Method and equipment for detecting that target vehicle is cut out of self-lane
By calculating the difference in the lateral distance change of the target vehicle relative to the lane and calculating the cut-out probability, the problem of inaccuracy of the adaptive cruise control system ACC when detecting the target vehicle cutting out of the lane is improved, and the detection capability and safety of the system are improved.
Patent Information
- Application Number
- CN202311781914.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-22
- Publication Date
- 2025-06-24
AI Technical Summary
When selecting the target vehicle, the existing adaptive cruise control system ACC is difficult to accurately detect whether the target vehicle is cut out of the lane, resulting in the system being unable to release the target in time, affecting the driving experience and system safety.
By calculating the lateral distance of the target vehicle with respect to the left/right lane line of the driving lane and its change difference, the accumulated vehicle cut-out probability is calculated, and when the probability is greater than the preset threshold and the overlap between the bounding box of the target vehicle and the driving lane is within the preset range, the target vehicle cut-out from the driving lane is determined.
The camera's detection ability of the target vehicle in the assisted driving system to cut out of the lane is improved, the correct trigger rate of the adaptive cruise control system ACC is enhanced, and product quality, customer satisfaction and system safety are improved.
Smart Images
Figure CN120191370A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of target detection, and more specifically, to a method and device for detecting a target vehicle cutting out of its own lane, a computer-readable storage medium, a computer program product, and an Adaptive Cruise Control (ACC) system. Background Art
[0002] The Adaptive Cruise Control (ACC) system is an extension of the traditional cruise control system. It uses radar sensors or cameras to detect the relative distance between the vehicle in front and the host vehicle, and actively controls the driving speed of the host vehicle to achieve the purpose of automatic following cruise.
[0003] One of the corresponding challenges is to correctly filter out vehicles with a tendency to "cut out" of their own lane when selecting an ACC target vehicle, so as to release the cut-out target in time and the host vehicle can accelerate to obtain a good driving experience. However, there are the following problems that make it difficult to handle the detection related to "cut out": 1) Due to the limitations of the camera product itself, there is sometimes a large error in the relative speed of the detected target; 2) The relative speed of the target vehicle needs to be converted into an absolute speed through the yaw angular velocity of the host vehicle, so it is sensitive to the magnitude of the yaw angle, and there is a certain error in the yaw angle detected by the current sensor, etc.
[0004] The above problems can easily lead to inaccurate detection of a target "cutting out" of its own lane, resulting in the Adaptive Cruise Control (ACC) system not releasing the originally cut-out target in time. Summary of the Invention
[0005] According to one aspect of the present application, there is provided a method for detecting a target vehicle cutting out of its own lane, the method including: determining that the target vehicle is located on the left lane line or the right lane line of its own lane; calculating a lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane and a change difference distBPGap of the lateral distance in the current cycle; calculating an accumulated vehicle cut-out probability based on the change difference distBPGap of the lateral distance; and determining that the target vehicle cuts out of its own lane when the accumulated vehicle cut-out probability is greater than a preset threshold and the overlap degree between the bounding box of the target vehicle and its own lane is within a preset range.
[0006] As a supplement or replacement of the above solution, in the above method, determining that the target vehicle is located on the left lane line or the right lane line of its own lane includes: determining that the target vehicle is located on the left lane line or the right lane line of its own lane based on the relationship between the bounding box of the target vehicle and the left / right lane line of its own lane.
[0007] As a supplement or replacement for the above solution, in the above method, calculating the lateral distance distBP of the target vehicle relative to the left / right lane line of the self-lane in the current cycle and the change difference distBPGap of the lateral distance includes: calculating the lateral distance distBP of the target vehicle relative to the left / right lane line of the self-lane in the current cycle; calculating the change difference distBPGap between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle; and storing the change difference distBPGap in a first list distBPGapList with a first capacity.
[0008] As a supplement or replacement for the above solution, in the above method, calculating the cumulative vehicle cut-out probability based on the change difference distBPGap of the lateral distance includes: when the first list distBPGapList is full, calculating the average value of the change differences distBPGap in the first list distBPGapList; storing the average value of the change differences distBPGap in a second list distBPGapMeanList with a second capacity; when the second list distBPGapMeanList is full, traversing each average value of the change differences distBPGap in the second list distBPGapMeanList and determining the corresponding cut-out probability using each average value of the change differences distBPGap; and accumulating the corresponding cut-out probabilities to obtain the cumulative vehicle cut-out probability.
[0009] As a supplement or replacement for the above solution, in the above method, the first capacity is 5, and the second capacity is 8.
[0010] As a supplement or replacement for the above solution, in the above method, calculating the cumulative vehicle cut-out probability based on the change difference distBPGap of the lateral distance further includes: when the first list distBPGapList is full, pushing the latest change difference distBPGap into the first list distBPGapList while deleting the earliest entered change difference distBPGap.
[0011] According to another aspect of the present application, there is provided a device for detecting a target vehicle cutting out of its own lane, the device comprising: a first determination device configured to determine that the target vehicle is located on the left lane line or the right lane line of its own lane; a first calculation device configured to calculate a lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane in the current cycle and a change difference distBPGap of the lateral distance; a second calculation device configured to calculate an accumulated vehicle cut-out probability based on the change difference distBPGap of the lateral distance; and a second determination device configured to determine that the target vehicle cuts out of its own lane when the accumulated vehicle cut-out probability is greater than a preset threshold and the overlap degree between the bounding box of the target vehicle and its own lane is within a preset range.
[0012] As a supplement or replacement to the above solution, in the above device, the first determination device is configured to: determine that the target vehicle is located on the left lane line or the right lane line of its own lane based on the relationship between the bounding box of the target vehicle and the left / right lane line of its own lane.
[0013] As a supplement or replacement to the above solution, in the above device, the first calculation device is configured to: calculate a lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane in the current cycle; calculate a change difference distBPGap between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle; and store the change difference distBPGap in a first list distBPGapList having a first capacity.
[0014] As a supplement or replacement to the above solution, in the above device, the second calculation device is configured to: calculate an average value of the change differences distBPGap in the first list distBPGapList when the first list distBPGapList is full; store the average value of the change differences distBPGap in a second list distBPGapMeanList having a second capacity; traverse each average value of the change differences distBPGap in the second list distBPGapMeanList when the second list distBPGapMeanList is full, and determine a corresponding cut-out probability using each average value of the change differences distBPGap; and accumulate the corresponding cut-out probabilities to obtain the accumulated vehicle cut-out probability.
[0015] As a supplement or replacement to the above solution, in the above device, the first capacity is 5, and the second capacity is 8.
[0016] As a supplement or replacement to the above solution, in the above device, the second computing device is further configured to: when the first list distBPGapList is full, push the latest change difference distBPGap into the first list distBPGapList while deleting the earliest entered change difference distBPGap.
[0017] According to another aspect of the present application, there is provided a computer-readable storage medium, the medium including instructions that, when running, execute the method as described above.
[0018] According to another aspect of the present application, there is provided a computer program product, including a computer program that, when executed by a processor, implements the method as described above.
[0019] According to another aspect of the present application, there is provided an adaptive cruise control system ACC, the adaptive cruise control system ACC including the device as described above.
[0020] In the detection solution for the target vehicle to cut out of its own lane in the embodiment of the present application, when it is determined that the target vehicle is located on the left lane line or the right lane line of its own lane, the lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane and the change difference distBPGap of the lateral distance are calculated in the current cycle, and the cumulative vehicle cut-out probability is calculated based on the calculated change difference distBPGap of the lateral distance. When the cumulative vehicle cut-out probability is greater than a preset threshold (for example, 1), and the overlap degree between the bounding box of the target vehicle and its own lane is within a preset range (for example, greater than 0 and less than 0.6), it is determined that the target vehicle has cut out of its own lane. The above detection solution can greatly improve the detection ability of the camera in the assisted driving system to detect that the target vehicle "cuts out" of its own lane, improve the correct trigger rate of the adaptive cruise control system ACC, and enhance the product quality, customer satisfaction, and system safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] From the following detailed description in conjunction with the drawings, the above and other objects and advantages of the present application will become more completely clear, wherein the same or similar elements are denoted by the same reference numerals.
[0022] Figure 1 The flowchart shows a method for detecting a target vehicle cutting out of its own lane according to an embodiment of the present application;
[0023] Figure 2 The structural diagram shows a device for detecting a target vehicle cutting out of its own lane according to an embodiment of the present application;
[0024] Figure 3 and Figure 4The schematic diagram of a scenario where a target vehicle is located on the left or right lane line of its own lane according to an embodiment of the present application is shown;
[0025] Figure 5 The schematic flowchart of a method for detecting that a target vehicle cuts out of its own lane according to an embodiment of the present application is shown;
[0026] Figure 6 The schematic diagram of the detection principle of the lateral distance of a target vehicle relative to the left / right lane line of its own lane according to an embodiment of the present application is shown; and
[0027] Figure 7 The schematic diagram of a cumulative function for calculating the vehicle cut-out probability according to an embodiment of the present application is shown. Detailed implementation manners
[0028] Hereinafter, the detection scheme for a target vehicle to cut out of its own lane according to each exemplary embodiment of the present application will be described in detail with reference to the accompanying drawings.
[0029] Figure 1 The schematic flowchart of a method 1000 for detecting that a target vehicle cuts out of its own lane according to an embodiment of the present application is shown. As Figure 1 shown, the method 1000 for detecting that a target vehicle cuts out of its own lane includes the following steps:
[0030] In step S110, it is determined that the target vehicle is located on the left or right lane line of its own lane;
[0031] In step S120, the lateral distance distBP of the target vehicle relative to the left / right lane line of the own lane and the change difference distBPGap of the lateral distance in the current cycle are calculated;
[0032] In step S130, the cumulative vehicle cut-out probability is calculated based on the change difference distBPGap of the lateral distance; and
[0033] In step S140, when the cumulative vehicle cut-out probability is greater than a preset threshold and the overlap degree between the bounding box of the target vehicle and the own lane is within a preset range, it is determined that the target vehicle cuts out of its own lane.
[0034] In the context of the present application, a "target vehicle" refers to a moving vehicle in front of the host vehicle selected by an Adaptive Cruise Control (ACC) system. Generally speaking, the ACC system can select a moving vehicle in front of the host vehicle as the primary target (i.e., the "target vehicle") and control the longitudinal motion state and following distance of the host vehicle in real time and comfortably according to the motion state of this primary target. The term "Adaptive Cruise Control (ACC) system" is also referred to as the adaptive cruise control function, which sends commands to the actuator based on the driving states of the front target vehicle and the host vehicle (e.g., distance and speed), thereby determining whether to accelerate or decelerate, or to exit the cruise. In some embodiments, when there is a risk of collision, the ACC system will prompt the driver and take active braking intervention. Moreover, when the distance from the vehicle ahead is too small, the ACC system can cooperate with the anti-lock braking system, etc., to appropriately brake the wheels, so as to always maintain a safe distance from the vehicle ahead. Generally speaking, the ACC system can, to a certain extent, reduce the driver's driving fatigue.
[0035] In one or more embodiments, a target vehicle's "cut-out" from a lane means that the target vehicle leaves the lane where the host vehicle is located. When determining that the original target vehicle has "cut out", if the ACC system can promptly release the cut-out target vehicle, it can further improve system safety and customer satisfaction.
[0036] In step S110, it is determined that the target vehicle is located on the left lane line or the right lane line of the host vehicle's lane. In one embodiment, step S110 includes: determining that the target vehicle is located on the left lane line or the right lane line of the host vehicle's lane based on the relationship between the bounding box of the target vehicle and the left / right lane line of the host vehicle's lane. For example, in the camera coordinate system, when the bounding box of the target vehicle intersects with the left lane line of the host vehicle's lane, it is determined that the target vehicle is located on the left lane line of the host vehicle's lane. Another example is that in the camera coordinate system, when the bounding box of the target vehicle intersects with the right lane line of the host vehicle's lane, it is determined that the target vehicle is located on the right lane line of the host vehicle's lane.
[0037] Figure 3 FIG. shows a schematic diagram of a scenario where a target vehicle is located on the left lane line of the host vehicle's lane according to an embodiment of the present application. As Figure 3 shown, the host vehicle 310 is traveling on the host vehicle's lane 330 defined by the left lane line 332 and the right lane line 334, while the target vehicle 320 in front of the host vehicle 310 is traveling on the left lane line 332 (i.e., onLineLeft). Figure 4 FIG. shows a schematic diagram of a scenario where a target vehicle is located on the right lane line of the host vehicle's lane according to an embodiment of the present application. As Figure 4As shown, the vehicle 410 travels on its own lane 430 defined by the left lane line 432 and the right lane line 434, while the target vehicle 420 in front of the vehicle 410 travels on the right lane line 434 (i.e., onLineRight).
[0038] In one embodiment, the cut-out motion relationship of the target vehicle relative to the lane line (e.g., the lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane) is calculated only when the target vehicle is traveling on the lane line (onLineLeft, onLineRight). In other words, in this embodiment, if the target vehicle is not on the lane line, the subsequent method steps for detecting the target vehicle cutting out of its own lane are not executed.
[0039] In step S120, the lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane and the change difference distBPGap of the lateral distance are calculated in the current cycle. In one embodiment, step S120 includes: calculating the lateral distance distBP of the target vehicle relative to the left / right lane line of its own lane in the current cycle; calculating the change difference distBPGap between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle; and storing the change difference distBPGap in a first list distBPGapList having a first capacity.
[0040] In one embodiment, the lateral distance distBP represents the lateral distance of the target vehicle (bounding box) relative to the left lane line and / or the right lane line of its own lane in a certain cycle. For example, when the target vehicle is traveling on the left lane line, the lateral distance between the left side of the bounding box of the target vehicle and the left lane line can be determined as the "lateral distance distBP".
[0041] Figure 6 The detection principle diagram of the lateral distance of the target vehicle relative to the left / right lane line of its own lane is shown. As Figure 6 shown, in the camera coordinate system, 610 represents the position of the camera; 620 represents the upper left vertex of the bounding box of the target object / vehicle; 640 represents the intersection point P_lef'(x', y') of the (bottom side) of the bounding box of the target object / vehicle and the left lane line Pepsilane_left; 645 represents the intersection point P_rig'(x_r', y_r') of the (bottom side) of the bounding box of the target object / vehicle and the right lane line Pepsilane_Right. In the camera coordinates, since the lane line is composed of many discrete image points, thus in Figure 6Among them, the image point 630 and the image point 635 respectively represent the two closest upper and lower points (the bottom edge of) the bounding box of the target object / vehicle, which are P2(x2, y2) and P1(x1, y1) respectively. 650 represents the lateral distance between the upper left vertex 620 of the bounding box of the target object / vehicle and the intersection point P_lef'(x', y') between the (bottom edge of) the bounding box of the target object / vehicle and the left lane line Pepsilane_left. In one embodiment, this lateral distance 650 can be determined as the lateral distance distBP of the target vehicle (bounding box) relative to the left lane line of its own lane.
[0042] In one embodiment, the intersection point P_lef'(x', y') between the (bottom edge of) the bounding box of the target object / vehicle and the left lane line Pepsilane_left can be determined based on both the image point 630 and the image point 635. Additionally, in one or more embodiments, the lateral distance dy and the longitudinal distance dx between the position 610 where the camera is located and the point 640 can be determined as the lateral distance and the longitudinal distance between the host vehicle and the target vehicle for subsequent vehicle control.
[0043] In step S130, the cumulative vehicle cut-out probability is calculated based on the change difference distBPGap of the lateral distance. In one embodiment, step S130 includes: when the first list distBPGapList storing multiple change differences distBPGap (i.e., the change difference between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle) is full, calculating the average value of all the change differences distBPGap in the first list distBPGapList; storing the average value of the change differences distBPGap in the second list distBPGapMeanList with a second capacity; when the second list distBPGapMeanList is full, traversing each average value of the change differences distBPGap in the second list distBPGapMeanList and determining the corresponding cut-out probability using each average value of the change differences distBPGap; and accumulating the corresponding cut-out probabilities to obtain the cumulative vehicle cut-out probability.
[0044] In one or more embodiments, the first capacity of the first list distBPGapList is 5, and the second capacity of the second list distBPGapMeanList is 8. Of course, those skilled in the art can understand that the above first capacity and second capacity are only examples here and not limitations, and the values of the first capacity and the second capacity can be adjusted according to actual needs.
[0045] In one embodiment, a cumulative function can be used to determine the corresponding cut-out probability by using the average value of each change difference distBPGap, and then the cumulative vehicle cut-out probability can be obtained. Figure 7 FIG. shows a schematic diagram of a cumulative function for calculating the vehicle cut-out probability according to an embodiment of the present application. As Figure 7 shown, the cumulative vehicle cut-out probability is initially 0. When the average value of the change difference distBPGap < 0.015, the corresponding cut-out probability is -0.1, and when the average value of the change difference distBPGap is greater than 0.015 but less than 0.025, the corresponding cut-out probability is 0.2, and so on. By accumulating the determined corresponding cut-out probabilities, the cumulative vehicle cut-out probability is finally obtained.
[0046] In one embodiment, step S130 further includes: when the first list distBPGapList is full, while pushing the latest change difference distBPGap into the first list distBPGapList, deleting the earliest entered change difference distBPGap ("first in, first out").
[0047] In step S140, when the cumulative vehicle cut-out probability is greater than a preset threshold and the overlap degree between the bounding box of the target vehicle and the self-lane is within a preset range, it is determined that the target vehicle cuts out of the self-lane. In one embodiment, the overlap degree can be determined according to the ratio of the lateral distance between the host vehicle and the (bounding box of the) target vehicle to the width of the target vehicle.
[0048] In one embodiment, when the cumulative vehicle cut-out probability is greater than or equal to 1 and the overlap degree is greater than 0 but less than 0.6, it is determined that the target vehicle "cuts out" of the self-lane, that is, the subsequent adaptive cruise control system ACC can release the target vehicle in a timely manner.
[0049] Figure 5 FIG. shows a schematic flow diagram of a method for detecting that a target vehicle cuts out of the self-lane according to an embodiment of the present application. As Figure 5As shown, the entire detection process starts at step S510; at step S520, the positional relationship between the bounding box of the target vehicle and the lane lines of its own lane is obtained in the pixel coordinate system / camera coordinate system (i.e., it is determined whether the target vehicle is on the left lane line or the right lane line); at step S530, the lateral distance between the bounding box and the lane line is calculated and defined as distBP; at step S540, the lateral distance difference of distBP between two cycles is calculated, defined as distBPGap, and saved to distBPGapList, whose capacity is 5; at step S550, if the size of distBPGapList reaches 5, the average value of distBPGapList is calculated and saved to distBPGapMeanList, whose capacity is 8 and represents the average distance change over 5 cycles; the earliest value in distBPGapList is deleted and a new value is pushed in; if the size of distBPGapList is less than 5, only the latest value is pushed in. At step S560, if the size of distBPGapMeanList reaches 8, the data in distBPGapMeanList is traversed, and the corresponding cut-out probability of each value is calculated according to the cumulative function and summed to obtain the final cut-out probability; if the size of distBPGapMeanList is less than 8, only the latest value is pushed in. At step S570, it is determined whether the final cut-out probability is greater than or equal to 1.0 and the overlap rate between the target vehicle and its own lane is in the range of (0, 0.6). If so, step S580 is executed to determine that the target vehicle has cut out of its own lane; otherwise, return to step S520 to continue the detection or execute step S590 to determine that the target vehicle has not cut out of its own lane.
[0050] In addition, it is easy for those skilled in the art to understand that the method 1000 for detecting whether a target vehicle cuts out of its own lane provided by one or more of the above embodiments of the present application can be implemented by a computer program. For example, the computer program is included in a computer program product, and when the computer program is executed by a processor, the method 1000 for detecting whether a target vehicle cuts out of its own lane according to one or more embodiments of the present application is implemented. Another example is that when a computer-readable storage medium (such as a USB flash drive) storing the computer program is connected to a computer, running the computer program can execute the method 1000 for detecting whether a target vehicle cuts out of its own lane according to one or more embodiments of the present application.
[0051] Refer to Figure 2 , Figure 2 shows a schematic structural diagram of a device 2000 for detecting whether a target vehicle cuts out of its own lane according to an embodiment of the present application. As Figure 2As shown in the figure, the device 2000 includes: a first determination device 210, a first calculation device 220, a second calculation device 230, and a second determination device 240. Among them, the first determination device 210 is configured to determine that the target vehicle is located on the left lane line or the right lane line of the self-lane; the first calculation device 220 is configured to calculate the lateral distance distBP of the target vehicle relative to the left / right lane line of the self-lane and the change difference distBPGap of the lateral distance in the current cycle; the second calculation device 230 is configured to calculate the cumulative vehicle cut-out probability based on the change difference distBPGap of the lateral distance; and the second determination device 240 is configured to determine that the target vehicle cuts out of the self-lane when the cumulative vehicle cut-out probability is greater than a preset threshold and the overlap degree of the bounding box of the target vehicle and the self-lane is within a preset range.
[0052] In one embodiment, the first determination device 210 is configured to: based on the relationship between the bounding box of the target vehicle and the left / right lane line of the self-lane, determine that the target vehicle is located on the left lane line or the right lane line of the self-lane.
[0053] In one embodiment, the first calculation device 220 is configured to: calculate the lateral distance distBP of the target vehicle relative to the left / right lane line of the self-lane in the current cycle; calculate the change difference distBPGap between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle; and store the change difference distBPGap in a first list distBPGapList having a first capacity (for example, 5).
[0054] In one embodiment, the second calculation device 230 is configured to: when the first list distBPGapList is full, calculate the average value of the change differences distBPGap in the first list distBPGapList; store the average value of the change differences distBPGap in a second list distBPGapMeanList having a second capacity (for example, 8); when the second list distBPGapMeanList is full, traverse each average value of the change differences distBPGap in the second list distBPGapMeanList, and determine the corresponding cut-out probability using each average value of the change differences distBPGap; and accumulate the corresponding cut-out probabilities to obtain the cumulative vehicle cut-out probability.
[0055] In one embodiment, the second computing device 230 is further configured to: when the first list distBPGapList is full, push the latest change difference distBPGap into the first list distBPGapList while deleting the earliest entered change difference distBPGap.
[0056] The above device 2000 for detecting that a target vehicle cuts out of its own lane can be integrated into various types of adaptive cruise control system ACC products.
[0057] In summary, the detection scheme for a target vehicle cutting out of its own lane in the embodiment of the present application calculates the lateral distance distBP of the target vehicle relative to the left / right lane line of the own lane and the change difference distBPGap of the lateral distance in the current cycle when determining that the target vehicle is located on the left lane line or the right lane line of the own lane, and calculates the cumulative vehicle cut-out probability based on the calculated change difference distBPGap of the lateral distance. When the cumulative vehicle cut-out probability is greater than a preset threshold (for example, 1), and the overlap degree between the bounding box of the target vehicle and the own lane is within a preset range (for example, greater than 0 and less than 0.6), it is determined that the target vehicle cuts out of the own lane. The above detection scheme can greatly improve the detection ability of the camera in the assisted driving system for the target vehicle to "cut out" of the own lane, improve the correct trigger rate of the adaptive cruise control system ACC, and enhance the product quality, customer satisfaction and system safety.
[0058] The above examples mainly illustrate the detection scheme for a target vehicle cutting out of its own lane in the embodiment of the present application. Although only some of the embodiments of the present application have been described, those of ordinary skill in the art should understand that the present application can be implemented in many other forms without departing from its gist and scope. Therefore, the examples and embodiments shown are regarded as illustrative rather than restrictive, and the present application may cover various modifications and substitutions without departing from the spirit and scope of the present application as defined by the various claims.
Claims
1. A method for detecting a target vehicle exiting its own lane, characterized in that, The method includes: Determine that the target vehicle is located on the left lane line or the right lane line of the own lane; Calculate the lateral distance distBP of the target vehicle relative to the left / right lane line of the own lane and the change difference distBPGap of the lateral distance in the current cycle; Calculate the cumulative vehicle cut-out probability based on the change difference distBPGap of the lateral distance; and When the cumulative vehicle cut-out probability is greater than a preset threshold and the overlap degree between the bounding box of the target vehicle and the own lane is within a preset range, determine that the target vehicle cuts out of the own lane.
2. The method according to claim 1, wherein Determining that the target vehicle is located on the left lane line or the right lane line of the own lane includes: Based on the relationship between the bounding box of the target vehicle and the left / right lane line of the own lane, determine that the target vehicle is located on the left lane line or the right lane line of the own lane.
3. The method according to claim 1, wherein Calculating the lateral distance distBP of the target vehicle relative to the left / right lane line of the own lane and the change difference distBPGap of the lateral distance in the current cycle includes: Calculate the lateral distance distBP of the target vehicle relative to the left / right lane line of the own lane in the current cycle; Calculate the change difference distBPGap between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle; and Store the change difference distBPGap in a first list distBPGapList with a first capacity.
4. The method according to claim 3, wherein, Calculating the cumulative vehicle cut-out probability based on the change difference distBPGap of the lateral distance includes: When the first list distBPGapList is full, calculate the average value of the change difference distBPGap in the first list distBPGapList; Store the average value of the change difference distBPGap in a second list distBPGapMeanList with a second capacity; When the second list distBPGapMeanList is full, traverse each average value of the change difference distBPGap in the second list distBPGapMeanList, and determine the corresponding cut-out probability using each average value of the change difference distBPGap; and Accumulate the corresponding cut-out probabilities to obtain the cumulative vehicle cut-out probability.
5. The method according to claim 4, wherein, The first capacity is 5, and the second capacity is 8.
6. The method according to claim 4, wherein, Calculating the cumulative vehicle cut-out probability based on the change difference distBPGap of the lateral distance further includes: When the first list distBPGapList is full, push the latest change difference distBPGap into the first list distBPGapList while deleting the earliest entered change difference distBPGap.
7. An apparatus for detecting a target vehicle exiting its own lane, characterized in that, The device includes: A first determination device for determining that the target vehicle is located on the left lane line or the right lane line of the own lane; A first computing device for calculating a lateral distance distBP of the target vehicle relative to the left / right lane line of the self-lane in the current cycle and a change difference distBPGap of the lateral distance; A second computing device for calculating an accumulated vehicle cut-out probability based on the change difference distBPGap of the lateral distance; and A second determining device for determining that the target vehicle cuts out of the self-lane when the accumulated vehicle cut-out probability is greater than a preset threshold and the overlap degree between the bounding box of the target vehicle and the self-lane is within a preset range.
8. The device according to claim 7, wherein, The first determining device is configured to: Determine that the target vehicle is located on the left lane line or the right lane line of the self-lane based on the relationship between the bounding box of the target vehicle and the left / right lane line of the self-lane.
9. The device according to claim 7, wherein, The first computing device is configured to: Calculate a lateral distance distBP of the target vehicle relative to the left / right lane line of the self-lane in the current cycle; Calculate a change difference distBPGap between the lateral distance distBP in the current cycle and the lateral distance distBP in the previous cycle; And Store the change difference distBPGap in a first list distBPGapList having a first capacity.
10. The device according to claim 9, wherein, The second computing device is configured to: Calculate an average value of the change differences distBPGap in the first list distBPGapList when the first list distBPGapList is full; Store the average value of the change differences distBPGap in a second list distBPGapMeanList having a second capacity; When the second list distBPGapMeanList is full, traverse each average value of the change differences distBPGap in the second list distBPGapMeanList and determine a corresponding cut-out probability using each average value of the change differences distBPGap; And Accumulate the corresponding cut-out probabilities to obtain the accumulated vehicle cut-out probability.
11. The device according to claim 10, wherein, The first capacity is 5, and the second capacity is 8.
12. The device according to claim 10, wherein, The second computing device is further configured to: When the first list distBPGapList is full, push the latest change difference distBPGap into the first list distBPGapList while deleting the earliest entered change difference distBPGap.
13. A computer-readable storage medium, characterized in that, The medium includes instructions that, when running, execute the method according to any one of claims 1 to 6.
14. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the method according to any one of claims 1 to 6.
15. An Adaptive Cruise Control System ACC, characterized in that, The adaptive cruise control system ACC includes the device according to any one of claims 7 to 12.