Method and device for determining alternate vehicle behavior, storage medium and electronic device

Abstract

Embodiments of the present application provide a method and device for determining a car-alternating behavior, a storage medium and an electronic device. The method comprises: obtaining a target video, wherein the target video comprises a first vehicle and a second vehicle; determining a first trajectory of the first vehicle and a second trajectory of the second vehicle according to the target video; determining whether the first vehicle triggers each event in a target event set within a first predetermined time period according to the first trajectory and the second trajectory; and determining that the first vehicle has performed a car-alternating behavior in a case where the first vehicle triggers each event in the target event set within the first predetermined time period, wherein the car-alternating behavior is used to represent that the first vehicle has performed a car-alternating operation on the second vehicle. Through the embodiments of the present application, the problem of low accuracy of determining the car-alternating behavior in the related art is solved, and the effect of improving the accuracy of determining the car-alternating behavior is achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of video surveillance technology, and more specifically, to a method, apparatus, storage medium, and electronic device for determining vehicle-cutting behavior. Background Technology

[0002] Video surveillance technology has been widely applied in many fields, and video analysis and processing has become a research hotspot. For example, video analysis can be used to determine whether a vehicle is engaging in targeted behavior, such as illegal lane changes, running red lights, or illegal cutting off other vehicles. Taking the determination of illegal cutting off another vehicle as an example, some related technologies use the vehicle's built-in camera to acquire image information of the vehicle's movement. By analyzing the vehicle's speed, trajectory, and relationship with lane markings, they aim to determine if illegal cutting off has occurred. However, the logic in these technologies is flawed and cannot guarantee that the vehicle has engaged in malicious cutting off; it may simply be a routine lane change. Furthermore, judging violations solely based on the vehicle's current field of vision results in low accuracy. Therefore, the accuracy of detecting illegal cutting off other vehicles in these related technologies is relatively low.

[0003] There is currently no effective solution to the problem of low accuracy in identifying tailgating behavior in related technologies. Summary of the Invention

[0004] This invention provides a method, apparatus, storage medium, and electronic device for determining tailgating behavior, in order to at least solve the problem of low accuracy in determining tailgating behavior in related technologies.

[0005] According to an embodiment of the present invention, a method for determining a vehicle-cutting behavior is provided, comprising: acquiring a target video, wherein the target video includes a first vehicle and a second vehicle; determining a first trajectory of the first vehicle and a second trajectory of the second vehicle based on the target video; determining whether the first vehicle triggers various events in a target event set within a first predetermined duration based on the first trajectory and the second trajectory; and determining that the first vehicle has engaged in the vehicle-cutting behavior if the first vehicle triggers various events in the target event set within the first predetermined duration, wherein the vehicle-cutting behavior indicates that the first vehicle has performed a vehicle-cutting operation on the second vehicle.

[0006] In an exemplary embodiment, determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers a first lane-changing event, an overtaking event, a second lane-changing event, and a deceleration event in chronological order within the first predetermined time period, wherein the first lane-changing event indicates that the first vehicle changes lanes from a first lane to a second lane, the overtaking event indicates that the first vehicle overtakes the second vehicle, the second lane-changing event indicates that the first vehicle changes lanes from the second lane to the first lane, and the target event set includes the first lane-changing event, the overtaking event, the second lane-changing event, and the deceleration event.

[0007] In an exemplary embodiment, determining whether the first vehicle triggers each event in the target event set within a first predetermined duration based on the first trajectory and the second trajectory includes: determining whether the first vehicle sequentially triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event based on the first trajectory and the second trajectory, and determining whether the difference between the fourth end time and the first start time is within the first predetermined duration, wherein the first lane change event indicates that the first vehicle changes lanes from the first lane to the second lane, the overtaking event indicates that the first vehicle overtakes the second vehicle, the second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane, the target event set includes the first lane change event, the overtaking event, the second lane change event, and the deceleration event, the first start time indicates the time when the first vehicle experiences the first lane change event, and the fourth end time indicates the time when the first vehicle experiences the deceleration event.

[0008] In an exemplary embodiment, determining whether the first vehicle sequentially triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event based on the first trajectory and the second trajectory, and determining whether the difference between the fourth end time and the first start time is within a first predetermined duration, includes: if the first vehicle is determined to have triggered the first lane change event based on the first trajectory, determining the first start time and the first end time of the first lane change event based on the first trajectory; if the first vehicle is determined to have triggered the overtaking event after the first end time based on the first trajectory and the second trajectory, determining the second end time of the overtaking event based on the first trajectory and the second trajectory; if the first vehicle is determined to have triggered the second lane change event after the second end time based on the first trajectory, determining the third end time of the second lane change event based on the first trajectory; if the first vehicle is determined to have triggered the deceleration event after the third end time based on the first trajectory, determining the fourth end time of the deceleration event based on the first trajectory; and determining whether the difference between the fourth end time and the first start time is within the first predetermined duration.

[0009] In an exemplary embodiment, determining that the first vehicle has engaged in the lane-blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining that the first vehicle has engaged in the lane-blocking behavior when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration.

[0010] In an exemplary embodiment, determining that the first vehicle has engaged in the lane-blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining whether there are other vehicles within a predetermined range ahead of the first vehicle when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration; and determining that the first vehicle has engaged in the lane-blocking behavior when it is determined that there are no other vehicles within the predetermined range ahead of the first vehicle.

[0011] In an exemplary embodiment, determining that the first vehicle has engaged in the lane-blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining that the first vehicle has engaged in the lane-blocking behavior when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration and the target duration is greater than or equal to the second predetermined duration, wherein the first vehicle continuously engages in the deceleration event between the fourth start time and the fourth end time, and the target duration represents the duration of the first vehicle from the fourth start time to the fourth end time.

[0012] In an exemplary embodiment, determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining, based on a second trajectory, whether the second vehicle has engaged in a third lane-changing event, wherein the third lane-changing event indicates that the second vehicle changes lanes from the first lane to the second lane; determining, if the second vehicle has engaged in the third lane-changing event, a fifth end time of the third lane-changing event; and determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle has engaged in a fourth lane-changing event within a third predetermined duration after the fifth end time, based on the first trajectory, wherein the fourth lane-changing event indicates that the first vehicle changes lanes from the first lane to the second lane.

[0013] In an exemplary embodiment, after determining that the first vehicle has engaged in the lane-changing behavior, the method further includes: sending target notification information, wherein the target notification information is used to indicate that the lane-changing behavior has occurred.

[0014] According to another embodiment of the present invention, a device for determining vehicle-cutting behavior is also provided, comprising: an acquisition module for acquiring a target video, wherein the target video includes a first vehicle and a second vehicle; a first determination module for determining a first trajectory of the first vehicle and a second trajectory of the second vehicle based on the target video; a second determination module for determining whether the first vehicle triggers each event in a target event set within a first predetermined duration based on the first trajectory and the second trajectory; and a third determination module for determining that the first vehicle has engaged in vehicle-cutting behavior if the first vehicle triggers each event in the target event set within the first predetermined duration, wherein the vehicle-cutting behavior indicates that the first vehicle has performed a vehicle-cutting operation on the second vehicle.

[0015] According to yet another embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0016] According to yet another embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0017] This invention acquires a target video, including a first vehicle and a second vehicle, and determines a first trajectory of the first vehicle and a second trajectory of the second vehicle based on the target video. Then, based on the first and second trajectories, it determines whether the first vehicle triggered various events in a target event set within a first predetermined time period. If the first vehicle triggered various events in the target event set within the first predetermined time period, it is determined that the first vehicle engaged in a cutting-off behavior, where cutting-off behavior indicates that the first vehicle performed a cutting-off operation against the second vehicle. In other words, by using the first trajectory of the first vehicle and the second trajectory of the second vehicle, it is determined that the first vehicle engaged in a cutting-off behavior when it is determined that the first vehicle triggered various events in the target event set within a first predetermined time period. This avoids the problem of low accuracy in related technologies that rely solely on image information of the vehicle's movement obtained from its built-in camera to determine whether a cutting-off behavior has occurred. Therefore, it solves the problem of low accuracy in determining cutting-off behavior in related technologies, achieving the effect of improving the accuracy of cutting-off behavior determination. Attached Figure Description

[0018] Figure 1 This is a mobile terminal hardware structure block diagram of the method for determining vehicle-blocking behavior according to an embodiment of the present invention;

[0019] Figure 2 This is a flowchart of a method for determining vehicle-blocking behavior according to an embodiment of the present invention;

[0020] Figure 3 This is an example diagram of vehicle tailgating behavior according to an embodiment of the present invention;

[0021] Figure 4 This is an overall flowchart of the vehicle tailgating behavior detection according to an embodiment of the present invention;

[0022] Figure 5 This is a flowchart of the detection process for tailgating behavior according to an embodiment of the present invention;

[0023] Figure 6 This is a structural block diagram of a device for determining vehicle-blocking behavior according to an embodiment of the present invention. Detailed Implementation

[0024] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0026] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a mobile terminal hardware structure block diagram of the method for determining vehicle-blocking behavior according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0027] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the method for determining vehicle blocking behavior in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0028] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0029] This embodiment provides a method for determining vehicle-cutting behavior. Figure 2 This is a flowchart of a method for determining tailgating behavior according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0030] Step S202: Obtain the target video, wherein the target video includes a first vehicle and a second vehicle;

[0031] Step S204: Determine the first trajectory of the first vehicle and the second trajectory of the second vehicle based on the target video;

[0032] Step S206: Determine whether the first vehicle triggers each event in the target event set within a first predetermined time period based on the first trajectory and the second trajectory;

[0033] Step S208: If the first vehicle triggers each event in the target event set within the first predetermined time period, it is determined that the first vehicle has engaged in a blocking behavior, wherein the blocking behavior indicates that the first vehicle has blocked the second vehicle.

[0034] Through the above steps, by acquiring target video, which includes a first vehicle and a second vehicle, a first trajectory of the first vehicle and a second trajectory of the second vehicle are determined based on the target video. Then, based on the first and second trajectories, it is determined whether the first vehicle triggered any of the events in the target event set within a first predetermined time period. If the first vehicle triggered any of the events in the target event set within the first predetermined time period, it is determined that the first vehicle engaged in a cutting-off behavior, where cutting-off behavior indicates that the first vehicle performed a cutting-off operation against the second vehicle. In other words, by using the first trajectory of the first vehicle and the second trajectory of the second vehicle, if it is determined that the first vehicle triggered any of the events in the target event set within the first predetermined time period, it is determined that the first vehicle engaged in a cutting-off behavior. This avoids the problem of low accuracy in related technologies that rely solely on image information of the vehicle's movement obtained from its built-in camera to determine whether a cutting-off behavior has occurred. Therefore, it solves the problem of low accuracy in determining cutting-off behavior in related technologies, achieving the effect of improving the accuracy of cutting-off behavior determination.

[0035] The entity performing the above steps may be an image processing system, a video surveillance system, a terminal, a processor with human-computer interaction capabilities configured on a storage device, or a processing device or processing unit with similar processing capabilities, but is not limited to these.

[0036] In the above embodiments, a target video is acquired, which includes a first vehicle and a second vehicle. For example, the target video may be a video of a road segment captured by a front-end road camera. Optionally, the target video may include videos captured by one or more road cameras. A first trajectory of the first vehicle and a second trajectory of the second vehicle are determined based on the target video. Trajectory tracking is performed on each vehicle based on the acquired target video. For example, trajectory tracking is performed on the first vehicle to obtain the first trajectory, and trajectory tracking is performed on the second vehicle to obtain the second trajectory. That is, trajectory tracking is performed on each vehicle through the linkage of video streams from one or more cameras, which allows for more accurate perception of traffic flow in each lane on the road. Then, based on the first and second trajectories, it is determined whether the first vehicle triggers any event in the target event set within a first predetermined time period. For example, based on the first and second trajectories, it is determined whether the first vehicle continuously triggers any event within a first predetermined time period (e.g., 1 minute, 2 minutes, or other durations). The system triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event. If both vehicles initially operate in the first lane, the system determines whether the first vehicle changed lanes from the first lane to the second lane based on the first trajectory. Then, it determines whether the first vehicle overtook the second vehicle based on the first and second trajectories. Next, it determines whether the first vehicle triggered a second lane change event (e.g., whether it changed back from the second lane to the first lane) based on the first trajectory. Finally, it determines whether the first vehicle triggered a deceleration event based on the first trajectory. When it is determined that the first vehicle triggered all events in the target event set within a predetermined time period (e.g., 1 minute, 2 minutes, or other durations), meaning the first vehicle consecutively triggered the first lane change event, overtaking event, second lane change event, and deceleration event within the predetermined time period, it can be determined that the first vehicle engaged in a lane-cutting behavior, specifically, a lane-cutting operation against the second vehicle. This avoids the low accuracy problem of methods in related technologies that rely solely on image information from the vehicle's built-in camera to determine whether a lane-cutting behavior has occurred. Therefore, this solves the problem of low accuracy in determining tailgating behavior in related technologies, and achieves the effect of improving the accuracy of tailgating behavior determination.

[0037] In an optional embodiment, determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event in chronological order within the first predetermined time period, wherein the first lane change event indicates that the first vehicle changes lanes from the first lane to the second lane, the overtaking event indicates that the first vehicle overtakes the second vehicle, the second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane, and the target event set includes the first lane change event, the overtaking event, the second lane change event, and the deceleration event. In this embodiment, when the first vehicle triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event in chronological order within a first predetermined time period (such as 1 minute, 2 minutes, or other time periods), it is determined that the first vehicle has engaged in a lane-cutting behavior. For example, if the first vehicle and the second vehicle are both initially in the first lane, it is determined whether the first vehicle changed lanes from the first lane to the second lane based on the first trajectory. Then, it is determined whether the first vehicle overtook the second vehicle from the second lane while the second vehicle was in the first lane based on the first trajectory. Next, it is determined whether the first vehicle triggered a second lane change event based on the first trajectory, such as whether the first vehicle changed back from the second lane to the first lane. Finally, it is determined whether the first vehicle triggered a deceleration event based on the first trajectory. When it is determined that the first vehicle continuously triggers the first lane change event, overtaking event, second lane change event, and deceleration event in chronological order within the first predetermined time period, it can be determined that the first vehicle has engaged in a lane-cutting behavior. In this embodiment, when the first vehicle triggers each event in the target event set within a first predetermined time period based on the first trajectory and the second trajectory, it can be determined that the first vehicle has engaged in a tailgating event against the second vehicle. Compared with related technologies that rely solely on the vehicle's driving trajectory obtained by the camera device carried by the vehicle itself to determine whether a tailgating behavior has occurred, this embodiment can improve the accuracy of tailgating behavior determination.

[0038] In an optional embodiment, determining whether the first vehicle triggers each event in the target event set within a first predetermined duration based on the first trajectory and the second trajectory includes: determining whether the first vehicle sequentially triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event based on the first trajectory and the second trajectory, and determining whether the difference between the fourth end time and the first start time is within the first predetermined duration, wherein the first lane change event indicates that the first vehicle changes lanes from the first lane to the second lane, the overtaking event indicates that the first vehicle overtakes the second vehicle, the second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane, the target event set includes the first lane change event, the overtaking event, the second lane change event, and the deceleration event, the first start time indicates the time when the first vehicle experiences the first lane change event, and the fourth end time indicates the time when the first vehicle experiences the deceleration event. In this embodiment, it can be determined whether the first vehicle sequentially triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event based on the first trajectory and the second trajectory; and a first start time is determined based on the first trajectory, for example, the start time of the first lane change event of the first vehicle; and a fourth end time is determined based on the first trajectory, for example, the end time of the deceleration event of the first vehicle; then it is determined whether the difference between the fourth end time and the first start time is within a first predetermined duration (such as 1 minute, 2 minutes, or other durations). For example, if it is determined that the difference between the fourth end time and the first start time is within the first predetermined duration, it is determined that the first vehicle has engaged in a lane-changing behavior; if it is determined that the difference between the fourth end time and the first start time is greater than the first predetermined duration, it is determined that the first vehicle has not engaged in a lane-changing behavior.

[0039] In an optional embodiment, determining whether the first vehicle sequentially triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event based on the first trajectory and the second trajectory, and determining whether the difference between the fourth end time and the first start time is within a first predetermined duration, includes: if the first vehicle is determined to have triggered the first lane change event based on the first trajectory, determining the first start time and the first end time of the first lane change event based on the first trajectory; if the first vehicle is determined to have triggered the overtaking event after the first end time based on the first trajectory and the second trajectory, determining the second end time of the overtaking event based on the first trajectory and the second trajectory; if the first vehicle is determined to have triggered the second lane change event after the second end time based on the first trajectory, determining the third end time of the second lane change event based on the first trajectory; if the first vehicle is determined to have triggered the deceleration event after the third end time based on the first trajectory, determining the fourth end time of the deceleration event based on the first trajectory; and determining whether the difference between the fourth end time and the first start time is within the first predetermined duration.In this embodiment, when analyzing the aforementioned target video, trajectory tracking is performed on the first vehicle and the second vehicle based on the target video to obtain the first trajectory of the first vehicle and the second trajectory of the second vehicle. When it is determined that the first vehicle has experienced a first lane change event based on the first trajectory, the first start time and the first end time of the first lane change event are determined. For example, if both the first vehicle and the second vehicle are initially in the first lane, the first start time (e.g., 12:00:00) and the first end time (e.g., 12:00:03) of the first vehicle changing lanes from the first lane to the second lane are determined based on the first trajectory. Then, based on the first trajectory and... The second trajectory determines whether the first vehicle overtook the second vehicle after the first end time (e.g., 12:00:03). In practical applications, the image coordinates of the first vehicle at a certain time T1 in the second lane can be determined based on multiple frames contained in the target video. For example, it could be the coordinates of the center point of the first vehicle's detection frame. Similarly, the image coordinates of the second vehicle at time T1 in the first lane can also be determined. When it is determined that the first vehicle overtook the second vehicle, the second end time of the overtaking event can be determined (e.g., 12:00:15), and then the first trajectory can be used to determine whether the first vehicle overtook the second vehicle after the first vehicle's overtaking event. Whether a second lane change event occurs after the second end time (e.g., 12:00:15), for example, whether the first vehicle changes back from the second lane to the first lane. If the first trajectory determines that the first vehicle has engaged in a second lane change event after the second end time, then the third end time of the second lane change event is determined based on the first trajectory (e.g., 12:00:30). Then, based on the first trajectory, it is determined whether the first vehicle has engaged in a deceleration event after the third end time (e.g., 12:00:30). If the first trajectory determines that the first vehicle has engaged in a deceleration event after the third end time, then the first vehicle is considered to have engaged in a second lane change event. When a deceleration event occurs on the road, the fourth end time of the deceleration event for the first vehicle can be determined based on the first trajectory (e.g., 12:00:40). Then, based on the first start time (e.g., 12:00:00) and the fourth end time (e.g., 12:00:40), it can be determined whether the first vehicle triggered each event in the target event set within a first predetermined duration. For example, if the difference between the fourth end time and the first start time is 40 seconds, and the preset first predetermined duration is 1 minute (or other duration), then it means that the first vehicle triggered each event in the target event set within the first predetermined duration. Through this embodiment, the purpose of determining whether the first vehicle sequentially triggered each event in the target event set within a first predetermined duration based on the first trajectory and the second trajectory is achieved.

[0040] In an optional embodiment, determining that the first vehicle has engaged in the lane-blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining that the first vehicle has engaged in the lane-blocking behavior when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration. In this embodiment, when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration, it can be determined that the first vehicle has engaged in the lane-blocking behavior, i.e., it is considered that the first vehicle has performed a lane-blocking operation against the second vehicle. The first predetermined duration is settable, and in practical applications, it can be flexibly set according to the specific conditions of different regions or road sections.

[0041] In an optional embodiment, determining that the first vehicle has engaged in the lane-blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining whether there are other vehicles within a predetermined range ahead of the first vehicle when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration; and determining that the first vehicle has engaged in the lane-blocking behavior when it is determined that there are no other vehicles within the predetermined range ahead of the first vehicle. Optionally, when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration, i.e., when it is determined that the first vehicle has triggered each event in the target event set within the first predetermined duration, it can be further determined whether there are other vehicles within a predetermined range in front of the first vehicle. For example, the predetermined range is 10m (or 20m, or 50m, or others). When it is determined that there are no other vehicles within the predetermined range in front of the first vehicle, it is determined that the first vehicle has engaged in a cutting-off behavior. That is, there are no other vehicles within the predetermined range in front of the first vehicle. At this time, the deceleration event triggered by the first vehicle is likely an intentional cutting-off behavior. Therefore, it can be further determined that the first vehicle has engaged in a cutting-off behavior. Through this embodiment, the accuracy of determining the cutting-off behavior can be further improved.

[0042] In an optional embodiment, determining that the first vehicle has engaged in the lane-blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining that the first vehicle has engaged in the lane-blocking behavior when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration and the target duration is greater than or equal to the second predetermined duration, wherein the first vehicle continuously engages in the deceleration event between the fourth start time and the fourth end time, and the target duration represents the duration of the first vehicle from the fourth start time to the fourth end time. In this embodiment, optionally, when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration, i.e., when it is determined that the first vehicle triggered each event in the target event set within the first predetermined duration, it can be further determined whether the target duration is greater than or equal to the second predetermined duration. The target duration refers to the duration during which the first vehicle continuously decelerates. For example, if the first vehicle decelerates continuously from 12:00:32 to 12:00:40, assuming the predetermined second predetermined duration is 5 seconds, and the target duration is 8 seconds, then it can be determined that the target duration is greater than or equal to the second predetermined duration. This further confirms that the first vehicle has engaged in lane-cutting behavior. That is, if the first vehicle changes back from the second lane to the first lane and continuously triggers deceleration events in front of the second vehicle for a sufficiently long time, it can more accurately determine that the first vehicle has engaged in lane-cutting behavior. Through this embodiment, the accuracy of determining lane-cutting behavior can be further improved.

[0043] In an optional embodiment, determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined duration includes: determining, based on a second trajectory, whether the second vehicle has engaged in a third lane-changing event, wherein the third lane-changing event indicates that the second vehicle changes lanes from the first lane to the second lane; determining, if the second vehicle has engaged in the third lane-changing event, a fifth end time for the third lane-changing event; and determining that the first vehicle has engaged in the lane-changing behavior when, based on the first trajectory, the first vehicle has engaged in a fourth lane-changing event within a third predetermined duration after the fifth end time. Optionally, when it is determined that the first vehicle has triggered each event in the target event set within the first predetermined time period, it can also be determined whether the second vehicle has experienced a third lane change event based on the second trajectory. In practical applications, users can set whether to track the lane change of the following vehicle (corresponding to the second vehicle mentioned above) as needed. This option is configurable. For example, in order to more accurately determine whether a tailgating or two-vehicle road rage has occurred, the user can choose to continue tracking the lane change of the following vehicle, that is, to determine whether the second vehicle has changed lanes from the original first lane to the second lane. When it is determined that the second vehicle has experienced a third lane change event, the fifth end time (e.g., 12:00:50) of the third lane change event of the second vehicle is determined based on the second trajectory. Then, based on the first trajectory, it is determined whether the first vehicle has experienced a fourth lane change event within the third predetermined time period (e.g., 5s or 10s or other durations) after the fifth end time (e.g., 12:00:50), that is, to determine whether the first vehicle and the second vehicle changed lanes synchronously (with a short time interval). When it is determined that the first vehicle has experienced a fourth lane change event within the third predetermined time period, it can be further determined that the first vehicle has engaged in tailgating behavior. This embodiment can further improve the accuracy of identifying tailgating behavior.

[0044] In an optional embodiment, after determining that the first vehicle has engaged in the lane-cutting behavior, the method further includes: sending a target notification message, wherein the target notification message is used to indicate that the lane-cutting behavior has occurred. In this embodiment, after the monitoring system determines that the first vehicle has engaged in lane-cutting behavior based on video analysis, it can send a target notification message, for example, to relevant departments or platforms. Optionally, in practical applications, the time period of the lane-cutting behavior, the video file, and the captured screenshots of the relevant vehicles can be saved so that relevant departments can directly view and process them. Through this embodiment, the purpose of issuing timely notification messages for lane-cutting behavior is achieved.

[0045] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. The present invention will be specifically described below with reference to the embodiments.

[0046] Figure 3 This is an example diagram of vehicle tailgating behavior according to an embodiment of the present invention. The embodiment of the present invention addresses... Figure 3 The detection of vehicles deliberately cutting off other vehicles is applicable to situations where cars are the main mode of transportation and the camera can monitor most road sections.

[0047] right Figure 3 To briefly describe the incident: In the diagram, vehicle ID 1 (corresponding to the first vehicle mentioned above) was originally following vehicle 2 (i.e., vehicle ID 2). It first changed lanes (corresponding to the first lane change event mentioned above), accelerated, overtook vehicle 2 (corresponding to the second vehicle mentioned above), and then changed lanes again (corresponding to the second lane change event mentioned above). It slowed down by braking in front of vehicle 2, and there were no vehicles on the road in front of vehicle 1.

[0048] Figure 4 This is an overall flowchart of the vehicle tailgating behavior detection according to an embodiment of the present invention. The process includes:

[0049] S402, Access to video from multiple road cameras (corresponding to the aforementioned target video); that is, first access the video streams from cameras deployed on the road;

[0050] S404, Vehicle trajectory (including the aforementioned first trajectory and second trajectory) tracking, that is, tracking the trajectory of all vehicles in the video; this step can be performed by the vehicle trajectory tracking module.

[0051] S406 utilizes video analytics to detect vehicle acceleration, lane change, and deceleration events; this step can be executed by the traffic incident detection module.

[0052] S408, For vehicles that continuously trigger the above events, the vehicle malicious cutting-off logic judgment module is sent to perform cutting-off judgment; this step can be executed by the vehicle cutting-off logic judgment module.

[0053] S410, after confirming that a vehicle-cutting event has occurred (corresponding to the aforementioned confirmation that the first vehicle has cut off another vehicle), generate a captured image and related video recordings for a period of time before and after the alarm; this step can be executed by the vehicle-cutting event alarm and recording module.

[0054] The detection process of tailgating behavior according to an embodiment of the present invention will be described in detail below.

[0055] Figure 5 This is a flowchart of the detection process for tailgating behavior according to an embodiment of the present invention. The process includes:

[0056] S502, vehicle tracking; for example, using Figure 3 Taking the tracking of vehicles with IDs marked 1 and 2 as an example;

[0057] S504, when a vehicle (such as a vehicle with ID 1) changes lanes, the changed lane number is recorded; for example... Figure 3 The first lane change was from lane 2 to lane 1;

[0058] S506, the vehicle accelerates and overtakes the vehicle in front in its original lane (such as the vehicle with ID mark 2);

[0059] S508, the vehicle changed lanes again and then returned to its original lane; Figure 3 The second lane change was from lane 1 to lane 2;

[0060] S510, Vehicle deceleration event detection: If the vehicle decelerates significantly, proceed to step S512.

[0061] S512 determines whether there is a vehicle in close proximity to the target vehicle in the lane; the close proximity can be defined as needed, such as 10-20m, 20-50m, or other distances;

[0062] S514, when the judgment result of the above step S512 is that there is no vehicle in close proximity to the target vehicle, determine whether the deceleration duration exceeds a set value; for example, the set value is 1 minute, or 2 minutes, or other time.

[0063] If the judgment result of step S514 is negative, it is considered that no vehicle cutting off has occurred. At this time, the tracking will continue until the vehicle leaves the road section.

[0064] S516, If the judgment result of the above step S514 is yes, further determine whether it is necessary to track the lane change situation of the following vehicle;

[0065] In practical applications, whether or not to track the lane change of the following vehicle is an optional configuration; if this option is not configured, that is, it is not necessary to track the lane change of the following vehicle, then it can be determined that the vehicle (such as the vehicle with ID marked as 1 above) has caused a blocking event.

[0066] S518, if the judgment result of the above step S516 is yes, further determine whether the following vehicle (such as the vehicle with ID mark 2 above) has changed lanes;

[0067] If the judgment result of step S518 is negative, it is considered that no vehicle cutting off has occurred. At this time, the tracking will continue until the vehicle leaves the road section.

[0068] S520, if the judgment result of the above step S518 is yes, further determine whether the target vehicle (corresponding to the vehicle with ID marked as 1) changes lanes synchronously;

[0069] If the judgment result of step S520 is negative, it is assumed that no vehicle cutting off has occurred. In this case, the tracking will continue until the vehicle leaves the road section.

[0070] S522, if the judgment result of the above step S520 is yes, it can be determined that the target vehicle has caused a vehicle blocking event.

[0071] Optionally, if the judgment result of step S512 is that there is a vehicle close in front of the target vehicle, step S516 can be entered, that is, to determine whether it is necessary to follow the vehicle behind to change lanes. If it is not necessary to follow the vehicle behind to change lanes, that is, if the tracking of the vehicle behind to change lanes is not activated and there is a vehicle close in front of the target vehicle, it can be considered as normal deceleration and no blocking incident has occurred.

[0072] Optionally, after executing the above steps S512-S516, if the judgment result of step S516 is negative, that is, if the tracking of the following vehicle changing lanes is not enabled, there is no vehicle in close proximity to the target vehicle, and the deceleration duration exceeds the set value, then the target vehicle can be considered to have caused a blocking event.

[0073] The functions of some of the modules involved in this embodiment will be described below.

[0074] Traffic incident detection module: When a vehicle changes lanes, the lane change is recorded and sent to the vehicle acceleration event detection module for continued tracking. If the target vehicle continues to trigger acceleration events and overtakes the vehicle in front in its original lane, it is sent to the vehicle lane change event detection module for continued tracking. If the target vehicle continues to trigger lane changes and returns to its original lane, it is sent to the vehicle deceleration event detection module for continued tracking. If the vehicle then triggers a deceleration event, it is sent to the vehicle lane departure logic judgment module for evaluation.

[0075] The operations performed by the traffic incident detection module correspond to steps S502-S510 above.

[0076] The lane-keeping logic judgment module first determines whether there are any vehicles in close proximity ahead of the target vehicle in its lane. If no vehicles are present, it further determines whether the duration of the target vehicle's deceleration event exceeds a threshold. If the threshold is exceeded, it is preliminarily identified as a lane-keeping event. At this point, depending on whether follower lane change tracking is enabled, two scenarios are considered. Otherwise, it is assumed that no lane-keeping event has occurred.

[0077] If the following vehicle lane change tracking function is enabled, further judgment is required on the tailgating incident. It is necessary to continue observing whether the following vehicle changes lanes, and simultaneously determine whether the target vehicle changes lanes synchronously; only when both conditions are met is a tailgating incident considered to have occurred.

[0078] If the following vehicle lane change tracking function is not enabled, it is assumed that a malicious lane-changing incident has occurred.

[0079] The operation performed by the vehicle blocking logic judgment module corresponds to steps S512-S522 above.

[0080] In the above embodiments, a method is provided to acquire road conditions through multi-camera linkage, detect traffic events caused by vehicles through video analysis, and determine malicious cutting off of vehicles by combining road conditions. This method tracks all vehicles observed on the road and improves the accuracy of vehicle cutting off detection through traffic event analysis. At the same time, since the cameras are connected to the regulatory department, alarm recordings and images can be saved and transmitted to regulatory personnel for confirmation in a timely and convenient manner.

[0081] Compared with related technologies, the embodiments of the present invention have the following advantages: 1) The embodiments of the present invention use multi-camera video stream linkage on the road to track the trajectory of each vehicle, thereby more accurately perceiving the traffic flow situation in each lane on the road; 2) Through video analysis technology, traffic events performed by vehicles are identified, and targets that continuously trigger vehicle lane change, vehicle acceleration, and braking deceleration events are further judged by vehicle cutting-off logic, improving the accuracy of vehicle malicious cutting-off detection; 3) For the time period when an alarm event occurs, video files and screenshots before and after the alarm are generated in a timely manner, which can be directly viewed and processed by regulatory authorities.

[0082] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0083] This embodiment also provides a device for determining vehicle-cutting behavior. Figure 6 This is a structural block diagram of a device for determining vehicle-blocking behavior according to an embodiment of the present invention, such as... Figure 6 As shown, the device includes:

[0084] Acquisition module 602 is used to acquire target video, wherein the target video includes a first vehicle and a second vehicle;

[0085] The first determining module 604 is used to determine the first trajectory of the first vehicle and the second trajectory of the second vehicle based on the target video.

[0086] The second determining module 606 is used to determine, based on the first trajectory and the second trajectory, whether the first vehicle triggers each event in the target event set within a first predetermined time period;

[0087] The third determining module 608 is used to determine that the first vehicle has performed the blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined time period, wherein the blocking behavior indicates that the first vehicle has blocked the second vehicle.

[0088] In an optional embodiment, the third determining module 608 includes: a first determining unit, configured to determine that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers a first lane-changing event, an overtaking event, a second lane-changing event, and a deceleration event in chronological order within the first predetermined time period, wherein the first lane-changing event indicates that the first vehicle changes lanes from the first lane to the second lane, the overtaking event indicates that the first vehicle overtakes the second vehicle, the second lane-changing event indicates that the first vehicle changes lanes from the second lane to the first lane, and the target event set includes the first lane-changing event, the overtaking event, the second lane-changing event, and the deceleration event.

[0089] In an optional embodiment, the second determining module 606 includes: a second determining unit, configured to determine whether the first vehicle sequentially triggers a first lane change event, an overtaking event, a second lane change event, and a deceleration event based on the first trajectory and the second trajectory, and to determine whether the difference between the fourth end time and the first start time is within the first predetermined duration, wherein the first lane change event indicates that the first vehicle changes lanes from the first lane to the second lane, the overtaking event indicates that the first vehicle overtakes the second vehicle, the second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane, the target event set includes the first lane change event, the overtaking event, the second lane change event, and the deceleration event, the first start time indicates the time when the first vehicle experiences the first lane change event, and the fourth end time indicates the time when the first vehicle experiences the deceleration event.

[0090] In an optional embodiment, the second determining unit includes: a first determining subunit, configured to, when a first lane change event is determined based on the first trajectory, determine a first start time and a first end time of the first lane change event, wherein the first lane change event indicates that the first vehicle changes lanes from a first lane to a second lane; a second determining subunit, configured to, when a first overtaking event is determined based on the first trajectory and the second trajectory, determine a second end time of the overtaking event, wherein the overtaking event indicates that the first vehicle overtakes the second vehicle; and a third determining subunit, configured to, when a second lane change event is determined based on the first trajectory and the second trajectory, determine a second end time of the overtaking event, wherein the overtaking event indicates that the first vehicle overtakes the second vehicle; and a third determining subunit, configured to, when a second lane change event is determined based on the first trajectory and the second end time, determine a second lane change event. In the case of a lane change event, a third end time is determined based on the first trajectory when the first vehicle experiences the second lane change event, wherein the second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane; a fourth determining subunit is configured to determine a fourth end time for the first vehicle experiencing the deceleration event based on the first trajectory when the first vehicle experiences a deceleration event after the third end time, wherein the fourth end time indicates the start time of the first vehicle experiencing the deceleration event; a fifth determining subunit is configured to determine, based on the first start time and the fourth end time, whether the first vehicle triggers each event in the target event set within the first predetermined duration, wherein the target event set includes the first lane change event, the overtaking event, the second lane change event, and the deceleration event.

[0091] In an optional embodiment, the third determining module 608 includes a third determining unit, configured to determine that the first vehicle has engaged in the lane-changing behavior when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration.

[0092] In an optional embodiment, the third determining module 608 includes: a fourth determining unit, configured to determine whether there are other vehicles within a predetermined range ahead of the first vehicle when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration; and a fifth determining unit, configured to determine that the first vehicle has engaged in the blocking behavior when it is determined that there are no other vehicles within the predetermined range ahead of the first vehicle.

[0093] In an optional embodiment, the third determining module 608 includes a sixth determining unit, configured to determine that the first vehicle has engaged in the lane-blocking behavior when the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration and the target duration is greater than or equal to the second predetermined duration, wherein the first vehicle continuously engages in the deceleration event between the fourth start time and the fourth end time, and the target duration represents the duration of the first vehicle from the fourth start time to the current time.

[0094] In an optional embodiment, the third determining module 608 includes: a seventh determining unit, configured to determine whether the second vehicle has committed a third lane change event based on a second trajectory when the first vehicle triggers each event in the target event set within a first predetermined duration, wherein the third lane change event indicates that the second vehicle changes lanes from the first lane to the second lane; an eighth determining unit, configured to determine a fifth end time of the third lane change event when the second vehicle has committed the third lane change event; and a ninth determining unit, configured to determine that the first vehicle has committed the lane-changing behavior when the first vehicle has committed a fourth lane change event within a third predetermined duration after the fifth end time based on the first trajectory, wherein the fourth lane change event indicates that the first vehicle changes lanes from the first lane to the second lane.

[0095] In an optional embodiment, the above apparatus further includes: a sending module, configured to send target prompt information after determining that the first vehicle has engaged in the lane-changing behavior, wherein the target prompt information is used to indicate that the lane-changing behavior has occurred.

[0096] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0097] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0098] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0099] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0100] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0101] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0102] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0103] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for determining the act of cutting off another vehicle, characterized in that, include: Acquire a target video, wherein the target video includes a first vehicle and a second vehicle; Determine the first trajectory of the first vehicle and the second trajectory of the second vehicle based on the target video; Based on the first trajectory and the second trajectory, it is determined whether the first vehicle triggers each event in the target event set within a first predetermined time period. The target event set includes a first lane change event, an overtaking event, a second lane change event, and a deceleration event. The first lane change event indicates that the first vehicle changes lanes from the first lane to the second lane. The overtaking event indicates that the first vehicle overtakes the second vehicle. The second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane. If the first vehicle triggers each of the events in the target event set within the first predetermined time period, it is determined that the first vehicle has engaged in a blocking behavior, wherein the blocking behavior indicates that the first vehicle has blocked the second vehicle.

2. The method according to claim 1, characterized in that, Determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: If the first vehicle triggers the first lane change event, the overtaking event, the second lane change event, and the deceleration event in chronological order within the first predetermined time period, it is determined that the first vehicle has engaged in the lane-changing behavior.

3. The method according to claim 1, characterized in that, The step of determining whether the first vehicle triggers any of the events in the target event set within a first predetermined time period based on the first trajectory and the second trajectory includes: Based on the first trajectory and the second trajectory, it is determined whether the first vehicle sequentially triggers the first lane change event, the overtaking event, the second lane change event, and the deceleration event, and whether the difference between the fourth end time and the first start time is within the first predetermined duration, wherein the first start time represents the time when the first vehicle experiences the first lane change event, and the fourth end time represents the end time when the first vehicle experiences the deceleration event.

4. The method according to claim 3, characterized in that, The step of determining whether the first vehicle sequentially triggers the first lane change event, the overtaking event, the second lane change event, and the deceleration event based on the first trajectory and the second trajectory, and determining whether the difference between the fourth end time and the first start time is within the first predetermined duration, includes: If it is determined that the first vehicle has experienced the first lane change event based on the first trajectory, the first start time and the first end time of the first lane change event are determined based on the first trajectory. If it is determined from the first trajectory and the second trajectory that the overtaking event occurred after the first end time, a second end time for the overtaking event of the first vehicle is determined from the first trajectory and the second trajectory. If it is determined from the first trajectory that the first vehicle causes the second lane change event after the second end time, a third end time for the second lane change event of the first vehicle is determined from the first trajectory. If it is determined from the first trajectory that the first vehicle decelerates after the third end time, the fourth end time of the deceleration event of the first vehicle is determined from the first trajectory. Determine whether the difference between the fourth end time and the first start time is within the first predetermined duration.

5. The method according to claim 4, characterized in that, Determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: If the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration, it is determined that the first vehicle has engaged in the lane-changing behavior.

6. The method according to claim 4, characterized in that, Determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: If the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration, it is determined whether there are other vehicles within a predetermined range ahead of the first vehicle. If it is determined that there are no other vehicles within a predetermined range in front of the first vehicle, it is determined that the first vehicle has engaged in the aforementioned lane-changing behavior.

7. The method according to claim 4, characterized in that, Determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: If the difference between the fourth end time and the first start time is less than or equal to the first predetermined duration and the target duration is greater than or equal to the second predetermined duration, it is determined that the first vehicle has engaged in the lane-changing behavior, wherein the first vehicle continuously engages in the deceleration event between the fourth start time and the fourth end time, and the target duration represents the duration of the first vehicle from the fourth start time to the fourth end time.

8. The method according to claim 1, characterized in that, Determining that the first vehicle has engaged in the lane-changing behavior when the first vehicle triggers each event in the target event set within the first predetermined time period includes: If the first vehicle triggers each of the events in the target event set within the first predetermined time period, it is determined whether the second vehicle has a third lane change event based on the second trajectory, wherein the third lane change event indicates that the second vehicle changes lanes from the first lane to the second lane; If it is determined that the third lane change event has occurred in the second vehicle, a fifth end time for the third lane change event in the second vehicle is determined; If, based on the first trajectory, it is determined that the first vehicle has engaged in the lane-changing behavior within a third predetermined time period after the fifth end time, the lane-changing event indicates that the first vehicle changed lanes from the first lane to the second lane.

9. The method according to any one of claims 1 to 8, characterized in that, After determining that the first vehicle has engaged in the lane-changing behavior, the method further includes: Send a target notification message, wherein the target notification message is used to indicate that the vehicle-blocking behavior has occurred.

10. A device for determining vehicle-cutting behavior, characterized in that, include: An acquisition module is used to acquire a target video, wherein the target video includes a first vehicle and a second vehicle; The first determining module is used to determine the first trajectory of the first vehicle and the second trajectory of the second vehicle based on the target video; The second determining module is used to determine whether the first vehicle triggers each event in the target event set within a first predetermined time period based on the first trajectory and the second trajectory. The target event set includes a first lane change event, an overtaking event, a second lane change event, and a deceleration event. The first lane change event indicates that the first vehicle changes lanes from the first lane to the second lane. The overtaking event indicates that the first vehicle overtakes the second vehicle. The second lane change event indicates that the first vehicle changes lanes from the second lane to the first lane. The third determining module is used to determine that the first vehicle has engaged in a blocking behavior when the first vehicle triggers each event in the target event set within the first predetermined time period, wherein the blocking behavior indicates that the first vehicle has blocked the second vehicle.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 9.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 9.

Images