An intelligent control method for monitoring system

Abstract

The present invention provides an intelligent control method for a monitoring system, comprising selecting a reference node, obtaining at least one set of key frames from video data recorded by the reference node, determining by the reference node that a reference object is located at the center of a second preset field of view, adjusting the field of view of a sampling unit in the reference node until the boundary of the second preset field of view intersects with a target object to obtain a field of view adjustment range; selecting a tracking node, and starting from a second frame, keeping the target object at the center of a first preset field of view; obtaining a two-axis pixel displacement rate of the target object within the second preset field of view within an interval from an Nth frame to an N+1th frame, and simultaneously obtaining a time delay from the reference node to a tracking node; after the reference node obtains each frame of image, the tracking node keeps the target image at the center of the second preset field of view and the synchronous field of view adjustment range is the same as that of the reference node, and supplements the field of view adjustment range according to the two-axis pixel displacement obtained by the time delay.

Description

Technical Field

[0001] The invention belongs to the field of image data processing, and in particular relates to an intelligent control method for a monitoring system. Background Art

[0002] With the continuous improvement of security requirements, monitoring systems have been widely used in various fields, such as urban security, industrial production, traffic management, etc. Traditional monitoring systems are mainly based on simple timed recording or manual operation to collect and store data. For example, most of the early urban traffic monitoring cameras only shoot at fixed time intervals. Although this method can obtain a certain amount of video data, it has many problems.

[0003] First, in the monitoring system installed at a fixed position, a monitoring device has a blind spot in the monitoring of a specified area, and when the monitored object leaves the monitoring area, it is difficult to relocate the position of the monitored object in space. In addition, in the continuous monitoring process, due to the lack of intelligent screening mechanism, a large amount of useless data is stored for a long time, occupying a large amount of storage space. At the same time, it becomes extremely difficult to retrieve valuable information from massive video data.

[0004] In view of this, an intelligent control method for a monitoring system is provided to achieve data cleaning during the monitoring process and to track and control a designated monitored object. Summary of the invention

[0005] To this end, the present invention provides an intelligent control method for a monitoring system, which realizes data cleaning during the monitoring process and tracks and controls a designated monitored object.

[0006] A first aspect of the present invention provides an intelligent control method for a monitoring system, comprising the following steps:

[0007] S1. Select one of the nodes in the monitoring system as a reference node, and obtain at least one group of key frames from the video data recorded by the reference node, where each group of key frames includes at least a first frame and a second frame;

[0008] The first frame is any frame after the target object is sampled, and the first frame at least includes the target object located within the first preset field of view and the reference object located within the second preset field of view;

[0009] The second frame is a designated frame within a preset sampling interval after the first frame, and between the second frame and the first frame, the target object is displaced by at least a first distance relative to the reference object;

[0010] S2, determining by the reference node that the reference object is located at the center of the second preset field of view, adjusting the field of view obtained by the reference node until the boundary of the second preset field of view intersects with the target object, and obtaining the field of view at this time as the field of view adjustment range;

[0011] S3, selecting another node sampled synchronously with the reference node as a tracking node, and starting from the second frame, keeping the target object at the center of the first preset field of view, and determining a tracking reference point;

[0012] The distance between the tracking reference point and the target object in the current frame is equal to the distance between the target object and the reference object in the current frame acquired by the reference node;

[0013] After obtaining the tracking reference point, in each frame, a second preset field of view range of the tracking node is used as the tracking range;

[0014] S4, obtaining the two-axis pixel displacement rate of the target object within the second preset field of view within the preset sampling interval from the Nth frame to the N+1th frame, and at the same time obtaining the time delay from the reference node synchronization signal to the tracking node;

[0015] S5. Acquire each frame image after the second frame, the tracking node keeps the target object at the center of the second preset field of view, and synchronizes the field of view adjustment range to be the same as the reference node, and supplements the field of view adjustment range according to the two-axis pixel displacement rate obtained by the time delay until its boundary intersects with the target object.

[0016] As a preferred embodiment, the first preset field of view is determined by the effective pixel range of the lens group of the sampling unit in the reference node within the average effective distortion range, and based on the effective pixel range, each boundary distance of the target object from its geometric center to the minimum bounding box of the target object is obtained, and is obtained by enlarging the boundary distances at equal intervals.

[0017] As a preferred embodiment, the second preset field of view range is a circular boundary formed by the distance between the reference object and the geometric center of the target object.

[0018] As a preferred manner, when the second preset field of view is larger than the first preset field of view, it is determined that the target is out of tracking and an alarm is initiated.

[0019] As a preferred method, when it is determined that the target is out of tracking, the following steps are also performed:

[0020] Acquire other nodes sampled asynchronously with the reference node, acquire video data of the nodes, and acquire the target object from the video data;

[0021] If the target object exists, use the node as a new reference node and execute steps S1-S5;

[0022] If the target object does not exist, obtain a new node until the target object is obtained;

[0023] If the target object does not exist in any node, an alarm is issued.

[0024] As a preferred embodiment, when acquiring other nodes sampled asynchronously with the reference node, the following steps are further performed:

[0025] When the reference node acquires each frame of image, an overlay trajectory map including a second preset field of view range and a motion trajectory of the target object generated by the reference node is acquired;

[0026] In the position of the superimposed trajectory, the data of other nodes closest to the trajectory are obtained as backup sampling nodes. When the target is out of tracking, data is obtained from the backup sampling nodes.

[0027] And the above steps are executed based on each backup sampling node to generate a superimposed trajectory map.

[0028] A second aspect of the present invention provides a monitoring system, comprising a plurality of monitoring nodes;

[0029] At least one sampling unit is provided in each of the monitoring nodes, and each of the sampling units is configured to have a fixed or variable field of view;

[0030] After any one of the plurality of monitoring nodes is configured as a reference node, a motion trajectory obtained with the reference node is obtained, and another node other than the reference node is called according to the motion trajectory.

[0031] As a preferred embodiment, the variable field of view is obtained by adjusting the angle of the sampling unit relative to the axis of the mounting carrier or the distance relative to the plane of the mounting carrier.

[0032] And / or obtained by adjusting the mirror group of the sampling unit.

[0033] According to a third aspect of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method as described in the first aspect of the present invention is implemented.

[0034] According to a fourth aspect of the present invention, there is provided a storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in the first aspect or the second aspect.

[0035] The above technical solution of the present invention has the following advantages compared with the prior art:

[0036] By setting up comprehensive monitoring of multiple monitoring nodes, when the first node obtains the identification of the target monitoring object, the data is transmitted to other nodes to reconstruct and adjust the monitoring image, thereby realizing the monitoring system control of multiple monitoring nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a schematic diagram of a frame of a tracking node provided by Embodiment 1 of the present invention;

[0038] Figure 2 This is a frame diagram of a reference node provided in the first embodiment of the present invention.

[0039] Figure 3 It is a schematic diagram of an electronic device provided in Embodiment 2 of the present invention.

[0040] in,

[0041] 1. First frame; 2. Second frame; 3. Nth frame; 4. N+1th frame; 5. Second preset field of view; 6. Reference object; 7. Target object; 8. Movement trajectory;

[0042] 30. Processor; 31. Memory; 32. Communication interface; 33. Bus. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] In a first aspect of the embodiments of the present disclosure, there is provided an intelligent control method for a monitoring system, such as Figure 1 and Figure 2 As shown, the following steps are included:

[0046] S1, selecting one of the nodes in the monitoring system as a reference node, obtaining at least one set of key frames from the video data recorded by the reference node, each set of key frames including at least a first frame 1 and a second frame 2;

[0047] The first frame 1 is any frame after the target object 7 is sampled, and the first frame 1 at least includes the target object 7 located within the first preset field of view and the reference object 6 located within the second preset field of view 5;

[0048] The second frame 2 is a designated frame within a preset sampling interval after the first frame 1, and between the second frame 2 and the first frame 1, the target object 7 is displaced by at least a first distance relative to the reference object 6;

[0049] S2, determining by the reference node that the reference object 6 is located at the center of the second preset field of view range 5, adjusting the field of view range obtained by the reference node until the boundary of the second preset field of view range 5 intersects with the target object 7, and obtaining the field of view range at this time as the field of view adjustment range;

[0050] S3, selecting another node sampled synchronously with the reference node as a tracking node, starting from the second frame 2, keeping the target object 7 at the center of the first preset field of view, and determining a tracking reference point;

[0051] The distance between the tracking reference point and the target object 7 in the current frame is equal to the distance between the target object 7 and the reference object 6 in the current frame acquired by the reference node;

[0052] In each frame after obtaining the tracking reference point, the second preset field of view range 5 of the tracking node is used as the tracking range;

[0053] S4, obtaining the two-axis pixel displacement rate of the target object 7 within the second preset field of view range 5 during the preset sampling interval from the Nth frame 3 to the N+1th frame 4, and simultaneously obtaining the time delay from the reference node synchronization signal to the tracking node;

[0054] S5. Acquire each frame image after the second frame 2. The tracking node keeps the target object 7 at the center of the second preset field of view range 5, and synchronizes the field of view adjustment range to be the same as the reference node, and supplements the field of view adjustment range according to the two-axis pixel displacement rate obtained according to the time delay until its boundary intersects with the target object 7.

[0055] As a preferred embodiment, the first preset field of view is determined by the effective pixel range of the lens group of the sampling unit in the reference node within the average effective distortion range, and based on the effective pixel range, the boundary distances of the target object 7 from its geometric center to the minimum bounding box of the target object 7 are obtained, and the boundary distances are enlarged at equal intervals according to the boundary distances.

[0056] As a preferred embodiment, the second preset field of view range 5 is a circular boundary formed by the distance between the geometric centers of the reference object 6 and the target object 7 .

[0057] As a preferred manner, when the second preset field of view is larger than the first preset field of view, it is determined that the target is out of tracking and an alarm is initiated.

[0058] As a preferred method, when it is determined that the target is out of tracking, the following steps are also performed:

[0059] Acquire other nodes sampled asynchronously with the reference node, acquire video data of the nodes, and acquire the target object 7 from the video data;

[0060] If the target object 7 exists, the node is used as a new reference node and steps S1 to S5 are executed;

[0061] If the target object 7 does not exist, obtain a new node until the target object 7 is obtained;

[0062] If the target object 7 does not exist in any node traversed, an alarm is generated.

[0063] As a preferred embodiment, when acquiring other nodes sampled asynchronously with the reference node, the following steps are further performed:

[0064] When the reference node acquires each frame of image, a superimposed trajectory diagram including a second preset field of view range 5 and a motion trajectory 8 of a target object 7 generated by the reference node is acquired;

[0065] In the position of the superimposed trajectory, the data of other nodes closest to the trajectory are obtained as backup sampling nodes. When the target is out of tracking, data is obtained from the backup sampling nodes.

[0066] And the above steps are executed based on each backup sampling node to generate a superimposed trajectory map.

[0067] A second aspect of the embodiments of the present disclosure provides a monitoring system, including a plurality of monitoring nodes;

[0068] At least one sampling unit is provided in each of the monitoring nodes, and each of the sampling units is configured to have a fixed or variable field of view;

[0069] After any one of the plurality of monitoring nodes is configured as a reference node, a motion trajectory obtained with the reference node is obtained, and another node other than the reference node is called according to the motion trajectory.

[0070] As a preferred embodiment, the variable field of view is obtained by adjusting the angle of the sampling unit relative to the axis of its mounting carrier or the distance relative to the plane of the mounting carrier, and / or by adjusting the lens group of the sampling unit.

[0071] The disclosed embodiment can accurately determine the relationship between the target object and the reference object by selecting the key frame of the reference node (including the first frame and the second frame under specific conditions). Based on this, the field of view range can be accurately adjusted so that the subsequent tracking has a more accurate starting point. For example, in steps S1-S2, an accurate foundation is laid for tracking the target object in the field of view adjustment, thereby effectively improving the tracking accuracy of the target. The reference node always takes the reference object as the target center during sampling, and does not need to adjust its angle and direction. At the same time, the distance between the target object and the reference object is used as the reference of the second preset field of view range. There is no need to additionally adjust the field of view range of the tracking node, and only synchronization with the reference node is required to complete the tracking. In the tracking process (such as steps S3-S5), the disclosed embodiment takes into account the pixel displacement rate of the target object and the time delay between nodes, and can adjust the field of view adjustment range in real time and accurately, so that the target is always kept in the appropriate field of view center, and the target is continuously accurately tracked, thereby realizing the collaborative work between the reference node and the tracking node, avoiding the tracking that cannot be adjusted in time due to a single node, thereby avoiding the loss of the target.

[0072] The disclosed embodiment uses a specific method for determining the first preset field of view range and the second preset field of view range (such as based on the effective distortion range of the sampling unit lens group and the geometric relationship between the target and the reference object) to enable the system to adapt to the position changes of the target and the reference object in different scenes, thereby enhancing the adaptability of the system in complex environments.

[0073] In the disclosed embodiment, when the target is out of tracking, the system has a complete response strategy. It can reacquire the target object from other nodes that are sampled asynchronously with the reference node, and only initiate an alarm if the target is not found after traversing all nodes. This multi-level processing method reduces the probability of false alarms caused by accidental factors causing target loss, and improves the robustness of the system.

[0074] By selecting synchronously sampled tracking nodes and using the information of the benchmark nodes (such as the distance between the target object and the reference object) to determine the tracking reference point and tracking range, the effective integration and utilization of information among multiple nodes is achieved, giving full play to the advantages of collaborative work of multiple nodes in the monitoring system.

[0075] The method of obtaining backup sampling nodes after the target is out of tracking (determining other nodes closest to the trajectory by overlaying the trajectory graph) can quickly obtain target information from other possible nodes, reducing the time and resource consumption of re-searching the target, and improving the efficiency of resource utilization of the entire monitoring system. In addition, by overlaying the trajectory graph to retain only the key frames, the amount of data storage can be reduced and a large amount of monitoring resources can be avoided.

[0076] Embodiment 2

[0077] Combination Figure 3 As shown, the embodiment of the present disclosure provides an electronic device for path planning of an automatic walking robot based on visual navigation, including a processor (processor) 30 and a memory (memory) 31. Optionally, the electronic device may also include a communication interface (CommunicationInterface) 32 and a bus 33. Among them, the processor 30, the communication interface 32, and the memory 31 can communicate with each other through the bus 33. The communication interface 32 can be used for information transmission. The processor 30 can call the logic instructions in the memory 31 to execute the method of the above-mentioned embodiment 1.

[0078] An embodiment of the present disclosure provides a storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the method as described in the first embodiment.

[0079] The above-mentioned storage medium may be a transient computer-readable storage medium or a non-transient computer-readable storage medium. Non-transient storage media include: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks or optical disks, and other media that can store program codes, which may also be transient storage media.

[0080] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0081] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these effects are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described effects, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, devices and units may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0082] The flowchart and block diagram in the accompanying drawings show the possible architecture, role and operation of the device, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical role. In some alternative implementations, the role marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed in parallel, and they can sometimes be executed in the opposite order, which can depend on the role involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed in parallel, and they can sometimes be executed in the opposite order, which can depend on the role involved. Each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based device that performs the specified role or action, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. An intelligent control method for a monitoring system, characterized in that: The steps include: S1. Select one of the nodes in the monitoring system as a reference node, and obtain at least one group of key frames from the video data recorded by the reference node, where each group of key frames includes at least a first frame and a second frame; The first frame is any frame after the target object is sampled, and the first frame at least includes the target object located within the first preset field of view and the reference object located within the second preset field of view; The second frame is a designated frame within a preset sampling interval after the first frame, and between the second frame and the first frame, the target object is displaced by at least a first distance relative to the reference object; S2, determining by the reference node that the reference object is located at the center of the second preset field of view, adjusting the field of view obtained by the reference node until the boundary of the second preset field of view intersects with the target object, and obtaining the field of view at this time as the field of view adjustment range; S3, selecting another node sampled synchronously with the reference node as a tracking node, and starting from the second frame, keeping the target object at the center of the first preset field of view, and determining a tracking reference point; The distance between the tracking reference point and the target object in the current frame is equal to the distance between the target object and the reference object in the current frame acquired by the reference node; After obtaining the tracking reference point, in each frame, a second preset field of view range of the tracking node is used as the tracking range; S4, obtaining the two-axis pixel displacement rate of the target object within the second preset field of view within the preset sampling interval from the Nth frame to the N+1th frame, and at the same time obtaining the time delay from the reference node synchronization signal to the tracking node; S5, acquiring each frame image after the second frame, the tracking node keeps the target object at the center of the second preset field of view, and synchronizes the field of view adjustment range to be the same as that of the reference node, and supplements the field of view adjustment range according to the two-axis pixel displacement rate obtained by the time delay until its boundary intersects with the target object; Among them, the first preset field of view is determined by the effective pixel range of the lens group of the sampling unit in the reference node within the average effective distortion range, and based on the effective pixel range, each boundary distance of the target object from its geometric center to the minimum bounding box of the target object is obtained, and is obtained by magnifying the boundary distances at equal intervals.

2. The intelligent control method of the monitoring system according to claim 1, characterized in that: The second preset field of view range is a circular boundary formed by the distance between the reference object and the geometric center of the target object.

3. The intelligent control method of the monitoring system according to claim 2, characterized in that: When the second preset field of view is larger than the first preset field of view, it is determined that the target is out of tracking and an alarm is initiated.

4. The intelligent control method of the monitoring system according to claim 3 is characterized in that: When it is determined that the target is out of tracking, the following steps are also performed: Acquire other nodes sampled asynchronously with the reference node, acquire video data of the nodes, and acquire the target object from the video data; If the target object exists, use the node as a new reference node and execute steps S1-S5; If the target object does not exist, obtain a new node until the target object is obtained; If the target object does not exist in any node, an alarm is issued.

5. The intelligent control method of the monitoring system according to claim 4, characterized in that: When acquiring other nodes sampled asynchronously with the reference node, the following steps are also performed: When the reference node acquires each frame of image, an overlay trajectory map including a second preset field of view range and a motion trajectory of the target object generated by the reference node is acquired; In the position of the superimposed trajectory, the data of other nodes closest to the trajectory are obtained as backup sampling nodes. When the target is out of tracking, data is obtained from the backup sampling nodes. And the above steps are executed based on each backup sampling node to generate a superimposed trajectory map.

6. A monitoring system, suitable for implementing the method according to any one of claims 1 to 5, characterized in that: Includes multiple monitoring nodes; At least one sampling unit is provided in each of the monitoring nodes, and each of the sampling units is configured to have a fixed or variable field of view; After any one of the plurality of monitoring nodes is configured as a reference node, a motion trajectory obtained with the reference node is obtained, and another node other than the reference node is called according to the motion trajectory.

7. The monitoring system according to claim 6, characterized in that: The variable field of view is obtained by adjusting the angle of the sampling unit relative to the axis of the mounting carrier or the distance relative to the plane of the mounting carrier. And / or obtained by adjusting the mirror group of the sampling unit.

8. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images