Road camera video selection method and system based on camera dynamic weight

Abstract

The present invention provides a road camera video selection method and system based on camera dynamic weights, comprising constructing a rectangular area with the latitude and longitude of a vehicle as the center, and dividing the rectangular area into four sub-areas; determining the vehicle's driving scene by utilizing the difference in the vehicle's heading angle at a desired moment and a previous moment; adjusting the regional weight of at least one sub-area according to the vehicle's driving scene; determining the priority of each roadside camera by utilizing the driving scene weight of each roadside camera, the regional weight of the sub-area where each roadside camera is located, and the current shared scene weight of each roadside camera; and selecting videos of a preset number of roadside cameras in descending order of priority, so that the camera acquisition algorithm is more in line with the video selection tendency under different road conditions and different vehicle operating states, avoiding the problem that a fixed algorithm cannot flexibly control the selection expectation, and improving the monitoring accuracy and response efficiency in a complex road network environment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a road camera video selection method and system based on camera dynamic weights. Background Art

[0002] As autonomous driving demonstration zones expand and the autonomous driving regulatory system improves, rapidly capturing video evidence of driving anomalies and accidents involving fully autonomous vehicles has become a technical challenge for autonomous vehicle regulation. Accurately and rapidly capturing roadside video as supplementary evidence in the event of an autonomous vehicle driving anomaly or accident is a pressing issue for the automated surveillance and regulatory industry.

[0003] The current mainstream roadside video acquisition solutions generally adopt the method of manually retrieving camera videos based on the location and time of the incident, or obtaining camera videos based on the vehicle's driving trajectory, direction, time and camera shooting range prediction.

[0004] Currently, all of the aforementioned methods have significant flaws. While manual camera selection and video recording yields high video capture accuracy, it carries high labor and time costs, is inefficient, and cannot meet the needs of the growing number of vehicles under supervision. Automated video capture based on vehicle trajectory and camera coverage also presents challenges. Limited by rigid camera selection logic, it cannot adapt to complex and changing road conditions and the camera selection preferences based on different scenarios. Consequently, the accuracy of camera video capture fails to meet regulatory requirements.

[0005] Therefore, how to improve monitoring accuracy and response efficiency in complex road network environments is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the Invention

[0006] The present invention provides a road camera video selection method and system based on camera dynamic weights, which are used to solve the defects of low monitoring accuracy and low response efficiency in complex road network environments in the prior art.

[0007] In one aspect, the present invention provides a method for selecting road camera videos based on camera dynamic weights, comprising:

[0008] A rectangular area is constructed with the longitude and latitude of the vehicle as the center, and the rectangular area is divided into four sub-areas; wherein the long axis direction of the rectangular area is consistent with the vehicle's travel direction, and the rectangular area contains the mapped longitude and latitude of multiple roadside cameras;

[0009] determining a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a desired moment and a second heading angle of the vehicle at a moment before the desired moment;

[0010] Adjusting a region weight of at least one sub-region according to a driving scenario of the vehicle;

[0011] The priority of each roadside camera is determined by using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the current shared scene weight of each roadside camera;

[0012] Select videos from a preset number of roadside cameras in descending order of priority.

[0013] According to a road camera video selection method based on camera dynamic weights provided by the present invention, a driving scene of a vehicle is determined by using a difference between a first heading angle of the vehicle at a desired moment and a second heading angle of the vehicle at a moment before the desired moment, comprising:

[0014] If the absolute value of the difference is less than or equal to a preset absolute value, determining the driving scene of the vehicle according to the scene range value to which the difference belongs;

[0015] If the absolute value of the difference is greater than the preset absolute value, the difference is summed or subtracted from the preset value to obtain a conversion value corresponding to the difference, and the driving scene of the vehicle is determined according to the scene range value to which the conversion value belongs.

[0016] According to a road camera video selection method based on camera dynamic weight provided by the present invention, if a target value is greater than a first preset difference value of the scene range value and less than a second preset difference value of the scene range value, it is determined that the driving scene of the vehicle is a right turn; wherein the first preset difference value is a positive number; wherein the target value includes the difference value or the conversion value;

[0017] If the target value is greater than or equal to a third preset difference of the scene range value and less than or equal to the first preset difference, it is determined that the driving scene of the vehicle is straight driving; wherein the third preset difference is a negative number;

[0018] If the target value is greater than the fourth preset difference of the scene range value and less than the third preset difference, it is determined that the driving scene of the vehicle is a left turn; wherein the preset absolute value is the difference between the second preset difference and the fourth preset difference.

[0019] According to a road camera video selection method based on camera dynamic weights provided by the present invention, the area weight of at least one sub-area is adjusted according to the driving scene of the vehicle, including:

[0020] According to the driving scene of the vehicle, using the overlap between the shooting range of each roadside camera and the vehicle trajectory, predicting the predicted shooting time of the vehicle in each sub-area;

[0021] The at least one sub-region is selected in descending order of the predicted shooting duration, and the region weight of the at least one sub-region is adjusted.

[0022] According to the present invention, a road camera video selection method based on camera dynamic weight is provided, which also includes:

[0023] If the driving scene of the vehicle is a left turn or a right turn, the width of the at least one sub-area is expanded by a preset multiple, or,

[0024] If the driving scenario of the vehicle is a left turn or a right turn, the turning radius of the vehicle is obtained, the expansion coefficient is determined based on a preset correlation between the turning radius and the expansion coefficient, and the width of the at least one sub-area is expanded according to the expansion coefficient.

[0025] According to the present invention, a road camera video selection method based on camera dynamic weights is provided. The priority of each roadside camera is determined by using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the shared scene weight of each roadside camera. The method includes:

[0026] Calculating the product of the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the shared scene weight of each roadside camera;

[0027] The priority of each roadside camera is set in descending order of the product.

[0028] According to the present invention, a road camera video selection method based on camera dynamic weight is provided, which also includes:

[0029] If the weight of any target camera of the remaining cameras in the camera cluster to which the i-th roadside camera among the multiple roadside cameras belongs changes, obtaining an adjusted weight of the any target camera; wherein the camera cluster is obtained by clustering all roadside cameras to be processed;

[0030] Determining a change in the shared scene weight of the i-th roadside camera using the adjusted weight;

[0031] The sum of the original shared scene weight of the i-th roadside camera and the change is used as the current shared scene weight of the i-th roadside camera.

[0032] According to a road camera video selection method based on camera dynamic weights provided by the present invention, the change in the shared scene weight of the i-th roadside camera is determined by using the adjusted weights, including:

[0033] Determining the similarity between the i-th roadside camera and the target camera;

[0034] Determining the weight transfer coefficient corresponding to the i-th roadside camera according to a preset correlation relationship between the similarity and the weight transfer coefficient;

[0035] The product of the adjustment weight and the weight transfer coefficient is used as the change amount.

[0036] On the other hand, the present invention also provides a road camera video selection system based on camera dynamic weights, comprising:

[0037] A construction module is configured to construct a rectangular area centered on the longitude and latitude of the vehicle and divide the rectangular area into four sub-areas; wherein the long axis of the rectangular area is consistent with the vehicle's travel direction, and the rectangular area contains the longitude and latitude of multiple roadside cameras;

[0038] a first determining module, configured to determine a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a required moment and a second heading angle of the vehicle at a moment before the required moment;

[0039] An adjustment module, configured to adjust the area weight of each sub-area according to the driving scenario of the vehicle;

[0040] A second determination module is configured to determine the priority of each roadside camera by using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the current shared scene weight of each roadside camera;

[0041] The selection module is used to select videos from a preset number of roadside cameras in order of priority from high to low.

[0042] On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the program, it implements any of the above-mentioned road camera video selection methods based on camera dynamic weights.

[0043] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described road camera video selection methods based on camera dynamic weights.

[0044] On the other hand, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned road camera video selection methods based on camera dynamic weights.

[0045] The present invention provides a road camera video selection method and system based on dynamic camera weights. A rectangular area is constructed with the vehicle's latitude and longitude as the center, and the rectangular area is divided into four subareas. The vehicle's driving scene is determined by using the difference between the vehicle's first heading angle at a desired moment and its second heading angle at a moment immediately preceding the desired moment. The regional weight of at least one subarea is adjusted based on the vehicle's driving scene. The priority of each roadside camera is determined by using the driving scene weight of each roadside camera, the regional weight of the subarea in which each roadside camera is located, and the current shared scene weight of each roadside camera. Videos from a preset number of roadside cameras are selected in descending order of priority. This allows the camera acquisition algorithm to better adapt to the video selection trends under different road conditions and vehicle operating conditions, avoids the problem of a fixed algorithm's inability to flexibly control selection expectations, and improves monitoring accuracy and response efficiency in complex road network environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 1 is a flow chart of a method for selecting road camera videos based on dynamic camera weights provided by an embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of a rectangular area constructed with the latitude and longitude of the vehicle as the center;

[0049] Figure 3 Schematic diagram of the C sub-area and D sub-area that need weight adjustment in the straight driving scenario;

[0050] Figure 4 This is a schematic diagram of the C and D sub-areas that need to be weighted in the left-turn scenario;

[0051] Figure 5 This is a schematic diagram of sub-area A and sub-area C that need to be weighted in a right-turn scenario;

[0052] Figure 62 is a schematic structural diagram of a road camera video selection system based on camera dynamic weights provided by an embodiment of the present invention;

[0053] Figure 7 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0055] Figure 1 It is a flowchart of a road camera video selection method based on camera dynamic weights provided by an embodiment of the present invention.

[0056] like Figure 1 As shown, the execution subject of the road camera video selection method based on camera dynamic weight provided by the embodiment of the present invention can be an electronic device, and the method mainly includes the following steps:

[0057] 101. Construct a rectangular area with the latitude and longitude of the vehicle as the center, and divide the rectangular area into four sub-areas;

[0058] In a specific implementation process, the operating data reported by the autonomous vehicle can be used to obtain the vehicle's latitude and longitude information and heading angle information, and a rectangular area can be constructed with the vehicle's latitude and longitude as the center, and the rectangular area can be divided into 4 sub-areas, such as Figure 2 shown. Figure 2 This is a schematic diagram of a rectangular area constructed with the vehicle's longitude and latitude as its center. The rectangular area can include four sub-areas, A to D. The long axis of the rectangular area aligns with the vehicle's travel direction. The rectangular area contains the mapped longitude and latitude of multiple roadside cameras. In other words, after projection, the projected coordinates of the multiple roadside cameras fall within the rectangular area.

[0059] It should be noted that the width of the rectangular area can be the same as the width of the current road and changes as the width of the current road changes. The length of the rectangular area can be set according to the vehicle's speed, wherein a first speed threshold and a second speed threshold can be set, and the second speed threshold is greater than the first speed threshold. When the vehicle's speed is less than or equal to the first speed threshold, the default length is used. When the vehicle's speed is greater than the first speed threshold but less than the second speed threshold, the ratio of the vehicle's speed to the first speed threshold can be calculated, and the ratio multiplied by the default length is calculated to obtain the length of the rectangular area. That is, L1=L0*a, where L1 is the length of the rectangular area, L0 is the default length, and a is the ratio of the vehicle's speed to the speed threshold. When the vehicle's speed is greater than the second speed threshold, the length of the rectangular area is 2L0.

[0060] 102. Determine a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a desired moment and a second heading angle of the vehicle at a moment before the desired moment;

[0061] In a specific implementation, the first heading angle of the vehicle at the desired moment and the difference between the second heading angle of the vehicle at the moment before the desired moment can be obtained from the vehicle's heading angle information. The difference between the first and second heading angles can be calculated. Further, the vehicle's driving scene can be determined based on the difference. The driving scene can include going straight, turning left, and turning right. The desired moment is the recording time of the event to be viewed, such as the time of an accident.

[0062] In a specific implementation, different scene range values ​​can be set according to different driving scenarios of the vehicle. After obtaining the difference between the first heading angle of the vehicle at the required moment and the second heading angle of the vehicle at the previous moment, the magnitude relationship between the difference and a preset absolute value is first determined. If the absolute value of the difference is less than or equal to the preset absolute value, the difference can be directly used, and the scene range value to which the difference belongs is determined, thereby determining the driving scenario of the vehicle. If the absolute value of the difference is greater than the preset absolute value, the difference cannot be directly used to determine the driving scenario of the vehicle. Instead, the difference can be summed or subtracted with the preset value to obtain a converted value corresponding to the difference, and the driving scenario of the vehicle can be determined based on the scene range value to which the converted value belongs.

[0063] Specifically, if the target value is greater than a first preset difference value of the scene range value and less than a second preset difference value of the scene range value, it is determined that the driving scene of the vehicle is a right turn; wherein the first preset difference value is a positive number; wherein the target value includes the difference value or the conversion value;

[0064] If the target value is greater than or equal to a third preset difference of the scene range value and less than or equal to the first preset difference, it is determined that the driving scene of the vehicle is straight driving; wherein the third preset difference is a negative number;

[0065] If the target value is greater than the fourth preset difference of the scene range value and less than the third preset difference, it is determined that the driving scene of the vehicle is a left turn; wherein the preset absolute value is the difference between the second preset difference and the fourth preset difference.

[0066] Specifically, taking the first preset difference as 20°, the second preset difference as 120°, the third preset difference as -20°, the fourth preset difference as -120°, and the preset absolute value as 240° as an example, different driving scenarios are set with their respective scene range values ​​as follows:

[0067] If the heading angle change (the difference between the heading angles before and after) is greater than 20° and less than 120°, the vehicle is determined to be turning right.

[0068] If the heading angle change is greater than -20° and less than 20°, it is determined that the vehicle is traveling straight.

[0069] If the heading angle change is greater than -120° and less than -20°, it is determined that the vehicle is turning left.

[0070] When the absolute value of the heading angle change is greater than 240°, special processing is required by adding or subtracting 360° before determining the vehicle's driving scenario. For example, if the heading angle at the desired moment is 10° and the previous moment's heading angle is 280°, the difference between the two is -270°. In this case, adding 360° to this difference indicates a right turn. If the heading angle at the desired moment is 280° and the previous moment's heading angle is 10°, the difference between the two is 270°. In this case, subtracting 360° from this difference indicates a left turn.

[0071] It's important to note that the heading angle change determination range can be adjusted through dynamic parameter configuration to optimize the accuracy of vehicle direction determination. For example, if the heading angle sensor experiences excessive noise, the straight ahead range can be expanded to filter out interference; if precision is high, the range can be narrowed to increase sensitivity. I won't go into detail here.

[0072] 103. Adjusting the regional weight of at least one sub-region according to the driving scenario of the vehicle;

[0073] In a specific implementation, the predicted shooting duration of the vehicle in each sub-area can be predicted based on the driving scenario of the vehicle and the degree of overlap between the shooting range of each roadside camera and the vehicle's trajectory. At least one sub-area is selected in descending order of predicted shooting duration, and the area weight of the at least one sub-area is adjusted. Furthermore, the length or width of the at least one sub-area can be adjusted. In other words, sub-areas corresponding to cameras with high overlap between the camera's shooting range and the vehicle's trajectory, and capable of capturing the vehicle for a long period of time, are preferentially selected for weight adjustment, as well as for length or width adjustment.

[0074] Specifically, see Figures 3 to 5 To determine at least one sub-region that needs to be weighted. Figure 3 This is a schematic diagram of the C and D sub-areas that need to be weighted in the straight-ahead scenario. Figure 4 This is a schematic diagram of the C and D sub-areas that need to be weighted in the left-turn scenario. Figure 5 This is a schematic diagram of sub-area A and sub-area C that require weight adjustment in a right-turn scenario.

[0075] Specifically, if Figure 3 As shown, Figure 3 In the figure, (a1)-(a5) are the shooting ranges of the lower left roadside camera, the lower left roadside camera, the upper right roadside camera, the lower right roadside camera, and the upper left roadside camera, respectively. Each shooting range is represented by two facing triangles, and (a1) and (a2) represent the states at different times when driving straight. Figure 3 It can be seen that when the vehicle is moving straight, the video capture area of ​​the cameras in this lane (the lower left roadside camera and the lower right roadside camera) has the highest overlap with the vehicle's driving trajectory, and the cameras can capture the vehicle for a long time. Therefore, the weights of sub-areas C and D are adjusted to 2, and the initial weights of sub-areas A and B are maintained at 1. The initial weights of sub-areas A and B can also be reduced to 0.5.

[0076] like Figure 4 As shown, Figure 4 In the figure, (a1)-(a4) are the shooting range of the lower left corner roadside camera, the shooting range of the upper right corner roadside camera, the shooting range of the upper left corner roadside camera, and the shooting range of the lower right corner roadside camera respectively. Figure 4It can be seen that the video capture areas of the oncoming lane (the upper-right roadside camera) and the lane below (the lower-right roadside camera) have the highest overlap with the vehicle's trajectory, allowing the cameras to capture the vehicle for a longer period of time. Therefore, the weights of sub-areas C and D are adjusted to 2, while the initial weights of sub-areas A and B remain at 1. Alternatively, the initial weights of sub-areas A and B can be reduced to 0.5. Furthermore, during a turn, the vehicle is moving slowly. Although the intended roadside camera has a higher shooting angle and longer capture time than other roadside cameras, the camera's acquisition area may prevent it from appearing within the camera selection area, leading to incorrect video selection. Therefore, when the vehicle is determined to be turning left, the widths of sub-areas C and D can be adjusted to twice their initial widths to increase the probability that the intended camera will be covered by the camera acquisition area. The vehicle's turning radius can also be determined. Based on a pre-set relationship between the turning radius and the expansion factor, an expansion factor is determined, and the width of at least one sub-area is expanded accordingly.

[0077] like Figure 5 As shown, Figure 5 In the figure, (a1)-(a4) are the shooting range of the lower left corner roadside camera, the shooting range of the upper left corner roadside camera, the shooting range of the lower right corner roadside camera, and the shooting range of the upper right corner roadside camera respectively. Figure 5 It can be seen that the capture ranges of the upper region (the upper left roadside camera) and the camera in the lane (the lower left roadside camera) overlap significantly with the vehicle's trajectory, allowing them to capture the current vehicle for extended periods of time. Therefore, the weights of subregions A and C are adjusted to 2, while the initial weights of subregions B and D are maintained at 1. Alternatively, the initial weights of subregions B and D can be reduced to 0.5. Furthermore, during a turn, the vehicle's speed is slow, and while the intended roadside camera has a higher capture angle and duration than other roadside cameras, the camera's acquisition area may prevent it from appearing within the camera selection area, leading to incorrect video selection. Therefore, when the vehicle is determined to be turning right, the widths of subregions A and C can be adjusted to twice their initial widths to increase the probability that the intended camera will be covered by the camera acquisition area. The vehicle's turning radius can also be determined. Based on a pre-set correlation between the turning radius and the expansion factor, an expansion factor is determined, and the width of at least one subregion is expanded accordingly.

[0078] In this embodiment, the vehicle driving scene can be determined based on the changes in the vehicle heading angle in the vehicle operation data, and the acquisition sub-areas can be dynamically weighted to make the camera acquisition algorithm more suitable for video selection tendencies under different road conditions and different vehicle operation states, avoiding the problem that fixed algorithms cannot flexibly control selection expectations.

[0079] 104. Determine the priority of each roadside camera using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the current shared scene weight of each roadside camera;

[0080] In a specific implementation, the product of the driving scene weight of each roadside camera, the area weight of the subarea in which each roadside camera resides, and the shared scene weight of each roadside camera can be calculated. The priority of each roadside camera is then set in descending order of these products. For example, for a left-turn driving scenario, the priority of each roadside camera is calculated as follows: camera left-turn weight * shared left-turn weight * camera area weight (one weight from each of the A, B, C, and D subareas).

[0081] In a specific implementation process, the shared scene weight of each roadside camera can be obtained as follows:

[0082] (1) if the weight of any target camera of the remaining cameras in the camera cluster to which the i-th roadside camera among the multiple roadside cameras belongs changes, obtain the adjusted weight of the any target camera;

[0083] Specifically, all roadside cameras to be processed can be clustered according to information such as cameras on the same street, the same camera shooting angle, and the same camera device pole position to obtain multiple camera clusters. The camera cluster to which the i-th roadside camera among the multiple roadside cameras in the rectangular area belongs can be determined, and the weight of any target camera of the remaining cameras in the camera cluster is changed to obtain the adjusted weight of any target camera.

[0084] (2) using the adjustment weight, determining a change in the shared scene weight of the i-th roadside camera;

[0085] After obtaining the adjustment weight of any target camera of the remaining cameras, the similarity between the i-th roadside camera and the target camera can be determined using a preset similarity algorithm (such as a cosine similarity algorithm). Based on the correlation between the preset similarity and the weight transfer coefficient, the weight transfer coefficient corresponding to the i-th roadside camera is determined, and the product of the adjustment weight and the weight transfer coefficient is used as the change.

[0086] That is to say, the roadside cameras in the same camera cluster usually have similar characteristics. If the shared scene weight of a roadside camera changes, other roadside cameras will usually follow the change, but they will not change directly according to the adjustment weight of the changed roadside camera. Instead, they will be determined based on the similarity between the two. If the similarity between the two is large, the adjustment amount of the shared scene weight of the i-th roadside camera will be close to the adjustment weight of the changed roadside camera. If the similarity between the two is small, the difference between the adjustment amount of the shared scene weight of the i-th roadside camera and the adjustment weight of the changed roadside camera will also be larger.

[0087] (3) The sum of the original shared scene weight of the i-th roadside camera and the change amount is used as the current shared scene weight of the i-th roadside camera.

[0088] Specifically, an initial shared scene weight can be set for each camera. The shared scene weight that changes over time from this initial shared scene weight serves as the original shared scene weight set for each camera. For the same camera cluster, as long as the weight of one camera is adjusted, the original shared scene weights of the other cameras can be changed accordingly, thereby reducing the workload of camera shared scene weight operation and maintenance.

[0089] In this embodiment, through the daily operations and maintenance of autonomous driving supervision, the selection weights of roadside cameras are dynamically adjusted and calibrated, improving the accuracy of roadside camera selection and avoiding the difficulties of logic adjustment caused by hard-coding. At the same time, the integrity requirements of camera information are reduced, adapting to complex camera information data. When camera information is insufficient to accurately obtain through logic coding, weight configuration can be used to effectively intervene in the algorithm selection results. The completely independent weight data structure of each camera weight effectively supports refined adjustments in key areas and complex road ends.

[0090] 105. Select videos from a preset number of roadside cameras in descending order of priority.

[0091] In a specific implementation process, videos from a preset number of roadside cameras can be selected in order of priority from high to low, so that the required videos can be obtained quickly and accurately, improving the monitoring accuracy and response efficiency in complex road network environments.

[0092] The road camera video selection method based on dynamic camera weights in this embodiment constructs a rectangular area centered on the longitude and latitude of the vehicle and divides the rectangular area into four sub-areas. The vehicle's driving scene is determined by using the difference between the vehicle's first heading angle at the desired moment and the vehicle's second heading angle at the moment immediately before the desired moment. The regional weight of at least one sub-area is adjusted based on the vehicle's driving scene. The priority of each roadside camera is determined by using the driving scene weight of each roadside camera, the regional weight of the sub-area in which each roadside camera is located, and the current shared scene weight of each roadside camera. Videos from a preset number of roadside cameras are selected in descending order of priority. In this way, the camera acquisition algorithm can be made more adaptable to the video selection tendencies under different road conditions and vehicle operating conditions, avoiding the problem of a fixed algorithm being unable to flexibly control selection expectations, and improving monitoring accuracy and response efficiency in complex road network environments.

[0093] Based on the same general inventive concept, the present invention also protects a road camera video selection system based on camera dynamic weights. The road camera video selection system based on camera dynamic weights provided by the present invention is described below. The road camera video selection system based on camera dynamic weights described below and the road camera video selection method based on camera dynamic weights described above can be referenced to each other.

[0094] Figure 6 : is a structural diagram of a road camera video selection system based on camera dynamic weights provided by an embodiment of the present invention, such as Figure 6 As shown, the road camera video selection system based on camera dynamic weights of this embodiment includes a construction module 61 , a first determination module 62 , an adjustment module 63 , a second determination module 64 and a selection module 65 .

[0095] The construction module 61 is configured to construct a rectangular area centered on the longitude and latitude of the vehicle and divide the rectangular area into four sub-areas; wherein the long axis of the rectangular area is consistent with the vehicle's travel direction, and the rectangular area contains the longitude and latitude of multiple roadside cameras;

[0096] A first determining module 62 is configured to determine a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a desired moment and a second heading angle of the vehicle at a moment before the desired moment;

[0097] An adjustment module 63, configured to adjust the area weight of each sub-area according to the driving scenario of the vehicle;

[0098] a second determining module 64 for determining the priority of each roadside camera by using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the current shared scene weight of each roadside camera;

[0099] The selection module 65 is used to select videos from a preset number of roadside cameras in descending order of priority.

[0100] Figure 7 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The road camera video selection system based on camera dynamic weights may include: a processor 710, a communications interface 720, a memory 730, and a communication bus 740. The processor 710, the communications interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call the logic instructions in the memory 730 to execute the road camera video selection method based on camera dynamic weights.

[0101] Furthermore, the logic instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0102] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the road camera video selection method based on the dynamic weight of the camera provided by the above methods.

[0103] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the road camera video selection method based on camera dynamic weights provided by the above methods.

[0104] It should be noted that the relevant user personal information that may be involved in the various embodiments of this application is strictly in accordance with the requirements of laws and regulations, follows the principles of legality, legitimacy and necessity, and is based on the reasonable purposes of business scenarios to process personal information that users actively provide during the use of products / services or generated due to the use of products / services, as well as personal information obtained with the user's authorization.

[0105] The user personal information processed by this application will vary depending on the specific product / service scenario and must be based on the specific scenario in which the user uses the product / service. This may involve the user's account information, device information, driving information, vehicle information, or other related information. This application will treat the user's personal information and its processing with a high degree of diligence.

[0106] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0107] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A road camera video selection method based on camera dynamic weight, characterized in that: include: A rectangular area is constructed with the longitude and latitude of the vehicle as the center, and the rectangular area is divided into four sub-areas; wherein the long axis direction of the rectangular area is consistent with the vehicle's travel direction, and the rectangular area contains the mapped longitude and latitude of multiple roadside cameras; determining a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a desired moment and a second heading angle of the vehicle at a moment before the desired moment; Adjusting a region weight of at least one sub-region according to a driving scenario of the vehicle; The priority of each roadside camera is determined by using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the current shared scene weight of each roadside camera; Select videos from a preset number of roadside cameras in descending order of priority.

2. The road camera video selection method based on camera dynamic weight according to claim 1 is characterized in that: Determining a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a desired moment and a second heading angle of the vehicle at a moment before the desired moment includes: If the absolute value of the difference is less than or equal to a preset absolute value, determining the driving scene of the vehicle according to the scene range value to which the difference belongs; If the absolute value of the difference is greater than the preset absolute value, the difference is summed or subtracted from the preset value to obtain a conversion value corresponding to the difference, and the driving scene of the vehicle is determined according to the scene range value to which the conversion value belongs.

3. The road camera video selection method based on camera dynamic weight according to claim 2 is characterized in that: If the target value is greater than a first preset difference value of the scene range value and less than a second preset difference value of the scene range value, determining that the driving scene of the vehicle is a right turn; wherein the first preset difference value is a positive number; wherein the target value includes the difference value or the conversion value; If the target value is greater than or equal to a third preset difference of the scene range value and less than or equal to the first preset difference, it is determined that the driving scene of the vehicle is straight driving; wherein the third preset difference is a negative number; If the target value is greater than the fourth preset difference of the scene range value and less than the third preset difference, it is determined that the driving scene of the vehicle is a left turn; wherein the preset absolute value is the difference between the second preset difference and the fourth preset difference.

4. The road camera video selection method based on camera dynamic weight according to claim 1, characterized in that: Adjusting the area weight of at least one sub-area according to the driving scenario of the vehicle includes: According to the driving scene of the vehicle, using the overlap between the shooting range of each roadside camera and the vehicle trajectory, predicting the predicted shooting time of the vehicle in each sub-area; The at least one sub-region is selected in descending order of the predicted shooting duration, and the region weight of the at least one sub-region is adjusted.

5. The road camera video selection method based on camera dynamic weight according to claim 4 is characterized in that: Also includes: If the driving scene of the vehicle is a left turn or a right turn, the width of the at least one sub-area is expanded by a preset multiple, or, If the driving scenario of the vehicle is a left turn or a right turn, the turning radius of the vehicle is obtained, the expansion coefficient is determined based on a preset correlation between the turning radius and the expansion coefficient, and the width of the at least one sub-area is expanded according to the expansion coefficient.

6. The road camera video selection method based on camera dynamic weight according to claim 1, characterized in that: The priority of each roadside camera is determined using the driving scene weight of each roadside camera, the regional weight of the sub-area where each roadside camera is located, and the shared scene weight of each roadside camera, including: Calculating the product of the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the shared scene weight of each roadside camera; The priority of each roadside camera is set in descending order of the product.

7. The road camera video selection method based on camera dynamic weight according to any one of claims 1 to 6, characterized in that: Also includes: If the weight of any target camera of the remaining cameras in the camera cluster to which the i-th roadside camera among the multiple roadside cameras belongs changes, obtaining an adjusted weight of the any target camera; wherein the camera cluster is obtained by clustering all roadside cameras to be processed; Determining a change in the shared scene weight of the i-th roadside camera using the adjusted weight; The sum of the original shared scene weight of the i-th roadside camera and the change is used as the current shared scene weight of the i-th roadside camera.

8. The road camera video selection method based on camera dynamic weight according to claim 7, characterized in that: Determining a change in the shared scene weight of the i-th roadside camera by using the adjustment weight includes: Determining the similarity between the i-th roadside camera and the target camera; Determining the weight transfer coefficient corresponding to the i-th roadside camera according to a preset correlation relationship between the similarity and the weight transfer coefficient; The product of the adjustment weight and the weight transfer coefficient is used as the change amount.

9. A road camera video selection system based on camera dynamic weight, characterized in that: include: A construction module is configured to construct a rectangular area centered on the longitude and latitude of the vehicle and divide the rectangular area into four sub-areas; wherein the long axis of the rectangular area is consistent with the vehicle's travel direction, and the rectangular area contains the longitude and latitude of multiple roadside cameras; a first determining module, configured to determine a driving scenario of the vehicle by using a difference between a first heading angle of the vehicle at a required moment and a second heading angle of the vehicle at a moment before the required moment; An adjustment module, configured to adjust the area weight of each sub-area according to the driving scenario of the vehicle; A second determination module is configured to determine the priority of each roadside camera by using the driving scene weight of each roadside camera, the area weight of the subarea where each roadside camera is located, and the current shared scene weight of each roadside camera; The selection module is used to select videos from a preset number of roadside cameras in order of priority from high to low.

10. An electronic device, characterized in that: The invention 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 road camera video selection method based on camera dynamic weight as described in any one of claims 1 to 8 is implemented.

Images