Driving state judgment method and device, computer device and storage medium

Abstract

The application relates to a driving state judgment method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining follow-up data of a target vehicle cluster, the follow-up data comprising a follow-up time length and a follow-up distance; clustering the target vehicle cluster based on the follow-up data to generate a clustered vehicle group, and determining a target vehicle group from the clustered vehicle group; obtaining adjacent traffic flow information of adjacent same-direction lanes of the target vehicle group; obtaining target vehicle light information of the target vehicle group, and determining parking intention information of the target vehicle group according to the target vehicle light information; obtaining a target traffic signal light state of a road where the target vehicle group is located; and determining a driving state of the target vehicle group based on the adjacent traffic flow information, the parking intention information and the target traffic signal light state. The method can improve the accuracy of vehicle behavior judgment.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer device, and storage medium for determining vehicle status. Background Technology

[0002] With the development of computer technology, more and more computer technologies are being combined with the automotive industry. Among them, autonomous driving technology is receiving increasing attention and is developing rapidly. Making scientific and reasonable judgments about the driving status of vehicles on the road is one of the important directions for tackling key problems in autonomous driving technology.

[0003] In traditional technology, the behavior of a stationary target vehicle is judged by a preset scenario and a preset behavior database. However, due to the limited amount of data in the preset behavior database, misjudgments are likely to occur for new scenarios that are not included in the preset behavior database, resulting in low accuracy in judging vehicle behavior. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for judging vehicle status, which can improve the accuracy of vehicle behavior judgment, in order to address the above-mentioned technical problems.

[0005] A method for determining vehicle status includes:

[0006] Acquire vehicle-following data for the target vehicle cluster, including following duration and following distance;

[0007] Based on vehicle tracking data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups;

[0008] Obtain adjacent traffic flow information of adjacent lanes in the same direction to the target vehicle group;

[0009] Obtain the target vehicle headlight information of the target vehicle group, and determine the parking intention information of the target vehicle group based on the target vehicle headlight information;

[0010] Obtain the status of the target traffic lights on the road where the target vehicle group is located;

[0011] The driving status of the target vehicle group is determined based on adjacent traffic flow information, parking intention information, and the status of the target traffic light.

[0012] In one embodiment, before obtaining the vehicle-following data of the target vehicle cluster, the method further includes:

[0013] Obtain the current distance between the first target vehicle and the second target vehicle in the target vehicle cluster;

[0014] Obtain the first vehicle speed of the first target vehicle and the second vehicle speed of the second target vehicle;

[0015] The following time between the first target vehicle and the second target vehicle is obtained based on the speed of the first vehicle, the speed of the second vehicle, and the current distance.

[0016] The following distance is obtained by combining the following duration with the speed of the first vehicle.

[0017] Following data is obtained from following distance and following time.

[0018] In one embodiment, clustering the target vehicle cluster based on vehicle tracking data to generate clustered vehicle groups, and determining the target vehicle group from the clustered vehicle groups, includes:

[0019] Obtain the target vehicle following data of the first and second target vehicles in the target vehicle cluster;

[0020] When the target vehicle following time is greater than or equal to a preset time threshold and the target vehicle following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group.

[0021] In one embodiment, when the target vehicle following duration of the target vehicle following data is greater than or equal to a preset duration threshold and the target vehicle following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group, including:

[0022] When the target following time is less than a preset time threshold or the target following distance is less than a preset distance threshold, the interval area between the first target vehicle and the second target vehicle is detected.

[0023] When the detection result of the interval region is a blind zone, the second preset duration threshold and the second preset distance threshold are obtained, and the second preset duration threshold is used as the preset duration threshold and the second preset distance threshold is used as the preset distance threshold.

[0024] Returning to the step of clustering the first target vehicle and the second target vehicle into a target vehicle group when the target vehicle following time of the target vehicle following data is greater than or equal to a preset time threshold and the target vehicle following distance is greater than or equal to a preset distance threshold, the second preset time threshold is less than a preset time threshold and the second preset distance threshold is less than a preset distance threshold.

[0025] In one embodiment, the method further includes:

[0026] Obtain the location information of the target vehicle group, which includes the lane information where the target vehicle group is located, the lane width information, and the geometry information of the obstacles;

[0027] The parking intention information of the target vehicle group is determined based on the location information.

[0028] In one embodiment, determining the driving status of a target vehicle group based on adjacent traffic flow information, parking intention information, and the status of the target traffic light includes:

[0029] When the target traffic light is in a state of prohibition and the parking intention information is not a parking intention, the first driving state of the target vehicle group is determined to be a normal stop state.

[0030] When the target traffic light status is "allow to pass" or the parking intention information is "parking intention", the first driving status of the target vehicle group is determined to be "abnormal stop".

[0031] When the first driving state is an abnormal stop state, obtain the speed difference between the target vehicle group and the speed of the adjacent traffic flow in the adjacent traffic flow information;

[0032] When the differential speed is less than the preset differential speed threshold and the parking intention information is not a parking intention, the second driving state of the target vehicle group is determined to be the normal stop state.

[0033] When the differential speed is greater than or equal to the preset differential speed threshold or the parking intention information is a parking intention, the second driving state is determined to be an abnormal stop state.

[0034] In one embodiment, the method further includes:

[0035] Obtain the distance between the target vehicle group and the current vehicle;

[0036] When the distance is greater than a preset threshold, the current vehicle and the target vehicle group are determined to be in a non-associated state.

[0037] A vehicle status determination device, the device comprising:

[0038] The feature extraction module is used to acquire vehicle following data of the target vehicle cluster, including following duration and following distance; based on the following data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is identified from the clustered vehicle groups; adjacent traffic flow information of adjacent lanes in the same direction of the target vehicle group is acquired; target vehicle light information of the target vehicle group is acquired, and parking intention information of the target vehicle group is determined based on the target vehicle light information; and the status of the target traffic lights on the road where the target vehicle group is located is acquired.

[0039] The judgment module is used to determine the driving status of the target vehicle group based on adjacent traffic flow information, parking intention information, and the status of the target traffic light.

[0040] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0041] Acquire vehicle-following data for the target vehicle cluster, including following duration and following distance;

[0042] Based on vehicle tracking data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups;

[0043] Obtain adjacent traffic flow information of adjacent lanes in the same direction to the target vehicle group;

[0044] Obtain the target vehicle headlight information of the target vehicle group, and determine the parking intention information of the target vehicle group based on the target vehicle headlight information;

[0045] Obtain the status of the target traffic lights on the road where the target vehicle group is located;

[0046] The driving status of the target vehicle group is determined based on adjacent traffic flow information, parking intention information, and the status of the target traffic light.

[0047] A computer-readable storage medium having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0048] Acquire vehicle-following data for the target vehicle cluster, including following duration and following distance;

[0049] Based on vehicle tracking data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups;

[0050] Obtain adjacent traffic flow information of adjacent lanes in the same direction to the target vehicle group;

[0051] Obtain the target vehicle headlight information of the target vehicle group, and determine the parking intention information of the target vehicle group based on the target vehicle headlight information;

[0052] Obtain the status of the target traffic lights on the road where the target vehicle group is located;

[0053] The driving status of the target vehicle group is determined based on adjacent traffic flow information, parking intention information, and the status of the target traffic light.

[0054] The aforementioned driving status determination method, device, computer equipment, and storage medium acquire vehicle-following data of the target vehicle cluster, then group the vehicles in the target vehicle cluster into clustered vehicle groups based on vehicle-following data between vehicles in the same lane within the target vehicle cluster, identify the target vehicle group within the clustered vehicle groups, extract adjacent traffic flow information from adjacent lanes in the same direction near the target vehicle group, including vehicle speed and traffic flow information of vehicles in adjacent lanes, acquire the target vehicle group's target headlight information in real time, determine the target vehicle group's parking intention information based on the target headlight information, acquire the target traffic light status of the road where the target vehicle group is located, and finally comprehensively determine the driving status of the target vehicle group based on adjacent traffic flow information, parking intention information, and target traffic light status. In this way, by clustering target vehicles into complete vehicle groups and extracting information about the surrounding environment of the vehicle groups, the driving status of the target vehicle groups is finally analyzed based on preset logic. Compared with the traditional method of judging the driving status of target vehicles by using a preset behavior database, this method does not rely on preset traffic scene data to judge the driving status. It solves the defect of the preset behavior database being prone to misjudgment in unfamiliar new traffic scenes due to the limitation of data volume, and effectively improves the accuracy of vehicle behavior judgment. Attached Figure Description

[0055] Figure 1 This is an application environment diagram of the vehicle status determination method in one embodiment;

[0056] Figure 2 This is a flowchart illustrating a method for determining vehicle status in one embodiment;

[0057] Figure 3 This is a schematic diagram of the process for generating vehicle following data in one embodiment;

[0058] Figure 4 This is a schematic diagram of the process for generating a target vehicle group in one embodiment;

[0059] Figure 5 This is a schematic diagram of the process for generating a target vehicle group in one embodiment;

[0060] Figure 6 This is a schematic diagram of the process for determining the parking intention information of a target vehicle group in one embodiment.

[0061] Figure 7 This is a flowchart illustrating the process of determining the driving status of a target train group in one embodiment;

[0062] Figure 8 This is a flowchart illustrating the process of determining the driving status of a target train group in one embodiment;

[0063] Figure 9 This is a structural block diagram of a vehicle status determination device in one embodiment;

[0064] Figure 10 This is an internal structural diagram of a computer device in one embodiment;

[0065] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0066] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0067] The driving status determination method provided in this application embodiment can be applied to, for example, Figure 1 The application environment shown. For example... Figure 1 As shown, terminal 102 acquires following data of the target vehicle cluster, including following duration and following distance; based on the following data, it clusters the target vehicle cluster to generate clustered vehicle groups, and identifies the target vehicle group from the clustered vehicle groups; it acquires adjacent traffic flow information of adjacent lanes in the same direction of the target vehicle group; it acquires target vehicle light information of the target vehicle group, and determines the parking intention information of the target vehicle group based on the target vehicle light information; it acquires the target traffic light status of the road where the target vehicle group is located; and it determines the driving status of the target vehicle group based on adjacent traffic flow information, parking intention information, and target traffic light status. Terminal 102 may specifically include, but is not limited to, at least one of various personal computers, laptops, smartphones, tablets, and computer devices deployed in vehicles.

[0068] In one embodiment, such as Figure 2 As shown, a method for determining vehicle status is provided, which is then applied to... Figure 1 Taking computer device 102 as an example, the following steps are included:

[0069] Step S202: Obtain vehicle following data of the target vehicle cluster, including following duration and following distance.

[0070] Among them, the following data is used to characterize the following driving characteristics between two vehicles in the same direction lane. It can characterize the similarity of the two vehicles in terms of motion behavior. For example, when the following duration and following distance in the following data of two cars in the same direction lane are greater than a preset threshold, it can indicate that the two cars have motion similarity represented by the preset threshold and belong to the "following state" in driving behavior. The following duration represents the length of time that the two cars meet the "following state" in terms of motion characteristics, and the following distance represents the distance traveled by the two cars under the condition that the motion characteristics meet the "following state".

[0071] Step S204: Based on the vehicle following data, cluster the target vehicle cluster to generate clustered vehicle groups, and determine the target vehicle group from the clustered vehicle groups.

[0072] Among them, a clustered vehicle group is a set containing at least one car. It is a group of cars in the target vehicle cluster that are divided according to having the same motion characteristics. The target vehicle group is one of the clustered vehicle groups.

[0073] Specifically, after the computer equipment acquires the following data between every two cars in the target vehicle cluster, it compares the following data with a preset threshold to determine whether the following data meets the "following state". If the condition is met, the target vehicles corresponding to the following data are clustered into a group of vehicles. The preset threshold can be set based on experience. Alternatively, the degree to which the following data and the target cars meet the "following state" correspondence can be labeled, and then a neural network model can be used to identify the following data to determine what kind of "following state" the target vehicles meet.

[0074] For example, pre-collecting following data between every two cars in the target vehicle cluster, classifying the car "following state" into three levels: "strong following," "moderate following," and "weak following." Using each level and its corresponding following data as training samples, the model is trained by inputting them into a neural network model. Then, the real-time following data collected from the current vehicle is input into the trained neural network model to obtain the following state between each car in the target vehicle cluster. Finally, each car in the target vehicle cluster is clustered according to the "strong following" level to obtain clustered car groups, and the target car group is determined from the clustered car groups.

[0075] Step S206: Obtain the adjacent traffic flow information of the adjacent lanes in the same direction of the target vehicle group.

[0076] The adjacent lanes in the same direction to the target vehicle group refer to the adjacent lanes that have the same direction as the current lane of the target vehicle group. For example, if the current lane of the target vehicle group is a straight lane, then the adjacent lanes in the same direction are straight lanes with the same direction. Traffic flow information includes the vehicle's speed and traffic flow data within a certain period of time.

[0077] Specifically, computer equipment controls the camera or lidar of the image acquisition device to collect traffic flow information of adjacent lanes in the same direction in real time, thus obtaining adjacent traffic flow information.

[0078] Step S208: Obtain the target vehicle light information of the target vehicle group, and determine the parking intention information of the target vehicle group based on the target vehicle light information.

[0079] The target vehicle light information includes image information of perceived hazard lights, right turn lights, parking lights, etc.

[0080] Specifically, the computer equipment controls the camera of the image acquisition device to acquire real-time images of all the lights of the target vehicle group, and identifies the position information, color attributes, and flashing frequency of the lights in the image information. Then, it reads a preset light status output correspondence table in the database and matches the identified light position information, color attributes, and flashing frequency in the light status output correspondence table to obtain the corresponding light output status. The light output status includes, for example, left turn intention status, right turn intention status, parking intention status, fault status, and emergency stop status. The light status output correspondence table is a pre-labeled correspondence between the position information, color attributes, and flashing frequency of the lights and the light output status. Based on the acquired light image information, the computer equipment identifies the target light information in the light image information, and then determines whether the target vehicle group has parking intention information based on the target light information and the light status output correspondence table.

[0081] Step S210: Obtain the status of the target traffic lights on the road where the target vehicle group is located.

[0082] The traffic light status indicates the permitted traffic conditions on the road, such as permitted left turn, permitted right turn, permitted straight ahead, prohibited left turn, prohibited right turn, prohibited straight ahead, etc. Permitted left turn means that left turns are allowed on the road at this time.

[0083] Specifically, the computer equipment controls the camera of the image acquisition device to search along the road and acquire environmental image information within a certain preset range around the target vehicle group in real time. When the image information of the traffic lights is acquired, the traffic lights in the image information are identified to generate traffic light information, which includes the color and shape of the traffic lights (such as discs or arrows). The computer equipment then reads the traffic light status correspondence table in the database and matches the traffic light status corresponding to the current traffic light information with the traffic light status correspondence table according to the traffic light information of the lane where the target vehicle group is located.

[0084] Step S212: Determine the driving status of the target vehicle group based on adjacent traffic flow information, parking intention information, and target traffic light status.

[0085] Among them, the driving status indicates the current movement status of the target vehicle group, including normal parking status and abnormal parking status. Normal parking status can be due to waiting for a red light or waiting for traffic congestion, while abnormal parking status can be due to stopping in a state of non-traffic congestion or not waiting for a red light, or a situation with obvious parking intention.

[0086] Specifically, the computer equipment detects the traffic flow in the lane where the target vehicle group is located and the traffic flow in adjacent lanes traveling in the same direction. It combines the parking intention information and the target traffic light status determined in the preceding steps to comprehensively judge the driving status of the target vehicle group. Different priorities can be set for adjacent traffic flow information, parking intention information, and target traffic light status. The driving status of the target vehicle group is then judged according to the priority from high to low. For example, if the priority of parking intention information, target traffic light status, and adjacent traffic flow information is set from high to low, the computer equipment will first determine whether the target vehicle group's parking behavior is abnormal based on the parking intention information. If it is abnormal, it will then determine whether the target vehicle group's parking behavior is abnormal based on the target traffic light status. If it is still abnormal, it will then determine whether the target vehicle group's parking behavior is abnormal based on the adjacent traffic flow information. The system uses traffic flow information to determine whether the target vehicle group's parking behavior is abnormal. If all three priority judgments indicate abnormal parking, the final output is that the target vehicle group is abnormally parked. Additionally, adjacent traffic flow information, parking intention information, and the target traffic light status can be freely combined to comprehensively judge the target vehicle group's driving status. For example, parking intention information combined with the target traffic light status can be used as a primary judgment criterion to determine the target vehicle group's driving status, while parking intention information combined with adjacent traffic flow information can be used as a secondary judgment criterion. Different priorities can be set between the primary and secondary judgment criteria as needed; for example, the priority of the primary judgment criterion can be set higher than that of the secondary judgment criterion, or vice versa.

[0087] The above-mentioned driving status determination method obtains the following data of the target vehicle cluster, then groups the vehicles in the target vehicle cluster into clustered vehicle groups based on the following data between vehicles in the same lane, and then identifies the target vehicle group in the clustered vehicle groups. Next, it extracts the adjacent traffic flow information of the adjacent lanes in the same direction near the target vehicle group. The adjacent traffic flow information includes the vehicle speed and traffic flow information of vehicles in adjacent lanes. Then, it obtains the target vehicle light information of the target vehicle group in real time, determines the parking intention information of the target vehicle group based on the target vehicle light information, obtains the target traffic light status of the road where the target vehicle group is located, and finally determines the driving status of the target vehicle group by comprehensively considering the adjacent traffic flow information, parking intention information, and target traffic light status. In this way, by clustering target vehicles into complete vehicle groups and extracting information about the surrounding environment of the vehicle groups, the driving status of the target vehicle groups is finally analyzed based on preset logic. Compared with the traditional method of judging the driving status of target vehicles by using a preset behavior database, this method does not rely on preset traffic scene data to judge the driving status. It solves the defect of the preset behavior database being prone to misjudgment in unfamiliar new traffic scenes due to the limitation of data volume, and effectively improves the accuracy of vehicle behavior judgment.

[0088] In one embodiment, such as Figure 3 As shown, before obtaining the vehicle-following data of the target vehicle cluster, the following steps are also included:

[0089] Step S302: Obtain the current distance between the first target vehicle and the second target vehicle in the target vehicle cluster.

[0090] The current distance represents the distance between the first target vehicle and the second target vehicle when it is first acquired.

[0091] Specifically, the computer equipment controls the ranging sensor equipment to detect the distance between the first target vehicle and the second target vehicle in real time. The ranging sensor equipment can be an ultrasonic ranging sensor, a laser ranging sensor, an infrared ranging sensor, etc., and there are no restrictions here.

[0092] Step S304: Obtain the first vehicle speed of the first target vehicle and the second vehicle speed of the second target vehicle.

[0093] Specifically, the computer equipment controls the speed measuring device to detect the speeds of the first target vehicle and the second target vehicle in real time to obtain the speeds of the first vehicle and the second vehicle, respectively. The speed measuring device can be a photoelectric speed sensor, a magnetoelectric speed sensor, a Hall speed sensor, or other speed sensors, and no specific restrictions are imposed here.

[0094] Step S306: Based on the speed of the first vehicle, the speed of the second vehicle, and the current distance, the following time between the first target vehicle and the second target vehicle is obtained.

[0095] The following time refers to the duration during which the first target vehicle and the second target vehicle meet the preset "following state". The "following state" of the first target vehicle and the second target vehicle is the motion state when the first target vehicle and the second target vehicle keep moving in the same direction and the dynamic distance between the two vehicles is less than a preset threshold.

[0096] Specifically, the computer equipment calculates the speed difference between the first target vehicle and the second target vehicle based on the speed of the first vehicle and the speed of the second vehicle. Then, it calculates the real-time dynamic distance between the two vehicles based on the speed difference between the two vehicles and the current distance. When the dynamic distance is less than a preset threshold, it is considered that the first target vehicle and the second target vehicle meet the "following state". Then, it calculates the time elapsed when the first target vehicle and the second target vehicle meet the "following state", that is, the following time.

[0097] Step S308: Obtain the following distance from the following duration and the speed of the first vehicle.

[0098] The following distance is the distance traveled by the first target vehicle and the second target vehicle when they are in the "following state".

[0099] Specifically, the computer equipment controls the speed measuring device to obtain the first vehicle speed of the first target vehicle in real time, then calculates the average vehicle speed within the time period represented by the following time based on the first vehicle speed, and then multiplies the average vehicle speed by the following time to obtain the following distance.

[0100] Step S310: Obtain vehicle following data from following distance and following time.

[0101] In this embodiment, the dynamic distance between the first target vehicle and the second target vehicle is calculated in real time by collecting their speeds and current distances. When the dynamic distance meets the preset conditions, the first target vehicle and the second target vehicle are considered to be in a "following state". The following time and following distance under the "following state" are calculated. The following data is composed of the following time and following distance, so that the following data can more comprehensively reflect the following situation of the two target vehicles over a period of time and improve the reliability of the following data.

[0102] In one embodiment, such as Figure 4 As shown, based on vehicle tracking data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups, including:

[0103] Step S402: Obtain the target vehicle following data of the first target vehicle and the second target vehicle in the target vehicle cluster.

[0104] Step S404: When the target following time of the target vehicle data is greater than or equal to a preset time threshold and the target following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group.

[0105] The preset duration threshold and preset distance threshold can be set based on experience and circumstances. They can be set uniformly regardless of vehicle type, or they can be set specifically for different vehicle types. For example, a first preset distance threshold can be set between small cars, a second preset distance threshold between a small car and a large truck, and a third preset distance threshold between large trucks. Considering that different types of motor vehicles have different tonnage and volume, the required distance and speed will also be different. For example, compared to small cars, large trucks have larger blind spots and greater tonnage, and their inertia is necessarily greater. If the speed of a large truck is too high, it is easy to cause a traffic accident due to insufficient braking. Small cars have smaller tonnage and are less likely to have this problem. Therefore, in actual traffic conditions, the speed of large trucks is lower than that of small cars. Thus, under the same following time, the following distance of large trucks is smaller. Therefore, the first preset distance threshold is set to be greater than the second preset distance threshold, and the second preset distance threshold is set to be greater than the third preset distance threshold.

[0106] In this embodiment, the computer device acquires target vehicle following data of the first and second target vehicles in the target vehicle cluster. The following time and following distance in the following data are compared with preset time thresholds and preset distance thresholds, respectively. When the following data meets the preset conditions, the first and second target vehicles are clustered into a target vehicle group. In this way, vehicles with the same motion characteristics are clustered into a whole of motion research objects, which can effectively offset the uncertainty of upstream data, enhance the richness of target vehicle group motion feature extraction, and improve analysis efficiency and accuracy.

[0107] In one embodiment, such as Figure 5 As shown, when the target vehicle following time is greater than or equal to a preset time threshold and the target vehicle following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group, including:

[0108] Step S502: When the target following time is less than a preset time threshold or the target following distance is less than a preset distance threshold, detect the interval area between the first target vehicle and the second target vehicle.

[0109] The interval area refers to the distance between the first target vehicle and the second target vehicle.

[0110] Specifically, if the computer determines that the target vehicle following time is less than a preset time threshold or the target vehicle following distance is less than a preset distance threshold, it will assume that the first target vehicle and the second target vehicle cannot be directly clustered into a target group. Instead, it will activate the lidar to detect the interval area between the first target vehicle and the second target vehicle. The lidar will detect whether the interval area is an undetectable blind spot. The undetectable blind spot is an area that cannot be illuminated by the laser beam emitted by the current vehicle.

[0111] Step S504: When the detection result of the interval area is a blind zone, obtain the second preset duration threshold and the second preset distance threshold, and use the second preset duration threshold as the preset duration threshold and the second preset distance threshold as the preset distance threshold.

[0112] Step S506, when the target following time of the target following data is greater than or equal to a preset time threshold and the target following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group, wherein the second preset time threshold is less than the preset time threshold and the second preset distance threshold is less than the preset distance threshold.

[0113] Specifically, when the computer device learns that the interval area is a blind spot based on the aforementioned steps, it assumes that there are other vehicles in the blind spot. Then, it obtains a more lenient second threshold condition, making the clustering condition of the first target vehicle and the second target vehicle more lenient. The second threshold condition is then used as a preset threshold condition, and the step of clustering the first target vehicle and the second target vehicle into a target vehicle group is returned when the target following duration of the target following data is greater than or equal to the preset duration threshold and the target following distance is greater than or equal to the preset distance threshold.

[0114] In this embodiment, the computer device detects the interval area between two target vehicles whose target vehicle following data does not meet the preset threshold conditions. When the interval area is an undetectable blind spot, a second preset duration threshold and a second preset distance threshold are obtained. Then, the vehicle following data of the first target vehicle and the second target vehicle are compared with the second preset duration threshold and the second preset distance threshold to complete the clustering of target vehicles. This avoids the situation where target vehicles that should be clustered into one group cannot be clustered into one group due to the existence of blind spots between target vehicles, thereby effectively improving the accuracy of clustering.

[0115] In one embodiment, such as Figure 6 As shown, the method further includes:

[0116] Step S602: Obtain the location information of the target vehicle group. The location information includes the lane information where the target vehicle group is located, the lane width information, and the geometric shape information of the obstacles.

[0117] Among them, obstacle geometry information is the outline information of the obstacle, which is used to characterize the shape category of the obstacle and to identify whether the current obstacle is a car type.

[0118] Specifically, the computer equipment controls the camera of the image acquisition device to acquire the geometric shape information of the obstacle of the target object. When the obstacle is identified as the target vehicle group by the obstacle geometric shape information, the environmental information within a preset range around the target vehicle group is collected to generate location information, including the location information of the lane where the target vehicle group is located and the lane width information.

[0119] Step S604: Determine the parking intention information of the target vehicle group based on the location information.

[0120] Specifically, the computer equipment analyzes the location information of the target vehicle group. When the road width is greater than or equal to the preset width threshold and the target vehicle group is more than 35 centimeters to the right of the center line of the rightmost lane, the current state of the target vehicle group is determined to be a parking state. When the road width is less than the preset width threshold, the type of motor vehicle in the target vehicle group is determined based on the geometric shape information of the obstacle, and the parking intention is determined based on the type of motor vehicle.

[0121] In this embodiment, environmental information around the target vehicle group is collected to obtain information on the road location, lane width, and obstacle geometry of the target vehicle group. This information is then used to determine whether the target vehicle group is in a parking state in the current environment. By utilizing the correlation between the parking state of the target vehicle and specific environmental information, the accuracy of judging the parking intention of the target vehicle group is effectively improved.

[0122] In one embodiment, such as Figure 7 As shown, the driving status of the target vehicle group is determined based on adjacent traffic flow information, parking intention information, and the status of the target traffic light, including:

[0123] Step S702: When the target traffic light is in a prohibited state and the parking intention information is not a parking intention, the first driving state of the target vehicle group is determined to be a normal stop state.

[0124] When the target traffic light is in a state of prohibition, it indicates that the target vehicle group's current parking behavior complies with the current road traffic rules. When there is no intention to park, it indicates that the target vehicle group's parking behavior is a normal driving state in response to the current traffic light instruction. Therefore, the first driving state of the target vehicle group is determined to be the normal stopping state.

[0125] Step S704: When the target traffic light status is "allow to pass" or the parking intention information is "parking intention", the first driving status of the target vehicle group is determined to be "abnormal stop".

[0126] Specifically, the computer equipment senses the status of the target traffic light and the parking intention information of the target vehicle group. When the traffic light status is "allowing passage", it determines that the current parking behavior of the target vehicle group is unreasonable and belongs to an abnormal stop state. Or, when it is determined that the target vehicle group intends to park, it directly determines that the first driving state of the target vehicle group is an abnormal stop state.

[0127] Step S706: When the first driving state is an abnormal stop state, obtain the speed difference between the target vehicle group and the speed of the adjacent traffic flow in the adjacent traffic flow information.

[0128] Specifically, when the computer device determines that the target vehicle group is in an abnormal parking state in the aforementioned step S704, it will obtain the speed difference between the target vehicle group and the adjacent traffic flow in the adjacent traffic flow information.

[0129] Step S708: When the differential speed is less than the preset differential speed threshold and the parking intention information is not a parking intention, the second driving state is determined to be a normal stop state.

[0130] Specifically, the computer equipment senses the parking intention information of the target vehicle group and the speed difference between the target vehicle group and the adjacent traffic flow in real time. When it is sensed that the target vehicle group does not intend to park and the speed difference is less than the preset speed difference threshold, it indicates that the traffic congestion in the lane where the target vehicle group is located is close to the congestion in the adjacent lane in the same direction. This indicates that the stopping behavior of the target vehicle group is caused by the congestion of the entire lane in the same direction, which is a reasonable stop. The driving state of the target vehicle group is determined to be a normal stopping state.

[0131] Step S710: When the differential speed is greater than or equal to the preset differential speed threshold or the parking intention information is a parking intention, the second driving state is determined to be an abnormal stop state.

[0132] Specifically, the computer equipment senses the parking intention information of the target vehicle group and the speed difference between the target vehicle group and the adjacent traffic flow in real time. When the speed difference is sensed to be greater than the preset speed difference threshold, it indicates that the congestion status of the lane where the target vehicle group is located is significantly different from the congestion status of the traffic flow in the adjacent lane in the same direction. Therefore, it can be determined that the current parking behavior of the target vehicle group is not caused by the congestion of the entire lane in the same direction, and the target vehicle group is judged to be in an abnormal stopping state. Alternatively, when the target vehicle group is sensed to be parking, the target vehicle group is directly judged to be in an abnormal stopping state.

[0133] In this embodiment, the parking intention information of the target vehicle group and the corresponding target traffic light status are used as the first judgment basis, and the parking intention information of the target vehicle group and the adjacent traffic flow information are used as the second judgment basis. If the target vehicle group is judged to be in a normal stopping state according to the first judgment basis, the final conclusion is "normal stopping state" and the second judgment basis will not be used again. However, if the target vehicle group is judged to be in an abnormal stopping state according to the first judgment basis, the second judgment basis will be used again. If the second judgment basis determines that the target vehicle group is in a normal stopping state, the final conclusion is "normal stopping state" and if the second judgment basis determines that the target vehicle group is in an abnormal stopping state, the final conclusion is "abnormal stopping state". This realizes the joint judgment of the driving state of the target vehicle group based on multiple environmental factors with priority, which improves the accuracy of the driving judgment of the target vehicle group.

[0134] In one embodiment, such as Figure 8 As shown, the method further includes:

[0135] Step S802: Obtain the distance between the target vehicle group and the current vehicle.

[0136] Specifically, the computer equipment controls the ranging device to measure the distance between the target vehicle group and the current vehicle in real time. The ranging device can be an ultrasonic ranging sensor, a laser ranging sensor, an infrared ranging sensor, or other ranging devices, and no specific restrictions are imposed here.

[0137] Step S804: When the distance is greater than a preset threshold, determine that the current vehicle and the target vehicle group are in a non-associated state.

[0138] Specifically, the computer equipment compares the distance between the target vehicle group and the current vehicle with a preset threshold in real time. When the distance is greater than the preset threshold, it is determined that the target vehicle group is too far from the current vehicle, and the target vehicle group is marked as unrelated or directly identified as a reasonable stopping state.

[0139] In this embodiment, the distance between the target vehicle group and the current vehicle is measured in real time, and then it is determined whether the distance is within a preset threshold range. If the distance exceeds the preset threshold, it is determined to be in a non-associated state or a normal stopped state. This can effectively eliminate redundant vehicle group information with low correlation over long distances, reduce the amount of data calculation, and reduce computational complexity.

[0140] This application also provides an application scenario in which the above-described driving status judgment method is applied.

[0141] Specifically, the application of this vehicle status determination method in this application scenario is as follows:

[0142] The onboard computer monitors real-time following data of the vehicle cluster ahead. Specifically, it measures the current distance between the first and second target vehicles in the cluster using a distance measuring device, and measures the speeds of the first and second target vehicles using a speed measuring device to obtain the speed difference. It then calculates the dynamic distance between the first and second target vehicles in real-time using the speed difference and the current distance, and compares this dynamic distance with a preset threshold. If the dynamic distance is less than the preset threshold, the vehicles are considered to be in a "following state." The system also calculates the following time and duration of the following actions in real-time. The distance traveled during the "following state" is used as the following distance. The following time between the first and second target vehicles is compared to a preset time threshold, and the following distance is compared to a preset distance threshold. If both the following time and distance exceed the preset time threshold, the first and second target vehicles are clustered into one vehicle group, which is then designated as the target vehicle group. If neither the following time nor the following distance meets the criteria for clustering, the current vehicle's LiDAR is used to detect undetectable blind spots between the first and second target vehicles. If an undetectable blind spot exists, the second preset time threshold is used... A second preset distance threshold is used to perform cluster analysis on the first and second target vehicles. When the following time exceeds the second preset time threshold and the following distance exceeds the second preset distance threshold, the first and second target vehicles are clustered into one vehicle group, which is then designated as the target vehicle group. The traffic flow information acquisition device is then used to detect traffic flow information in adjacent lanes in the same direction as the target vehicle group. The camera of the image acquisition device is used to capture real-time images of the target vehicle group's headlights, and the image information is analyzed to determine the target vehicle group's parking intention. Finally, the camera of the image acquisition device is used to capture images of the target traffic lights on the road where the target vehicle group is located, and the image information is analyzed to obtain the target traffic signal information. The system considers the status of traffic lights and uses the target vehicle group's parking intention information and the corresponding target traffic light status as the first criterion, and the target vehicle group's parking intention information and adjacent traffic flow information as the second criterion. If the target vehicle group is judged to be in a normal stopping state according to the first criterion, the final conclusion is "normal stopping state," and the second criterion is not used again. However, if the target vehicle group is judged to be in an abnormal stopping state according to the first criterion, the second criterion is used again. If the second criterion determines that the target vehicle group is in a normal stopping state, the final conclusion is "normal stopping state." If the second criterion determines that the target vehicle group is in an abnormal stopping state, the final conclusion is "abnormal stopping state."

[0143] In this embodiment, the following data of the target vehicle cluster is obtained, and then the vehicles in the target vehicle cluster are grouped according to the following data between vehicles in the same lane in the target vehicle cluster to generate clustered vehicle groups. The target vehicle group is then identified in the clustered vehicle groups. Next, the adjacent traffic flow information of the adjacent lanes in the same direction near the target vehicle group is extracted. The adjacent traffic flow information includes the vehicle speed and traffic flow information of vehicles in adjacent lanes. Then, the target vehicle light information of the target vehicle group is obtained in real time. The parking intention information of the target vehicle group is determined according to the target vehicle light information. Then, the target traffic light status of the road where the target vehicle group is located is obtained. Finally, the driving status of the target vehicle group is determined by comprehensively considering the adjacent traffic flow information, parking intention information and target traffic light status. In this way, by clustering target vehicles into complete vehicle groups and extracting information about the surrounding environment of the vehicle groups, the driving status of the target vehicle groups is finally analyzed based on preset logic. Compared with the traditional method of judging the driving status of target vehicles by using a preset behavior database, this method does not rely on preset traffic scene data to judge the driving status. It solves the defect of the preset behavior database being prone to misjudgment in unfamiliar new traffic scenes due to the limitation of data volume, and effectively improves the accuracy of vehicle behavior judgment.

[0144] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0145] In one embodiment, such as Figure 9 As shown, a vehicle status determination device is provided. This device can be a software module, a hardware module, or a combination of both integrated into a computer device. Specifically, the device includes: a feature extraction module 902 and a determination module 904, wherein:

[0146] The feature extraction module 902 is used to acquire following data of the target vehicle cluster, including following duration and following distance; based on the following data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups; adjacent traffic flow information of adjacent lanes in the same direction of the target vehicle group is acquired; target vehicle light information of the target vehicle group is acquired, and parking intention information of the target vehicle group is determined based on the target vehicle light information; and the status of the target traffic lights on the road where the target vehicle group is located is acquired.

[0147] The judgment module 904 is used to determine the driving status of the target vehicle group based on adjacent traffic flow information, parking intention information, and the status of the target traffic light.

[0148] In one embodiment, the feature extraction module 902 is further configured to obtain the current distance between the first target vehicle and the second target vehicle in the target vehicle cluster; obtain the first vehicle speed of the first target vehicle and the second vehicle speed of the second target vehicle; obtain the following time between the first target vehicle and the second target vehicle based on the first vehicle speed, the second vehicle speed and the current distance; obtain the following distance from the following time and the first vehicle speed; and obtain the following data from the following distance and the following time.

[0149] In one embodiment, the feature extraction module 902 is further configured to acquire target vehicle following data of the first target vehicle and the second target vehicle in the target vehicle cluster; when the target following duration of the target following data is greater than or equal to a preset duration threshold and the target following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group.

[0150] In one embodiment, the feature extraction module 902 is further configured to detect the interval region between the first target vehicle and the second target vehicle when the target following time is less than a preset time threshold or the target following distance is less than a preset distance threshold; when the detection result of the interval region is a blind zone, obtain the second preset time threshold and the second preset distance threshold, use the second preset time threshold as the preset time threshold, and use the second preset distance threshold as the preset distance threshold; return to the step of clustering the first target vehicle and the second target vehicle into a target vehicle group when the target following time of the target following data is greater than or equal to the preset time threshold and the target following distance is greater than or equal to the preset distance threshold, wherein the second preset time threshold is less than the preset time threshold and the second preset distance threshold is less than the preset distance threshold.

[0151] In one embodiment, the feature extraction module 902 is further configured to obtain the location information of the target vehicle group, including the lane information where the target vehicle group is located, the lane width information, and the geometric shape information of the obstacle; and determine the parking intention information of the target vehicle group based on the location information.

[0152] In one embodiment, the determination module 904 is further configured to: determine the first driving state of the target vehicle group as a normal stop state when the target traffic light state is "prohibit passage" and the parking intention information is "not a parking intention"; determine the first driving state of the target vehicle group as an abnormal stop state when the target traffic light state is "allow passage" or the parking intention information is "parking intention"; when the first driving state is an abnormal stop state, obtain the speed difference between the speed of the target vehicle group and the speed of the adjacent traffic flow in the adjacent traffic flow information; when the speed difference is less than a preset speed difference threshold and the parking intention information is "not a parking intention", determine the second driving state as a normal stop state; and when the speed difference is greater than or equal to the preset speed difference threshold or the parking intention information is "parking intention", determine the second driving state as an abnormal stop state.

[0153] In one embodiment, the determination module 904 is further used to obtain the distance between the target vehicle group and the current vehicle; when the distance is greater than a preset threshold, it is determined that the current vehicle and the target vehicle group are in a non-associated state.

[0154] The aforementioned driving status determination device acquires the following data of the target vehicle cluster, then groups the vehicles in the target vehicle cluster into clustered vehicle groups based on the following data between vehicles in the same lane within the target vehicle cluster. The device then identifies the target vehicle group within the clustered vehicle groups, extracts the adjacent traffic flow information of the adjacent lanes in the same direction near the target vehicle group, including the vehicle speed and traffic flow information of vehicles in adjacent lanes, acquires the target vehicle group's target headlight information in real time, determines the target vehicle group's parking intention information based on the target headlight information, acquires the target traffic light status of the road where the target vehicle group is located, and finally determines the driving status of the target vehicle group based on the adjacent traffic flow information, parking intention information, and target traffic light status. In this way, by clustering target vehicles into complete vehicle groups and extracting information about the surrounding environment of the vehicle groups, the driving status of the target vehicle groups is finally analyzed based on preset logic. Compared with the traditional method of judging the driving status of target vehicles by using a preset behavior database, this method does not rely on preset traffic scene data to judge the driving status. It solves the defect of the preset behavior database being prone to misjudgment in unfamiliar new traffic scenes due to the limitation of data volume, and effectively improves the accuracy of vehicle behavior judgment.

[0155] For specific limitations regarding the vehicle status determination device, please refer to the limitations of the vehicle status determination method above, which will not be repeated here. Each module in the aforementioned vehicle status determination device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0156] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as vehicle following data, adjacent traffic flow information, traffic light status, and target vehicle light information. The network interface is used for communication with external terminals via a network connection.

[0157] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for determining vehicle status. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0158] Those skilled in the art will understand that Figure 10 and Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0159] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0160] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0161] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0162] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0163] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method of determining a running state of a vehicle, characterized by, The method includes: Acquire vehicle following data of the target vehicle cluster, including following duration and following distance; Based on the vehicle following data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups; Obtain the adjacent traffic flow information of the adjacent lanes in the same direction of the target vehicle group; Obtain the target vehicle headlight information of the target vehicle group, and determine the parking intention information of the target vehicle group based on the target vehicle headlight information; Obtain the status of the target traffic lights on the road where the target vehicle group is located; The driving status of the target vehicle group is determined based on the adjacent traffic flow information, the parking intention information, and the target traffic light status.

2. The method of claim 1, wherein, Before acquiring the vehicle-following data of the target vehicle cluster, the process also includes: Obtain the current distance between the first target vehicle and the second target vehicle in the target vehicle cluster; Obtain the first vehicle speed of the first target vehicle and the second vehicle speed of the second target vehicle; The following time between the first target vehicle and the second target vehicle is obtained based on the speed of the first vehicle, the speed of the second vehicle, and the current distance. The following distance is obtained by dividing the following duration by the speed of the first vehicle; The following data is obtained from the following distance and the following duration.

3. The method of claim 1, wherein, The step of clustering the target vehicle cluster based on the vehicle following data to generate clustered vehicle groups, and determining the target vehicle group from the clustered vehicle groups, includes: Obtain the target vehicle following data of the first target vehicle and the second target vehicle in the target vehicle cluster; When the target vehicle following time of the target vehicle following data is greater than or equal to a preset time threshold and the target vehicle following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group.

4. The method of claim 3, wherein, When the target vehicle following duration of the target vehicle following data is greater than or equal to a preset duration threshold and the target vehicle following distance is greater than or equal to a preset distance threshold, the first target vehicle and the second target vehicle are clustered into a target vehicle group, including: When the target following time is less than the preset time threshold or the target following distance is less than the preset distance threshold, the interval area between the first target vehicle and the second target vehicle is detected; When the detection result of the interval area is a blind zone, a second preset duration threshold and a second preset distance threshold are obtained, and the second preset duration threshold is used as the preset duration threshold and the second preset distance threshold is used as the preset distance threshold. The step of clustering the first target vehicle and the second target vehicle into a target vehicle group when the target vehicle following time of the target vehicle following data is greater than or equal to a preset time threshold and the target vehicle following distance is greater than or equal to a preset distance threshold is returned. The second preset time threshold is less than the preset time threshold and the second preset distance threshold is less than the preset distance threshold.

5. The method of claim 1, wherein, The method further includes: The location information of the target vehicle group is obtained, including the lane information where the target vehicle group is located, the lane width information, and the geometric shape information of the obstacle; The parking intention information of the target vehicle group is determined based on the location information.

6. The method of claim 1, wherein, Determining the driving status of the target vehicle group based on the adjacent traffic flow information, the parking intention information, and the target traffic light status includes: When the target traffic light is in a state of prohibiting passage and the parking intention information is not a parking intention, the first driving state of the target vehicle group is determined to be a normal stop state. When the target traffic light status is "allowed to pass" or the parking intention information is "parking intention", the first driving status of the target vehicle group is determined to be "abnormal stop". When the first driving state is an abnormal stop state, the speed difference between the target vehicle group and the speed of the adjacent traffic flow in the adjacent traffic flow information is obtained; When the differential speed is less than a preset differential speed threshold and the parking intention information is not a parking intention, the second driving state of the target vehicle group is determined to be a normal stop state. When the differential speed is greater than or equal to the preset differential speed threshold or the parking intention information is a parking intention, the second driving state is determined to be an abnormal stop state.

7. The method of claim 1, wherein, The method further includes: Obtain the distance between the target vehicle group and the current vehicle; When the distance is greater than a preset threshold, the current vehicle and the target vehicle group are determined to be in a non-associated state.

8. A running state determining device characterized by comprising: The device includes: The feature extraction module is used to acquire following data of the target vehicle cluster, including following duration and following distance; based on the following data, the target vehicle cluster is clustered to generate clustered vehicle groups, and the target vehicle group is determined from the clustered vehicle groups; adjacent traffic flow information of adjacent lanes in the same direction of the target vehicle group is acquired; target vehicle light information of the target vehicle group is acquired, and parking intention information of the target vehicle group is determined based on the target vehicle light information; and the status of the target traffic lights on the road where the target vehicle group is located is acquired. The judgment module is used to determine the driving status of the target vehicle group based on the adjacent traffic flow information, the parking intention information, and the target traffic light status. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images