Video analytics-based methods, equipment, and storage media for tracking key controlled items.

Abstract

The present invention discloses a method, device and storage medium for tracking key controlled items based on video analysis, wherein the tracking method includes step S1: obtaining target object information and person information carrying the target object, marking the person carrying the target object as the main target; step S2: tracking the main target, and judging in real time whether there are other objects passing by the main target, if so, marking the objects passing by the main target as secondary targets, and executing step S3; if not, continuing to track the main target; step S3: obtaining real-time video information of the secondary target, judging whether the secondary target carries the same type of target object, if so, switching the secondary target to the main target, and returning to step S2; if not, returning to step S2. The method for tracking controlled items of the present invention can greatly improve the accuracy of identifying and tracking controlled items.

Description

Technical Field

[0001] The present invention relates to the technical field of video image analysis and processing, and in particular to a method, device and storage medium for tracking key controlled items based on video analysis. Background Art

[0002] At present, video surveillance is an important part of the security system. It is a comprehensive system with strong prevention capabilities. In the process of video surveillance, cameras are used to shoot pedestrians or road conditions, identify whether there are controlled items in the shooting picture, and quickly find the location of controlled items and track them through video image analysis and processing, so as to understand the dynamics of controlled items in time and make corresponding security management decisions as soon as possible to reduce accidents.

[0003] However, the existing video surveillance system generally tracks the controlled items only. If the controlled items are hidden in the clothes of the target person, the monitoring system cannot identify the location of the controlled items and cannot continue to track the controlled items. Alternatively, after the existing video surveillance system identifies that the target person is carrying the controlled items, the system only tracks the whereabouts of the target person. However, if the target person transfers the controlled items to other persons during the movement, the video surveillance system cannot identify that the controlled items have been transferred and can only continue to track the original target person. At this time, the target person no longer carries the controlled items, and it is meaningless to continue tracking the target person. Summary of the invention

[0004] In order to overcome the deficiencies of the prior art, one of the objectives of the present invention is to provide a method for tracking key controlled items based on video analysis, which can improve the accuracy of identifying and tracking controlled items.

[0005] A second object of the present invention is to provide an electronic device.

[0006] A third object of the present invention is to provide a storage medium.

[0007] One of the purposes of the present invention is achieved by the following technical solution:

[0008] The key controlled items tracking method based on video analysis includes:

[0009] Step S1: Acquire target object information and person information carrying the target object, and mark the person carrying the target object as the main target;

[0010] Step S2: Track the main target and determine in real time whether there are other objects passing by the main target. If yes, mark the objects passing by the main target as secondary targets and execute step S3; if no, continue to track the main target;

[0011] Step S3: Obtain real-time video information of the secondary target, determine whether the secondary target in the real-time video carries the same type of target object, if yes, switch the secondary target to the main target and return to step S2; if not, directly return to step S2.

[0012] Furthermore, the method for obtaining the target object information and the person information carrying the target object in step S1 is:

[0013] Retrieve the video images taken by the camera installed in the preset area, obtain the captured images of each object in the video images, compare the captured images with the preset images of controlled objects for similarity, and when a captured image with a similarity higher than a preset value appears, mark the object corresponding to the captured image as a target object, and generate target object information according to the type of the target object;

[0014] A captured image of a person carrying the target object is obtained from the video image, feature information of the person in the captured image is extracted, and the feature information is bound to the target object information.

[0015] Furthermore, at least three camera devices are arranged in each of the preset areas, and the shooting ranges of all the camera devices overlap and cover the preset areas.

[0016] Furthermore, each of the camera devices has a rotation angle of 0 to 120° in the horizontal direction.

[0017] Furthermore, the method for tracking the main target in step S2 is:

[0018] Control any camera device in the preset area where the main target is located to track and shoot the main target, and determine in real time whether the main target has left the current preset area. If the main target has left the current preset area, control any camera device in the adjacent area to continue tracking and shooting the main target.

[0019] Furthermore, the method for determining whether there are other objects passing by the main target in step S2 is:

[0020] The main target is taken as the center and a preset distance is extended in all directions outside the center to divide the designated range of the main target. It is determined whether there is an object outside the designated range entering the designated range of the main target and then leaving the designated range of the main target. If so, the object is marked as a secondary target.

[0021] Furthermore, in step S3, the method for obtaining the real-time video information of the secondary target and determining whether the secondary target carries the target of the same type is:

[0022] When an object outside the specified range enters the specified range of the main target, the direction in which the object enters the specified range is identified; when the object is marked as a secondary target, the camera device in the preset area where the main target is located is controlled to shoot the secondary target with a shooting angle facing the entry direction of the secondary target to obtain real-time video information of the front of the secondary target, and then the video image of the secondary target is compared with the preset image of the controlled object for similarity. If the similarity is higher than the preset value, it means that the target object has been transferred to the secondary target.

[0023] Furthermore, it also includes: when there is any object marked as the main target or the secondary target, the geographical location information of the main target or the secondary target is obtained according to the positioning information of the camera device, and the geographical location information of the main target or the secondary target and the character feature information of the main target or the secondary target are sent to the alarm system.

[0024] The second object of the present invention is achieved by adopting the following technical solution:

[0025] An electronic device comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for tracking key controlled items based on video analysis when executing the computer program.

[0026] The third object of the present invention is achieved by adopting the following technical solution:

[0027] A storage medium stores a computer program, which, when executed, implements the above-mentioned method for tracking key controlled items based on video analysis.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] Mark the person carrying the controlled item as the main target, mark the object passing the main target as the secondary target, and then determine whether the secondary target carries the controlled item. This way, it can be identified whether the controlled item has been transferred to other people during the movement of the main target. If the controlled item has been transferred, the secondary target carrying the controlled item will be tracked, thereby improving the accuracy of identifying and tracking the controlled item. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A schematic diagram of the shooting range of multiple camera devices of the present invention;

[0031] Figure 2 The figure is a flow chart of a method for tracking key controlled items based on video analysis according to the present invention. DETAILED DESCRIPTION

[0032] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0033] Embodiment 1

[0034] This embodiment provides a method for tracking key controlled items based on video analysis. The system of this embodiment can be used in conjunction with an existing security monitoring system; Figure 1 As shown, in the security monitoring system, a plurality of multi-angle cameras are used to shoot a video of a preset area, wherein the preset area is a pre-planned area of ​​a certain area, in which a plurality of cameras are arranged, and the road conditions in the preset area are photographed by the plurality of cameras; in this embodiment, at least three cameras are arranged in the preset area, if the number of cameras is three, the lines between the three cameras form a triangle, if the number of cameras is four, the lines between the four cameras form a quadrilateral; and all cameras are oriented to shoot in the direction of the center point of the triangle or quadrilateral, such as Figure 1 As shown, Figure 1 The middle quadrilateral area A is the shooting range of the four cameras, and the quadrilateral area B is the preset area, so that the shooting ranges of all cameras can completely cover the area of ​​the preset area after being superimposed, avoiding blind spots in the preset area.

[0035] The camera devices can be rotated vertically and horizontally at their respective installation positions, and each of the camera devices in this embodiment has a rotation angle of 0 to 120 degrees in the horizontal direction, which can facilitate accurate capture and tracking of people carrying controlled items. Each camera device has its own unique code, and each camera device has its own positioning information, and the geographical location of the camera device and the unique code are bound to obtain the geographical location of each camera device and its corresponding preset area location.

[0036] like Figure 2 As shown, the key controlled item tracking method of this embodiment specifically includes the following steps:

[0037] Step S1: Acquire target object information and person information carrying the target object, and mark the person carrying the target object as a main target.

[0038] Among them, the existing security monitoring system can be used in advance to identify whether there is anyone carrying controlled items in the preset area. Some existing security monitoring systems can directly analyze the type of controlled items and the video image feature information, height, gender and other personal information of the person carrying the controlled items. At this time, the above-mentioned target object information and the person carrying the target object can be directly obtained from the security monitoring system. In addition, if the existing security monitoring system cannot recognize the above information, it is also possible to directly retrieve the video images taken by the camera equipment installed in the preset area, obtain the captured images of each object in the video image, wherein the captured images include images of people and objects, and compare the captured images with the preset controlled object images for similarity. When a captured image with a similarity higher than a preset value appears, the object corresponding to the captured image is marked as a target object, and the target object is the controlled object. When importing the controlled object image, the type of controlled object can also be imported, so as to know the type of target object in the video image, and generate target object information according to the type of target object. In addition, a captured image of a person carrying the target object in the video image is obtained, and the characteristic information of the person in the captured image is extracted. The characteristic information is the person information carrying the target object, and it is bound to the target object information so as to track the main target.

[0039] Step S2: Track the main target and determine in real time whether there are other objects passing by the main target. If so, mark the objects passing by the main target as secondary targets and execute step S3; if not, continue to track the main target.

[0040] After the main target is determined, any camera device in the preset area where the main target is located is controlled to track and shoot the main target. The shooting angle of the camera device moves along with the movement of the main target, so that the main target always appears in the video image of the camera device. In addition, multiple cameras in the preset area can cooperate with each other to make the main target appear in the video image taken by any camera device when it is in the preset area. At the same time, it is also necessary to determine in real time whether the main target has left the current preset area. If the main target has left the current preset area, any camera device in the adjacent area is controlled to continue tracking and shooting the main target.

[0041] Among them, the method for judging whether there are other objects passing by the main target is: taking the main target as the center in advance, extending the preset distance in all directions outside the center to divide the designated range of the main target, wherein the preset distance can be a relatively close width to the main target, for example, a circular range with a radius of 50cm with the main target as a circle; then judging whether there are objects outside the designated range entering the designated range of the main target and then leaving the designated range of the main target, if so, it means that the object has passed by the main target, and the object is marked as a secondary target. In this close contact opportunity, the main target carrying controlled items may transfer the controlled items to the secondary target passing by, so it is necessary to identify and analyze whether the secondary target is carrying controlled items.

[0042] If a controlled item is hidden on the main target, the tracking method of this embodiment is also applicable. Since the controlled item will be revealed when the main target transfers the controlled item, the controlled item can be re-identified by the camera equipment during the period from when the controlled item is revealed to when it is hidden on the secondary target, so as to determine whether the controlled item has been transferred.

[0043] Step S3: Acquire the real-time video information of the secondary target, determine whether the secondary target carries the same type of target object, if yes, switch the secondary target to the main target and return to step S2; if no, directly return to step S2.

[0044] When it is identified in step S2 that an object outside the specified range enters the specified range of the main target, the direction in which the object enters the specified range is determined according to the moving direction of the object in the video image; when the object is marked as a secondary target, the camera device in the preset area where the main target is located is controlled to shoot the secondary target with a shooting angle facing the entry direction of the secondary target to obtain real-time video information of the front of the secondary target, and then the video image of the secondary target is compared with the preset controlled object image for similarity. If the similarity is higher than the preset value, it means that the target object has been transferred to the secondary target. For example, if Figure 1 As shown, when the secondary target enters the specified range along direction a, the camera device Q with a shooting angle in direction b is controlled to shoot the secondary target, so that the camera device with a shooting angle in direction b will definitely shoot the front of the secondary target. At this time, it is determined whether the secondary target in the video image shot along direction b carries any controlled items. If so, it means that the controlled items have been transferred to the secondary target. At this time, the secondary target replaces the original main target and becomes the new target person. The new target person is tracked and returns to step S2 to determine whether an object passes by the new target person.

[0045] During the tracking, identification and analysis process, when any object is marked as the main target or the secondary target, the unique coding information and positioning information of the camera equipment in the preset area where the main target or the secondary target is located are obtained, so as to obtain the geographic location information of the main target or the secondary target, and the geographic location information of the main target or the secondary target, the personal feature information of the main target or the secondary target, etc. are sent to the alarm system for the management personnel to view, so as to facilitate the tracking and management of controlled items and the persons carrying controlled items.

[0046] Embodiment 2

[0047] The present embodiment provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for tracking key controlled items based on video analysis in the first embodiment when executing the computer program; in addition, the present embodiment also provides a storage medium on which a computer program is stored, wherein the computer program implements the above-mentioned method for tracking key controlled items based on video analysis when executed.

[0048] The device and storage medium in this embodiment and the method in the aforementioned embodiment are two aspects based on the same inventive concept. The method implementation process has been described in detail above, so those skilled in the art can clearly understand the structure and implementation process of the system in this embodiment based on the aforementioned description. For the sake of brevity of the specification, they will not be repeated here.

[0049] The above-mentioned embodiments are only preferred embodiments of the present invention and cannot be used to limit the scope of protection of the present invention. Any non-substantial changes and substitutions made by technicians in this field on the basis of the present invention shall fall within the scope of protection required by the present invention.

Claims

1. A method for tracking key controlled items based on video analysis, characterized in that: include: Step S1: Acquire target object information and person information carrying the target object, and mark the person carrying the target object as the main target; Step S2: Track the main target and determine in real time whether there are other objects passing by the main target. If there are other objects, mark the objects passing by the main target as secondary targets and execute step S3; If not, continue to track the main target; Step S3: obtaining real-time video information of the secondary target, determining whether the secondary target in the real-time video carries the same type of target object, if yes, switching the secondary target to the primary target and returning to step S2; if no, directly returning to step S2; The method for determining whether there are other objects passing by the main target in step S2 is: Taking the main target as the center, a preset distance is extended in all directions outside the center to divide the designated range of the main target, and judging whether there is an object outside the designated range entering the designated range of the main target and then leaving the designated range of the main target, if so, marking the object as a secondary target; The method for obtaining the real-time video information of the secondary target in step S3 and determining whether the secondary target carries the same type of target object is as follows: When an object outside the specified range enters the specified range of the main target, the direction in which the object enters the specified range is identified; when the object is marked as a secondary target, the camera device in the preset area where the main target is located is controlled to shoot the secondary target with a shooting angle facing the entry direction of the secondary target to obtain real-time video information of the front of the secondary target, and then the video image of the secondary target is compared with the preset controlled object image for similarity. If the similarity is higher than the preset value, it means that the target object has been transferred to the secondary target.

2. The method for tracking key controlled items based on video analysis according to claim 1, characterized in that: The method for obtaining the target object information and the person information carrying the target object in step S1 is: Retrieve the video images taken by the camera installed in the preset area, obtain the captured images of each object in the video images, compare the captured images with the preset images of controlled objects for similarity, and when a captured image with a similarity higher than a preset value appears, mark the object corresponding to the captured image as a target object, and generate target object information according to the type of the target object; A captured image of a person carrying the target object is obtained from the video image, feature information of the person in the captured image is extracted, and the feature information is bound to the target object information.

3. The method for tracking key controlled items based on video analysis according to claim 2, characterized in that: At least three camera devices are arranged in each of the preset areas, and the shooting ranges of all the camera devices overlap and cover the preset areas.

4. The method for tracking key controlled items based on video analysis according to claim 3 is characterized in that: Each of the camera devices has a rotation angle of 0 to 120 degrees in the horizontal direction.

5. The method for tracking key controlled items based on video analysis according to claim 1, characterized in that: The method for tracking the main target in step S2 is: Control any camera device in the preset area where the main target is located to track and shoot the main target, and determine in real time whether the main target has left the current preset area. If the main target has left the current preset area, control any camera device in the adjacent area to continue tracking and shooting the main target.

6. The method for tracking key controlled items based on video analysis according to claim 1, characterized in that: Also includes: When there is any object marked as the main target or the secondary target, the geographic location information of the main target or the secondary target is obtained according to the positioning information of the camera device, and the geographic location information of the main target or the secondary target and the character feature information of the main target or the secondary target are sent to the alarm system.

7. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for tracking key controlled items based on video analysis as described in any one of claims 1 to 6.

8. A storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the method for tracking key controlled items based on video analysis as described in any one of claims 1 to 6 is implemented.

Images