块56。
其中，提取模块52，用于分别提取至少两个监控区域中目标的行动轨迹；判断模块54，用于判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；轨迹生成模块56，用于在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹。
在本申请实施例中，通过分别提取至少两个监控区域中目标的行动轨迹；判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹，达到了对目标跟踪系统易部署的目的，从而实现了提升对目标任务的跟踪效率的技术效果，进而解决了由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的 技术问题。
此处需要说明的是，上述提取模块52、判断模块54和轨迹生成模块56对应于实施例一中的步骤S202至步骤S206，三个模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例一所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在实施例一提供的跨区域目标轨迹跟踪的方法中，可以通过软件实现，也可以通过硬件实现。
可选的，提取模块52包括：第一提取单元，用于在至少两个监控区域包括第一监控区域和第二监控区域的情况下，在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹；第二提取单元，用于在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹。
此处需要说明的是，上述第一提取单元和第二提取单元对应于实施例一中的步骤S202中的Step1和Step2，两个模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例一所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在实施例一提供的跨区域目标轨迹跟踪的方法中，可以通过软件实现，也可以通过硬件实现。
可选的，判断模块54包括：获取单元，用于在至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取第一监控区域与第二监控区域的重叠区域；标记单元，用于标记重叠区域中至少一个目标，并依据标记后的至少一个目标生成行动轨迹；判断单元，用于判断重叠区域中至少一个目标的行动轨迹是否与第一监控区域中至少一个目标的行动轨迹，以及第二监控区域中至少一个目标的行动轨迹的重合度大于预设值。
此处需要说明的是，上述获取单元、标记单元和判断单元对应于实施例一中的步骤S204中的Step1至Step3，三个模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例一所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在实施例一提供的跨区域目标轨迹跟踪的方法中，可以通过软件实现，也可以通过硬件实现。
实施例4
根据本申请实施例，还提供了一种用于实施上述数据处理方法的装置，图5a是根据本发明实施例四的数据处理装置的结构示意图。
如图5a所示，该数据处理装置，包括：第一获取模块52a、第二获取模块54a、轨 迹确定模块56a和显示模块58a。
第一获取模块52a，用于获取至少两个存在交集区域的地理围栏数据，其中，交集区域为公共区域，地理围栏数据包括其中物体的行动轨迹；第二获取模块54a，用于分别获取两个地理围栏数据中第一行动轨迹和第二行动轨迹；轨迹确定模块56a，用于确定第一行动轨迹和第二行动轨迹为匹配轨迹；显示模块58a，用于展示第一行动轨迹和第二行动轨迹。
在本申请实施例中，通过获取至少两个存在交集区域的地理围栏数据，其中，交集区域为公共区域，地理围栏数据包括其中物体的行动轨迹；分别获取两个地理围栏中第一行动轨迹和第二行动轨迹；确定第一行动轨迹和第二行动轨迹为匹配轨迹；展示第一行动轨迹和第二行动轨迹，达到了对目标跟踪系统易部署的目的，从而实现了提升对目标任务的跟踪效率的技术效果，进而解决了由于现有技术中需要通过多台人脸识别摄像机对每层同一个目标人物的面部特征进行识别并监控拍摄，导致的部署复杂且目标人物跟踪效率低的技术问题。
此处需要说明的是，上述第一获取模块52a、第二获取模块54a、轨迹确定模块56a和显示模块58a对应于实施例二中的步骤S402至步骤S408，四个模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例二所公开的内容。需要说明的是，上述模块作为装置的一部分可以运行在实施例二提供的数据处理方法中，可以通过软件实现，也可以通过硬件实现。
实施例5
根据本申请实施例的又一个方面，提供了一种跨区域目标轨迹跟踪的系统，包括：
至少两个微型监控设备，用于标记拍摄到的至少一个目标，并依据标记后的至少一个目标生成至少一个目标的行动轨迹，并将至少一个目标的行动轨迹上报至服务器；服务器，用于获取至少两个微型监控设备上传的至少一个目标的行动轨迹，判断在至少两个微型监控设备拍摄的重叠区域中是否在相同时间出现至少一个目标，并计算至少一个目标在至少两个微型监控设备所处监控区域的重合度，在重合度大于预设值的情况下，确定至少两个微型监控设备所处监控区域中至少一个目标是同一个目标，并生成至少一个目标的在至少两个微型监控设备所处监控区域的行动轨迹。
具体的，如实施例1中的图3所示，服务器可以为图3中的后台服务器，在本申请实施例中，如图6所示，图6是根据本发明实施例五的跨区域目标轨迹跟踪的系统的交 互示意图。具体如下：
S1，至少两个微型监控设备标记拍摄到的至少一个目标；
S2，至少两个微型监控设备依据标记后的至少一个目标生成至少一个目标的行动轨迹；
S3，至少两个微型监控设备将至少一个目标的行动轨迹上报至服务器；
S4，服务器获取至少两个微型监控设备上传的至少一个目标的行动轨迹，判断在至少两个微型监控设备拍摄的重叠区域中是否在相同时间出现至少一个目标；
S5，服务器计算至少一个目标在至少两个微型监控设备所处监控区域的重合度，在重合度大于预设值的情况下，确定至少两个微型监控设备所处监控区域中至少一个目标是同一个目标；
S6，服务器生成至少一个目标的在至少两个微型监控设备所处监控区域的行动轨迹。
实施例6
根据本申请实施例的再一个方面，提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述实施例1中的跨区域目标轨迹跟踪的方法。
实施例7
根据本申请实施例的再一个方面，提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述实施例1中的跨区域目标轨迹跟踪的方法。
实施例8
根据本申请实施例的再一个方面，提供了一种存储介质，存储介质包括存储的程序，其中，在程序运行时控制存储介质所在设备执行上述实施例2中的数据处理方法。
实施例9
根据本申请实施例的再一个方面，提供了一种处理器，处理器用于运行程序，其中，程序运行时执行上述实施例2中的数据处理方法。
实施例10
本申请的实施例还提供了一种存储介质。可选地，在本实施例中，上述存储介质可以用于保存上述实施例一所提供的跨区域目标轨迹跟踪的方法所执行的程序代码。
可选地，在本实施例中，上述存储介质可以位于计算机网络中计算机终端群中的任意一个计算机终端中，或者位于移动终端群中的任意一个移动终端中。
可选地，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：分 别提取至少两个监控区域中目标的行动轨迹；判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值；在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹。
可选的，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：在分别提取至少两个监控区域中目标的行动轨迹之前，在至少两个监控区域包括第一监控区域和第二监控区域的情况下，当目标进入第一监控区域时，通过监控设备对目标进行标记，并依据标记在第一监控区域中生成对应目标在第一监控区域的行动轨迹；当目标离开第一监控区域时，调用与第一监控区域相邻的第二监控区域的监控设备，判断第二监控区域的监控设备是否拍摄到至少一个目标；在判断结果为是的情况下，对第二监控区域中至少一个目标进行标记，并生成目标在第二监控区域的行动轨迹。
可选的，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：分别提取至少两个监控区域中目标的行动轨迹包括：在至少两个监控区域包括第一监控区域和第二监控区域的情况下，在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹；在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹。
进一步地，可选的，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：在第一监控区域中，分别对第一监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹包括：对第一监控区域以预设单元格进行划分，得到栅格形式的第一监控区域的第一位置分格图；依据至少一个目标在第一位置分格图进行标记；依据标记后的至少一个目标在第一位置分格图的位置变化，生成轨迹矩阵；将轨迹矩阵确定为标记后的至少一个目标在第一监控区域的行动轨迹。
可选的，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：在第二监控区域中，分别对第二监控区域中至少一个目标进行标记，并提取标记后的至少一个目标的行动轨迹包括：对第二监控区域以预设单元格进行划分，得到栅格形式的第二监控区域的第二位置分格图；依据至少一个目标在第二位置分格图进行标记；依据标记后的至少一个目标在第二位置分格图的位置变化，生成轨迹矩阵；将轨迹矩阵确定为标记后的至少一个目标在第二监控区域的行动轨迹。
可选的，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：判断至少两个监控区域中目标的行动轨迹的重合度是否大于预设值包括：在至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取第一监控区域与第二监控区域的 重叠区域；标记重叠区域中至少一个目标，并依据标记后的至少一个目标生成行动轨迹；判断重叠区域中至少一个目标的行动轨迹是否与第一监控区域中至少一个目标的行动轨迹，以及第二监控区域中至少一个目标的行动轨迹的重合度大于预设值。
进一步地，可选的，在本实施例中，存储介质被设置为存储用于执行以下步骤的程序代码：在判断结果为至少两个监控区域中目标的行动轨迹的重合度大于预设值的情况下，生成目标在至少两个监控区域中的行动轨迹包括：在重合度大于预设值的情况下，确定重叠区域中的至少一个目标与第一监控区域中至少一个目标以及第二监控区域中至少一个目标为同一目标；依据时间和第一监控区域与第二监控区域中至少一个目标的位置变化，生成至少一个目标的行动轨迹。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
在本申请的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的技术内容，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的 全部或部分步骤。而前述的存储介质包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述仅是本申请的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本申请原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本申请的保护范围。

Claims (17)

  1. 一种数据处理方法，其特征在于，包括：
    获取至少两个存在交集区域的地理围栏数据，其中，所述交集区域为公共区域，所述地理围栏数据包括其中物体的行动轨迹；
    分别获取两个所述地理围栏数据中第一行动轨迹和第二行动轨迹；
    确定所述第一行动轨迹和第二行动轨迹为匹配轨迹；
    展示所述第一行动轨迹和第二行动轨迹。
  2. 一种跨区域目标轨迹跟踪的方法，其特征在于，包括：
    分别提取至少两个监控区域中目标的行动轨迹；
    判断所述至少两个监控区域中所述目标的行动轨迹的重合度是否大于预设值；
    在判断结果为所述至少两个监控区域中所述目标的行动轨迹的重合度大于预设值的情况下，生成所述目标在所述至少两个监控区域中的行动轨迹。
  3. 根据权利要求2所述的方法，其特征在于，在所述分别提取所述至少两个监控区域中所述目标的行动轨迹之前，所述方法还包括：
    在所述至少两个监控区域包括第一监控区域和第二监控区域的情况下，当所述目标进入所述第一监控区域时，通过监控设备对所述目标进行标记，并依据所述标记在所述第一监控区域中生成对应所述目标在第一监控区域的行动轨迹；
    当所述目标离开所述第一监控区域时，调用与所述第一监控区域相邻的所述第二监控区域的监控设备，判断所述第二监控区域的监控设备是否拍摄到至少一个目标；
    在判断结果为是的情况下，对所述第二监控区域中至少一个目标进行标记，并生成所述目标在所述第二监控区域的行动轨迹。
  4. 根据权利要求2或3所述的方法，其特征在于，所述分别提取至少两个监控区域中目标的行动轨迹包括：
    在所述至少两个监控区域包括第一监控区域和第二监控区域的情况下，在所述第一监控区域中，分别对所述第一监控区域中至少一个目标进行标记，并提取标记后的所述至少一个目标的行动轨迹；
    在所述第二监控区域中，分别对所述第二监控区域中至少一个目标进行标记，并提取标记后的所述至少一个目标的行动轨迹。
  5. 根据权利要求4所述的方法，其特征在于，所述在所述第一监控区域中，分别对所述第一监控区域中至少一个目标进行标记，并提取标记后的所述至少一个目标的行 动轨迹包括：
    对所述第一监控区域以预设单元格进行划分，得到栅格形式的所述第一监控区域的第一位置分格图；
    依据所述至少一个目标在所述第一位置分格图进行标记；
    依据标记后的所述至少一个目标在所述第一位置分格图的位置变化，生成轨迹矩阵；
    将所述轨迹矩阵确定为标记后的所述至少一个目标在所述第一监控区域的行动轨迹。
  6. 根据权利要求4所述的方法，其特征在于，所述在所述第二监控区域中，分别对所述第二监控区域中至少一个目标进行标记，并提取标记后的所述至少一个目标的行动轨迹包括：
    对所述第二监控区域以预设单元格进行划分，得到栅格形式的所述第二监控区域的第二位置分格图；
    依据所述至少一个目标在所述第二位置分格图进行标记；
    依据标记后的所述至少一个目标在所述第二位置分格图的位置变化，生成轨迹矩阵；
    将所述轨迹矩阵确定为标记后的所述至少一个目标在所述第二监控区域的行动轨迹。
  7. 根据权利要求2或3所述的方法，其特征在于，所述判断所述至少两个监控区域中所述目标的行动轨迹的重合度是否大于预设值包括：
    在所述至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取所述第一监控区域与所述第二监控区域的重叠区域；
    标记所述重叠区域中至少一个目标，并依据标记后的所述至少一个目标生成行动轨迹；
    判断所述重叠区域中至少一个目标的行动轨迹是否与所述第一监控区域中至少一个目标的行动轨迹，以及所述第二监控区域中至少一个目标的行动轨迹的重合度大于所述预设值。
  8. 根据权利要求7所述的方法，其特征在于，所述在判断结果为所述至少两个监控区域中所述目标的行动轨迹的重合度大于预设值的情况下，生成所述目标在所述至少两个监控区域中的行动轨迹包括：
    在所述重合度大于所述预设值的情况下，确定所述重叠区域中的至少一个目标与所述第一监控区域中至少一个目标以及所述第二监控区域中至少一个目标为同一目标；
    依据时间和所述第一监控区域与所述第二监控区域中所述至少一个目标的位置变化，生成所述至少一个目标的行动轨迹。
  9. 一种数据处理装置，其特征在于，包括：
    第一获取模块，用于获取至少两个存在交集区域的地理围栏数据，其中，所述交集区域为公共区域，所述地理围栏数据包括其中物体的行动轨迹；
    第二获取模块，用于分别获取两个所述地理围栏数据中第一行动轨迹和第二行动轨迹；
    轨迹确定模块，用于确定所述第一行动轨迹和第二行动轨迹为匹配轨迹；
    显示模块，用于展示所述第一行动轨迹和第二行动轨迹。
  10. 一种跨区域目标轨迹跟踪的装置，其特征在于，包括：
    提取模块，用于分别提取至少两个监控区域中目标的行动轨迹；
    判断模块，用于判断所述至少两个监控区域中所述目标的行动轨迹的重合度是否大于预设值；
    轨迹生成模块，用于在判断结果为所述至少两个监控区域中所述目标的行动轨迹的重合度大于预设值的情况下，生成所述目标在所述至少两个监控区域中的行动轨迹。
  11. 根据权利要求10所述的装置，其特征在于，所述提取模块包括：
    第一提取单元，用于在所述至少两个监控区域包括第一监控区域和第二监控区域的情况下，在所述第一监控区域中，分别对所述第一监控区域中至少一个目标进行标记，并提取标记后的所述至少一个目标的行动轨迹；
    第二提取单元，用于在所述第二监控区域中，分别对所述第二监控区域中至少一个目标进行标记，并提取标记后的所述至少一个目标的行动轨迹。
  12. 根据权利要求10所述的装置，其特征在于，所述判断模块包括：
    获取单元，用于在所述至少两个监控区域包括第一监控区域和第二监控区域的情况下，获取所述第一监控区域与所述第二监控区域的重叠区域；
    标记单元，用于标记所述重叠区域中至少一个目标，并依据标记后的所述至少一个目标生成行动轨迹；
    判断单元，用于判断所述重叠区域中至少一个目标的行动轨迹是否与所述第一监控区域中至少一个目标的行动轨迹，以及所述第二监控区域中至少一个目标的行动轨迹的 重合度大于所述预设值。
  13. 一种跨区域目标轨迹跟踪的系统，其特征在于，包括：
    至少两个微型监控设备，用于标记拍摄到的至少一个目标，并依据标记后的所述至少一个目标生成所述至少一个目标的行动轨迹，并将所述至少一个目标的行动轨迹上报至服务器；
    服务器，用于获取所述至少两个微型监控设备上传的所述至少一个目标的行动轨迹，判断在所述至少两个微型监控设备拍摄的重叠区域中是否在相同时间出现至少一个目标，并计算所述至少一个目标在所述至少两个微型监控设备所处监控区域的重合度，在所述重合度大于预设值的情况下，确定所述至少两个微型监控设备所处监控区域中至少一个目标是同一个目标，并生成所述至少一个目标的在所述至少两个微型监控设备所处监控区域的行动轨迹。
  14. 一种存储介质，其特征在于，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行权利要求2至8中任意一项所述的跨区域目标轨迹跟踪的方法。
  15. 一种处理器，其特征在于，所述处理器用于运行程序，其中，所述程序运行时执行权利要求2至8中任意一项所述的跨区域目标轨迹跟踪的方法。
  16. 一种存储介质，其特征在于，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行权利要求1所述的数据处理方法。
  17. 一种处理器，其特征在于，所述处理器用于运行程序，其中，所述程序运行时执行权利要求1所述的数据处理方法。
PCT/CN2018/096094 2017-07-28 2018-07-18 跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统 Ceased WO2019019943A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710632975.X 2017-07-28
CN201710632975.XA CN109309809A (zh) 2017-07-28 2017-07-28 跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统

Publications (1)

Publication Number Publication Date
WO2019019943A1 true WO2019019943A1 (zh) 2019-01-31

Family

ID=65041068

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/096094 Ceased WO2019019943A1 (zh) 2017-07-28 2018-07-18 跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统

Country Status (3)

Country Link
CN (1) CN109309809A (zh)
TW (1) TW201911118A (zh)
WO (1) WO2019019943A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111274336A (zh) * 2019-12-18 2020-06-12 浙江大华技术股份有限公司 目标轨迹的处理方法、装置、存储介质及电子装置
CN111369587A (zh) * 2019-06-13 2020-07-03 杭州海康威视系统技术有限公司 一种跟踪方法及装置
CN111784730A (zh) * 2020-07-01 2020-10-16 杭州海康威视数字技术股份有限公司 一种对象跟踪方法、装置、电子设备及存储介质
CN113592919A (zh) * 2021-08-02 2021-11-02 金茂智慧科技(广州)有限公司 安防控制方法及相关装置
CN113947789A (zh) * 2021-09-09 2022-01-18 北京品恩科技股份有限公司 一种赛事用场景人脸识别技术

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111914592B (zh) * 2019-05-08 2023-09-05 杭州海康威视数字技术股份有限公司 多相机联合取证方法、装置及系统
CN110728249B (zh) * 2019-10-21 2023-07-28 上海市刑事科学技术研究院 目标行人的跨摄像机识别方法、装置及系统
CN111724412A (zh) * 2020-06-17 2020-09-29 杭州海康威视数字技术股份有限公司 确定运动轨迹的方法、装置及计算机存储介质
CN111986227B (zh) * 2020-08-26 2023-09-01 杭州海康威视数字技术股份有限公司 轨迹生成方法、装置、计算机设备及存储介质
CN112118427B (zh) * 2020-10-29 2022-11-04 上海擎感智能科技有限公司 监控方法、系统、服务器及计算机存储介质
CN116012405B (zh) * 2021-10-22 2025-11-21 深圳成谷科技有限公司 一种轨迹拼接方法、轨迹拼接装置及电子设备
CN116311954A (zh) * 2022-12-26 2023-06-23 杭州海康威视数字技术股份有限公司 一种获取车牌信息的方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007096002A1 (en) * 2006-02-27 2007-08-30 Robert Bosch Gmbh Trajectory retrieval system, method and software for trajectory data retrieval
CN101854516A (zh) * 2009-04-02 2010-10-06 北京中星微电子有限公司 视频监控系统、视频监控服务器及视频监控方法
CN102156863A (zh) * 2011-05-16 2011-08-17 天津大学 跨摄像头的多运动目标跟踪方法
CN102256065A (zh) * 2011-07-25 2011-11-23 中国科学院自动化研究所 基于视频监控网络的视频自动浓缩方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101299811A (zh) * 2008-06-04 2008-11-05 上海世科嘉车辆技术研发有限公司 一种动态倒车影像辅助系统
CN104104915A (zh) * 2014-07-21 2014-10-15 四川沛阳科技有限公司 基于移动终端的多功能行车监控预警系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007096002A1 (en) * 2006-02-27 2007-08-30 Robert Bosch Gmbh Trajectory retrieval system, method and software for trajectory data retrieval
CN101854516A (zh) * 2009-04-02 2010-10-06 北京中星微电子有限公司 视频监控系统、视频监控服务器及视频监控方法
CN102156863A (zh) * 2011-05-16 2011-08-17 天津大学 跨摄像头的多运动目标跟踪方法
CN102256065A (zh) * 2011-07-25 2011-11-23 中国科学院自动化研究所 基于视频监控网络的视频自动浓缩方法

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111369587A (zh) * 2019-06-13 2020-07-03 杭州海康威视系统技术有限公司 一种跟踪方法及装置
CN111369587B (zh) * 2019-06-13 2023-05-02 杭州海康威视系统技术有限公司 一种跟踪方法及装置
CN111274336A (zh) * 2019-12-18 2020-06-12 浙江大华技术股份有限公司 目标轨迹的处理方法、装置、存储介质及电子装置
CN111274336B (zh) * 2019-12-18 2023-05-09 浙江大华技术股份有限公司 目标轨迹的处理方法、装置、存储介质及电子装置
CN111784730A (zh) * 2020-07-01 2020-10-16 杭州海康威视数字技术股份有限公司 一种对象跟踪方法、装置、电子设备及存储介质
CN111784730B (zh) * 2020-07-01 2024-05-03 杭州海康威视数字技术股份有限公司 一种对象跟踪方法、装置、电子设备及存储介质
CN113592919A (zh) * 2021-08-02 2021-11-02 金茂智慧科技(广州)有限公司 安防控制方法及相关装置
CN113947789A (zh) * 2021-09-09 2022-01-18 北京品恩科技股份有限公司 一种赛事用场景人脸识别技术

Also Published As

Publication number Publication date
TW201911118A (zh) 2019-03-16
CN109309809A (zh) 2019-02-05

Similar Documents

Publication Publication Date Title
WO2019019943A1 (zh) 跨区域目标轨迹跟踪的方法及数据处理方法、装置和系统
US20230351794A1 (en) Pedestrian tracking method and device, and computer-readable storage medium
CN106094875B (zh) 一种移动机器人的目标跟随控制方法
CN104299236B (zh) 一种基于场景标定结合插值的目标定位方法
CN108234927B (zh) 视频追踪方法和系统
CN110175587B (zh) 一种基于人脸识别和步态识别算法的视频追踪方法
CN107529221A (zh) 一种结合视频监控和Wi‑Fi定位的追踪分析系统及方法
CN110672111A (zh) 车辆行车路径规划方法、装置、系统、介质和设备
CN103839308A (zh) 人数获取方法、装置及系统
CN111983603A (zh) 运动轨迹接力方法、系统、装置和中心端处理设备
CN111126411B (zh) 一种异常行为识别方法及装置
CN113011445A (zh) 标定方法、识别方法、装置及设备
US20210034927A1 (en) Apparatus and method for person detection, tracking, and identification utilizing wireless signals and images
D'Orazio et al. A survey of automatic event detection in multi-camera third generation surveillance systems
CN110675426A (zh) 人体跟踪方法、装置、设备及存储介质
US11412186B2 (en) Enhanced video system
CN112633096A (zh) 客流的监测方法、装置、电子设备及存储介质
CN111310524B (zh) 多视频关联方法及装置
CN109769105A (zh) 一种村级监控系统
CN110378292B (zh) 三维空间定位系统和方法
CN115690157A (zh) 一种基于Transformer的毫米波雷达行人轨迹预测方法
CN110633648A (zh) 一种自然行走状态下的人脸识别方法和系统
KR101332820B1 (ko) 객체 추적 시스템 및 방법, 객체관리장치 및 그 장치의 구동방법, 촬영장치 및 그 장치의 구동방법
Pham et al. Fusion of wifi and visual signals for person tracking
CN114323025A (zh) 一种室内导航方法、装置及电子设备

Legal Events

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

Ref document number: 18839497

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18839497

Country of ref document: EP

Kind code of ref document: A1