Highway accident handling and tracking method and system based on video monitoring

Abstract

The invention relates to a video monitoring-based highway accident handling tracking method and device, and the method comprises the steps: obtaining video monitoring data of a video monitoring system, marking the processing type of each time period in the video monitoring data, and obtaining a plurality of video time periods; establishing a change probability matrix according to the video monitoring data, and on the basis of the proportion recorded by the change probability matrix, calculating the virtual proportion of the virtual non-change video time period to the video time period of the processing type; and allocating an accident disposal tracking processing resource proportion to the video monitoring system according to the virtual proportion change trend of the video monitoring data. Through the above steps, the processing type change of accident handling tracking of each video monitoring system is dynamically identified, the processing resources allocated to each video monitoring system are dynamically adjusted, and the pertinence, robustness and accuracy of accident handling tracking are improved so as to be close to the actual demand of accident tracking handling.

Description

Technical Field

[0001] The present application relates to the field of digital traffic management technology, and in particular to a method and system for tracking highway accident handling based on video surveillance. Background Art

[0002] Expressway, also known as highway for short, refers to a road designed for high-speed driving of cars. With the advancement of infrastructure construction, the mileage of expressways has grown rapidly. In view of the driving characteristics of cars on expressways, monitoring and management of various sections of expressways is crucial. At present, the monitoring of expressways is mainly divided into traffic monitoring, video monitoring, tunnel monitoring, service area monitoring, etc. Among them, video monitoring is the main monitoring method, which relies on the development of the gantry infrastructure and computer infrastructure of expressways. With the update of monitoring and shooting equipment, communication networks and digital video data processing methods, the application scenarios are broader.

[0003] Therefore, in the process of highway accident handling and tracking based on video surveillance, video surveillance can provide high-value image data for relevant processing entities, improve the pertinence and efficiency of real-time monitoring and processing, and at the same time, the image data of video surveillance can also serve as the basis for big data applications. With the application and promotion of big data processing, big data processing of image data can enrich the execution means of accident handling and tracking, such as accident section demarcation, traffic flow information prediction, and processing personnel allocation. However, due to the differences in video surveillance hardware and data storage on highways, the data uniformity of various image data is poor, and there are differences in data time period, data resolution, etc. The big data platform for accident handling and tracking is an indiscriminate link to various distributed video surveillance systems. The robustness and accuracy of big data applications for video surveillance image data are limited by processing resources and are insufficient, resulting in a low degree of matching between highway accident handling and tracking based on video surveillance and actual needs. Summary of the invention

[0004] In view of the above analysis, the embodiments of the present invention aim to provide a method and device for highway accident handling and tracking based on video surveillance, so as to solve the problem that the big data platform for accident handling and tracking in the prior art implementation results is to indiscriminately link various distributedly deployed video surveillance systems, and the robustness and accuracy of big data applications for video surveillance image data are insufficient due to limited processing resources, resulting in a low match between highway accident handling and tracking based on video surveillance and actual needs.

[0005] The present application embodiment provides a highway accident handling tracking method based on video surveillance, comprising the steps of:

[0006] Acquire video surveillance data of a video surveillance system, and mark a processing type of each time period in the video surveillance data to obtain a plurality of video time periods;

[0007] A change probability matrix is ​​established according to the video surveillance data; wherein the change probability matrix includes the proportion of the video period before the video change to the total video period; wherein the video change includes the change of the processing type of the video period along a single time axis; the total video period is the duration of the video surveillance data;

[0008] Based on the proportion of the change probability matrix records, calculate the virtual proportion of the virtual video time period without change to the video time period of this processing type;

[0009] According to the changing trend of the virtual proportion of the video surveillance data, the accident handling tracking processing resource proportion is allocated to the video surveillance system.

[0010] The highway accident handling and tracking method based on video surveillance in the embodiment of the present application obtains video surveillance data of a video surveillance system, and marks the processing type of each time period in the video surveillance data to obtain multiple video time periods. A change probability matrix is ​​established based on the video surveillance data, and based on the proportion recorded in the change probability matrix, the virtual proportion of virtual video time periods that do not produce changes to the video time periods of this type of processing is calculated. The proportion of accident handling and tracking processing resources is allocated to the video surveillance system according to the change trend of the virtual proportion of the video surveillance data. Through the above steps, the changes in the processing type of accident handling and tracking of each video surveillance system are dynamically identified, and the processing resources allocated to each video surveillance system are dynamically adjusted to improve the pertinence, robustness and accuracy of accident handling and tracking to meet the actual needs of accident tracking and disposal.

[0011] As one of the optional embodiments, the process of acquiring video surveillance data of a video surveillance system and marking the processing type of each time period in the video surveillance data to obtain multiple video time periods includes the steps of:

[0012] The video surveillance data is equally divided into a number of unit time periods, and each unit time period is marked; wherein unit time periods of the same processing type and continuous on a single time axis are merged into the video time period.

[0013] As one of the optional embodiments, the processing type includes tracking that needs to be processed and tracking that does not need to be processed;

[0014] The tracking to be processed includes multiple tracking processing classes.

[0015] As one of the optional embodiments, the process of establishing a change probability matrix based on video surveillance data is as follows:

[0016]

[0017] Among them, λ ij It indicates the proportion of the video time period of processing type i to the total video time period when the video time period of processing type i is changed to the video time period of processing type j; λ indicates the change probability matrix.

[0018] As one of the optional embodiments, the process of calculating the virtual proportion of the virtual video time period without change to the video time period of this processing type based on the proportion recorded in the change probability matrix is ​​as follows:

[0019]

[0020] Among them, λ T represents the virtual proportion, It indicates the proportion of the video period in which the p processing type changes from a certain video surveillance data to the next video surveillance data to the total video period of the next video surveillance data. Indicates the proportion of the video period of the first video surveillance data p processing type to the total video period;

[0021] Among them, i, j, and p all represent processing types, and n represents the total number of processing types.

[0022] As one of the optional embodiments, the process of allocating the accident handling tracking processing resource ratio to the video monitoring system according to the virtual ratio change trend of the video monitoring data includes the steps of:

[0023] An allocation curve of the accident handling and tracking processing resources is fitted based on the negative correlation between the virtual proportion and the accident handling and tracking processing resource proportion.

[0024] As one of the optional embodiments, the negative correlation process between the virtual proportion and the accident handling tracking processing resource proportion is as follows:

[0025]

[0026] Among them, Δ y represents the proportion of accident tracking processing resources for y video surveillance data, Δ y+1 It indicates the proportion of accident handling and tracking processing resources of the next video surveillance data of the y video surveillance data. represents the virtual proportion of y video surveillance data, λ T y+1 Indicates the virtual proportion of the next video surveillance data of the y video surveillance data.

[0027] The embodiment of the present application also provides a highway accident handling tracking device based on video surveillance, comprising:

[0028] A video marking module, used to obtain video surveillance data of a video surveillance system, and mark the processing type of each time period in the video surveillance data to obtain multiple video time periods;

[0029] A matrix establishment module, used to establish a change probability matrix according to the video surveillance data; wherein the change probability matrix includes the proportion of the video period before the video change to the total video period; wherein the video change includes the change of the processing type of the video period along a single time axis; the total video period is the duration of the video surveillance data;

[0030] The proportion calculation module calculates the virtual proportion of the virtual video time period without change to the video time period of the processing type based on the proportion recorded in the change probability matrix;

[0031] The proportion allocation module is used to allocate the accident handling tracking processing resource proportion to the video monitoring system according to the virtual proportion change trend of the video monitoring data.

[0032] The highway accident handling and tracking device based on video surveillance of the embodiment of the present application obtains the video surveillance data of the video surveillance system, and marks the processing type of each time period in the video surveillance data to obtain multiple video time periods. A change probability matrix is ​​established according to the video surveillance data, and the virtual proportion of the virtual video time periods that do not produce changes to the video time periods of this type of processing is calculated based on the proportion recorded in the change probability matrix. The proportion of accident handling and tracking processing resources is allocated to the video surveillance system according to the change trend of the virtual proportion of the video surveillance data. Through the above steps, the changes in the processing type of accident handling and tracking of each video surveillance system are dynamically identified, and the processing resources allocated to each video surveillance system are dynamically adjusted to improve the pertinence, robustness and accuracy of accident handling and tracking to meet the actual needs of accident tracking and disposal.

[0033] At least one embodiment of the present application further provides a data control device, including:

[0034] one or more memories non-transitorily storing computer-executable instructions;

[0035] One or more processors are configured to run computer executable instructions, wherein the computer executable instructions, when executed by the one or more processors, implement the highway accident handling and tracking method based on video surveillance according to any embodiment of the present application.

[0036] The above-mentioned data control device obtains the video surveillance data of the video surveillance system, and marks the processing type of each time period in the video surveillance data to obtain multiple video time periods. A change probability matrix is ​​established according to the video surveillance data, and based on the proportion recorded in the change probability matrix, the virtual proportion of the virtual video time period without change in the video time period of this type of processing is calculated. According to the change trend of the virtual proportion of the video surveillance data, the accident handling tracking processing resource proportion is allocated to the video surveillance system. Through the above steps, the changes in the processing type of accident handling tracking of each video surveillance system are dynamically identified, and the processing resources allocated to each video surveillance system are dynamically adjusted to improve the pertinence, robustness and accuracy of accident handling tracking to meet the actual needs of accident tracking and disposal.

[0037] At least one embodiment of the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, a highway accident handling and tracking method based on video surveillance according to any embodiment of the present application is implemented.

[0038] The above-mentioned non-transitory computer-readable storage medium obtains the video surveillance data of the video surveillance system, and marks the processing type of each time period in the video surveillance data to obtain multiple video time periods. A change probability matrix is ​​established according to the video surveillance data, and based on the proportion recorded in the change probability matrix, the virtual proportion of the virtual video time period without change in the video time period of this type of processing is calculated. According to the change trend of the virtual proportion of the video surveillance data, the accident handling tracking processing resource proportion is allocated to the video surveillance system. Through the above steps, the changes in the processing type of accident handling tracking of each video surveillance system are dynamically identified, and the processing resources allocated to each video surveillance system are dynamically adjusted to improve the pertinence, robustness and accuracy of accident handling tracking to meet the actual needs of accident tracking and disposal. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A flowchart of a highway accident handling and tracking method based on video surveillance according to an embodiment of the application;

[0040] Figure 2 This is a schematic diagram of the structure of the highway accident handling and tracking system;

[0041] Figure 3 A flowchart of a highway accident handling and tracking method based on video surveillance according to a preferred embodiment;

[0042] Figure 4 Determining a schematic diagram for video period marking;

[0043] Figure 5 It is a module structure diagram of a highway accident handling and tracking device based on video monitoring according to an embodiment of the application;

[0044] Figure 6 A schematic block diagram of a data control device provided by the present invention;

[0045] Figure 7 A schematic diagram of a non-transitory computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be clearly and completely described below in conjunction with the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the described embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which this application belongs. "First", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0048] In order to keep the following description of the embodiments of the present application clear and concise, the present application omits detailed descriptions of some known functions and known components.

[0049] The embodiment of the present application provides a highway accident handling and tracking method based on video surveillance.

[0050] Figure 1 FIG. 1 is a flow chart of a highway accident handling and tracking method based on video surveillance according to an embodiment of an application. Figure 1 As shown, a highway accident handling and tracking method based on video surveillance in an embodiment of the application includes steps S100 to S103:

[0051] S100, acquiring video surveillance data of a video surveillance system, and marking a processing type of each time period in the video surveillance data to obtain a plurality of video time periods;

[0052] S101, establishing a change probability matrix according to the video surveillance data; wherein the change probability matrix includes the proportion of the video period before the video change to the total video period; wherein the video change includes the change of the processing type of the video period along a single time axis; the total video period is the duration of the video surveillance data;

[0053] S102, based on the ratio recorded in the change probability matrix, calculating the virtual ratio of the virtual video time period that does not generate a change to the video time period of the processing type;

[0054] S103, allocating an accident handling tracking processing resource ratio to the video surveillance system according to a virtual ratio change trend of the video surveillance data.

[0055] Figure 2 The schematic diagram of the highway accident handling and tracking system is as follows: Figure 2 As shown, the highway accident handling and tracking system is based on a unified data platform 10, connected to each distributed video monitoring system 11, receives video monitoring data S1 from each video monitoring system, and performs accident identification, classification processing and handling tracking. The data platform currently mainly relies on machine vision algorithms to process video monitoring data accordingly. With the deployment of various highways and the increase in traffic pressure, some of the original video monitoring systems have problems in connecting with the processing resources of the data platform, resulting in high data processing pressure on the data platform, and problems in handling and tracking accidents of some video monitoring systems.

[0056] Based on the current system, the execution body of the method steps of the embodiment of the present application can be attached to the highway accident handling tracking system, or a separate data system can be built to complete the adjustment in conjunction with the data interaction of the highway accident handling tracking system.

[0057] The acquired video surveillance data has been pre-marked with processing types in the highway accident handling tracking system, and the processing types are associated and matched with abnormal warning and accident handling tracking. For example, when abnormal traffic information and accident level waiting for processing information are marked, a video period with a specific processing type is formed.

[0058] Preferably, the processing type includes tracking that needs to be processed and tracking that does not need to be processed;

[0059] The tracking to be processed includes multiple tracking processing classes.

[0060] Among them, the tracking and processing category corresponds to the administrative processing division of the highway accident disposal tracking system, and the tracking and processing category is delineated through data identification.

[0061] Preferably, after acquiring the video surveillance data, the processing type can also be marked from the video surveillance data according to the corresponding machine vision algorithm to obtain the video period. For example, the machine vision algorithm module of the highway accident handling tracking system is called to execute the update of the video period.

[0062] As one of the preferred embodiments, Figure 3 FIG. 1 is a flow chart of a method for tracking highway accidents based on video surveillance according to a preferred embodiment of the present invention. Figure 3 As shown, in step S100, the video surveillance data of the video surveillance system is obtained, and the processing type of each time period is marked in the video surveillance data to obtain a plurality of video time periods, including step S200:

[0063] S200, dividing the video surveillance data into a number of unit time periods, and marking each unit time period; wherein unit time periods of the same processing type and continuous on a single time axis are merged into the video time period.

[0064] In this preferred embodiment, the video surveillance data is divided into unit time periods BASE and the unit time periods BASE are marked. Figure 4 As shown, the marking of the original highway accident handling tracking system is based on the actual recognition result of the processing type, and there is no fixed rule for the starting point and end point of the video period (A / B). When corresponding to the unit period division of the embodiment of the present application, the unit period BASE with a single time axis is merged into a video period. Preferably, the unit period where the starting point and the end point are located is divided into unit periods with tracking processing classes according to the proportion of the processing type. The smaller the unit period, the higher the accuracy of the subsequent virtual proportion.

[0065] Based on the solution of the preferred embodiment, the execution entity needs to call the machine vision algorithm module from the highway accident handling and tracking system to execute the marking of step S200 and form an independently marked video period.

[0066] like Figure 4 As shown in the figure, the video time period corresponds to the processing type one by one, and has a certain proportion in the total video time period. Figure 4 The video period A along the single time axis is shown to be changed to the video period B. By analogy, the conversion probability matrix includes the proportion of the video period before the video change to the total video period, that is, when the video period A is changed to the video period B, the proportion of the video period A to the total video period. The total video period is the duration of the video surveillance data.

[0067] The change probability matrix is ​​established as follows:

[0068]

[0069] Among them, λij It indicates the proportion of the video time period of processing type i to the total video time period when the video time period of processing type i is changed to the video time period of processing type j; λ indicates the change probability matrix.

[0070] Based on this, in step S102, based on the proportion recorded in the change probability matrix, the virtual proportion of the virtual video time period without change to the video time period of this processing type is calculated as follows:

[0071]

[0072] Among them, λ T represents the virtual proportion, It indicates the proportion of the video period in which the p processing type changes from a certain video surveillance data to the next video surveillance data to the total video period of the next video surveillance data. Indicates the proportion of the video period of the first video surveillance data p processing type to the total video period;

[0073] Among them, i, j, and p all represent processing types, and n represents the total number of processing types.

[0074] The virtual proportion of the video surveillance data is determined, and the higher the virtual proportion, the lower the accident handling tracking demand of the video surveillance data. At the same time, in the application embodiment, the video surveillance data of the video surveillance system is continuously updated, and the video surveillance data is obtained by time period to form continuous video surveillance data on a single time axis, and the virtual proportions of different video surveillance data are calculated independently.

[0075] As one of the preferred embodiments, Figure 3 As shown, step S103 is a process of allocating accident handling tracking processing resource proportions to the video surveillance system according to the virtual proportion change trend of the video surveillance data, including step S201:

[0076] S201, fitting an allocation curve of accident handling tracking and processing resources based on the negative correlation between the virtual proportion and the accident handling tracking and processing resource proportion.

[0077] Among them, the accident handling and tracking processing resources are the computing resources and processing resources of the highway accident handling and tracking system, which are positively correlated with the granularity of accident handling and tracking. Reducing the accident handling and tracking processing resources includes reducing the computing power allocation and processing personnel allocation of the machine vision algorithm module, and reducing the accident warning level.

[0078] Preferably, the process of virtual proportion and the accident handling tracking processing resource proportion is as follows:

[0079]

[0080] Among them, Δ y represents the proportion of accident tracking processing resources for y video surveillance data, Δ y+1 It indicates the proportion of accident handling and tracking processing resources of the next video surveillance data of the y video surveillance data. represents the virtual proportion of y video surveillance data, Indicates the virtual proportion of the next video surveillance data of the y video surveillance data.

[0081] The highway accident handling and tracking method based on video surveillance of any embodiment of the present disclosure obtains video surveillance data of a video surveillance system, and marks the processing type of each time period in the video surveillance data to obtain multiple video time periods. A change probability matrix is ​​established based on the video surveillance data, and the virtual proportion of virtual video time periods that do not produce changes to the video time periods of this type of processing is calculated based on the proportion recorded in the change probability matrix. The proportion of accident handling and tracking processing resources is allocated to the video surveillance system according to the change trend of the virtual proportion of the video surveillance data. Through the above steps, the changes in the processing type of accident handling and tracking of each video surveillance system are dynamically identified, and the processing resources allocated to each video surveillance system are dynamically adjusted to improve the pertinence, robustness and accuracy of accident handling and tracking to meet the actual needs of accident tracking and handling.

[0082] The embodiment of the present application also provides a highway accident handling and tracking device based on video surveillance.

[0083] Figure 5 FIG. 1 is a module structure diagram of a highway accident handling and tracking device based on video surveillance according to an embodiment of an application. Figure 5 As shown, a highway accident handling tracking device based on video surveillance in an application embodiment includes:

[0084] The video marking module 100 is used to obtain video surveillance data of the video surveillance system, and mark the processing type of each time period in the video surveillance data to obtain multiple video time periods;

[0085] The matrix establishment module 101 is used to establish a change probability matrix according to the video surveillance data; wherein the change probability matrix includes the proportion of the video period before the video change to the total video period; wherein the video change includes the change of the processing type of the video period along a single time axis; the total video period is the duration of the video surveillance data;

[0086] The proportion calculation module 102 calculates the virtual proportion of the virtual video time period without change to the video time period of the processing type based on the proportion recorded in the change probability matrix;

[0087] The proportion allocation module 103 is used to allocate the accident handling tracking processing resource proportion to the video monitoring system according to the virtual proportion change trend of the video monitoring data.

[0088] The highway accident handling and tracking device based on video surveillance of the embodiment of the present application obtains the video surveillance data of the video surveillance system, and marks the processing type of each time period in the video surveillance data to obtain multiple video time periods. A change probability matrix is ​​established according to the video surveillance data, and the virtual proportion of the virtual video time periods that do not produce changes to the video time periods of this type of processing is calculated based on the proportion recorded in the change probability matrix. The proportion of accident handling and tracking processing resources is allocated to the video surveillance system according to the change trend of the virtual proportion of the video surveillance data. Through the above steps, the changes in the processing type of accident handling and tracking of each video surveillance system are dynamically identified, and the processing resources allocated to each video surveillance system are dynamically adjusted to improve the pertinence, robustness and accuracy of accident handling and tracking to meet the actual needs of accident tracking and disposal.

[0089] At least one embodiment of the present application also provides a data control device. Figure 6 A schematic block diagram of a data control device provided in at least one embodiment of the present application. Figure 6 As shown, the data control device 20 may include one or more memories 200 and one or more processors 201. The memory 200 is used to store computer executable instructions non-transiently; the processor 201 is used to run the computer executable instructions, and when the computer executable instructions are run by the processor 201, the processor 201 may execute one or more steps in the highway accident handling and tracking method based on video monitoring according to any embodiment of the present application.

[0090] The specific implementation and related explanation of each step of the method for handling and tracking highway accidents based on video surveillance can be found in the above-mentioned embodiment of the method for handling and tracking highway accidents based on video surveillance, and will not be repeated here. Figure 6 The components of the data control device 20 shown are merely exemplary and non-limiting. The data control device 20 may also have other components according to actual application requirements.

[0091] In one embodiment, the processor 201 and the memory 200 can communicate with each other directly or indirectly. For example, the processor 201 and the memory 200 can communicate via a network connection. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network, and the present application does not limit the type and function of the network. For another example, the processor 201 and the memory 200 can also communicate via a bus connection. The bus may be a peripheral component interconnect standard (PCI) bus or an extended industrial standard architecture (EISA) bus, etc. For example, the processor 201 and the memory 200 may be arranged at a remote data server end (cloud) or a distributed energy system end (local end), or may be arranged at a client end (e.g., a mobile device such as a mobile phone). For example, the processor 201 may be a device having data processing capability and / or instruction execution capability such as a central processing unit (CPU), a tensor processor (TPU), or a graphics processor GPU, and may control other components in the data prediction device 20 to perform desired functions. The central processing unit (CPU) may be an X86 or ARM architecture, etc.

[0092] In one embodiment, the memory 200 may include any combination of one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), portable compact disk read-only memory (CD-ROM), USB memory, flash memory, etc. One or more computer executable instructions may be stored on the computer-readable storage medium, and the processor 201 may execute the computer executable instructions to implement various functions of the data prediction device 20. Various applications and various data, as well as various data used and / or generated by the application, etc. may also be stored in the memory 200.

[0093] It should be noted that the data control device 20 can achieve technical effects similar to the aforementioned highway accident handling and tracking method based on video surveillance, and the repeated parts will not be repeated.

[0094] At least one embodiment of the present application also provides a non-transitory computer-readable storage medium. Figure 7 A schematic diagram of a non-transitory computer-readable storage medium provided for at least one embodiment of the present application. Figure 7As shown, one or more computer executable instructions 301 may be non-transitory stored on the non-transitory computer readable storage medium 30. For example, when the computer executable instructions 301 are executed by a computer, the computer may execute one or more steps in the highway accident handling and tracking method based on video monitoring according to any embodiment of the present application.

[0095] In one embodiment, the non-transitory computer-readable storage medium 30 may be applied to the above-mentioned data control device 20 , for example, it may be the memory 200 in the data control device 20 .

[0096] In one embodiment, the description of the non-transitory computer-readable storage medium 30 may refer to the description of the memory 200 in the embodiment of the data control device 20, and the repeated parts will not be repeated.

[0097] It should be noted that the memory 200 stores different non-transiently stored computer executable instructions, and the data control device 20 corresponds to a firmware upgrade device. When the computer executable instructions are executed by the processor 201, the processor 201 can execute one or more steps in the highway accident handling and tracking method based on video surveillance according to any embodiment of the present application.

[0098] There are a few points to note about this application:

[0099] (1) The drawings of the embodiments of the present application only relate to the structures related to the embodiments of the present application, and other structures may refer to the general design.

[0100] (2) For the sake of clarity, the thickness and size of layers or structures are exaggerated in the drawings used to describe the embodiments of the present invention. It is understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element, or there may be intervening elements.

[0101] (3) In the absence of conflict, the embodiments of the present application and the features in the embodiments may be combined with each other to obtain new embodiments. The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. The protection scope of the present application shall be based on the protection scope of the claims.

[0102] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0103] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A highway accident handling and tracking method based on video surveillance, characterized in that: Includes steps: Acquire video surveillance data of a video surveillance system, and mark a processing type of each time period in the video surveillance data to obtain a plurality of video time periods; A change probability matrix is ​​established according to the video surveillance data; wherein the change probability matrix includes the proportion of the video period before the video change to the total video period; wherein the video change includes the change of the processing type of the video period along a single time axis; the total video period is the duration of the video surveillance data; Based on the proportion of the change probability matrix records, calculate the virtual proportion of the virtual video time period without change to the video time period of this processing type; According to the changing trend of the virtual proportion of the video surveillance data, the accident handling tracking processing resource proportion is allocated to the video surveillance system.

2. The highway accident handling and tracking method based on video surveillance according to claim 1 is characterized in that: The process of obtaining video surveillance data of a video surveillance system and marking the processing type of each time period in the video surveillance data to obtain multiple video time periods includes the steps of: The video surveillance data is equally divided into a number of unit time periods, and each unit time period is marked; wherein unit time periods of the same processing type and continuous on a single time axis are merged into the video time period.

3. The highway accident handling and tracking method based on video surveillance according to claim 2 is characterized in that: The processing type includes tracking that needs to be processed and tracking that does not need to be processed; The tracking to be processed includes multiple tracking processing classes.

4. The highway accident handling and tracking method based on video surveillance according to claim 1 is characterized in that: The process of establishing the change probability matrix based on video surveillance data is as follows: Among them, λ ij It indicates the proportion of the video time period of processing type i to the total video time period when the video time period of processing type i is changed to the video time period of processing type j; λ indicates the change probability matrix.

5. The highway accident handling and tracking method based on video surveillance according to claim 4 is characterized in that: The process of calculating the virtual proportion of the virtual video time period without change to the video time period of this type of processing based on the proportion of the change probability matrix records is as follows: Among them, λ T represents the virtual proportion, It indicates the proportion of the video period in which the p processing type changes from a certain video surveillance data to the next video surveillance data to the total video period of the next video surveillance data. Indicates the proportion of the video period of the first video surveillance data p processing type to the total video period; Among them, i, j, and p all represent processing types, and n represents the total number of processing types.

6. The highway accident handling and tracking method based on video surveillance according to claim 1 is characterized in that: The process of allocating the accident handling tracking processing resource ratio to the video monitoring system according to the virtual ratio change trend of the video monitoring data comprises the steps of: An allocation curve of the accident handling and tracking processing resources is fitted based on the negative correlation between the virtual proportion and the accident handling and tracking processing resource proportion.

7. The highway accident handling and tracking method based on video surveillance according to claim 6 is characterized in that: The negative correlation process between the virtual ratio and the accident handling and tracking resource ratio is as follows: Among them, Δ y represents the proportion of accident tracking processing resources for y video surveillance data, Δ y+1 It indicates the proportion of accident handling and tracking processing resources of the next video surveillance data of the y video surveillance data. represents the virtual proportion of y video surveillance data, Indicates the virtual proportion of the next video surveillance data of the y video surveillance data.

8. A highway accident handling tracking device based on video surveillance, characterized in that: include: A video marking module, used to obtain video surveillance data of a video surveillance system, and mark the processing type of each time period in the video surveillance data to obtain multiple video time periods; A matrix establishment module, used to establish a change probability matrix according to the video surveillance data; wherein the change probability matrix includes the proportion of the video period before the video change to the total video period; wherein the video change includes the change of the processing type of the video period along a single time axis; the total video period is the duration of the video surveillance data; The proportion calculation module calculates the virtual proportion of the virtual video time period without change to the video time period of the processing type based on the proportion recorded in the change probability matrix; The proportion allocation module is used to allocate the accident handling tracking processing resource proportion to the video monitoring system according to the virtual proportion change trend of the video monitoring data.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the highway accident handling and tracking method based on video surveillance as described in any one of claims 1 to 7.

10. A data control device, characterized in that: include: one or more memories non-transitorily storing computer-executable instructions; One or more processors are configured to run computer executable instructions, wherein the computer executable instructions, when executed by the one or more processors, implement the highway accident handling and tracking method based on video surveillance as described in any one of claims 1 to 7.

Images