Road intersection congestion detection method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a road intersection congestion detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining the vehicle information of an intersection, the vehicle information at least comprises the first time when a vehicle stops for the first time when the vehicle does not pass through a first stop line of the intersection, and the second time when the vehicle passes through a second stop line of the intersection; inputting the first time and the second time into a congestion judgment model obtained through pre-training for calculation, and obtaining congestion levels corresponding to all directions in the intersection in the first preset period; wherein the congestion judgment model is used for calculating the average time of passing through the intersection in the current direction according to the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light period. According to the invention, the fusion vehicle information is obtained through the congestion judgment model, the congestion levels in all directions in the intersection are determined in combination with the traffic light period, and the accuracy of intersection congestion detection and the applicability in different scenes are effectively improved by introducing the judgment conditions of the congestion levels.

Description

Technical Field

[0001] The present invention relates to the technical field of servers, and in particular to a method, device, equipment and storage medium for detecting road intersection congestion. Background Art

[0002] With the improvement of my country's economic development level, more and more families choose to buy cars for travel. The rapid increase in the number of motor vehicles has caused the urban traffic conditions to deteriorate, leading to increasing urban road congestion and reduced traffic efficiency, which has had a huge impact on people's lives and work.

[0003] At present, in the detection of urban road congestion, the impact of various vehicle driving scenarios on the detection accuracy has not been taken into account. In order to obtain congestion information at road intersections in a timely manner, the detected congestion information is automatically reported. The frequent changes in traffic flow will also cause frequent reporting of congestion information, and it is impossible to obtain accurate road congestion information. Summary of the invention

[0004] The present invention provides a road intersection congestion detection method, device, equipment and storage medium, which obtains vehicle information fused by multiple cameras, calculates the average time it takes for vehicles to pass through the intersection, and obtains the congestion level corresponding to each direction in the current intersection, so as to improve the accuracy of road intersection congestion information detection.

[0005] According to a first aspect of an embodiment of the present invention, a method for detecting road intersection congestion is provided, the method comprising:

[0006] Acquire vehicle information of the intersection, the vehicle information at least including: a first time when the vehicle stops for the first time when the vehicle does not pass the first stop line of the intersection, and a second time when the vehicle passes the second stop line of the intersection;

[0007] Inputting the first time and the second time into a pre-trained congestion judgment model for calculation, to obtain the congestion level corresponding to each direction of the intersection within a first preset period;

[0008] Among them, the congestion judgment model is used to calculate the average time of passing through the intersection in the current direction of the intersection based on the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light cycle.

[0009] Optionally, the step of inputting the first time and the second time into a pre-trained congestion judgment model to calculate and obtain the congestion level corresponding to each direction of the intersection within a first preset period includes:

[0010] Taking the difference between the first time and the second time as the time taken for the vehicle to pass through the intersection;

[0011] Obtain information on the number of vehicles passing through the intersection in the current direction;

[0012] Combining the vehicle data information with the time taken by each vehicle to pass through the intersection, obtaining the sum of the time taken by all vehicles in the current direction of the intersection to pass through the intersection within the first preset period;

[0013] Combining the ratio of the sum of the time taken by all vehicles in the current direction of the intersection to pass through the intersection and the vehicle quantity information, an average time taken by all vehicles in the current direction of the intersection to pass through the intersection is obtained;

[0014] The congestion level of the current direction of the intersection within the first preset period is determined based on a first ratio of an average time to pass through the intersection in the current direction of the intersection to the traffic light cycle.

[0015] Optionally, determining the congestion level in the current direction of the intersection within the first preset period according to a first ratio of an average time of passing through the intersection in the current direction of the intersection to the traffic light cycle includes:

[0016] Determining the congestion level of the current direction of the intersection according to the interval where the first ratio is located, the congestion level at least includes: smooth, second-level congestion, third-level congestion, and fourth-level congestion;

[0017] Acquiring density data of vehicles in the lane that have not passed the intersection according to a second preset period;

[0018] When the congestion level is level 3 congestion or level 4 congestion, and the vehicle density data exceeds a specific threshold, a level 3 congestion event or a level 4 congestion event is reported.

[0019] Optionally, acquiring density data of vehicles in the lane that do not pass through the intersection according to the second preset period includes:

[0020] Counting the number of vehicles in the current lane that have not passed the intersection according to the second preset period, and using the number of vehicles as the vehicle density data;

[0021] If the number of vehicles that have not passed the intersection in multiple lanes is counted, the maximum value among the multiple numbers of vehicles is used as the vehicle density data.

[0022] Optionally, the method further comprises:

[0023] Acquire the congestion level of the current direction of the intersection, and if the congestion level is the third level congestion or the fourth level congestion, confirm that a congestion event exists at the intersection;

[0024] Obtain a second ratio representing the degree of congestion in the current direction of the intersection within a third preset period. If the second ratio is less than the minimum value in the interval corresponding to the third level of congestion, and the difference between the second ratio and the first ratio is greater than 0.2, then confirm that the intersection is free of congestion, wherein the third preset period is the next preset period of the first preset period.

[0025] Optionally, the acquiring the vehicle information at the intersection includes:

[0026] Collecting the position information of the vehicle at the intersection through a camera and obtaining the coordinate identification of the vehicle;

[0027] Identify the first stop line and the second stop line of the intersection according to the high-precision map data, and obtain the vehicle information of the intersection in combination with the coordinate identification of the vehicle;

[0028] The position information of the vehicle at the intersection is obtained by fusing the position information of the vehicle at the intersection collected by all cameras.

[0029] Optionally, the identifying the first stop line and the second stop line of the intersection according to the high-precision map data, and acquiring the vehicle information of the intersection in combination with the coordinate identification of the vehicle, includes:

[0030] Obtain the second stop line corresponding to each direction in the intersection;

[0031] Confirming the driving direction of the vehicle at the intersection in combination with the coordinate identification of the vehicle;

[0032] The vehicle information is acquired according to the driving direction of the vehicle at the intersection and a second stop line corresponding to the driving direction.

[0033] According to a second aspect of an embodiment of the present invention, a road intersection congestion detection device is provided, the device comprising:

[0034] A vehicle information acquisition module, used to acquire vehicle information of the intersection, the vehicle information at least including: a first time when the vehicle stops for the first time when the vehicle does not pass the first stop line of the intersection, and a second time when the vehicle passes the second stop line of the intersection;

[0035] A congestion level calculation module, configured to input the first time and the second time into a pre-trained congestion judgment model for calculation, and obtain the congestion level corresponding to each direction of the intersection within a first preset period;

[0036] Among them, the congestion judgment model is used to calculate the average time of passing through the intersection in the current direction of the intersection based on the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light cycle.

[0037] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute any of the road intersection congestion detection methods described in the first aspect.

[0038] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, storing a computer program for use in conjunction with an electronic device, wherein the computer program can be executed by a processor to complete the road intersection congestion detection method described in any one of the first aspects.

[0039] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0040] The method for detecting congestion at a road intersection disclosed in an embodiment of the present invention obtains vehicle information at an intersection according to a first preset period, wherein the vehicle information at least includes: a first time when the vehicle stops for the first time when it fails to pass through a first stop line at the intersection, and a second time when the vehicle passes through a second stop line at the intersection; the first time and the second time are input into a pre-trained congestion judgment model for calculation, so as to obtain the congestion levels corresponding to each direction at the intersection within the first preset period; wherein the congestion judgment model is used to calculate the average time for passing through the intersection in the current direction of the intersection according to the vehicle information, and the congestion level is determined based on the average time for passing through the intersection and the traffic light cycle. The present invention calculates the average time for vehicles to pass through the intersection through the congestion judgment model, and obtains the congestion levels corresponding to each direction at the intersection in combination with the traffic light cycle at the intersection, and at the same time introduces vehicle density and conditional judgment on the release of congestion events, thereby effectively improving the detection accuracy of congestion at the intersection at night, and avoiding the frequent generation and reporting of congestion events, so as to effectively extract the actual congestion information of the road intersection from the reported events.

[0041] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 is a flowchart of a method for detecting road intersection congestion provided by an embodiment of the present invention;

[0044] Figure 2is a road intersection schematic diagram provided by an embodiment of the present invention;

[0045] Figure 3 is a flowchart of step 102 of a road intersection congestion detection method provided by an embodiment of the present invention;

[0046] Figure 4 is a structural block diagram of a road intersection congestion detection device provided by an embodiment of the present invention;

[0047] Figure 5 It is a block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0049] The hard disk auxiliary test device, method and storage medium provided by the embodiments of the present invention are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0050] Reference Figure 1 , shows a road intersection congestion detection method according to an embodiment of the present invention, which may specifically include the following steps:

[0051] Step 101, obtaining vehicle information at an intersection, the vehicle information at least including: a first time when the vehicle stops for the first time before passing a first stop line at the intersection, and a second time when the vehicle passes a second stop line at the intersection.

[0052] In order to detect the congestion situation at the road intersection, the congestion situation is judged by the time taken by the vehicle to pass through the intersection, and the congestion level of the road intersection is obtained. In the embodiment of the present invention, the vehicle at the road intersection can be identified by camera acquisition or video monitoring, and the identified vehicle is recorded, and the vehicle information of the vehicle at the road intersection is obtained according to the record.

[0053] Reference Figure 2, shows a schematic diagram of a road intersection. Exemplarily, there are vehicles coming from four directions at the road intersection in the figure. The stop line in one direction of the road intersection is set as the first stop line, and the stop lines in the other three directions are the corresponding second stop lines in each direction. The time when the vehicle P0 in the figure passes through the road intersection is determined by the two moments when the vehicle stops for the first time before passing the first stop line of the road intersection and the moment when the vehicle passes the second stop line of the intersection. Therefore, based on the identification record of the vehicle, the vehicle information obtained includes at least: the first time when the vehicle stops for the first time when it does not pass the first stop line of the intersection, and the second time when the vehicle passes the second stop line of the intersection.

[0054] Specifically, the driving direction of the identified vehicle at the current intersection can be determined based on the second stop line that the identified vehicle passes through, that is, the congestion information of the corresponding direction in the current road intersection is calculated based on the acquired vehicle information. In an embodiment of the present invention, the location information of the vehicle is obtained through a camera, and the UTM (Universal Transverse Mercator Grid System) coordinates are used to represent it, and the road intersection is identified in combination with high-precision map data to obtain the first stop line of the road intersection and the second stop line in each direction. At the same time, the location and time of the first stop of the vehicle, the time of passing the second stop line, etc. are determined in combination with the UTM coordinates of the vehicle, so as to obtain the vehicle information at the intersection, wherein the input data of the congestion judgment model is the fusion result of the data collected by all cameras, that is, the location information of the vehicle at the intersection is obtained by fusing the vehicle location information collected by all cameras, and the fused vehicle location information can effectively avoid the problem of vehicle overlap and blind spot omission caused by the simple superposition of multiple camera data.

[0055] In an embodiment of the present invention, data from multiple cameras collected for the same vehicle are fused, and the fused vehicle information at the intersection is used as input data for a congestion judgment model to improve the accuracy of collecting the position information of each vehicle at the intersection. If the collected information of each camera is used as input data, the same vehicle may be repeatedly collected in the overlapping areas of different cameras, resulting in duplicate vehicle information in the vehicle information at the intersection. Accordingly, data may be missed in the blind spots of the camera, resulting in a lack of some vehicle information in the vehicle information at the intersection.

[0056] Step 102, input the first time and the second time into a pre-trained congestion judgment model to calculate the congestion level corresponding to each direction at the intersection within a first preset period; wherein the congestion judgment model is used to calculate the average time to pass through the intersection in the current direction of the intersection based on vehicle information, and the congestion level is determined based on the average time to pass through the intersection and the traffic light cycle.

[0057] In an embodiment of the present invention, the acquired vehicle information is used as input data of a pre-trained congestion judgment model. After calculation and processing by the congestion judgment model, the average time for vehicles to pass through the intersection in the current direction of the intersection is obtained, and the congestion level corresponding to each direction in the road intersection within a first preset period determined according to the average time of passing through the intersection and the traffic light cycle is further output.

[0058] The road intersection congestion detection method disclosed in the embodiment of the present invention calculates the average time it takes for vehicles to pass through the intersection through a congestion judgment model, and obtains the congestion level corresponding to each direction of the intersection in combination with the traffic light cycle of the intersection. At the same time, the collected data of all cameras are integrated to effectively avoid the problem of repeated vehicle recognition and omission of vehicles in blind spots caused by simple superposition of camera collected data, thereby effectively improving the accuracy of recognition and detection of road intersection congestion.

[0059] Further, see Figure 3 , Figure 3 1 is a method flow chart of step 102 of a method for detecting congestion at a road intersection provided by an embodiment of the present invention. Step 102 may include:

[0060] Step 301, taking the difference between the first time and the second time as the time taken for the vehicle to pass through the intersection.

[0061] Specifically, the first stop of the vehicle before it passes the first stop line of the intersection indicates that the first parking position of the vehicle is after the first stop line of the road intersection, that is, the vehicle has not passed the road intersection at this time, wherein the identified vehicle is monitored, if there are two connected road intersections, the first stop of the identified vehicle after passing the previous intersection of the current intersection is the first stop of the vehicle before it passes the first stop line of the intersection, and the vehicle passing the second stop line of the intersection indicates that the vehicle passes the current road intersection. Therefore, based on the acquired vehicle information, the time from the first time to the second time is recorded as the time taken for the identified vehicle to pass the intersection.

[0062] Step 302, obtaining information on the number of vehicles passing through the intersection in the current direction.

[0063] Step 303, combining the vehicle data information with the time taken by each vehicle to pass through the intersection, obtains the total time taken by all vehicles in the current direction of the intersection to pass through the intersection within the first preset period.

[0064] While obtaining the second time, the vehicle's driving direction, that is, the direction of the road intersection corresponding to the currently calculated congestion level, can be obtained. Combined with the identification and recording of vehicles in the road intersection, the number of vehicles passing through the intersection in the current direction can be obtained. For example, the number of vehicles passing through the left turn direction is 10, indicating that a total of 10 vehicles are passing through the current intersection in the left turn direction. Among them, the time taken to pass the intersection is obtained by identifying each vehicle, and combined with the vehicle data information, the total time taken for all vehicles in the current direction of the intersection to pass through the intersection within the first preset period can be obtained. For example, a total of 10 vehicles pass through the current intersection in the left turn direction, and the time taken for each of the 10 vehicles to pass through the intersection is added together to obtain the total time taken for all vehicles in the current direction to pass through the intersection.

[0065] Among them, a first preset period is set to calculate the total time taken for vehicles to pass through the intersection. For example, if the first preset period is set to 2 minutes, the data information of the total time taken for vehicles to pass through the intersection is obtained every 2 minutes, and the statistical time of the event that all vehicles in the current direction of the intersection pass through the intersection corresponds to within 4 minutes, that is, the total time taken for all vehicles in the current direction that pass through the road intersection in the past 4 minutes is counted. It should be noted that the first preset period and the statistical time for all vehicles in the current direction of the intersection passing through the intersection can be set differently as needed.

[0066] Step 304, combining the ratio of the total time taken by all vehicles passing through the intersection in the current direction of the intersection to the vehicle quantity information, obtains the average time taken to pass through the intersection in the current direction of the intersection.

[0067] Step 305, determining the congestion level of the current direction of the intersection within a first preset period based on a first ratio of the average time to pass through the intersection in the current direction of the intersection to the traffic light cycle.

[0068] In an embodiment of the present invention, the average time for passing through the intersection in the current direction of the intersection is obtained based on the ratio of the total time taken for all vehicles in the current direction to pass through the intersection to the vehicle quantity information in the current direction, that is, the average time taken for each vehicle in the current direction to pass through the intersection.

[0069] Taking into account the actual driving scenarios of vehicles, vehicles can only drive through the intersection when the traffic light in the current direction of the intersection shows green. When the traffic light in the current direction of the intersection shows red or yellow, the vehicle waits for passage behind the first stop line of the intersection. Therefore, the average time for each vehicle to pass through the intersection in the current direction is related to the traffic light cycle of the intersection. The traffic light cycle in the current direction of the road is obtained through a functional module related to the traffic light, and the congestion level in the current direction of the intersection within the first preset period is determined based on a first ratio of the average time to pass through the intersection in the current direction of the intersection to the traffic light cycle. Specifically, the first ratio in different intervals corresponds to different congestion levels. The congestion level of the current direction of the intersection is divided according to the interval where the first ratio is obtained, wherein the congestion level includes at least: smooth, secondary congestion, tertiary congestion, and quaternary congestion. For example, when the first ratio is in the interval of 0 to 0.75, the congestion level is smooth, and there is no congestion at the current intersection. When the first ratio is in the interval of 0.75 to 1.5, the congestion level is secondary congestion, indicating that the current intersection is relatively smooth. When the first ratio is in the interval of 1.5 to 2.25, the congestion level is tertiary congestion, indicating that there is congestion at the current intersection. When the first ratio is greater than 2.25, the congestion level is quaternary congestion, indicating that there is congestion at the current intersection and the congestion is relatively serious. It should be noted that the ratio for determining the congestion level of the current direction of the intersection and the corresponding interval value can be set in combination with actual conditions, and the present invention does not make specific limitations.

[0070] In order to obtain the congestion situation at the road intersection in time, the corresponding functional module reports the congestion events at the intersection. Taking into account the different driving scenarios of vehicles, fewer vehicles at night or longer period traffic lights at the intersection may lead to false alarms of congestion events at the intersection. In the embodiment of the present invention, the congestion level in the current direction of the intersection is judged in combination with the density data of vehicles that have not passed the intersection in the lane. Specifically, when the congestion level corresponding to the first ratio is obtained as level three congestion or level four congestion, the density data of vehicles that have not passed the intersection in the lane is judged. Only when it is confirmed that the congestion level is level three congestion or level four congestion, and the vehicle density data also exceeds a specific threshold, the corresponding functional module reports the level three congestion event or level four congestion event, and combines it with the density data of vehicles that have not passed the intersection in the lane, which can effectively avoid false alarms of scenes with fewer vehicles at night.

[0071] The vehicle density data of the lane that has not passed the intersection is obtained through the following steps:

[0072] Counting the number of vehicles that have not passed the intersection in the current lane according to a second preset period, and using the number of vehicles as vehicle density data;

[0073] If the number of vehicles that have not passed the intersection in multiple lanes is counted, the maximum value among the multiple numbers of vehicles is used as the vehicle density data.

[0074] In an embodiment of the present invention, the number of vehicles that have not passed the intersection in the current lane is counted, and the number of vehicles obtained by counting is used as vehicle density data. If there are multiple lanes at present, the vehicle density data in the current direction depends on the lane with the largest number of vehicles. In this way, the number of vehicles that have not passed the intersection in the multiple lanes is counted, and the maximum value of the multiple vehicle numbers is used as the vehicle density data.

[0075] Furthermore, when the congestion level in the current direction of the intersection corresponds to level three congestion or level four congestion, it is considered that a congestion event exists at the current intersection, and the congestion level in the current direction of the intersection is continuously calculated based on the first preset period, such as recalculating the congestion level in the current direction of the intersection every first preset period. For example, if the first ratio obtained within the first preset period corresponds to level three congestion or level four congestion, that is, there is a congestion event, the next preset period of the first preset period is taken as the third preset period, and the second ratio within the third preset period is calculated, that is, the new ratio obtained one first preset period away from the current first ratio is less than the interval range corresponding to the level three congestion event. The minimum value in the range, such as the second ratio is less than 1.5, and the difference between the second ratio and the current first ratio is greater than 0.2, it can be considered that the congestion event at the intersection has been lifted; when the second ratio in the next preset period of the first preset period satisfies both that it does not belong to the third-level congestion event and the difference with the current first ratio is greater than 0.2, it can be considered that the congestion event in the current direction of the intersection has been lifted, thereby effectively avoiding the ping-pong effect caused by the multiple ratios obtained gathering at the boundary of the judgment interval of the third-level congestion. If multiple ratios keep jumping around 1.5, it will lead to the continuous generation, release, generation and release of congestion events, and frequent and multiple reporting of information, causing confusion of data and information.

[0076] The method for detecting congestion at a road intersection disclosed in an embodiment of the present invention obtains vehicle information at an intersection according to a first preset period, wherein the vehicle information at least includes: a first time when the vehicle stops for the first time when it fails to pass through a first stop line at the intersection, and a second time when the vehicle passes through a second stop line at the intersection; the first time and the second time are input into a pre-trained congestion judgment model for calculation, so as to obtain the congestion level corresponding to each direction at the intersection within the first preset period; wherein the congestion judgment model is used to calculate the average time for passing through the intersection in the current direction of the intersection according to the vehicle information, and the congestion level is determined based on the average time for passing through the intersection and the traffic light cycle. The present invention calculates the average time for vehicles to pass through the intersection through the congestion judgment model, and obtains the congestion level corresponding to each direction at the intersection in combination with the traffic light cycle at the intersection, and at the same time introduces vehicle density and conditional judgment on the release of congestion events, thereby effectively improving the detection accuracy of congestion in night driving scenes, and avoiding the frequent generation and reporting of congestion events caused by the ping-pong effect, so as to effectively extract the actual congestion information of the road intersection from the reported events.

[0077] The embodiment of the present invention also provides a road intersection congestion detection device. Figure 4 , shows a road intersection congestion detection device according to an embodiment of the present invention, which may include the following modules:

[0078] The vehicle information acquisition module 401 is used to acquire the vehicle information of the intersection, wherein the vehicle information includes at least: a first time when the vehicle stops for the first time before passing the first stop line of the intersection, and a second time when the vehicle passes the second stop line of the intersection;

[0079] A congestion level calculation module 402, configured to input the first time and the second time into a pre-trained congestion judgment model for calculation, and obtain the congestion level corresponding to each direction of the intersection within a first preset period;

[0080] Among them, the congestion judgment model is used to calculate the average time of passing through the intersection in the current direction of the intersection based on the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light cycle.

[0081] Furthermore, the congestion level calculation module 402 includes:

[0082] A vehicle passing time calculation module, used to use the difference between the first time and the second time as the time taken for the vehicle to pass through the intersection;

[0083] A vehicle quantity acquisition module is used to obtain the vehicle quantity information of vehicles passing through the intersection in the current direction;

[0084] A time sum calculation module, used to combine the vehicle data information with the time taken by each vehicle to pass through the intersection, to obtain the sum of the time taken by all vehicles in the current direction of the intersection to pass through the intersection within the first preset period;

[0085] An average time calculation module, used to obtain an average time for passing through the intersection in the current direction of the intersection by combining the ratio of the total time taken by all vehicles passing through the intersection in the current direction of the intersection to the vehicle quantity information;

[0086] The congestion level calculation submodule is used to determine the congestion level of the current direction of the intersection within the first preset period according to a first ratio of the average time of passing through the intersection in the current direction of the intersection to the traffic light cycle.

[0087] Furthermore, the congestion level submodule includes:

[0088] A congestion level confirmation module, used to determine the congestion level of the current direction of the intersection according to the interval where the first ratio is located, and the congestion level includes at least: smooth, second-level congestion, third-level congestion, and fourth-level congestion;

[0089] A vehicle density acquisition module, used to acquire density data of vehicles in the lane that have not passed the intersection according to a second preset period;

[0090] The congestion event reporting module is used to report a level 3 congestion event or a level 4 congestion event when the congestion level is level 3 congestion or level 4 congestion and the vehicle density data exceeds a specific threshold.

[0091] Furthermore, the vehicle density acquisition module includes:

[0092] a vehicle number counting module, configured to count the number of vehicles in the current lane that have not passed the intersection according to the second preset period, and use the number of vehicles as the vehicle density data;

[0093] The vehicle density confirmation module is used to count the number of vehicles that have not passed the intersection in multiple lanes and use the maximum value of the multiple numbers of vehicles as the vehicle density data.

[0094] Furthermore, the device also includes:

[0095] a congestion event confirmation module, configured to obtain the congestion level of the current direction of the intersection, and if the congestion level is the third level congestion or the fourth level congestion, confirm that a congestion event exists at the intersection;

[0096] A congestion event release module is used to obtain a second ratio representing the congestion level in the current direction of the intersection within a third preset period. If the second ratio is less than the minimum value in the interval corresponding to the third level of congestion, and the difference between the second ratio and the first ratio is greater than 0.2, it is confirmed that the congestion event at the intersection is released, wherein the third preset period is the next preset period of the first preset period.

[0097] Furthermore, the vehicle information acquisition module 401 includes:

[0098] A vehicle position acquisition module, used to acquire the position information of the vehicle at the intersection through a camera and obtain the coordinate identification of the vehicle;

[0099] A vehicle information acquisition submodule, used to identify the first stop line and the second stop line of the intersection according to the high-precision map data, and acquire the vehicle information of the intersection in combination with the coordinate identification of the vehicle;

[0100] The position information of the vehicle at the intersection is obtained by fusing the position information of the vehicle at the intersection collected by all cameras.

[0101] Furthermore, the vehicle information acquisition submodule includes:

[0102] A second stop line acquisition module, used to acquire the second stop lines corresponding to each direction in the intersection;

[0103] A direction confirmation module, used to confirm the driving direction of the vehicle at the intersection in combination with the coordinate identification of the vehicle;

[0104] The directional vehicle information acquisition module is used to acquire the vehicle information according to the driving direction of the vehicle at the intersection and the second stop line corresponding to the driving direction.

[0105] The road intersection congestion detection device disclosed in the embodiment of the present invention calculates the average time for vehicles to pass through the intersection through a congestion judgment model, and obtains the congestion level corresponding to each direction of the intersection in combination with the traffic light cycle of the intersection. At the same time, it introduces the comparison of vehicle density to effectively improve the detection accuracy of congestion at the intersection at night. At the same time, it introduces the conditional judgment of the release of congestion events to avoid the frequent generation and reporting of congestion events, and can effectively extract the actual congestion information of the road intersection from the reported events.

[0106] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0107] Reference Figure 5 , an embodiment of the present invention further provides an electronic device, such as Figure 5 As shown, it includes a processor 501, a communication interface 502, a memory 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other through the communication bus 504.

[0108] Memory 503, used for storing computer programs;

[0109] The processor 501 is used to execute the program stored in the memory 503, and implements the following steps:

[0110] Acquire vehicle information of the intersection, the vehicle information at least including: a first time when the vehicle stops for the first time when the vehicle does not pass the first stop line of the intersection, and a second time when the vehicle passes the second stop line of the intersection;

[0111] Inputting the first time and the second time into a pre-trained congestion judgment model for calculation, to obtain the congestion level corresponding to each direction of the intersection within a first preset period;

[0112] Among them, the congestion judgment model is used to calculate the average time of passing through the intersection in the current direction of the intersection based on the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light cycle.

[0113] An embodiment of the present invention further provides a computer-readable storage medium, in which instructions are stored. When the computer-readable storage medium is run on a computer, the computer is enabled to execute the road intersection congestion detection method described in any of the above embodiments.

[0114] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0115] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0116] The above is a detailed introduction to a road intersection congestion detection method, device, equipment and storage medium provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A road intersection congestion detection method, It is characterized in that The method comprises: Acquire vehicle information of the intersection, the vehicle information at least including: a first time when the vehicle stops for the first time when the vehicle does not pass the first stop line of the intersection, and a second time when the vehicle passes the second stop line of the intersection; Inputting the first time and the second time into a pre-trained congestion judgment model for calculation, to obtain the congestion level corresponding to each direction of the intersection within a first preset period; Among them, the congestion judgment model is used to calculate the average time of passing through the intersection in the current direction of the intersection based on the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light cycle.

2. The method according to claim 1, It is characterized in that The step of inputting the first time and the second time into a pre-trained congestion judgment model for calculation to obtain the congestion level corresponding to each direction of the intersection within a first preset period includes: Taking the difference between the first time and the second time as the time taken for the vehicle to pass through the intersection; Obtain information on the number of vehicles passing through the intersection in the current direction; Combining the vehicle data information with the time taken by each vehicle to pass through the intersection, obtaining the total time taken by all vehicles in the current direction of the intersection to pass through the intersection within the first preset period; Combining the ratio of the sum of the time taken by all vehicles in the current direction of the intersection to pass through the intersection and the vehicle quantity information, an average time taken by all vehicles in the current direction of the intersection to pass through the intersection is obtained; The congestion level of the current direction of the intersection within the first preset period is determined based on a first ratio of an average time to pass through the intersection in the current direction of the intersection to the traffic light cycle.

3. The method according to claim 2, It is characterized in that Determining the congestion level of the current direction of the intersection within the first preset period according to the first ratio of the average time of passing through the intersection in the current direction of the intersection to the traffic light cycle includes: Determining the congestion level of the current direction of the intersection according to the interval where the first ratio is located, the congestion level at least includes: smooth, second-level congestion, third-level congestion, and fourth-level congestion; Acquiring density data of vehicles in the lane that have not passed the intersection according to a second preset period; When the congestion level is level 3 congestion or level 4 congestion, and the vehicle density data exceeds a specific threshold, a level 3 congestion event or a level 4 congestion event is reported.

4. The method according to claim 3, It is characterized in that The obtaining density data of vehicles in the lane that have not passed the intersection according to the second preset period includes: Counting the number of vehicles in the current lane that have not passed the intersection according to the second preset period, and using the number of vehicles as the vehicle density data; If the number of vehicles that have not passed the intersection in multiple lanes is counted, the maximum value among the multiple numbers of vehicles is used as the vehicle density data.

5. The method according to claim 3, It is characterized in that The method further comprises: Acquire the congestion level of the current direction of the intersection, and if the congestion level is the third level congestion or the fourth level congestion, confirm that a congestion event exists at the intersection; Obtain a second ratio representing the degree of congestion in the current direction of the intersection within a third preset period. If the second ratio is less than the minimum value in the interval corresponding to the third level of congestion, and the difference between the second ratio and the first ratio is greater than 0.2, then confirm that the intersection is free of congestion, wherein the third preset period is the next preset period of the first preset period.

6. The method according to claim 1, It is characterized in that The obtaining of the vehicle information at the intersection includes: Collecting the position information of the vehicle at the intersection through a camera and obtaining the coordinate identification of the vehicle; Identify the first stop line and the second stop line of the intersection according to the high-precision map data, and obtain the vehicle information of the intersection in combination with the coordinate identification of the vehicle; The position information of the vehicle at the intersection is obtained by fusing the position information of the vehicle at the intersection collected by all cameras.

7. The method according to claim 6, It is characterized in that The step of identifying the first stop line and the second stop line of the intersection according to the high-precision map data and acquiring the vehicle information of the intersection in combination with the coordinate identification of the vehicle includes: Obtain the second stop line corresponding to each direction in the intersection; Confirming the driving direction of the vehicle at the intersection in combination with the coordinate identification of the vehicle; The vehicle information is acquired according to the driving direction of the vehicle at the intersection and a second stop line corresponding to the driving direction.

8. A road intersection congestion detection device, It is characterized in that The device comprises: A vehicle information acquisition module, used to acquire vehicle information of the intersection, the vehicle information at least including: a first time when the vehicle stops for the first time when the vehicle does not pass the first stop line of the intersection, and a second time when the vehicle passes the second stop line of the intersection; A congestion level calculation module, configured to input the first time and the second time into a pre-trained congestion judgment model for calculation, and obtain the congestion level corresponding to each direction of the intersection within a first preset period; Among them, the congestion judgment model is used to calculate the average time of passing through the intersection in the current direction of the intersection based on the vehicle information, and the congestion level is determined based on the average time of passing through the intersection and the traffic light cycle.

9. An electronic device, include: one or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program for use in conjunction with an electronic device, wherein the computer program can be executed by a processor to implement the method of any one of claims 1 to 7.

Images