Road information processing method and device

Abstract

An embodiment of the present application provides a road information processing method and device, the method comprising: obtaining target vehicle data that is within a first time period at the time of shooting from a plurality of vehicle data sent by a plurality of shooting devices in a first area. For a first shooting device among the plurality of shooting devices, determining the first number of vehicles corresponding to the first shooting device at the target time based on the target vehicle data, the first number of vehicles being the number of vehicles that have been shot by the first shooting device within the first time period and have not been shot by the remaining shooting devices and continue to travel at the target time. Determine the number of vehicles on the way in the first area at the target time based on the number of first vehicles corresponding to each of the plurality of shooting devices in the first area. The technical solution of the present application can determine the number of vehicles on the way to effectively reflect the overall driving status in the first area, thereby effectively expanding the richness of traffic indicators.

Description

Technical Field

[0001] The embodiments of the present application relate to computer technology, and in particular to a road information processing method and device. Background Art

[0002] The widespread distribution of traffic cameras on roads provides a certain technical basis for collecting vehicle data on roads.

[0003] Currently, vehicle data collected by traffic cameras can be used to determine the speed of vehicles passing by a traffic camera, or to determine the volume of vehicles passing by a traffic camera. However, this data is often microscopic data for a specific vehicle or traffic camera. There is currently no effective solution for measuring the overall traffic status in an area based on vehicle data collected by traffic cameras. Summary of the Invention

[0004] The embodiments of the present application provide a road information processing method and device to overcome the problem of being unable to effectively measure the overall driving status in an area.

[0005] In a first aspect, an embodiment of the present application provides a road information processing method, comprising:

[0006] Obtaining target vehicle data whose shooting time is within a first time period from a plurality of vehicle data sent by a plurality of shooting devices in a first area, where the first time period is a time period corresponding to a preset time length before the target time;

[0007] For a first camera among the multiple cameras, determining, based on the target vehicle data, a first number of vehicles corresponding to the first camera at a target time, where the first number of vehicles is the number of vehicles that were captured by the first camera during the first time period and that have not been captured by any other cameras at the target time and are still traveling.

[0008] The number of vehicles on the way in the first area at the target time is determined according to the number of first vehicles corresponding to each of the plurality of photographing devices in the first area.

[0009] In a second aspect, an embodiment of the present application provides a road information processing device, comprising:

[0010] An acquisition module is configured to acquire, from a plurality of pieces of vehicle data sent by a plurality of photographing devices in a first area, target vehicle data whose photographing moment is within a first time period, where the first time period is a time period corresponding to a preset time length before the target time;

[0011] a determining module configured to determine, for a first camera among the plurality of cameras, a first number of vehicles corresponding to the first camera at a target time based on the target vehicle data, where the first number of vehicles is the number of vehicles that were captured by the first camera within the first time period and that have not been captured by any other cameras at the target time and are still traveling;

[0012] The determining module is further configured to determine the number of vehicles on the way in the first area at the target time according to the number of first vehicles corresponding to each of the plurality of photographing devices in the first area.

[0013] In a third aspect, an embodiment of the present application provides a road information processing device, including:

[0014] Memory, used to store programs;

[0015] A processor is used to execute the program stored in the memory. When the program is executed, the processor is used to execute the method described in the first aspect above.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the method described in the first aspect above.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect and any of the various possible designs of the first aspect.

[0018] Embodiments of the present application provide a road information processing method and apparatus. The method includes: obtaining target vehicle data from multiple pieces of vehicle data transmitted by multiple cameras in a first area, wherein the first period is a period corresponding to a preset time period before a target time. For a first camera among the multiple cameras, determining a first number of vehicles corresponding to the first camera at the target time based on the target vehicle data. The first number of vehicles is the number of vehicles captured by the first camera during the first period that have not been captured by other cameras and are still traveling at the target time. Determining the number of vehicles in transit within the first area at the target time based on the first number of vehicles captured by each of the multiple cameras in the first area. By selecting the target vehicle data within the first period and determining the first number of vehicles corresponding to each camera based on the target vehicle data, wherein the first number of vehicles is actually the number of vehicles traveling within the sub-area corresponding to the camera at the target time, and then combining the first number of vehicles captured by each of the multiple cameras in the first area, the number of vehicles in transit within the first area at the target time can be effectively determined. The number of vehicles in transit effectively reflects the overall driving status within the first area, thereby effectively expanding the richness of traffic indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0020] Figure 1 A schematic diagram of an application scenario of road information processing provided in an embodiment of the present application;

[0021] Figure 2 A diagram showing the system architecture for road information processing provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of a road information processing method provided in an embodiment of the present application;

[0023] Figure 4 A flowchart of a road information processing method provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the first period provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram illustrating implementation of the preset probabilities for each preset time period provided in an embodiment of the present application;

[0026] Figure 7 The process of the road information processing method provided in the embodiment of the present application Figure 3 ;

[0027] Figure 8 A schematic diagram of the implementation of the vehicle trajectory provided in the embodiment of the present application;

[0028] Figure 9 A processing flow chart of the road information processing method provided in an embodiment of the present application;

[0029] Figure 10 A schematic diagram of the structure of a road information processing device provided in an embodiment of the present application;

[0030] Figure 11 A schematic diagram of the hardware structure of a road information processing device provided in an embodiment of the present application;

[0031] Figure 12 A schematic diagram of cloud-based processing of the road information processing method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0033] In order to better understand the technical solution of this application, the relevant technologies involved in this application are further introduced in detail below.

[0034] Traffic cameras are widely distributed on current urban roads. They are mainly used to capture violations and monitor accidents. They also collect a large amount of vehicle data. The vehicle information collected by traffic cameras can provide a certain basis for corresponding data analysis.

[0035] For example, you can combine Figure 1 and Figure 2 Understand the application scenarios of the road information processing method provided in this application, Figure 1 This is a schematic diagram of an application scenario of road information processing provided in an embodiment of the present application. Figure 2 This is a system architecture diagram for road information processing provided in an embodiment of the present application.

[0036] like Figure 1As shown, a traffic camera 101 may be provided at the checkpoint, wherein the traffic camera 101 may take pictures of the corresponding vehicles.

[0037] Among them, a checkpoint refers to a point including one or more traffic cameras. When a vehicle passes through the checkpoint, the traffic camera can record the vehicle's license plate and the time of capturing the vehicle through the captured vehicle image. The vehicle data collected by the traffic camera, for example, can include the vehicle license plate and the time of capturing the vehicle.

[0038] And can also be combined Figure 2 It is understood that for each traffic camera in each checkpoint, it can report the collected vehicle data to the processing device, and the processing device will perform subsequent data processing.

[0039] The execution subject of each embodiment in this application is the processing device currently introduced, where the processing device can be, for example, a local server, a cloud server, a processor or a chip, etc., which has data receiving and sending functions and data processing functions. This embodiment does not limit the specific implementation method of the processing device, and it can be selected and set according to actual needs.

[0040] Based on the above introduction, the technical concept of the road information processing method proposed in this application is introduced below.

[0041] Currently, vehicle data collected by traffic cameras typically determines the speed or volume of vehicles passing a camera. Speed and volume can be used to determine the efficiency and delay of a specific intersection, or by combining speed and volume data from multiple traffic cameras to determine the efficiency and delay of a specific road section. However, both speed and volume data are microscopic data specific to a specific vehicle, traffic camera, or road section.

[0042] However, there is currently no effective solution to measure the overall driving status in a certain area based on vehicle data collected by traffic cameras, such as determining the spatial macroscopic status of vehicles on urban roads, and it cannot be directly obtained by measuring certain data.

[0043] Against the technical background introduced above, this application proposes the following technical concept: by combining the vehicle data uploaded by multiple traffic cameras in the area, analyzing the number of vehicles that were not captured by other traffic cameras after being captured by each traffic camera, the number of vehicles on the way within the range corresponding to each traffic camera can be determined. Finally, the number of vehicles on the way within the range corresponding to each traffic camera is summarized, and the number of vehicles on the way in the area can be obtained simply and effectively.

[0044] The road information processing method provided by this application is introduced below with reference to specific embodiments. Figure 3 This is a flowchart of the road information processing method provided in an embodiment of the present application.

[0045] like Figure 3 As shown, the method includes:

[0046] S301, in the first area of the plurality of vehicle data sent by the plurality of shooting devices, obtain the target vehicle data shooting time is located in the first period, the first period is the period corresponding to the preset duration before the target moment.

[0047] Among them, the first area is the area where the number of vehicles in transit needs to be determined. In one possible implementation method, the first area can be, for example, an administrative area covering a certain area, or the first area can also be a self-divided area covering a certain area, etc. This embodiment does not limit the specific implementation method of the first area, as long as the first area is an area covering a certain area and the number of vehicles in transit needs to be determined.

[0048] It can be understood that the first area may include multiple checkpoints, and each checkpoint includes at least one shooting device. Therefore, the first area may include multiple shooting devices, where the shooting device is the traffic camera introduced above.

[0049] Each camera in the first area can capture images of passing vehicles, analyze the captured vehicle images to obtain vehicle data, and then send the vehicle data to the processing device. Therefore, the processing device in this embodiment can receive multiple pieces of vehicle data sent by multiple camera devices in the first area.

[0050] In one possible implementation, vehicle data may include, for example, a vehicle identification, a capture time, and a device identification. The vehicle identification may be, for example, the vehicle's license plate number. The capture time is the moment when the camera captures the vehicle, and the device identification is the identification of the camera. The specific implementation of the device identification can be selected and configured based on actual needs, as long as it can distinguish between different camera devices. The same applies to the vehicle identification. It should also be noted that, in actual implementation, the specific content of the vehicle data is not limited to that described above; any information related to the captured vehicle can be considered vehicle data in this embodiment.

[0051] The vehicle data includes the time at which the vehicle was photographed. In this embodiment, target vehicle data having a photographing time within a first time period can be obtained from multiple pieces of vehicle data sent by multiple photographing devices in the first area. The first time period is a time period corresponding to a preset time period before the target time.

[0052] It is understood that because vehicles on the road are mobile, determining the number of vehicles en route within the first area requires determining the number of vehicles en route at a specific time in order to obtain an accurate and effective indicator. In this embodiment, the target time is the time at which the number of vehicles en route needs to be determined. The specific target time can be selected and set based on actual needs. The preset duration described above can also be selected and set based on actual needs.

[0053] S302. For a first shooting device among multiple shooting devices, determine the first number of vehicles corresponding to the first shooting device at the target time based on the target vehicle data, where the first number of vehicles is the number of vehicles that are photographed by the first shooting device within the first time period and have not been photographed by other shooting devices at the target time and continue to travel.

[0054] In this embodiment, when determining the number of vehicles in transit, each camera in the first area is processed separately and then aggregated. The processing method for each camera is similar, so the following description uses any first camera among multiple cameras as an example, and does not elaborate on the processing method for each camera.

[0055] In this embodiment, the target vehicle data specifically refers to vehicle data captured by multiple cameras within a first time period. Therefore, in this embodiment, the number of vehicles captured by the first camera within the first time period and still traveling at the target time, which have not yet been captured by other cameras, can be determined based on the target vehicle data. This number is referred to herein as the first vehicle number corresponding to the first camera at the target time.

[0056] It can be understood that the vehicle photographed by the first camera during the first time period and not yet photographed by the other cameras at the target time is actually the vehicle located between the first camera and the next camera. Then this vehicle can be counted as the vehicle in transit corresponding to the first camera. According to such logical calculation, there will be no situation where multiple cameras calculate the number of vehicles in transit for the same vehicle, so as to ensure the accuracy of the determined number of vehicles in transit.

[0057] Furthermore, in this embodiment, when determining the first number of vehicles for the first camera, the vehicle must have been captured by the first camera within the first time period and continue to travel. This is because some vehicles may not be captured by other cameras after being captured by the first camera. This may be because the vehicle is parked somewhere. Parked vehicles are not counted as vehicles in transit. Therefore, this logic can also ensure the accuracy of the determined number of vehicles in transit.

[0058] And in a possible implementation, the preset duration introduced above can be the longest time between the moment the first vehicle is photographed by one camera and the moment it is photographed by the next camera, wherein the preset duration can be an empirical value. Based on such a preset duration, the first time period is determined, and then the target vehicle data within the first time period is selected for processing. Compared with the implementation method based on the analysis of vehicle data in the entire time period, this implementation method can effectively reduce the amount of data to be processed. This is because for vehicle data that exceeds the preset duration before the target moment, either the vehicle has been photographed by other cameras or the vehicle has stopped. Therefore, there is no need to analyze the vehicle data that exceeds the preset duration before the target moment.

[0059] S303: Determine the number of vehicles on the way in the first area at the target time according to the first number of vehicles corresponding to each of the plurality of photographing devices in the first area.

[0060] In this embodiment, the first number of vehicles corresponding to each of the multiple cameras in the first area can be determined according to the aforementioned implementation method. It is understood that the first number of vehicles is actually the number of vehicles in transit determined within the range corresponding to the camera and its adjacent cameras. The number of vehicles in transit can be understood as the number of vehicles currently traveling on the roads in the first area.

[0061] Therefore, the number of vehicles en route in the first area at the target time can be determined based on the number of first vehicles corresponding to each of the multiple cameras in the first area. For example, the number of first vehicles corresponding to each of the multiple cameras in the first area can be added together to determine the number of vehicles en route in the first area at the target time. Alternatively, the summed result can be combined with a corresponding coefficient to determine the number of vehicles en route in the first area at the target time. The specific implementation method can be selected and set according to actual needs, as long as the number of vehicles en route in the first area is calculated based on the number of first vehicles corresponding to each of the multiple cameras in the first area.

[0062] The road information processing method provided by an embodiment of the present application includes: obtaining target vehicle data at a first time period from multiple pieces of vehicle data transmitted by multiple cameras in a first area, where the first time period is a period corresponding to a preset duration before a target time. For a first camera among the multiple cameras, determining a first number of vehicles corresponding to the first camera at the target time based on the target vehicle data, where the first number of vehicles is the number of vehicles captured by the first camera during the first time period and that have not been captured by other cameras and are still traveling at the target time. Determining the number of vehicles in transit within the first area at the target time based on the first number of vehicles corresponding to each of the multiple cameras in the first area. By selecting the target vehicle data within the first time period and determining the first number of vehicles corresponding to each camera based on the target vehicle data, where the first number of vehicles is actually the number of vehicles traveling within the sub-area corresponding to the camera at the target time, and finally combining the first number of vehicles corresponding to each of the multiple cameras in the first area, the number of vehicles in transit within the first area at the target time can be effectively determined. The number of vehicles in transit effectively reflects the overall driving status within the first area, thereby effectively expanding the richness of traffic indicators.

[0063] Based on the above introduction, Figures 4 to 6 The specific implementation method of determining the first number of vehicles corresponding to the first shooting device in the road information processing method provided by this application is further introduced in detail. Figure 4 This is a flowchart of a road information processing method provided in an embodiment of the present application. Figure 5 This is a schematic diagram of the first period provided in the embodiment of the present application. Figure 6 A schematic diagram of the implementation of the preset probability of each preset time period provided in an embodiment of the present application.

[0064] like Figure 4 As shown, the method includes:

[0065] S401. For the i-th time slice among the n time slices, obtain the second number of vehicles corresponding to the i-th time slice based on the target vehicle data. The second number of vehicles is the number of vehicles that are photographed by the first shooting device within the time range of the i-th time slice and have not been photographed by other shooting devices at the target time.

[0066] In this embodiment, the preset duration is composed of n consecutive time slices. In one possible implementation, for example, the length of a time slice is fixed, and then n time slices are counted forward from the target time to obtain the first time period, where n is an integer greater than or equal to 1.

[0067] For example, you can combine Figure 5Understand the relationship between the target time, preset duration, time slice and the first period. Figure 5 As shown, assuming the target time is Figure 5 The position shown in t0, and assuming Figure 5 In the example, n is 4, which means that 4 time slices are calculated from the target time t0, respectively referring to Figure 5 As shown in time slice 1, time slice 2, time slice 3 and time slice 4 in .

[0068] Assuming a time slice is 10 minutes long, and following the logic described above, n is 4, which means the preset duration is 40 minutes. This means, for example, that after a vehicle is captured by one camera, it will be captured by another camera or parked within 40 minutes. Therefore, in actual implementation, the specific value of n can be determined according to this logic. Specifically, the target vehicle data is processed based on the target vehicle data within this first period. This effectively reduces the amount of unnecessary data to be processed, improving data processing efficiency.

[0069] Among them, each time slice corresponds to a time range, such as Figure 5 As shown, the time range of time slice 1 is t1~t0, the time range of time slice 2 is t2~t1, the time range of time slice 3 is t3~t2, and the time range of time slice 4 is t4~t3. The time range composed of these four time slices can be understood as the preset duration, which is the duration corresponding to the time range of t4~t0. And refer to Figure 5 It can be determined that the starting time of time slice 4 is t4, wherein the period between t4 and t0 is the first period in this embodiment.

[0070] Based on the above introduction, it can be understood that the specific implementation of the preset duration depends on the value of n, that is, it depends on how many time slices before the target moment are selected. The specific number of time slices to be selected depends on the length of the time slices on the one hand, and on the empirical value on how many time slices a vehicle will pass after passing through one camera before passing through the next camera on the other hand. Based on this method to determine the first time period, it is possible to effectively filter out the target vehicle data that may be analyzed for the first number of vehicles, thereby reducing the amount of data to be processed, thereby improving the speed and efficiency of data processing.

[0071] The preset duration includes multiple time slices. In this embodiment, each of the multiple time slices will be processed separately, and the processing of each time slice is also similar. Therefore, the i-th time slice among the multiple time slices will be introduced below, where i is an integer greater than or equal to 1 and less than or equal to n.

[0072] It should also be noted that the sorting method of the multiple time slices introduced in this embodiment is to sort from the target time forward, that is, the time slice closest to the target time is the first time slice, the time slice second closest to the target time is the second time slice, and so on, until the nth time slice.

[0073] Specifically, the target vehicle data is multiple pieces of vehicle data collected by multiple cameras in the first area during the first time period. Therefore, in this embodiment, for the i-th time slice, the number of vehicles captured by the first camera within the i-th time slice and not captured by other cameras at the target time can be obtained based on the target vehicle data. In this embodiment, this number is referred to as the second vehicle number corresponding to the i-th time slice.

[0074] Let's take an example here. For example, if the value of i is 2, then for the second time slice, the number of vehicles that were photographed by the first camera within the time range of the second time slice and have not been photographed by other cameras at the target time can be obtained based on the target vehicle data.

[0075] Corresponding to Figure 5 As for the specific moment shown, that is, it is photographed by the first photographing device within the time range of t2 to t1, and has not been photographed by other photographing devices as of the target moment t0.

[0076] S402. Obtain a first probability corresponding to the i-th time slice, where the first probability is the probability that the vehicle is photographed by the first camera within the time range of the first time slice, has not been photographed by other cameras after i time slices, and continues to travel.

[0077] Similarly, still for the i-th time slice, in this embodiment, the first probability corresponding to the i-th time slice can be obtained, where the first probability is the probability that the vehicle is photographed by the first shooting device within the time range of the i-th time slice, and has not been photographed by the remaining shooting devices after i time slices and the vehicle continues to travel.

[0078] In a possible implementation, for example, historical data can be mined to obtain the preset probability P corresponding to each of the multiple preset time periods. A，d，i , where the preset probability P A，d，iis the probability that the vehicle is photographed by the first photographing device A during the preset time period d, has not been photographed by other photographing devices after i time slices, and continues to travel.

[0079] For example, you can combine Figure 6 To understand, such as Figure 6 As shown, assuming that the unit is one hour, the Figure 6 There are 24 preset time periods shown, and then a plurality of preset probabilities corresponding to each preset time period are determined, wherein the plurality of preset probabilities include preset probabilities corresponding to time slices of different numbers i.

[0080] It is understandable that the probability of a vehicle continuing to move after being captured by the first camera and not being captured by other cameras after a certain number of time slices have passed is different. This is because as the vehicle continues to move, the probability of it being captured by other cameras or stopping increases. Therefore, specifically, the greater the number of time slices that pass after the vehicle is captured by the first camera, the lower the corresponding preset probability.

[0081] For example, Figure 6 In the example, for the preset time period of 00:00-1:00, the probability that a vehicle is captured by the first camera within this preset time period, and has not been captured by any other camera after one time slot, and continues to move is 90%. For the same preset time period, the probability that a vehicle is captured by the first camera within this preset time period, and has not been captured by any other camera after two time slots, and continues to move is 80%. For the same preset time period, the probability that a vehicle is captured by the first camera within this preset time period, and has not been captured by any other camera after three time slots, and continues to move is 60%. For the same preset time period, the probability that a vehicle is captured by the first camera within this preset time period, and has not been captured by any other camera after four time slots, and continues to move is 40%.

[0082] Based on this example, it can be determined that the smaller the value of i, the shorter the time that has passed since the vehicle was photographed by the first camera, and the greater the probability that the vehicle was photographed and continued to travel. The implementation of the remaining preset time periods is similar and will not be repeated here.

[0083] It is understandable that Figure 6 The implementation of the preset time periods and the corresponding preset probabilities is merely introduced as an example. In the actual implementation process, the specific division of the preset time periods and the specific implementation of the various preset probabilities corresponding to each preset time period can be determined according to actual needs and actual conditions.

[0084] Based on the preset time periods and preset probabilities introduced above, in this embodiment, when obtaining the first probability corresponding to the i-th preset time period, for example, the target preset time period described in the i-th time slice can be determined among multiple preset time periods, and then the preset probability corresponding to the target preset time period is determined as the first probability corresponding to the i-th time slice.

[0085] For example, in the above Figure 6 Based on the example introduced, assuming that the time range corresponding to the current i-th time slice is 00:30-00:40, then it can be determined that the target preset period to which the i-th time slice belongs is the preset period of 00:00-1:00. At the same time, assuming that the value of i in the current example is 3, then refer to Figure 6 What can be determined is that the first probability corresponding to the third time slice is 60%, which corresponds to the probability that the vehicle is photographed by the first camera within the time range of 00:30-00:40, and has not been photographed by other cameras after three time slices and continues to move.

[0086] It can be understood that by pre-setting and dividing multiple preset time periods, and then mining historical data to determine the preset probabilities corresponding to each preset time period, the corresponding first probabilities can be determined for various possible time ranges of the i-th time slice, thereby ensuring that the first probability corresponding to the i-th time slice can be effectively determined for various possible situations in the actual implementation process.

[0087] S403. Determine the third number of vehicles corresponding to the i-th time slice based on the second number of vehicles corresponding to the i-th time slice and the first probability corresponding to the i-th time slice. The third number of vehicles is the number of vehicles that are photographed by the first shooting device within the time range of the i-th time slice and have not been photographed by other shooting devices at the target time and continue to travel.

[0088] In this embodiment, the second vehicle count corresponding to the i-th time slice is determined. The second vehicle count is the actual number of vehicles captured by the first camera during the i-th time slice and not captured by any other cameras at the target time. In other words, the second vehicle count is the true number of vehicles determined based on actual vehicle data. However, based on actual vehicle data, we can only count the number of vehicles not captured by any other cameras; we cannot distinguish which of these vehicles are still moving and which are parked.

[0089] Therefore, further, in this embodiment, a first probability corresponding to the i-th time slice is determined, where the first probability is the probability that the vehicle has not been photographed by other photographing devices after i time slices have passed since it was photographed by the first photographing device, and the vehicle is still moving.

[0090] Therefore, a calculation can be performed combining the second number of vehicles corresponding to the i-th time slice and the first probability corresponding to the i-th time slice to ensure that the probability of vehicles continuing to travel is taken into account, based on the actual number of vehicles not captured. This determines the third number of vehicles corresponding to the i-th time slice, where the third number of vehicles is the number of vehicles captured by the first camera within the time range of the i-th time slice, that have not been captured by other cameras by the target time, and that continue to travel. It can be understood that by combining the second number of vehicles and the first probability to determine the third number of vehicles, it can be ensured that the third number of vehicles is the number of vehicles in transit determined for the i-th time slice, and the accuracy of this number can be effectively guaranteed.

[0091] S404: Determine the number of first vehicles corresponding to the first shooting device at the target time according to the number of third vehicles corresponding to each time slice.

[0092] After determining the third number of vehicles corresponding to each time slice, for example, the third number of vehicles corresponding to each time slice may be summed up to determine the first number of vehicles corresponding to the first shooting device at the target time.

[0093] For example, the number of first vehicles can satisfy the following formula 1:

[0094]

[0095] Where A represents the first shooting device, π(i) represents the time range of the i-th time slice, and P A，π(i)，i It represents the first probability corresponding to the i-th time slice, ||A π(i)，i || represents the number of second vehicles corresponding to the i-th time slice, C A，t Indicates the number of first vehicles corresponding to the first shooting device at the target time.

[0096] Among them, the time range π(i) of the i-th time slice is actually the time range of [ti×k, t-(i-1)×k], where t is the target time and k is the duration of a single time slice.

[0097] In actual implementation, the specific implementation method for determining the first number of vehicles is not limited to Formula 1 described above. For example, formulas obtained by adding corresponding parameters to Formula 1 or performing identity transformation on Formula 1 can also be used to determine the first number of vehicles. In actual implementation, any method for determining the first number of vehicles according to the logic described above falls within the implementation method of the embodiments of the present application.

[0098] This embodiment introduces a specific implementation for determining the number of first vehicles corresponding to the first camera device. It should also be noted that the reason why this embodiment adopts this method of processing each time slice separately when determining the number of first vehicles is because we know that there are camera devices installed on each key road in the first area, so the vehicle will always be captured once during the driving process. If the camera devices are set up relatively densely, the time interval between the two captures will be relatively short. If the camera devices are set up relatively sparsely, the time interval between the two captures will be relatively long. Then, the problem of evaluating the number of vehicles in motion corresponding to the first camera device at the target moment can be converted into evaluating how long it will take for each vehicle to stop or be captured by the next camera device after being captured by the camera device. Then, by aggregating the vehicles in transit according to the time slice, the number of first vehicles corresponding to the first camera device can be effectively obtained.

[0099] It is also important to understand that, in addition to collecting the actual second vehicle count based on actual vehicle data, this embodiment also determines a first probability corresponding to each time slice, taking into account the probability that the vehicle continues to travel if it is not captured by the next camera. However, based on the above description, it can be determined that the probability of a vehicle continuing to travel and not being captured varies after different numbers of time slices have passed. Therefore, in this embodiment, separate processing is performed on a time slice basis, followed by aggregation, to effectively ensure the accuracy and validity of the final determination of the first vehicle count.

[0100] Among them, the implementation method of determining the first number of vehicles in the road information processing method provided in this embodiment is compared with the implementation method of inferring and estimating the number of vehicles on the road through some indicators (such as the speed and flow rate introduced above). The solution in this embodiment is based on the actual situation of the vehicles being photographed and the number of vehicles on the road determined based on the probability information mined from historical data. Therefore, it can effectively ensure the accuracy of the determined number of vehicles on the road.

[0101] Based on the above introduction, it can be understood that after determining the number of first vehicles corresponding to each of the multiple shooting devices in the first area, the number of vehicles on the way in the first area at the target time can be determined based on the multiple first vehicle numbers. For example, it can be expressed as C D，t =∑ A∈D C A，t。 Among them, C D，t It represents the number of vehicles on the way in the first area D at the target time t.

[0102] In a possible implementation, after obtaining the number of vehicles in transit in the first area at the target time, for example, the number of vehicles in transit may be further corrected.

[0103] Among them, when the shooting equipment in the first area has complete coverage and is evenly distributed, the number of vehicles in transit determined based on the above-mentioned content can accurately and effectively reflect the number of vehicles in transit in the first area. However, the actual data situation is often difficult to perfectly meet, and there may be some blind spots in monitoring. Therefore, for example, historical data can be analyzed to determine the correction coefficient, and then the number of vehicles in transit can be corrected by the correction coefficient, so as to make up for the missed detection caused by the distribution problem of the shooting equipment.

[0104] In one possible implementation, for example, a correction coefficient can be determined for each area. For example, for the first area, the correction coefficient is used to compensate for the number of vehicles traveling in the first area but not captured by the camera. The number of vehicles in transit can then be corrected based on the correction coefficient to obtain a corrected number of vehicles in transit.

[0105] In one possible implementation, for example, the missed detection coefficient α corresponding to the first area can be determined based on the average missed detection rate and average number of captures by the cameras within the first area. α can serve as the correction factor described above, compensating for the number of vehicles not captured. For example, the missed detection coefficient α can be multiplied by the number of vehicles in transit to obtain the corrected number of vehicles in transit. The missed detection coefficient α is typically a number greater than 1.

[0106] For example, it can be expressed as: in It represents the corrected number of vehicles on the road.

[0107] Or in another possible implementation, for example, the probability of the vehicle trajectory being captured by the camera can be evaluated based on historical data, or it can be called the capture rate β.

[0108] For example, roads with camera devices in the first area can be marked as 1, and roads without camera devices in the first area can be marked as 0. Then, based on the average vehicle en route duration h (for example, a typical vehicle trip duration is 15 to 30 minutes), the capture rate corresponding to the first area D at the target time can be determined. This can be expressed as the following formula 2:

[0109]

[0110] Among them, the number of trajectories that passed through the road marked as 1 during the [t, th] period can reflect the situation of the vehicle being photographed during the trip, and the total number of trajectories in the [t, th] period can reflect the overall situation of the vehicle trip. Then these two ratios can reflect the probability of the vehicle being photographed during the trip. Therefore, the capture rate β corresponding to the first area D at the target time t can be obtained D，t .

[0111] Alternatively, if the missed detection rate of the photographing device itself is taken into consideration, the numerator in the above formula 2 may be replaced with the expected value of the missed detection rate of the photographing device.

[0112] Based on the above introduction, it can be determined that the capture rate β itself is a number less than 1, where the capture rate β can also be used as the correction coefficient introduced above. When correcting the number of vehicles in transit by the capture rate β, for example, it can be expressed as: in It represents the corrected number of vehicles on the road.

[0113] Therefore, in the road information processing method provided in the embodiment of the present application, after obtaining the number of vehicles on the road, the number of vehicles on the road can be further corrected by a correction coefficient, thereby effectively compensating for the problem of not capturing vehicles traveling in the first area due to uneven distribution of shooting equipment, incomplete coverage, and other issues, thereby further improving the accuracy of the determined number of vehicles on the road.

[0114] Based on the above introduction, in this embodiment, after determining the number of vehicles in transit for the first area, for example, if you want to further determine the number of vehicles in transit in a smaller area in the first area, the embodiment of the present application also provides a corresponding processing method.

[0115] In a possible implementation, for a first sub-area in a first area, a proportion parameter corresponding to the first sub-area is obtained, where the proportion parameter is used to indicate a proportion of the number of vehicles in the first sub-area to the number of vehicles in the first area;

[0116] The number of vehicles on the way corresponding to the first sub-area is determined according to the proportion parameter corresponding to the first sub-area and the number of vehicles on the way in the first area.

[0117] The first area may include multiple sub-areas, such as a road or a residential area. This embodiment does not limit the specific implementation of the sub-areas in the first area; the specific division and selection of sub-areas can be selected and configured based on actual needs. The processing methods for any sub-area in the first area are similar, so the following description uses the first sub-area in the first area as an example, and does not elaborate on the processing of each sub-area.

[0118] A ratio parameter corresponding to the first sub-area can be obtained, where the ratio parameter indicates the proportion of the number of vehicles in the first sub-area to the total number of vehicles in the first area. For example, at a certain moment, there are 1000 vehicles in the first area, and there are 100 vehicles in the first sub-area. Then, the ratio parameter corresponding to the first sub-area is 10%.

[0119] In actual implementation, the scale parameter corresponding to the first sub-region may be obtained based on data fusion mining of multiple historical moments, and may be determined according to actual conditions.

[0120] The number of vehicles in transit corresponding to the first sub-region can then be determined based on the ratio parameter corresponding to the first sub-region and the number of vehicles in transit within the first region. For example, the number of vehicles in transit corresponding to the first sub-region can be determined by multiplying the ratio parameter corresponding to the first sub-region by the number of vehicles in transit within the first region. The number of vehicles in transit within the first region used in the calculation process can be, for example, the number of vehicles in transit directly calculated as described above, or it can be a corrected number of vehicles in transit, and this embodiment does not impose any restrictions on this.

[0121] Therefore, the road information processing method provided in the embodiment of the present application can not only determine the number of vehicles in transit for the first area, but also effectively determine the number of vehicles in transit for a small number of sub-areas in the first area, thereby effectively expanding the use scenarios of determining the number of vehicles in transit.

[0122] Based on the above introduction, it can be understood that the processing device in this application needs to receive vehicle data sent by multiple shooting devices in the first area, and then perform the above-mentioned processing based on the vehicle data.

[0123] However, in one possible implementation, for example, the vehicle data sent by the shooting device in the first area that is initially received by the processing device can be called original vehicle data, where each piece of original vehicle data can include, for example, the shooting time ts for the vehicle and the vehicle identification vhc_id of the shot vehicle.

[0124] The processing device can then filter the original vehicle data based on the shooting time and vehicle identification in the original vehicle data to obtain filtered vehicle data. The processing processes described in the above embodiments, for example, can all be performed based on the filtered vehicle data.

[0125] Data filtering may include at least one of the following:

[0126] The shooting time in the original vehicle data is corrected according to the time error.

[0127] It is understandable that because multiple shooting devices collect data separately, in order to ensure that the data collected to the processing device is based on the same time standard, it is necessary to perform time correction on the shooting time in the original vehicle data based on the time error in the original vehicle data to ensure that the filtered vehicle data have the same reference time.

[0128] For example, the time error Δt between the capturing device and the processing device can be determined, and then the capturing time in the original vehicle data can be corrected based on the time error. For example, it can be expressed as ts`=ts-Δt.

[0129] And data filtering can also include:

[0130] If it is determined that the vehicle identification does not conform to the preset rules, the original vehicle data corresponding to the vehicle identification that does not conform to the preset rules is discarded.

[0131] If it is determined that the occurrence frequency of the vehicle identification is lower than the preset threshold, the original vehicle data corresponding to the vehicle identification with the occurrence frequency lower than the preset threshold is discarded.

[0132] Among them, when the vehicle identification does not meet the preset rules, or when the frequency of occurrence of the vehicle identification is very low, it can be considered that a false detection has occurred, and the original data can be discarded and will not participate in subsequent data processing.

[0133] In this embodiment, by filtering the original vehicle data and then performing subsequent processing based on the filtered vehicle data, the data can be effectively screened before processing, thereby effectively ensuring the quality of the data used for subsequent processing, thereby improving the speed and efficiency of determining the number of vehicles in transit.

[0134] The original vehicle data also includes the device identifier of the shooting device, devc_id. In this embodiment, the location information of the shooting device can be determined based on the device identifier of the shooting device, where the location information can include, for example, the road segment identifier rid of the road segment corresponding to the shooting device in the road network.

[0135] In a possible implementation, the positioning information of the shooting device can be expressed as<devc_id,rid,fc,Δt> Where devc_id is the device identifier of the camera, rid is the segment identifier of the road segment corresponding to the camera in the road network, fc is the positioning offset corresponding to the rid segment, and Δt is the time error between the camera and processing devices described above, which can also be understood as a clock offset.

[0136] And in the actual implementation process, when determining the section identification of the section corresponding to the shooting device in the road network, for example, the corresponding section can be determined in the road network based on the latitude and longitude coordinates of the shooting device, and then the corresponding section identification can be determined.

[0137] It is also understandable that after the vehicle data collected by multiple cameras is uploaded to the processing device, the processing device needs to concatenate the vehicle data collected by multiple cameras based on the positioning information of the cameras to analyze the vehicle's driving trajectory and, further, the number of vehicles on the road as described above. Therefore, the accuracy of the positioning information of the camera devices is particularly important.

[0138] Therefore, in the technical solution provided by this application, it is also possible to regularly check whether the positioning information of the shooting device is accurate. If the positioning information of the shooting device is inaccurate, the positioning information of the shooting device can be adjusted. Figures 7 and 8 The implementation method of determining the positioning information of the shooting device is described. Figure 7 The process of the road information processing method provided in the embodiment of the present application Figure 3 , Figure 8 A schematic diagram of the implementation of the vehicle trajectory provided in an embodiment of the present application.

[0139] like Figure 7 As shown, the method includes:

[0140] S701: Acquire multiple vehicle tracks that pass through the first shooting device within a second time period.

[0141] When determining the accuracy of the positioning information of the first camera, it is necessary to process multiple vehicle tracks that have passed through the first camera. To facilitate processing, multiple vehicle tracks within a period of time can usually be selected. Therefore, in this embodiment, multiple vehicle tracks that have passed through the first camera during a second period of time can be obtained. The specific implementation of the second period of time can be selected according to actual needs, as long as the second period of time exists in the past.

[0142] For example, you can combine Figure 8 To understand, such as Figure 8 As shown, assuming Figure 8 m0 in represents the first shooting device, and it is assumed that three vehicle trajectories passing through the first shooting device are obtained in the second period. They are Figure 8 As shown in FIG, a trajectory 1 consisting of m1→m2→m0→m3, a trajectory 2 consisting of m4→m0→m5, and a trajectory 3 consisting of m6→m0→m7, wherein m1 to m7 represent different shooting devices respectively.

[0143] S702: Determine, from among the multiple vehicle trajectories, a second photographing device that is located adjacent to and behind the first photographing device at the time of the vehicle passing.

[0144] After determining a plurality of vehicle trajectories that pass the first camera, a second camera whose vehicle's passing time is located after and adjacent to the first camera may be determined among the plurality of vehicle trajectories.

[0145] For example, Figure 8 In the example, the second camera adjacent to the first camera at the time when the vehicle passes in trajectory 1 is m3, the second camera adjacent to the first camera at the time when the vehicle passes in trajectory 2 is m5, and the second camera adjacent to the first camera at the time when the vehicle passes in trajectory 3 is m7.

[0146] S703: Determine a first positioning accuracy of the first shooting device according to the positioning information of the first shooting device.

[0147] Then, the first positioning accuracy of the first camera device can be determined based on the positioning information of the first camera device. It is understandable that there can be multiple second cameras, and the processing method for each second camera device is similar, so the following only takes one second camera device as an example for description.

[0148] In a possible implementation, a first average driving time from the first shooting device to the second shooting device may be determined based on a sub-trajectory located between the first shooting device and the second shooting device in the plurality of vehicle trajectories.

[0149] The second camera can be understood as a downstream device of the first camera, and a sub-track between the first camera and the second camera can be determined in multiple vehicle tracks. Figure 8 In the example, in trajectory 1, the sub-trajectory between the first shooting device m0 and the second shooting device m3 is m0→m3, the sub-trajectory between the first shooting device m0 and the second shooting device m5 in trajectory 2 is m0→m5, and the sub-trajectory between the first shooting device m0 and the second shooting device m7 in trajectory 3 is m0→m7.

[0150] Therefore, in this embodiment, a first average driving time from the first camera to the second camera can be determined based on the multiple sub-trajectories determined above. For example, the average of the driving times of the multiple sub-trajectories can be determined as the first average driving time.

[0151] The solution to the first average driving time can satisfy the following formula 3:

[0152]

[0153] Where v represents the sub-track, p represents the second time period, k represents the first shooting device, and k' represents the second shooting device, then |v∈K k→k｀，p | represents the number of sub-trajectories between the first shooting device k and the second shooting device k' in the second time period p, ts` v，k It is the corrected shooting time corresponding to the first shooting device k in the sub-trackline v, ts` v，k｀ is the corrected shooting time corresponding to the second shooting device k' in the sub-trackline v, then the corresponding ts' v，k -ts` v，k｀ It represents the driving time corresponding to the sub-trajectory v. Referring to the calculation of formula 3, t k→k｀，p It represents the first average driving time of p from the first camera k to the second camera k′ in the second time period.

[0154] And then, according to the positioning information of the first shooting device, a first path from the first shooting device to the second shooting device can be determined on the electronic map, and a first calculated driving time corresponding to the first path can be determined.

[0155] Based on the above introduction, it can be determined that the positioning information of the first shooting device can include the road section identification corresponding to the first shooting device in the road network. For example, the first path from the first shooting device to the second shooting device can be determined in the electronic map based on the road section corresponding to the first shooting device and the road section corresponding to the second shooting device.

[0156] The first path may be, for example, a path that takes the least time to travel from the first camera to the second camera, or a path that is the shortest in length from the first camera to the second camera, etc. For example, the Dijkstra algorithm may be used to determine the first path, or other algorithms may be used to determine the path between the two cameras on an electronic map, and this embodiment does not impose any restrictions on this.

[0157] After determining the first path, in this embodiment, the driving time corresponding to the first path needs to be determined, which is referred to herein as the first calculated driving time. For example, the first calculated driving time corresponding to the first path can be determined based on the average speed of each road segment included in the first path during the second time period, as well as the length of the first path. In an optional implementation, to achieve a driving time as close as possible to the actual driving time, for example, based on the driving time determined based on speed and length, at each traffic light intersection for the determined first path, 15 seconds, 10 seconds, and 5 seconds of signal light time consumption for left turn, straight ahead, and right turn, respectively, can be added to obtain the first calculated driving time.

[0158] For example, you can refer to the following formula 4 to understand the first calculation of driving time:

[0159]

[0160] Wherein, τ(k→k') represents the set of road segments included in the first path from the first photographing device k to the second photographing device k' in the electronic map, i represents the road segment i in the road segment set, and len i represents the length of road section i, s(r i , p) represents the average speed of road section i in the second period p, c i T represents the additional signal light time consumption for the driving direction of the traffic light intersection at road section i, k→k`，p It represents the first calculated driving time of p from the first camera k to the second camera k′ in the second time period.

[0161] Then, a first positioning accuracy of the first camera device can be determined based on the first average driving time and the first calculated driving time. The first positioning accuracy can be understood as the positioning accuracy determined for the sub-trajectory between the first camera device and the second camera device.

[0162] It is understandable that the first average driving time is actually the actual time taken to travel from the first camera to the second camera, determined based on the actual vehicle trajectory. The second calculated driving time is based on the positioning information of the first camera in the road section, and the theoretical time taken to travel from the first camera to the second camera is determined based on the positioning information. Based on this, if the difference between the first average driving time and the first calculated driving time is not large, it means that the actual time taken to travel from the first camera to the second camera is relatively close to the theoretical time taken to travel based on the positioning information in the road network, which means that the positioning information of the first camera is relatively accurate. Alternatively, if the difference between the first average driving time and the first calculated driving time is relatively large, it means that the actual time taken and the theoretical time taken are not close, which means that the positioning information of the first camera is not accurate.

[0163] In a possible implementation, for example, the following formula 5 may be referred to to understand a possible implementation of determining the first positioning accuracy.

[0164]

[0165] Among them S k→k`，p It represents the first positioning accuracy of the first camera k in the second period p. Referring to the above formula 5, it can be determined that, for example, the first average driving time t k→k`，p The first calculated driving time T is 0.9 times k→k`，p and 1.4 times the average driving time T calculated in the first step k→k`，p If the first average driving time t k→k`，p Greater than 4 times the first calculated driving time T k→k`，p , then the first positioning accuracy is equal to 0.

[0166] In other words, the greater the difference between the first average driving time and the first calculated driving time, the lower the first positioning accuracy; and the smaller the difference between the first average driving time and the first calculated driving time, the higher the first positioning accuracy, in an inversely proportional relationship. In actual implementation, the first positioning accuracy can be determined by adhering to this principle. The specific determination method is not limited to that described in Formula 5 above and can be selected and set according to actual needs.

[0167] S704: Determine, from among the multiple vehicle trajectories, a third photographing device that is located before and adjacent to the first photographing device at the time of the vehicle passing.

[0168] After determining the plurality of vehicle trajectories that pass the first photographing device, it is possible to determine, among the plurality of vehicle trajectories, a third photographing device whose passing time of the vehicle is located before and adjacent to the first photographing device.

[0169] For example, Figure 8 In the example, the third camera that is adjacent to the first camera at the time when the vehicle passes in trajectory 1 is m2, the third camera that is adjacent to the first camera at the time when the vehicle passes in trajectory 2 is m4, and the third camera that is adjacent to the first camera at the time when the vehicle passes in trajectory 3 is m6.

[0170] S705: Determine a second positioning accuracy of the first shooting device according to the positioning information of the first shooting device.

[0171] Then, the second positioning accuracy of the first camera device can be determined based on the positioning information of the first camera device. It is understandable that there can be multiple third cameras, and the processing method for each third camera device is similar, so the following only uses one third camera device as an example for description.

[0172] In a possible implementation, a second average driving time from the third shooting device to the first shooting device may be determined based on a sub-trackline located between the third shooting device and the second shooting device in the plurality of vehicle tracks;

[0173] determining, on the electronic map, a second path from the third camera to the first camera based on the positioning information of the first camera, and determining a second calculated driving time corresponding to the second path;

[0174] A second positioning accuracy of the first camera is determined based on the second average driving time and the second calculated driving time, wherein the second positioning accuracy can be understood as a positioning accuracy determined for the sub-trajectory between the first camera and the third camera.

[0175] Wherein, the second positioning accuracy S of the first shooting device k relative to the third shooting device k`` in the second time period p is determined k→k``，p The implementation method of is similar to the implementation method of determining the first positioning accuracy described above, and will not be repeated here.

[0176] S706 : Determine the accuracy of the positioning information of the first shooting device in the second time period according to the first positioning accuracy, the number of tracks corresponding to the first positioning accuracy, the second positioning accuracy, and the number of tracks corresponding to the second positioning accuracy.

[0177] After determining the first positioning accuracy of the first shooting device relative to each second shooting device, and the second positioning accuracy of the first shooting device relative to each third shooting device, it can be understood that for any second shooting device, there may be multiple sub-trajectories between the first shooting device and the second shooting device, and correspondingly, for any third shooting device, there may also be multiple sub-trajectories between the first shooting device and the third shooting device.

[0178] The accuracy of the positioning information of the first shooting device in the second time period can be determined based on the first positioning accuracy, the number of sub-tracks between the first shooting device and the second shooting device, the second positioning accuracy, and the number of sub-tracks between the first shooting device and the third shooting device.

[0179] For example, we can understand it by combining the following formula six:

[0180]

[0181] Among them, N k→k`，p represents the number of sub-trajectories between the first shooting device k and the second shooting device k', ∑ k` N k→k`，p It represents the sum of the number of sub-trajectories corresponding to the multiple second shooting devices, N k→k``，p represents the number of sub-trajectories between the first camera k and the third camera k``, ∑ k`` N k→k``，p It represents the sum of the number of sub-tracks corresponding to the multiple third shooting devices. And the numerator in Formula 6 represents the sum of the positioning accuracy rates corresponding to each sub-track. k.p It represents the accuracy of the positioning information of the first shooting device k in the second time period p.

[0182] In a possible implementation, the accuracy of the positioning information of the first shooting device in a second time period can be directly used as the final accuracy basis. Or in a possible implementation, multiple different second time periods S can be used as the final accuracy basis. k.p The average value of the corresponding accuracy is determined as the accuracy of the positioning information corresponding to the first shooting device. Thus, an accuracy S that does not distinguish between time periods can be obtained. k , in order to improve the effectiveness of indicators of positioning information accuracy.

[0183] In the road information processing method provided in the embodiment of the present application, the first average driving time between the first camera and the second camera downstream thereof can be determined based on the vehicle trajectory, and the first calculated driving time from the first camera to the second camera can also be determined in the electronic map based on the positioning information of the first camera. The first average driving time is the actual driving time, and the first calculated driving time is the theoretical driving time determined based on the positioning information. Then, by comparing the difference between the first average driving time and the first calculated driving time, the first positioning accuracy of the first camera relative to the second camera can be accurately and effectively determined. Similarly, the second positioning accuracy of the first camera relative to the third camera upstream thereof can be accurately and effectively determined. Then, the positioning accuracy corresponding to each sub-trajectory and the number of sub-trajectories are combined to determine the accuracy of the positioning information of the first camera. Compared with the implementation method of comparing the driving speed of the vehicle between two checkpoints with the corresponding threshold (this implementation method requires setting different thresholds for different road sections), or the implementation method of manual sampling, the method provided in this embodiment can, on the one hand, effectively ensure the effectiveness and correctness of the determined positioning accuracy without adjusting parameters, and on the other hand, it can be implemented automatically without investing too much manpower costs.

[0184] Based on the above combination, in one possible implementation, for example, the accuracy of the positioning information of the first camera can be periodically determined, taking a first duration as a period. If the accuracy of the positioning information of the first camera is lower than a preset accuracy, then it can be considered that the positioning information of the first camera has a significant deviation. This may be due to a deviation in the road section where the first camera locates the electronic device, or a significant deviation in the time error of the first camera. In either case, the aforementioned large discrepancy between the actual driving time and the theoretical driving time can result.

[0185] At this time, the vehicle data collected by the first camera device will no longer be usable. Therefore, the processing device can stop receiving the original vehicle data sent by the first camera device until the accuracy of the positioning information of the first camera device is higher than or equal to the preset accuracy, that is, until the accuracy of the positioning information of the first camera device is normal, and then adopt the vehicle data collected by the first camera device to determine the number of vehicles on the road.

[0186] By regularly checking the accuracy of the positioning information of the shooting equipment and promptly stopping receiving vehicle data collected by the shooting equipment with abnormal positioning when the accuracy of the positioning information of the shooting equipment is poor, the correctness of the vehicle data in the data source can be guaranteed, and the accuracy of the number of vehicles in transit finally calculated can be effectively guaranteed.

[0187] In an optional implementation, for example, a corresponding accuracy curve can be drawn based on the accuracy of different second time periods to analyze the source of the deviation, where the source of the deviation may be positioning deviation or clock deviation. For positioning deviation, positioning deviation is related to the average road speed, so the accuracy curve has a certain trend correlation with the RID (road section) speed curve. For clock deviation, because the device clock deviation is relatively constant in different time periods, the accuracy curve is relatively flat.

[0188] On the basis of the above-mentioned embodiments, Figure 9 A complete explanation of the road information processing method provided in this application is given. Figure 9 This is a processing flow chart of the road information processing method provided in an embodiment of the present application.

[0189] like Figure 9 As shown, the processing device can receive the original vehicle data uploaded by multiple shooting devices, and then perform data filtering on the vehicle data, where the data filtering can include the clock correction and false detection identification introduced above. False detection identification is to choose whether to retain the vehicle data based on the vehicle's license plate. The specific data filtering method can refer to the introduction of the above embodiment.

[0190] And, refer to Figure 9 What is certain is that the historical trajectory can be used to determine the accuracy of the positioning information of the camera in the checkpoint, and then whether to receive the vehicle data sent by the camera will be determined based on the accuracy of the positioning information.

[0191] After the data filtering process described above, we can get Figure 9 The filtered vehicle data shown, wherein the filtered vehicle data can also be used together with the historical vehicle trajectory to determine the capture rate in the offline data, and its specific implementation method can refer to the introduction of the above embodiment.

[0192] The number of vehicles on the way in the first area can then be calculated based on the filtered vehicle data, and the number of vehicles on the way determined can be corrected based on the capture rate determined offline to obtain Figure 9 The number of vehicles in transit in the first area is shown.

[0193] Furthermore, a ratio parameter of a sub-area within the first area may be determined based on the historical trajectory, and then the number of vehicles in transit in the sub-area within the first area may be determined according to the ratio parameter.

[0194] The determination of the camera's positioning accuracy, the camera capture rate, and the sub-area scale parameters can all be completed offline. The calculation of the number of vehicles in transit within the first area is performed online. Therefore, the road information processing method provided in this embodiment of the application can effectively determine the real-time number of vehicles in transit, accurately and effectively reflecting the overall vehicle situation within the first area at the current moment.

[0195] In one possible implementation, the quotient of the number of vehicles in transit and the road's carrying capacity can effectively reflect the level of congestion in a first area or a sub-area within the first area, thereby effectively helping city managers provide data support for macro-level traffic management and organizational optimization. For example, the number of vehicles in transit can be used as data support to set different restricted traffic periods during holidays, or the comparison of the number of vehicles in transit in different areas can be used to rationally determine the distribution of management resources. In actual implementation, the specific application of the number of vehicles in transit can be selected and configured based on actual needs.

[0196] Figure 10 This is a schematic diagram of the structure of the road information processing device provided in the embodiment of the present application. Figure 10 As shown, the device 100 includes: an acquisition module 1001 , a determination module 1002 and a processing module 1003 .

[0197] An acquisition module 1001 is configured to acquire, from a plurality of pieces of vehicle data sent by a plurality of photographing devices in a first area, target vehicle data whose photographing moment is within a first time period, where the first time period is a time period corresponding to a preset time length before the target time;

[0198] a determining module 1002 configured to determine, for a first camera among the plurality of cameras, a first number of vehicles corresponding to the first camera at a target time based on the target vehicle data, where the first number of vehicles is the number of vehicles captured by the first camera during the first time period and that have not been captured by any other cameras at the target time and are still traveling;

[0199] The determining module 1002 is further configured to determine the number of vehicles on the way in the first area at the target time according to the number of first vehicles corresponding to each of the plurality of photographing devices in the first area.

[0200] In one possible design, the preset duration consists of n consecutive time slices, where n is an integer greater than or equal to 1;

[0201] The determining module 1002 is specifically configured to:

[0202] For an i-th time slice among the n time slices, obtaining, based on the target vehicle data, a second number of vehicles corresponding to the i-th time slice, where the second number of vehicles is the number of vehicles captured by the first camera within the time range of the i-th time slice and not captured by any other camera at the target time, where i is an integer greater than or equal to 1 and less than or equal to n;

[0203] Obtaining a first probability corresponding to the i-th time slice, where the first probability is the probability that the vehicle is photographed by the first camera within the time range of the i-th time slice, has not been photographed by any other camera after i time slices, and continues to travel;

[0204] Determine, based on the second number of vehicles corresponding to the i-th time slice and the first probability corresponding to the i-th time slice, a third number of vehicles corresponding to the i-th time slice, where the third number of vehicles is the number of vehicles that were captured by the first camera within the time range of the i-th time slice and that have not been captured by other cameras at the target time and continue to travel;

[0205] The number of first vehicles corresponding to the first shooting device at the target time is determined according to the number of third vehicles corresponding to each of the time slices.

[0206] In one possible design, the determining module 1002 is specifically configured to:

[0207] Obtaining the target preset time period to which the i-th time slice belongs;

[0208] The preset probability corresponding to the target preset time period is determined as the first probability corresponding to the i-th time slice, and the preset probability is the probability that the vehicle is photographed by the first shooting device during the target preset time period, and has not been photographed by other shooting devices after i time slices and the vehicle continues to travel.

[0209] In one possible design, the acquisition module 1001 is further configured to:

[0210] After determining the number of vehicles in transit within the first area at the target time based on the first number of vehicles corresponding to each of the plurality of photographing devices in the first area, obtaining a correction coefficient corresponding to the first area, the correction coefficient being used to compensate for the number of vehicles traveling in the first area that were not photographed;

[0211] The apparatus further includes: a processing module 1003;

[0212] The processing module 1003 is configured to correct the number of vehicles in transit according to the correction coefficient to obtain a corrected number of vehicles in transit.

[0213] In one possible design, the acquisition module 1001 is further configured to:

[0214] After determining the number of vehicles in transit within the first area at the target time based on the first number of vehicles corresponding to each of the plurality of photographing devices within the first area, obtaining, for a first sub-area within the first area, a ratio parameter corresponding to the first sub-area, the ratio parameter being used to indicate a proportion of the number of vehicles in the first sub-area to the number of vehicles in the first area;

[0215] The processing module 1003 is specifically configured to:

[0216] The number of vehicles on the way corresponding to the first sub-area is determined according to the proportion parameter corresponding to the first sub-area and the number of vehicles on the way in the first area.

[0217] In one possible design, the processing module 1003 is further configured to:

[0218] Before acquiring target vehicle data having a shooting time within a first time period from the plurality of vehicle data sent by the plurality of shooting devices in the first area, receiving original vehicle data sent by the shooting devices in the first area, the original vehicle data including the shooting time of the vehicle and the vehicle identification of the shot vehicle;

[0219] filtering the original vehicle data according to the shooting time and the vehicle identification to obtain filtered vehicle data;

[0220] The data filtering includes at least one of the following:

[0221] The shooting time in the original vehicle data is corrected according to the time error; and if it is determined that the vehicle identification does not comply with the preset rules, the original vehicle data corresponding to the vehicle identification that does not comply with the preset rules is discarded; and if it is determined that the occurrence frequency of the vehicle identification is lower than the preset threshold, the original vehicle data corresponding to the vehicle identification whose occurrence frequency is lower than the preset threshold is discarded.

[0222] In a possible design, the original vehicle data also includes a device identification of the photographing device;

[0223] The processing module 1003 is further configured to:

[0224] Determining, with a first time period as a period, an accuracy rate of positioning information of the first shooting device, where the positioning information is determined according to a device identifier of the first shooting device;

[0225] If the accuracy is lower than the preset accuracy, the receiving of the original vehicle data sent by the first shooting device is stopped until the accuracy of the positioning information of the first shooting device is higher than or equal to the preset accuracy.

[0226] In one possible design, the processing module 1003 is specifically configured to:

[0227] Acquire multiple vehicle tracks that pass through the first shooting device during a second time period;

[0228] Determining, from the plurality of vehicle trajectories, a second photographing device that is located adjacent to and behind the first photographing device at the time of the vehicle passing, and determining a first positioning accuracy of the first photographing device based on the positioning information of the first photographing device;

[0229] Determining, from the plurality of vehicle trajectories, a third photographing device that is located before and adjacent to the first photographing device at the time of the vehicle passing, and determining a second positioning accuracy rate of the first photographing device based on the positioning information of the first photographing device;

[0230] Determine the accuracy of the positioning information of the first shooting device in the second time period based on the first positioning accuracy, the number of sub-tracks between the first shooting device and the second shooting device, the second positioning accuracy, and the number of sub-tracks between the first shooting device and the third shooting device.

[0231] In one possible design, the processing module 1003 is specifically configured to:

[0232] determining a first average driving time from the first shooting device to the second shooting device based on the sub-trajectories between the first shooting device and the second shooting device in the plurality of vehicle trajectories;

[0233] determining, on an electronic map, a first path from the first photographing device to the second photographing device based on the positioning information of the first photographing device, and determining a first calculated driving time corresponding to the first path;

[0234] A first positioning accuracy of the first shooting device is determined according to the first average driving time and the first calculated driving time.

[0235] In one possible design, the processing module 1003 is further configured to:

[0236] After determining the accuracy corresponding to the first shooting device in the second time period based on the first positioning accuracy and the second positioning accuracy, the average value of the accuracy rates corresponding to multiple different second time periods is determined as the accuracy of the positioning information corresponding to the first shooting device.

[0237] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0238] Figure 11 A schematic diagram of the hardware structure of the road information processing device provided in the embodiment of the present application is shown as follows: Figure 11 As shown, the road information processing device 110 of this embodiment includes: a processor 1101 and a memory 1102;

[0239] Memory 1102, for storing computer-executable instructions;

[0240] The processor 1101 is configured to execute computer-executable instructions stored in the memory to implement the various steps of the road information processing method in the above embodiment. For details, please refer to the relevant description in the above method embodiment.

[0241] Optionally, the memory 1102 may be independent or integrated with the processor 1101 .

[0242] When the memory 1102 is independently provided, the road information processing device further includes a bus 1103 for connecting the memory 1102 and the processor 1101 .

[0243] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the road information processing method executed by the above road information processing device is implemented.

[0244] Based on the contents of the above embodiments, the road information processing method provided by this application can also be completed by cloud processing. Figure 12 Further details on the implementation of the road information processing method provided by this application on the cloud. Figure 12 A schematic diagram of cloud-based processing of the road information processing method provided in an embodiment of the present application.

[0245] like Figure 12 As shown, there may be multiple cameras on the road, each of which can capture vehicles traveling on the road and obtain vehicle data of the captured vehicles. The cameras on the road can then report all the collected vehicle data to the cloud. The reporting method can be, for example, real-time reporting or scheduled reporting based on a fixed period, which is not limited in this embodiment.

[0246] After the cloud obtains the vehicle data reported by each camera on the road, the vehicle data of multiple cameras can be aggregated to determine the vehicle data on the way.

[0247] For example, if it is currently necessary to determine the in-transit vehicle data for the first area, the cloud can first determine the multiple shooting devices in the first area among the multiple shooting devices, and then obtain the multiple vehicle data sent by the multiple shooting devices in the first area, and on this basis, obtain the target vehicle data within the first time period at the time of shooting. The specific implementation of the first time period and the target vehicle data can refer to the introduction of the above embodiment and will not be repeated here.

[0248] The cloud can then process each of the multiple cameras in the first area. For example, for the first camera among the multiple cameras, the cloud can determine, based on the target vehicle data, the number of vehicles captured by the first camera during the first time period that have not been captured by other cameras and are still traveling at the target time, and use this number as the first vehicle count corresponding to the first camera at the target time. It should be understood that determining the first vehicle data for each camera means, in effect, determining, for each camera, the number of vehicles currently traveling in the area between it and its neighboring cameras.

[0249] Afterwards, the cloud can effectively determine the number of vehicles on the way in the first area at the target time based on the number of first vehicles corresponding to multiple shooting devices in the first area. The number of vehicles on the way can effectively reflect the overall driving status in the first area, thereby effectively expanding the richness of traffic indicators.

[0250] During the implementation of the road information processing method provided by this application on the cloud, various specific processing methods on the cloud are similar to those described in the above embodiments. For details, please refer to the description of the above embodiments and will not be repeated here.

[0251] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0252] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or module, which can be electrical, mechanical or other forms.

[0253] The above-mentioned integrated module implemented in the form of a software functional module can be stored in a computer-readable storage medium. The above-mentioned software functional module is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the method described in various embodiments of the present application.

[0254] It should be understood that the processor described above may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), or application-specific integrated circuits (ASICs). A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0255] The memory may include a high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk.

[0256] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0257] The storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0258] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0259] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application 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 or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A road information processing method, characterized in that: include: Obtaining target vehicle data whose shooting time is within a first time period from a plurality of vehicle data sent by a plurality of shooting devices in a first area, where the first time period is a time period corresponding to a preset time length before the target time; For a first camera among the multiple cameras, determining, based on the target vehicle data, a first number of vehicles corresponding to the first camera at the target time, where the first number of vehicles is the number of vehicles that were photographed by the first camera within the first time period and that have not been photographed by other cameras at the target time and are still traveling; determining the number of vehicles on the way in the first area at the target time according to the number of first vehicles corresponding to each of the plurality of photographing devices in the first area; The preset duration is composed of n consecutive time slices, where n is an integer greater than or equal to 1; The determining, based on the target vehicle data, the first number of vehicles corresponding to the first shooting device at the target time includes: For an i-th time slice among the n time slices, obtaining, based on the target vehicle data, a second number of vehicles corresponding to the i-th time slice, where the second number of vehicles is the number of vehicles captured by the first camera within the time range of the i-th time slice and not captured by any other camera at the target time, where i is an integer greater than or equal to 1 and less than or equal to n; Obtaining a first probability corresponding to the i-th time slice, where the first probability is the probability that the vehicle is photographed by the first camera within the time range of the i-th time slice, has not been photographed by any other camera after i time slices, and continues to travel, wherein the first probability corresponding to each time slice is determined by mining historical data to determine a preset probability corresponding to each preset time period by pre-setting a plurality of preset time periods; Determine, based on the second number of vehicles corresponding to the i-th time slice and the first probability corresponding to the i-th time slice, a third number of vehicles corresponding to the i-th time slice, where the third number of vehicles is the number of vehicles that were captured by the first camera within the time range of the i-th time slice and that have not been captured by other cameras at the target time and continue to travel; The number of first vehicles corresponding to the first shooting device at the target time is determined according to the number of third vehicles corresponding to each of the time slices.

2. The method according to claim 1, characterized in that The obtaining of the first probability corresponding to the i-th time slice includes: Obtaining the target preset time period to which the i-th time slice belongs; The preset probability corresponding to the target preset time period is determined as the first probability corresponding to the i-th time slice, and the preset probability is the probability that the vehicle is photographed by the first shooting device during the target preset time period, and has not been photographed by other shooting devices after i time slices and the vehicle continues to travel.

3. The method according to any one of claims 1-2, characterized in that After determining the number of vehicles in transit in the first area at the target time based on the first number of vehicles corresponding to each of the plurality of photographing devices in the first area, the method further includes: Obtaining a correction coefficient corresponding to the first area, where the correction coefficient is used to compensate for the number of vehicles traveling in the first area that are not captured; The number of vehicles in transit is corrected according to the correction coefficient to obtain a corrected number of vehicles in transit.

4. The method according to any one of claims 1 to 2, characterized in that After determining the number of vehicles in transit in the first area at the target time based on the first number of vehicles corresponding to each of the plurality of photographing devices in the first area, the method further includes: For a first sub-area in the first area, obtaining a proportion parameter corresponding to the first sub-area, where the proportion parameter is used to indicate a proportion of the number of vehicles in the first sub-area to the number of vehicles in the first area; The number of vehicles on the way corresponding to the first sub-area is determined according to the proportion parameter corresponding to the first sub-area and the number of vehicles on the way in the first area.

5. The method according to any one of claims 1-2, characterized in that Among the plurality of vehicle data sent by the plurality of photographing devices in the first area, obtaining the target vehicle data whose photographing time is before the target vehicle data within the first time period, the method further includes: Receiving original vehicle data sent by a photographing device in the first area, the original vehicle data including a photographing time of the vehicle and a vehicle identification of the photographed vehicle; filtering the original vehicle data according to the shooting time and the vehicle identification to obtain filtered vehicle data; The data filtering includes at least one of the following: The shooting time in the original vehicle data is corrected according to the time error; and if it is determined that the vehicle identification does not comply with the preset rules, the original vehicle data corresponding to the vehicle identification that does not comply with the preset rules is discarded; and if it is determined that the occurrence frequency of the vehicle identification is lower than the preset threshold, the original vehicle data corresponding to the vehicle identification whose occurrence frequency is lower than the preset threshold is discarded.

6. The method according to claim 5, characterized in that The original vehicle data also includes a device identification of the photographing device; The method further comprises: Determining, with a first time period as a period, an accuracy rate of positioning information of the first shooting device, where the positioning information is determined according to a device identifier of the first shooting device; If the accuracy is lower than the preset accuracy, the receiving of the original vehicle data sent by the first shooting device is stopped until the accuracy of the positioning information of the first shooting device is higher than or equal to the preset accuracy.

7. The method according to claim 6, characterized in that Determining the accuracy of the positioning information of the first shooting device includes: Acquire multiple vehicle tracks that pass through the first shooting device during a second time period; Determining, from the plurality of vehicle trajectories, a second photographing device that is located adjacent to and behind the first photographing device at the time of the vehicle passing, and determining a first positioning accuracy of the first photographing device based on the positioning information of the first photographing device; Determining, from the plurality of vehicle trajectories, a third photographing device that is located before and adjacent to the first photographing device at the time of the vehicle passing, and determining a second positioning accuracy rate of the first photographing device based on the positioning information of the first photographing device; Determine the accuracy of the positioning information of the first shooting device in the second time period based on the first positioning accuracy, the number of sub-tracks between the first shooting device and the second shooting device, the second positioning accuracy, and the number of sub-tracks between the first shooting device and the third shooting device.

8. The method according to claim 7, characterized in that The determining, based on the positioning information of the first shooting device, a first positioning accuracy of the first shooting device includes: determining a first average driving time from the first shooting device to the second shooting device based on the sub-trajectories between the first shooting device and the second shooting device in the plurality of vehicle trajectories; determining, on an electronic map, a first path from the first photographing device to the second photographing device based on the positioning information of the first photographing device, and determining a first calculated driving time corresponding to the first path; A first positioning accuracy of the first shooting device is determined according to the first average driving time and the first calculated driving time.

9. The method according to any one of claims 7-8, characterized in that After determining the accuracy rate corresponding to the first shooting device in the second time period based on the first positioning accuracy rate and the second positioning accuracy rate, the method further includes: An average value of the accuracy rates corresponding to a plurality of different second time periods is determined as the accuracy rate of the positioning information corresponding to the first shooting device.

10. A road information processing device, characterized in that: include: An acquisition module is configured to acquire, from a plurality of pieces of vehicle data sent by a plurality of photographing devices in a first area, target vehicle data whose photographing moment is within a first time period, where the first time period is a time period corresponding to a preset time length before the target time; a determining module configured to determine, for a first camera among the plurality of cameras, a first number of vehicles corresponding to the first camera at a target time based on the target vehicle data, where the first number of vehicles is the number of vehicles that were captured by the first camera within the first time period and that have not been captured by any other cameras at the target time and are still traveling; The determining module is further configured to determine the number of vehicles on the way in the first area at the target time according to the number of first vehicles corresponding to each of the plurality of photographing devices in the first area; The preset duration is composed of n consecutive time slices, where n is an integer greater than or equal to 1; The determination module is specifically configured to, for an i-th time slice among the n time slices, obtain, based on the target vehicle data, a second number of vehicles corresponding to the i-th time slice, where the second number of vehicles is the number of vehicles that have been photographed by the first camera within the time range of the i-th time slice and have not been photographed by other cameras at the target time, where i is an integer greater than or equal to 1 and less than or equal to n; and obtain a first probability corresponding to the i-th time slice, where the first probability is the probability that a vehicle has been photographed by the first camera within the time range of the i-th time slice and has not been photographed by other cameras after i time slices and that the vehicle continues to travel; Determine, based on the second number of vehicles corresponding to the i-th time slice and the first probability corresponding to the i-th time slice, a third number of vehicles corresponding to the i-th time slice, where the third number of vehicles is the number of vehicles that were captured by the first camera within the time range of the i-th time slice and that have not been captured by other cameras at the target time and continue to travel; According to the number of third vehicles corresponding to each of the time slices, the number of first vehicles corresponding to the first shooting device at the target moment is determined, wherein a plurality of preset time periods are divided by preset, and the preset probability corresponding to each preset time period is determined by mining the historical data to determine the first probability corresponding to each time slice.

11. A road information processing device, characterized in that: include: Memory, used to store programs; A processor is configured to execute the program stored in the memory. When the program is executed, the processor is configured to execute the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that The method comprises instructions which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 9.

13. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images