A lane-changing judgment method, device, apparatus and storage medium

Abstract

The application discloses a lane changing judgment method and device, equipment and storage medium, and relates to the technical field of auxiliary driving. The method comprises the following steps: obtaining target parameter information through collected image data; the target parameter information comprises a longitudinal distance between a vehicle and a target vehicle and a longitudinal relative speed between the vehicle and the target vehicle; determining a distance interval corresponding to the vehicle at present according to the longitudinal distance and a distance division rule; the distance interval is determined based on a longitudinal dangerous distance and a longitudinal safe distance of the vehicle at different speeds; determining a corresponding vehicle lane changing judgment rule according to the distance interval corresponding to the vehicle at present, and judging whether the vehicle meets a lane changing condition by using the vehicle lane changing judgment rule and a longitudinal average relative speed corresponding to the vehicle at present. The application can improve the lane changing triggering rate and success rate, and reduce the use cost.

Description

Technical Field

[0001] This invention relates to the field of driver assistance technology, and in particular to a lane change detection method, device, equipment, and storage medium. Background Technology

[0002] Currently, the lane change assist system determines the forward lane change area and, through trajectory planning, switches the vehicle from the lane keeping system to the lane change assist system, controlling the vehicle to change lanes to the adjacent lane. After the lane change is completed, the lane change assist system switches back to the lane keeping system, controlling the vehicle to stay on the center line of the lane, thereby assisting the driver in completing the lane change and reducing driver fatigue.

[0003] In existing technologies, the accuracy of lane change judgment using visual sensors is not high, and the judgment results are relatively absolute, which is not conducive to drivers' use of lane change assistance functions. Current technologies also utilize both visual and radar sensors for lane change judgment, but this increases development costs to some extent. Therefore, how to achieve accurate lane change judgment while saving costs is a pressing technical problem that needs to be solved. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a lane change detection method, apparatus, device, and storage medium, which can improve the lane change trigger rate and success rate, and reduce usage costs. The specific solution is as follows:

[0005] Firstly, this application discloses a lane change determination method, including:

[0006] Target parameter information is obtained from the collected image data; the target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle.

[0007] Based on the longitudinal distance and distance division rules, the current distance interval corresponding to the vehicle is determined; the distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different vehicle speeds;

[0008] The corresponding lane change judgment rule is determined based on the current distance range of the vehicle. The vehicle lane change judgment rule and the current longitudinal average relative speed of the vehicle are used to determine whether the vehicle meets the lane change conditions.

[0009] Optionally, the lane change determination method further includes:

[0010] Select a preset number of newly acquired image frames, obtain the longitudinal relative velocity corresponding to each image frame, and calculate the average longitudinal relative velocity.

[0011] The longitudinal average relative velocity is periodically updated with the preset number of image frames as the period.

[0012] Optionally, the step of determining whether the vehicle meets the lane change conditions using the vehicle lane change judgment rules and the vehicle's current longitudinal average relative speed includes:

[0013] If the vehicle is currently in the first distance interval, it is determined that the vehicle meets the lane change conditions; the first distance interval indicates that the longitudinal distance is greater than the longitudinal safety distance corresponding to the current vehicle speed;

[0014] If the vehicle is currently in the second distance interval, then based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle, it is determined whether the vehicle meets the lane change conditions; the second distance interval indicates that the longitudinal distance is less than the longitudinal safe distance corresponding to the current vehicle speed and greater than the longitudinal danger distance corresponding to the current vehicle speed.

[0015] If the vehicle is currently in the third distance interval, then the vehicle is judged to meet the lane change conditions based on the current longitudinal average relative speed; the third distance interval represents the longitudinal distance being less than the longitudinal danger distance corresponding to the current vehicle speed.

[0016] Optionally, if the vehicle currently corresponds to the third distance interval, determining whether the vehicle meets the lane change conditions based on the vehicle's current longitudinal average relative speed includes:

[0017] Based on the longitudinal average relative speed and the first average speed threshold, it is determined whether the speed of the target vehicle is greater than the speed of the vehicle itself, and whether the relative speed between the two vehicles is greater than the first average speed threshold.

[0018] If so, then the vehicle is deemed to meet the lane change requirements.

[0019] Optionally, if the vehicle is currently in the second distance interval, then based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle, it is determined whether the vehicle meets the lane change conditions, including:

[0020] Based on the longitudinal average relative velocity, determine whether the target vehicle's speed is greater than the vehicle's speed;

[0021] If so, then the vehicle is deemed to meet the lane-changing conditions;

[0022] If not, then determine whether the vehicle meets the lane change conditions based on the actual collision time between the vehicle and the target vehicle and the expected collision time between the vehicle and the target vehicle.

[0023] Optionally, determining whether the vehicle meets the lane-changing conditions based on the actual collision time between the vehicle and the target vehicle and the expected collision time between the vehicle and the target vehicle includes:

[0024] The actual collision time between the vehicle and the target vehicle is determined based on the current longitudinal distance and average longitudinal relative speed of the vehicle.

[0025] Based on the current longitudinal average relative speed of the vehicle and the relationship between the longitudinal relative speed and the expected collision time, the expected collision time between the vehicle and the target vehicle is determined.

[0026] If the actual collision time is greater than the expected collision time, then the vehicle is determined to meet the lane change conditions.

[0027] Optionally, before determining the current distance interval corresponding to the vehicle based on the longitudinal distance and distance division rules, the method further includes:

[0028] Based on the target vehicle information in the target parameter information, determine whether there is a target vehicle in the target lane to be changed to;

[0029] If it exists, then perform the operation of determining the current distance interval of the vehicle based on the longitudinal distance and distance division rules;

[0030] If it does not exist, then the vehicle is deemed to meet the lane change conditions.

[0031] Secondly, this application discloses a lane change detection device, comprising:

[0032] The information acquisition module is used to obtain target parameter information through the collected image data; the target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle.

[0033] The distance interval determination module is used to determine the current distance interval of the vehicle based on the longitudinal distance and the distance division rules; the distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different vehicle speeds;

[0034] The lane change judgment module is used to determine the corresponding vehicle lane change judgment rule based on the current distance range of the vehicle, and use the vehicle lane change judgment rule and the current longitudinal average relative speed of the vehicle to determine whether the vehicle meets the lane change conditions.

[0035] Thirdly, this application discloses an electronic device, including:

[0036] Memory, used to store computer programs;

[0037] A processor is used to execute the computer program to implement the aforementioned lane change determination method.

[0038] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned lane change judgment method.

[0039] In this application, target parameter information is obtained through collected image data. This target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and their longitudinal relative speed. Based on the longitudinal distance and distance division rules, the current distance interval corresponding to the vehicle is determined. This distance interval is determined based on the vehicle's longitudinal danger distance and longitudinal safety distance at different speeds. A corresponding lane-change judgment rule is determined based on the current distance interval, and the vehicle's lane-change judgment rule, along with its current longitudinal average relative speed, is used to determine whether the vehicle meets the lane-change conditions. Therefore, by using the distance interval determined based on the vehicle's longitudinal danger distance and longitudinal safety distance at different speeds, the current distance interval corresponding to the vehicle is determined. Then, based on the lane-change judgment rule corresponding to this distance interval, combined with the longitudinal average relative speed, a lane-change area is judged. This improves the lane-change trigger rate and success rate by comprehensively judging the lane-change area by combining relative distance and relative speed. Furthermore, it only requires a single visual sensor, without relying on radar sensors, reducing usage costs. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A flowchart of a lane change judgment method provided in this application;

[0042] Figure 2 This application provides a specific schematic diagram of distance interval division;

[0043] Figure 3 A flowchart illustrating a specific lane change determination method provided in this application;

[0044] Figure 4 This application provides a specific schematic diagram illustrating the relationship between longitudinal relative velocity and desired collision time.

[0045] Figure 5 A flowchart illustrating a specific lane change determination method provided in this application;

[0046] Figure 6 A flowchart illustrating a specific lane change determination method provided in this application;

[0047] Figure 7 This application provides a schematic diagram of the structure of a lane change detection device;

[0048] Figure 8 This application provides a structural diagram of an electronic device. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] In existing technologies, the accuracy of lane change judgment using visual sensors is not high, and the judgment results are relatively absolute, which is not conducive to the driver's use of lane change assistance functions. Existing technologies also utilize both visual and radar sensors for lane change judgment, but this increases development costs to some extent. To overcome the above technical problems, this application proposes a lane change judgment method that can improve the lane change trigger rate and success rate while reducing usage costs.

[0051] This application discloses a lane change determination method. See also Figure 1 As shown, the method may include the following steps:

[0052] Step S11: Obtain target parameter information through the collected image data; the target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle.

[0053] In this embodiment, target parameter information, including the target vehicle, is first obtained through the collected image data. Specifically, image data can be collected using a smart camera on the vehicle, such as a front-facing intelligent camera (IFC). This camera can detect vehicle targets in the left and right lanes ahead and provide the detected target attributes, i.e., the target vehicle's ID. Each target vehicle is assigned a unique ID (0-255) by the IFC. If the target remains, the ID remains unchanged; if the target disappears, the ID becomes 0; if a new target appears, a new ID is assigned. The target parameter information includes the longitudinal distance (RelDisLog) between the vehicle and the target vehicle, i.e., the longitudinal distance between the center of the target vehicle's rear and the center of the vehicle's front bumper, with positive values ​​for the front and negative values ​​for the rear. The target parameter information also includes the longitudinal relative speed (Relνx) between the vehicle and the target vehicle, with positive values ​​for the target vehicle's speed being higher than the vehicle's speed and negative values ​​for the target vehicle's speed being lower.

[0054] Step S12: Determine the current distance interval of the vehicle based on the longitudinal distance and distance division rules; the distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different speeds.

[0055] In this embodiment, before determining the current distance interval corresponding to the vehicle based on the longitudinal distance and distance division rules, the process may further include: determining whether there is a target vehicle in the target lane to be changed based on the target vehicle information in the target parameter information; if there is, then performing the operation of determining the current distance interval corresponding to the vehicle based on the longitudinal distance and distance division rules; if there is no target vehicle, then determining that the vehicle meets the lane-changing conditions. That is, if there is no vehicle in the lane to be changed, the vehicle can change lanes directly; if there is a vehicle, then further lane-changing judgment is made based on the longitudinal distance between vehicles.

[0056] In this embodiment, after obtaining the longitudinal distance, the distance interval corresponding to the vehicle is determined according to the distance division rules. The distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different speeds, that is, different intervals are pre-divided according to the distance value of the vehicle.

[0057] The distance range is determined based on the longitudinal hazard distance and longitudinal safety distance of the vehicle at different speeds, and may include: determining a first target speed and a second target speed; the first target speed is less than the second target speed, and the speed range formed by the first target speed and the second target speed is the speed range for reasonable lane changes; determining the longitudinal hazard distance and longitudinal safety distance corresponding to the first target speed, and determining the longitudinal hazard distance and longitudinal safety distance corresponding to the second target speed; constructing a first function based on the longitudinal hazard distance corresponding to the first target speed and the longitudinal hazard distance corresponding to the second target speed, so as to determine the longitudinal hazard distance corresponding to different speeds within the speed range according to the first function; constructing a second function based on the longitudinal safety distance corresponding to the first target speed and the longitudinal safety distance corresponding to the second target speed, so as to determine the longitudinal safety distance corresponding to different speeds within the speed range according to the second function; the longitudinal hazard distance and longitudinal safety distance corresponding to speeds less than the first target speed are the same as the longitudinal hazard distance and longitudinal safety distance corresponding to the first target speed, respectively; the longitudinal hazard distance and longitudinal safety distance corresponding to speeds greater than the second target speed are the same as the longitudinal hazard distance and longitudinal safety distance corresponding to the second target speed, respectively. It should be noted that the aforementioned longitudinal safety distance can be understood as follows: if the longitudinal distance between vehicles exceeds this distance, it indicates that lane changing is completely safe; if the longitudinal distance between vehicles is greater than the longitudinal danger distance but less than the longitudinal safety distance, it indicates that lane changing is not completely safe and further judgment is required; if the longitudinal distance between vehicles is less than the longitudinal safety distance, it indicates that lane changing poses a risk and conditional judgment is required.

[0058] For example, if the first target speed is selected as 40 kph and the second target speed as 120 kph; based on experience, the longitudinal danger distance corresponding to the first target speed is set to 10 m and the longitudinal safety distance to 25 m; based on experience, the longitudinal danger distance corresponding to the second target speed is set to 25 m and the longitudinal safety distance to 75 m. Following this method, the following can be obtained: Figure 2 The distance range shown is divided into three intervals. The first interval is defined as the distance above the upper limit ①, the third interval as the distance below the lower limit ③, and the second interval as the distance between the upper and lower limits ②. Both the upper and lower limit parameters are adjustable. For example, if the current vehicle speed is 60 kph, according to the second function: y = 0.625x, the corresponding longitudinal safety distance is determined to be 37.5. According to the first function: y = 3 / 16x + 2.5, the corresponding dangerous safety distance is determined to be 13.75. If the longitudinal distance is 40, the vehicle is currently in the first interval; if the longitudinal distance is less than 37.5 but greater than 13.75, the vehicle is currently in the second interval; if the longitudinal distance is less than 13.75, the vehicle is currently in the third interval.

[0059] Step S13: Determine the corresponding lane change judgment rule based on the current distance range of the vehicle, and use the lane change judgment rule and the current longitudinal average relative speed of the vehicle to determine whether the vehicle meets the lane change conditions.

[0060] In this embodiment, after determining the corresponding distance range, the lane change judgment rule corresponding to that range is used to make the lane change judgment. That is, this embodiment configures the corresponding lane change judgment rule for different distance ranges, so as to better adapt to the lane change judgment under different distances. When making the lane change judgment, this embodiment comprehensively judges the two factors of longitudinal distance and longitudinal average relative speed, which improves the accuracy of the lane change judgment.

[0061] In this embodiment, the lane change judgment method further includes: selecting a preset number of newly acquired image frames, obtaining the longitudinal relative velocity corresponding to each image frame, and calculating the average longitudinal relative velocity; periodically updating the longitudinal average relative velocity using the preset number of image frames as a period. That is, the longitudinal average relative velocity (Af_Mean) is calculated once every preset number of image frames, for example, every 5 consecutive frames. Specifically, the longitudinal average relative velocity is averaged for each of these 5 frames, and the specific number of consecutive frames can be adjusted by parameters. Specifically, this can be achieved by setting an array and cyclically assigning values ​​to the elements in the array. For example, taking 1 frame per second as an example, the array includes Af[4], Af[3], Af[2], Af[1], and Af[0], which can represent the longitudinal average relative velocity in the first 5 seconds, the longitudinal average relative velocity in the first 4 seconds, the longitudinal average relative velocity in the first 3 seconds, the longitudinal average relative velocity in the first 2 seconds, and the longitudinal average relative velocity in the first 1 second, respectively. By continuously assigning values, when an update is needed, the value of the array representing the longitudinal average relative velocity in the first 5 seconds can be taken.

[0062] As can be seen from the above, in this embodiment, target parameter information is obtained through collected image data. This target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and their longitudinal relative speed. Based on the longitudinal distance and distance division rules, the current distance interval corresponding to the vehicle is determined. This distance interval is determined based on the vehicle's longitudinal danger distance and longitudinal safety distance at different speeds. A corresponding lane-change judgment rule is determined based on the current distance interval, and the vehicle's lane-change judgment rule and its current longitudinal average relative speed are used to determine whether the vehicle meets the lane-change conditions. Therefore, by using the distance interval determined based on the vehicle's longitudinal danger distance and longitudinal safety distance at different speeds, the current distance interval corresponding to the vehicle is determined. Then, based on the lane-change judgment rule corresponding to this distance interval, combined with the longitudinal average relative speed, a lane-change judgment is made. Thus, by combining relative distance and relative speed to comprehensively determine the lane-change area, the lane-change trigger rate and success rate are improved. Furthermore, only a single visual sensor is needed, without relying on radar sensors, reducing usage costs.

[0063] This application discloses a specific method for determining lane changes. See [link to relevant documentation]. Figure 3 As shown, the method may include the following steps:

[0064] Step S21: Obtain target parameter information through the collected image data; the target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle.

[0065] Step S22: Determine the current distance interval of the vehicle based on the longitudinal distance and distance division rules; the distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different speeds.

[0066] Step S23: If the vehicle is currently in the first distance interval, it is determined that the vehicle meets the lane change conditions; the first distance interval indicates that the longitudinal distance is greater than the longitudinal safety distance corresponding to the current vehicle speed.

[0067] According to the distance division rules, the first distance interval represents a longitudinal distance greater than the longitudinal safety distance corresponding to the current vehicle speed. At this time, it can be assumed that the vehicle will not be affected by other vehicles when changing lanes, so it can be directly determined that the vehicle meets the lane changing conditions.

[0068] Step S24: If the vehicle is currently in the second distance interval, then determine whether the vehicle meets the lane change conditions based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle; the second distance interval indicates that the longitudinal distance is less than the longitudinal safe distance corresponding to the current vehicle speed and greater than the longitudinal danger distance corresponding to the current vehicle speed.

[0069] According to the distance division rules, the second distance interval indicates that the longitudinal distance is less than the longitudinal safe distance corresponding to the current vehicle speed, but greater than the longitudinal dangerous distance corresponding to the current vehicle speed, meaning that the lane change has a certain impact and further judgment is needed.

[0070] In this embodiment, if the vehicle is currently in the second distance interval, determining whether the vehicle meets the lane-changing conditions based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle can include: determining whether the target vehicle's speed is greater than the vehicle's speed based on the longitudinal average relative speed; if so, the vehicle meets the lane-changing conditions; if not, determining whether the vehicle meets the lane-changing conditions based on the actual collision time and the expected collision time between the vehicle and the target vehicle. Here, the target vehicle specifically refers to the vehicle in front, and the smart camera specifically refers to the front-facing camera. If the speed of the vehicle in front is greater than that of the vehicle, it can be determined that even if the vehicle changes lanes, it will not be affected by the vehicle in front. If the speed of the vehicle in front is less than that of the vehicle, further judgment based on the collision time is required. If the target vehicle is behind the vehicle, the vehicle's speed needs to be greater than that of the target vehicle.

[0071] The process of determining whether a vehicle meets the lane-changing conditions based on the actual collision time and the expected collision time between the vehicle and the target vehicle may include: determining the actual collision time between the vehicle and the target vehicle based on the vehicle's current longitudinal distance and average longitudinal relative speed; determining the expected collision time between the vehicle and the target vehicle based on the vehicle's current average longitudinal relative speed and the relationship between longitudinal relative speed and expected collision time; and determining that the vehicle meets the lane-changing conditions if the actual collision time is greater than the expected collision time. Collision time (TTC) refers to the time required for two objects to collide at their current speed and direction. The relationship between longitudinal relative speed and expected collision time is as follows: Figure 4 As shown, the horizontal axis represents the longitudinal average relative velocity, and the vertical axis represents the desired collision time. This can be determined by querying... Figure 4 The expected collision time corresponding to the current vehicle speed can be determined. The 1.4m / s and 3.5m / s in the figure are determined empirically and can be modified according to the situation. Figure 4 The characteristics indicate that when the longitudinal average relative velocity is less than 1.4 m / s, a collision distance of 12 m is sufficient for braking; when the longitudinal average relative velocity is greater than 3.5 m / s, a collision distance of 6 m is the minimum standard. Specifically, when Af_Mean is below 1.4 m / s, the expected TTC is set to 12 s; when Af_Mean is above 3.5 m / s, the expected TTC is set to 6 s; when Af_Mean is between 1.4 m / s and 3.5 m / s, the expected collision time is interpolated based on the relationship between the longitudinal relative velocity and the expected collision time. In this range: Expected collision time = -20 / 7 × longitudinal average relative velocity + 16. Both the above parameters and the expected TTC parameter are adjustable.

[0072] The formula for calculating the actual collision time between the aforementioned vehicle and the target vehicle is as follows:

[0073]

[0074] Where Af_Mean is the longitudinal average relative velocity, and RelDisLog is the longitudinal distance.

[0075] For example, if the current longitudinal average relative speed is 2.1, the relationship between the longitudinal average relative speed and the expected collision time can be used to determine that the expected collision time is 10. If the longitudinal distance is 15 at this time, the actual collision time is about 7.1. It can be seen that the actual collision time is less than the expected collision time, so it is determined that the vehicle does not meet the lane change conditions.

[0076] Step S25: If the vehicle is currently in the third distance interval, determine whether the vehicle meets the lane change conditions based on the vehicle's current longitudinal average relative speed; the third distance interval represents the longitudinal distance being less than the longitudinal danger distance corresponding to the current vehicle speed.

[0077] According to the distance division rules, the third distance interval indicates that the longitudinal distance is less than the longitudinal danger distance corresponding to the current vehicle speed, that is, there is a certain danger in changing lanes and further judgment is needed.

[0078] In this embodiment, determining whether the vehicle meets the lane-changing conditions based on its current longitudinal average relative speed within the third distance interval can include: determining whether the target vehicle's speed is greater than the vehicle's speed and whether the relative speed between the two vehicles is greater than the first average speed threshold, based on the longitudinal average relative speed and a first average speed threshold; if so, the vehicle is deemed to meet the lane-changing conditions. Here, the target vehicle specifically refers to the vehicle in front, and the smart camera specifically refers to the front-facing camera. That is, if the target vehicle's speed is greater than the vehicle's speed and the relative speed between the two vehicles is greater than a certain level, then the lane-changing conditions can be considered met. If the target vehicle is behind the vehicle, the vehicle's speed must be greater than the target vehicle's speed, and the speed difference must be greater than a certain value.

[0079] For example Figure 5 and Figure 6 The image shows a specific method for determining lane changes. The specific steps are as follows:

[0080] 1. The logic begins to run. First, it checks if a target ID exists on the left. If ID = 0, meaning no target exists, then the area is designated as an allowed lane-changing zone; otherwise, it proceeds to the next level of judgment.

[0081] 2. The second layer of judgment checks whether the longitudinal distance RelDisLog of the target on the left falls within the first interval. If it does, it means the target vehicle is far from the vehicle, so TTC is no longer considered and the area is set as a lane-changing zone; otherwise, proceed to the next layer of judgment.

[0082] 3. The third layer of judgment checks whether the longitudinal distance RelDisLog of the target on the left falls within the third interval. This interval is the interval closest to the vehicle. If the target is within this interval, the relative vehicle speed is determined.

[0083] 4. If Af_Mean>5m / s (adjustable parameter), it means that the target vehicle's speed is significantly higher than the vehicle's speed, and it is set as a lane-changing zone; otherwise, it is set as a lane-changing zone.

[0084] 5. If the vertical distance RelDisLog of the target on the left does not fall within the third interval, it will eventually fall within the second interval.

[0085] 6. The logical judgment of the variable lane area in the second interval is as follows: Figure 6 Within the second interval, if the target vehicle's speed (Af_Mean) is greater than 0 m / s (adjustable parameter), it means the target vehicle is faster than the vehicle, and this is designated as a lane-changing zone.

[0086] 7. If the relative vehicle speed is less than 0 m / s, then TTC is determined.

[0087] 8. If the actual TTC is greater than the expected TTC, then set it as a lane-changing zone; otherwise, set it as a lane-changing zone.

[0088] 9. The lane change zone for vehicles on the right is determined using the same logic as that on the left.

[0089] The specific processes of steps S21 and S22 can be found in the relevant content disclosed in the foregoing embodiments, and will not be repeated here.

[0090] As can be seen from the above, in this embodiment, target parameter information is obtained through collected image data. The target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle. Based on the longitudinal distance and distance division rules, the current distance interval corresponding to the vehicle is determined. The distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different vehicle speeds. If the vehicle currently corresponds to the first distance interval, it is determined that the vehicle meets the lane change conditions. The first distance interval indicates that the longitudinal distance is greater than the longitudinal safety distance corresponding to the current vehicle speed. If the vehicle currently corresponds to the second distance interval, it is determined whether the vehicle meets the lane change conditions based on the current longitudinal average relative speed of the vehicle and the collision time between the vehicle and the target vehicle. The second distance interval indicates that the longitudinal distance is less than the longitudinal safety distance corresponding to the current vehicle speed and greater than the longitudinal danger distance corresponding to the current vehicle speed. If the vehicle currently corresponds to the third distance interval, it is determined whether the vehicle meets the lane change conditions based on the current longitudinal average relative speed of the vehicle. The third distance interval indicates that the longitudinal distance is less than the longitudinal danger distance corresponding to the current vehicle speed. It is evident that using both longitudinal distance and average longitudinal relative speed for lane change judgment improves the lane change trigger rate and success rate, and only requires a single vision sensor, without relying on radar sensors, thus reducing usage costs.

[0091] Accordingly, this application also discloses a lane change detection device, see [link to relevant documentation]. Figure 7 As shown, the device includes:

[0092] The information acquisition module 11 is used to obtain target parameter information through the collected image data; the target parameter information includes the longitudinal distance between the vehicle and the target vehicle and the longitudinal relative speed between the vehicle and the target vehicle.

[0093] The distance interval determination module 12 is used to determine the current distance interval of the vehicle based on the longitudinal distance and the distance division rules; the distance interval is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different vehicle speeds;

[0094] The lane change judgment module 13 is used to determine the corresponding vehicle lane change judgment rule based on the current distance interval of the vehicle, and use the vehicle lane change judgment rule and the current longitudinal average relative speed of the vehicle to determine whether the vehicle meets the lane change conditions.

[0095] As can be seen from the above, in this embodiment, target parameter information is obtained through collected image data. This target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and their longitudinal relative speed. Based on the longitudinal distance and distance division rules, the current distance interval corresponding to the vehicle is determined. This distance interval is determined based on the vehicle's longitudinal danger distance and longitudinal safety distance at different speeds. A corresponding lane-change judgment rule is determined based on the current distance interval, and the vehicle's lane-change judgment rule and its current longitudinal average relative speed are used to determine whether the vehicle meets the lane-change conditions. Therefore, by using the distance interval determined based on the vehicle's longitudinal danger distance and longitudinal safety distance at different speeds, the current distance interval corresponding to the vehicle is determined. Then, based on the lane-change judgment rule corresponding to this distance interval, combined with the longitudinal average relative speed, a lane-change judgment is made. Thus, by combining relative distance and relative speed to comprehensively determine the lane-change area, the lane-change trigger rate and success rate are improved. Furthermore, only a single visual sensor is needed, without relying on radar sensors, reducing usage costs.

[0096] In some specific embodiments, the lane change determination device may specifically include:

[0097] The longitudinal average relative velocity calculation unit is used to select a preset number of newly acquired image frames, obtain the longitudinal relative velocity corresponding to each image frame, and calculate the average value to obtain the longitudinal average relative velocity.

[0098] The update unit is used to periodically update the longitudinal average relative velocity with the preset number of image frames as the period.

[0099] In some specific embodiments, the lane change determination module 13 may specifically include:

[0100] The first lane change determination unit is used to determine that the vehicle meets the lane change conditions if the vehicle is currently in a first distance interval; the first distance interval represents that the longitudinal distance is greater than the longitudinal safety distance corresponding to the current vehicle speed.

[0101] The second lane change judgment unit is used to determine whether the vehicle meets the lane change conditions based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle if the vehicle is currently in the second distance interval. The second distance interval represents that the longitudinal distance is less than the longitudinal safe distance corresponding to the current vehicle speed and greater than the longitudinal danger distance corresponding to the current vehicle speed.

[0102] The third lane change judgment unit is used to determine whether the vehicle meets the lane change conditions based on the current longitudinal average relative speed of the vehicle if the vehicle is currently in the third distance interval; the third distance interval represents the longitudinal distance being less than the longitudinal danger distance corresponding to the current vehicle speed.

[0103] In some specific embodiments, the third lane change determination unit may specifically include:

[0104] The vehicle speed determination unit is used to determine whether the speed of the target vehicle is greater than the speed of the vehicle itself, and whether the relative speed between the two vehicles is greater than the first average speed threshold, based on the longitudinal average relative speed and the first average speed threshold.

[0105] The determination unit is used to determine that the vehicle meets the lane change conditions if the determination result of the vehicle speed determination unit is yes.

[0106] In some specific embodiments, the second lane change determination unit may specifically include:

[0107] The vehicle speed determination unit is used to determine whether the speed of the target vehicle is greater than the speed of the vehicle itself based on the longitudinal average relative speed.

[0108] The determination unit is used to determine that the vehicle meets the lane change conditions if the determination result of the vehicle speed determination unit is yes.

[0109] The lane change condition judgment unit is used to determine whether the vehicle meets the lane change conditions if the actual collision time between the vehicle and the target vehicle and the expected collision time between the vehicle and the target vehicle are not met.

[0110] In some specific embodiments, the lane change condition determination unit may specifically include:

[0111] The actual collision time determination unit is used to determine the actual collision time between the vehicle and the target vehicle based on the current longitudinal distance and average longitudinal relative speed of the vehicle.

[0112] The expected collision time determination unit is used to determine the expected collision time between the vehicle and the target vehicle based on the current longitudinal average relative speed of the vehicle and the relationship between the longitudinal relative speed and the expected collision time.

[0113] The determination unit is used to determine that the vehicle meets the lane change conditions if the actual collision time is greater than the expected collision time.

[0114] In some specific embodiments, the lane change determination device may specifically include:

[0115] The target vehicle determination unit is used to determine whether there is a target vehicle in the target lane to be changed based on the target vehicle information in the target parameter information.

[0116] An execution unit is configured to, if a target vehicle exists, perform the operation of determining the current distance interval corresponding to the vehicle based on the longitudinal distance and the distance division rules;

[0117] The determination unit is used to determine if the vehicle meets the lane change conditions if no target vehicle exists.

[0118] Furthermore, this application also discloses an electronic device, see [link to relevant documentation]. Figure 8 As shown, the content in the figure should not be considered as any limitation on the scope of use of this application.

[0119] Figure 8 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the lane change determination method disclosed in any of the foregoing embodiments.

[0120] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0121] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon include operating system 221, computer program 222 and data 223 including target parameter information, etc. The storage method can be temporary storage or permanent storage.

[0122] The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the massive data 223 in the memory 22. The operating system 221 can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the lane change judgment method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0123] Furthermore, this application also discloses a computer storage medium storing computer-executable instructions. When the computer-executable instructions are loaded and executed by a processor, they implement the lane change judgment method steps disclosed in any of the foregoing embodiments.

[0124] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0125] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0126] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0127] The foregoing has provided a detailed description of the lane change judgment method, apparatus, device, and storage medium provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A lane change detection method, characterized in that, include: Target parameter information is obtained from the acquired image data; The target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle; Based on the longitudinal distance and distance division rules, determine the current distance interval corresponding to the vehicle; The distance range is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different speeds; Based on the current distance range of the vehicle, the corresponding lane change judgment rule is determined, and the vehicle is used to determine whether the vehicle meets the lane change conditions using the vehicle lane change judgment rule and the current longitudinal average relative speed of the vehicle. The step of determining the corresponding lane-change judgment rule based on the current distance interval of the vehicle, and using the lane-change judgment rule and the current longitudinal average relative speed of the vehicle to determine whether the vehicle meets the lane-change conditions, includes: If the vehicle is currently in the second distance interval, then based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle, it is determined whether the vehicle meets the lane change conditions; the second distance interval indicates that the longitudinal distance is less than the longitudinal safe distance corresponding to the current vehicle speed and greater than the longitudinal danger distance corresponding to the current vehicle speed. The step of determining whether the vehicle meets the lane-changing conditions based on the vehicle's current average longitudinal relative speed and the collision time between the vehicle and the target vehicle includes: Based on the longitudinal average relative velocity, determine whether the target vehicle's speed is greater than the vehicle's speed; If so, then the vehicle is deemed to meet the lane-changing conditions; If not, the actual collision time between the vehicle and the target vehicle is determined based on the current longitudinal distance and average longitudinal relative speed of the vehicle; the expected collision time between the vehicle and the target vehicle is determined based on the current average longitudinal relative speed of the vehicle and the relationship between longitudinal relative speed and expected collision time; if the actual collision time is greater than the expected collision time, the vehicle is determined to meet the lane change conditions.

2. The lane change judgment method according to claim 1, characterized in that, Also includes: Select a preset number of newly acquired image frames, obtain the longitudinal relative velocity corresponding to each image frame, and calculate the average longitudinal relative velocity. The longitudinal average relative velocity is periodically updated with the preset number of image frames as the period.

3. The lane change judgment method according to claim 1, characterized in that, The step of determining the corresponding lane change judgment rule based on the current distance range of the vehicle, and using the lane change judgment rule and the current longitudinal average relative speed of the vehicle to determine whether the vehicle meets the lane change conditions, includes: If the vehicle is currently in the first distance interval, it is determined that the vehicle meets the lane change conditions; the first distance interval indicates that the longitudinal distance is greater than the longitudinal safety distance corresponding to the current vehicle speed; If the vehicle is currently in the third distance interval, then the vehicle is judged to meet the lane change conditions based on the current longitudinal average relative speed; the third distance interval represents the longitudinal distance being less than the longitudinal danger distance corresponding to the current vehicle speed.

4. The lane change judgment method according to claim 3, characterized in that, If the vehicle is currently in the third distance interval, then the determination of whether the vehicle meets the lane change conditions is based on the vehicle's current longitudinal average relative speed, including: Based on the longitudinal average relative speed and the first average speed threshold, it is determined whether the speed of the target vehicle is greater than the speed of the vehicle itself, and whether the relative speed between the two vehicles is greater than the first average speed threshold. If so, then the vehicle is deemed to meet the lane change requirements.

5. The lane change judgment method according to claim 1, characterized in that, Before determining the current distance interval corresponding to the vehicle based on the longitudinal distance and distance division rules, the method further includes: Based on the target vehicle information in the target parameter information, determine whether there is a target vehicle in the target lane to be changed to; If it exists, then perform the operation of determining the current distance interval of the vehicle based on the longitudinal distance and distance division rules; If it does not exist, then the vehicle is deemed to meet the lane change conditions.

6. A lane change detection device, characterized in that, include: The information acquisition module is used to obtain target parameter information from the acquired image data; The target parameter information includes the longitudinal distance between the vehicle and the target vehicle, and the longitudinal relative speed between the vehicle and the target vehicle; The distance interval determination module is used to determine the current distance interval of the vehicle based on the longitudinal distance and the distance division rules. The distance range is determined based on the longitudinal danger distance and longitudinal safety distance of the vehicle at different speeds; The lane change judgment module is used to determine the corresponding lane change judgment rule based on the current distance range of the vehicle, and use the lane change judgment rule and the current longitudinal average relative speed of the vehicle to determine whether the vehicle meets the lane change conditions. The lane change determination module includes: The second lane change judgment unit is used to determine whether the vehicle meets the lane change conditions based on the vehicle's current longitudinal average relative speed and the collision time between the vehicle and the target vehicle if the vehicle is currently in the second distance interval. The second distance interval represents that the longitudinal distance is less than the longitudinal safe distance corresponding to the current vehicle speed and greater than the longitudinal danger distance corresponding to the current vehicle speed. The second lane change determination unit includes: The vehicle speed determination unit is used to determine whether the speed of the target vehicle is greater than the speed of the vehicle itself based on the longitudinal average relative speed. The determination unit is used to determine that the vehicle meets the lane change conditions if the determination result of the vehicle speed determination unit is yes. The lane change condition determination unit is used to determine the actual collision time between the vehicle and the target vehicle based on the current longitudinal distance and average longitudinal relative speed of the vehicle if the judgment result of the vehicle speed determination unit is negative; to determine the expected collision time between the vehicle and the target vehicle based on the current longitudinal average relative speed of the vehicle and the relationship between the longitudinal relative speed and the expected collision time; and to determine that the vehicle meets the lane change condition if the actual collision time is greater than the expected collision time.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the lane change determination method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein the computer programs, when executed by a processor, implement the lane change determination method as described in any one of claims 1 to 5.

Images