Lane line detection method, device and equipment and storage medium

Abstract

The invention discloses a lane line detection method and device, equipment and a storage medium. The lane line detection method comprises the following steps: acquiring motion information and lane line information acquired from a target vehicle at the current moment; based on the motion information and / or the lane line information, at least one constraint parameter is determined, and the at least one constraint parameter is related to speed information of the target vehicle and / or distance information between the target vehicle and the lane line; and determining that the lane line of the target vehicle is in an effective state according to the lane line detection result of the target vehicle in response to the condition that each constraint parameter meets the constraint condition. According to the scheme, the accuracy of the lane line detection result of the target vehicle can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a lane line detection method, apparatus, device, and storage medium. Background Art

[0002] The Lane Keeping Assist System (LKAS) usually relies on cameras or other sensors to identify and track lane lines. When the perception system detects lane lines, it calculates the confidence of the lane lines and decides whether to activate the lane keeping function based on this confidence. However, in the actual driving environment, lane lines may be interrupted or unclear due to various reasons (such as road construction, weather conditions, old road surfaces, etc.). In this case, the perception system does not change the confidence of the lane lines because it believes that the interruption of the lane lines is temporary and the continuity of the lane lines can still be restored through the fitting algorithm. If the lane lines completely disappear in some areas, but the perception system still "generates" virtual lane lines through the fitting algorithm, the lane keeping system may wrongly think that the lane lines exist, keeping the confidence of the lane lines unchanged and continuing to trigger the lane keeping function. In this case, the driver may mistakenly think that the lane lines actually exist, resulting in the vehicle still driving along the virtual lane lines without actual lane lines, increasing the driving risk of the vehicle.

[0003] In view of the existing technical deficiencies, how to provide an effective lane line detection solution is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention

[0004] This application provides at least one lane line detection method, apparatus, device, and storage medium.

[0005] This application provides a lane line detection method, including: obtaining motion information and lane line information collected for a target vehicle at a current moment; determining at least one constraint parameter based on the motion information and / or the lane line information, where the at least one constraint parameter is related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line; and in response to each constraint parameter satisfying a constraint condition, determining that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state.

[0006] In some embodiments, the lane line information includes a lane line confidence level, and at least one constraint parameter includes a first constraint parameter corresponding to the lane line confidence level in the lane line information. In response to each constraint parameter satisfying the constraint condition, determining that the lane line detection result of the target vehicle is in a valid state, including: in response to the first constraint parameter satisfying the first constraint condition, determining that the lane line detection result of the target vehicle is in a valid state, where the first constraint condition is related to the lane line confidence level.

[0007] In some embodiments, the motion information includes the current vehicle speed, and at least one constraint parameter includes a second constraint parameter. The constraint condition includes the constraint condition corresponding to the second constraint parameter. Based on the motion information and / or the lane line information, determining at least one constraint parameter, including: according to the current vehicle speed, determining the lane line length within a preset time, and using the lane line length as the second constraint parameter.

[0008] In some embodiments, the lane line information includes the lane line coefficients in the target lane line equation corresponding to the target vehicle, and at least one constraint parameter includes a third constraint parameter and / or a fourth constraint parameter. The constraint condition includes the constraint condition corresponding to the third constraint parameter and / or the fourth constraint parameter. Based on the motion information and / or the lane line information, determining at least one constraint parameter, including: according to the first coefficient and the second coefficient in the lane line coefficients, determining the target distance and / or the lane width between the preset part of the target vehicle and the lane line; using the difference between the target distance and the historical target distance as the third constraint parameter, where the historical target distance is used to represent the target distance determined at a historical moment before the current moment; and / or, using the lane width as the fourth constraint parameter.

[0009] In some embodiments, the lane line information includes the lane line start distance, and at least one constraint parameter includes a fifth constraint parameter. The constraint condition includes the constraint condition corresponding to the fifth constraint parameter. Based on the motion information and / or the lane line information, determining at least one constraint parameter, including: obtaining the wheelbase of the target vehicle; using the difference between the lane line start distance and the wheelbase as the fifth constraint parameter.

[0010] In some embodiments, the motion information includes the current vehicle speed, the lane line information includes the lane line coefficients in the target lane line equation corresponding to the target vehicle, and at least one constraint parameter includes a sixth constraint parameter. The constraint condition includes the constraint condition corresponding to the sixth constraint parameter. Based on the motion information and / or the lane line information, determining at least one constraint parameter, including: based on the current vehicle speed and the second coefficient in the lane line coefficients, determining the target speed, where the target speed is used to represent the relative speed between the target vehicle and the lane line; using the difference between the target speed and the historical target speed as the sixth constraint parameter, where the historical target speed is used to represent the target speed determined at a historical moment before the current moment.

[0011] In some embodiments, the lane line information includes the lane line coefficients in the target lane line equation corresponding to the target vehicle, at least one of the constraint parameters includes a seventh constraint parameter, the constraint condition includes the constraint condition corresponding to the seventh constraint parameter, and based on the motion information and / or the lane line information, determining at least one constraint parameter includes: determining the lane line curvature based on a third coefficient in the lane line coefficients; determining the change in the lane line curvature based on the lane line curvature, and using the change in the lane line curvature as the seventh constraint parameter.

[0012] The present application provides a lane line detection device, including: an acquisition module, a first determination module, and a second determination module; the acquisition module is configured to acquire the motion information and lane line information collected for the target vehicle at the current moment; the first determination module is configured to determine at least one constraint parameter based on the motion information and / or the lane line information, and at least one constraint parameter is related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line; the second determination module is configured to, in response to each constraint parameter satisfying the constraint condition, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state.

[0013] The present application provides an electronic device, including a memory and a processor, and the processor is configured to execute program instructions stored in the memory to implement the above-mentioned lane line detection method.

[0014] The present application provides a computer-readable storage medium, on which program instructions are stored, and when the program instructions are executed by a processor, the above-mentioned lane line detection method is implemented.

[0015] In the above solution, based on the motion information and lane line information collected for the target vehicle at the current moment, at least one constraint parameter is determined, and the lane line detection result of the target vehicle is determined through the relationship between the constraint parameter related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line and the constraint condition, which can avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings here are incorporated into the specification and constitute a part of this specification. These drawings show embodiments consistent with the present application and are used together with the specification to explain the technical solutions of the present application.

[0018] Figure 1 It is a flowchart illustration of an embodiment of the lane line detection method of the present application Figure 1 ;

[0019] Figure 2 is a flowchart illustration of an embodiment of the lane line detection method of the present application Figure 2 ;

[0020] Figure 3 is a flowchart illustration of an embodiment of the lane line detection method of the present application Figure 3 ;

[0021] Figure 4 is a schematic structural diagram of an embodiment of the lane line detection device of the present application;

[0022] Figure 5 is a schematic structural diagram of an embodiment of the electronic device of the present application;

[0023] Figure 6 is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. Detailed implementation manners

[0024] The solutions of the embodiments of the present application will be described in detail below with reference to the accompanying drawings of the specification.

[0025] In the following description, specific details such as specific system architectures, interfaces, and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the present application.

[0026] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after. In addition, "multiple" in this article means two or more than two. In addition, the term "at least one" in this article means any one of multiple or any combination of at least two of multiple. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0027] This application provides some lane line detection methods and lane line detection devices. The application scenarios of the lane line detection method include, but are not limited to, scenarios of performing lane line detection on a target vehicle, or scenarios of determining whether a lane keeping function is activated, where the target object may be an electric motor. The execution subject of the lane line detection method may be a lane line detection device. For example, the lane line detection device may be disposed in a terminal device, a server, or other processing devices. Among them, the terminal device may be a device for lane line detection, a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, etc. In some possible implementation manners, the lane line detection method may be implemented by a processor invoking computer-readable instructions stored in a memory.

[0028] Please refer to Figure 1 , Figure 1 which is a flowchart of an embodiment of the lane line detection method of this application. Figure 1 . Specifically, the lane line detection method may include the following steps:

[0029] Step S11: Obtain the motion information and lane line information collected for the target vehicle at the current moment.

[0030] The target vehicle may be a vehicle that needs to perform lane line detection. The target vehicle may also be referred to as the host vehicle. The motion information may be the host vehicle motion information of the target vehicle. The motion information includes, but is not limited to, the host vehicle speed, lateral acceleration, longitudinal acceleration, yaw rate, vehicle wheelbase, vehicle width, etc. related to the target vehicle. The lane line information may be information related to the lane lines of the target vehicle. Among them, the lane line information includes, but is not limited to, the lane line length Range, the lane line start distance, the lane line coefficient, and the lane line confidence. Specifically, the lane line length may be expressed as Range. The lane line start distance may be the lane line start distance based on the position of the center of the rear axle of the host vehicle, and the lane line start distance may be expressed as Startpointx. The lane line confidence is the confidence determined by the perception fusion function for the current lane line state and sent, and may be expressed as Confidence lane。The lane line coefficient can be the polynomial coefficient in the target lane line equation corresponding to the target vehicle. The target lane line equation can be the equation of the lane line fitting sent by the perception fusion function, which is a cubic polynomial. Exemplarily, the lane line coefficient can include a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient. Among them, the first coefficient, the second coefficient, the third coefficient, and the fourth coefficient are respectively represented as C0, C1, C2, and C3. If it is the left lane line, the first coefficient C0 is positive. If it is the right lane line, the first coefficient C0 is negative. The first coefficient C0 is used to determine the distance between the center of the rear axle of the target vehicle and the left and right lane lines. The second coefficient C1 is used to determine the lane line orientation angle. The lane line orientation angle is used to represent the relative position angle between the vehicle body orientation and the left and right lane lines. The third coefficient C2 is used to determine the lane line curvature. The fourth coefficient C3 is used to determine the change in the lane line curvature.

[0031] The above motion information can be the information collected by the chassis controller of the target vehicle through specific sensors. The above lane line information is the information collected by the image acquisition device on the target vehicle. Alternatively, the above lane line information is the information obtained after the information collected by the image acquisition device on the target vehicle is processed by the perception fusion module.

[0032] Step S12: Determine at least one constraint parameter based on the motion information and / or the lane line information.

[0033] At least one constraint parameter is related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line. In some other application scenarios, at least one constraint parameter is related to the speed information of the target vehicle. In some other application scenarios, at least one constraint parameter is related to the distance information between the target vehicle and the same lane line. In some other application scenarios, at least one constraint parameter is related to the speed information of the target vehicle and the distance information between the target vehicle and the same lane line.

[0034] The constraint parameter is related to the lane line that the target vehicle needs to judge. Among them, by judging whether the constraint parameter is within the preset range, it can be determined whether the lane line of the target vehicle is in an effective state.

[0035] In some application scenarios, the speed information of the target vehicle can be related to the above motion information. Specifically, the speed information of the target vehicle can be any one or more of the above motion information, and can also be a combination of any one or more of the above motion information. In some other application scenarios, the speed information of the target vehicle can be obtained by combining the above motion information and the above lane line information. In some application scenarios, the distance information can be the information related to the lane line distance obtained from at least one of the above lane line information.

[0036] In some application scenarios, the above step S12 may be to determine at least one constraint parameter based on motion information. In other application scenarios, the above step S12 may be to determine at least one constraint parameter based on lane line information. In still other application scenarios, the above step S12 may be to determine at least one constraint parameter based on motion information and lane line information.

[0037] Step S13: In response to each constraint parameter satisfying the constraint condition, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state.

[0038] The constraint condition is used to represent the preset range of each constraint parameter. The constraint condition may include the preset range corresponding to any one constraint parameter, or may include the preset range corresponding to a combination of at least some constraint parameters. In this application, the example is that the constraint condition includes the constraint conditions corresponding to each constraint parameter. The lane line detection result includes that the lane line of the target vehicle is in an effective state, or the lane line of the target vehicle is not in an effective state. When the lane line detection result is that the lane line of the target vehicle is in an effective state, it indicates that the lane line condition is good and there is no large jump, etc., and the lane line condition meets the function activation requirements. When the lane line detection result is that the lane line of the target vehicle is not in an effective state, it indicates that the lane line condition is poor and there may be a large jump, etc., and the lane line condition does not meet the function activation requirements.

[0039] The above step S13 may be to determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state when each constraint parameter satisfies the constraint condition. In some application scenarios, when each constraint parameter satisfies the constraint condition, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state. In other application scenarios, when at least some of each constraint parameter satisfy the constraint condition, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state. At least some of each constraint parameter may be constraint parameters that satisfy the preset priority ranking. It can be understood that before performing the above step S13, determine the priority between each constraint parameter. Use the constraint parameter that satisfies the preset priority ranking as the target constraint parameter. The method for determining the priority between each constraint parameter may be to obtain the priority of each pre-set constraint parameter, or to determine the priority between each constraint parameter based on the received priority configuration instruction. The priority configuration instruction is obtained in response to the priority configuration operation on the preset configuration interface. The above step S13 may be to determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state in response to the target constraint parameter satisfying the constraint condition.

[0040] In some other application scenarios, in response to at least some of the constraint parameters not meeting the constraint conditions, the lane line detection result of the target vehicle is determined to be that the lane lines of the target vehicle are not in a valid state. Specifically, at least some of the constraint parameters can be any one or more of the constraint parameters.

[0041] After the above step S13, in response to the lane line detection result being determined to be that the lane lines of the target vehicle are in a valid state, the lane keeping function is allowed to be activated.

[0042] Exemplarily, each constraint parameter includes, but is not limited to, one or more of lane line confidence, displacement of the center of the rear axle of the vehicle from the lane line, lateral speed of the vehicle, and distance from the starting point of the lane line. The above step S13 can be, when the lane line confidence meets the constraint condition corresponding to the lane line confidence, to determine whether the displacement of the center of the rear axle of the vehicle from the lane line, the lateral speed of the vehicle, and the distance from the starting point of the lane line respectively meet their respective corresponding constraint conditions, that is, within the required range. In response to the displacement of the center of the rear axle of the vehicle from the lane line, the lateral speed of the vehicle, and the distance from the starting point of the lane line respectively meeting their respective corresponding constraint conditions, the lane line detection result of the target vehicle is determined to be that the lane lines of the target vehicle are in a valid state.

[0043] In the above solution, based on the motion information and lane line information collected for the target vehicle at the current moment, at least one constraint parameter is determined. By the relationship between the constraint parameter related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line and the constraint conditions, the lane line detection result of the target vehicle is determined, which can avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0044] In some embodiments, the lane line information includes lane line confidence, and at least one constraint parameter includes a first constraint parameter corresponding to the lane line confidence in the lane line information. The above step S13 can include the following steps: In response to the first constraint parameter meeting the first constraint condition, the lane line detection result of the target vehicle is determined to be that the lane lines of the target vehicle are in a valid state, and the first constraint condition is related to the lane line confidence.

[0045] The first constraint parameter is the lane line confidence. The above step S12 can be taking the lane line confidence as the first constraint parameter. The constraint conditions include a first constraint condition corresponding to the first constraint parameter. Specifically, the first constraint condition is a confidence threshold. The first constraint parameter meeting the first constraint condition can be that the first constraint parameter is greater than or equal to the confidence threshold. Exemplarily, the confidence threshold can be expressed as Confidence threshold。The lane line confidence sets two levels of confidence for the lane line according to the value sent by perception and sets a confidence threshold. The lane line confidence includes a first level and a second level. For the lane line confidence at the first level, the lane line is in good condition. For the lane line confidence at the second level, the lane line condition is poor. Specifically, the lane line confidence in the first constraint parameter may include the confidence corresponding to the left lane line and / or the confidence corresponding to the right lane line. The confidence threshold in the first constraint condition includes the confidence threshold corresponding to the left lane line and / or the confidence threshold corresponding to the right lane line.

[0046] When the first constraint parameter is greater than or equal to the confidence threshold, the lane line detection result of the target vehicle is determined to be that the lane line of the target vehicle is in an effective state. At this time, the lane line confidence is at the first level. When the first constraint parameter is less than the confidence threshold, the lane line detection result of the target vehicle is determined to be that the lane line of the target vehicle is not in an effective state. At this time, the lane line confidence is at the second level.

[0047] Responding to the lane line confidence being greater than or equal to the confidence threshold, determining that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state may include: In some application scenarios, when the confidence corresponding to the left lane line is greater than or equal to the confidence threshold corresponding to the left lane line, the lane line detection result of the target vehicle is determined to be that the lane line of the target vehicle is in an effective state. In some other application scenarios, when the confidence corresponding to the right lane line is greater than or equal to the confidence threshold corresponding to the right lane line, the lane line detection result of the target vehicle is determined to be that the lane line of the target vehicle is in an effective state. In some other application scenarios, when the confidence corresponding to the left lane line is greater than or equal to the confidence threshold corresponding to the left lane line and the confidence corresponding to the right lane line is greater than or equal to the confidence threshold corresponding to the right lane line, the lane line detection result of the target vehicle is determined to be that the lane line of the target vehicle is in an effective state.

[0048] It can be considered that by comparing the first constraint parameter with the first constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result with a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0049] In some embodiments, the motion information includes the current vehicle speed, at least one constraint parameter includes a second constraint parameter, the constraint condition includes the constraint condition corresponding to the second constraint parameter, and the above step S12 may include: determining the lane line length within a preset time according to the current vehicle speed and using the lane line length as the second constraint parameter.

[0050] In some application scenarios, the above step S12 may be to use the product of the current vehicle speed in the motion information and the preset time as the lane line length within the preset time, and use the lane line length within the preset time as the second constraint parameter. In other application scenarios, the above step S12 may be to use the lane line length in the lane line information as the second constraint parameter. In still other application scenarios, perform preset processing on the lane line length within the preset time and the lane line length in the lane line information to obtain a reference lane line length. The preset processing may be taking an average, selecting a maximum value, selecting a minimum value, etc., and use the above reference lane line length as the second constraint parameter. It can be understood that the second constraint parameter may be any one or more of the above lane line length within the preset time, the lane line length in the lane line information, and the reference lane line length.

[0051] The constraint conditions include a second constraint condition corresponding to the second constraint parameter. The second constraint condition is a length threshold for the lane line length. The above step S13 may be to determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state in response to the second constraint parameter satisfying the second constraint condition, and the second constraint condition is related to the lane line length.

[0052] The lane line length in the second constraint parameter may include the length corresponding to the left lane line and / or the length corresponding to the right lane line. The length threshold in the second constraint condition includes the length threshold corresponding to the left lane line and / or the length threshold corresponding to the right lane line.

[0053] Determining that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state in response to the lane line length being greater than or equal to the length threshold may include: In some application scenarios, when the length corresponding to the left lane line is greater than or equal to the length threshold corresponding to the left lane line, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state. In other application scenarios, when the length corresponding to the right lane line is greater than or equal to the length threshold corresponding to the right lane line, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state. In still other application scenarios, when the length corresponding to the left lane line is greater than or equal to the length threshold corresponding to the left lane line and the length corresponding to the right lane line is greater than or equal to the length threshold corresponding to the right lane line, determine that the lane line detection result of the target vehicle is that the lane line of the target vehicle is in an effective state.

[0054] The length threshold can be a preset length value or a dynamically determined length value. Any one of the lane line length within the above preset time, the lane line length in the lane line information, and the reference lane line length is the second constraint parameter, and any other one is the length threshold of the lane line length. Specifically, the lane line length in the lane line information is the second constraint parameter. The lane line length within the preset time is the second constraint condition. When the lane line length in the lane line information is greater than or equal to the lane line length within the preset time, the lane line length meets the requirements, and the lane line detection result of the target vehicle is determined to be in an effective state.

[0055] Exemplarily, when the above lane line confidence is greater than or equal to the confidence threshold, when the left lane line length in the lane line information is greater than or equal to the left lane line length within the preset time, and the right lane line length in the lane line information is greater than or equal to the right lane line length within the preset time, the lane line length meets the requirements, and the lane line detection result of the target vehicle is determined to be in an effective state.

[0056] It can be considered that by comparing the second constraint parameter with the second constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result with a single judgment factor, thereby improving the accuracy of the lane line detection result. In addition, by considering any one or more of the lane line length within the above preset time, the lane line length in the lane line information, and the reference lane line length, the accuracy of the lane line detection can be controlled.

[0057] In some embodiments, the lane line information includes the lane line coefficients in the target lane line equation corresponding to the target vehicle, at least one of the constraint parameters includes a third constraint parameter and / or a fourth constraint parameter, and the constraint condition includes the constraint condition corresponding to the third constraint parameter and / or the fourth constraint parameter. The above step S12 may include the following steps: Determine the target distance and / or lane width between the preset part of the target vehicle and the lane line according to the first coefficient and the second coefficient in the lane line coefficients. The difference between the target distance and the historical target distance is used as the third constraint parameter, and the historical target distance is used to represent the target distance determined at a historical moment before the current moment. And / or, the lane width is used as the fourth constraint parameter.

[0058] The lane line coefficient can be the polynomial coefficient in the target lane line equation corresponding to the target vehicle. The target lane line equation can be the equation of the lane line fitting sent by the perception fusion function, which is a cubic polynomial. Exemplarily, the lane line coefficient can include a first coefficient, a second coefficient, a third coefficient, and a fourth coefficient. Among them, the first coefficient, the second coefficient, the third coefficient, and the fourth coefficient are respectively represented as C0, C1, C2, and C3. If it is the left lane line, the first coefficient C0 is positive. If it is the right lane line, the first coefficient C0 is negative. The first coefficient C0 is used to determine the distance between the center of the rear axle of the target vehicle and the left and right lane lines. The second coefficient C1 is used to determine the lane line orientation angle. The lane line orientation angle is used to represent the relative position angle between the vehicle body orientation and the left and right lane lines. The third coefficient C2 is used to determine the lane line curvature. The fourth coefficient C3 is used to determine the change in the lane line curvature.

[0059] In some application scenarios, the target distance between the preset part of the target vehicle and the lane line is determined according to the first coefficient and the second coefficient in the lane line coefficient. In some application scenarios, the lane width is determined according to the first coefficient and the second coefficient in the lane line coefficient. In some application scenarios, the target distance between the preset part of the target vehicle and the lane line and the lane width are determined according to the first coefficient and the second coefficient in the lane line coefficient.

[0060] Specifically, the steps to determine the target distance between the preset part of the target vehicle and the lane line according to the first coefficient and the second coefficient in the lane line coefficient can be: determine the target distance between the preset part of the target vehicle and the lane line according to the second coefficient in the lane line coefficient. Among them, according to the second coefficient in the lane line coefficient, the lane line orientation angle is determined. Based on the lane line orientation angle and the first coefficient in the lane line coefficient, the target distance between the preset part of the target vehicle and the lane line is determined. Among them, the preset part is the center of the rear axle of the vehicle. The target distance is the distance between the center of the rear axle of the vehicle and the lane line. Among them, the target distance includes the distance between the center of the rear axle of the vehicle and the left lane line, and / or the distance between the center of the rear axle of the vehicle and the right lane line. The difference between the target distance and the historical target distance is used as the third constraint parameter. The historical target distance is the target distance between the preset part of the target vehicle and the historical lane line at the historical moment determined based on the first coefficient and the second coefficient in the historical lane line information after collecting the historical motion information and the historical lane line information at the historical moment. In some application scenarios, the historical moment can be the previous moment before the current moment. In some other application scenarios, the historical moment can be the moment before the current moment and in the same traffic scenario as the current moment. The traffic scenario can be scenarios such as elevated roads, flat ground, tunnels, etc.

[0061] Specifically, for the process of determining the lane line orientation angle based on the second coefficient in the lane line coefficient, please refer to the following formulas (1) and (2):

[0062] θ left =-atan(C1 left ) Formula (1);

[0063] θ right =-atan(C1 right ) Formula (2);

[0064] Where, θ left and θ right are the left lane line orientation angle and the right lane line orientation angle respectively. C1 left and C1 right are the second coefficient of the left lane line and the second coefficient of the right lane line respectively.

[0065] Specifically, for the process of determining the target distance between the preset part of the target vehicle and the lane line based on the lane line orientation angle and the first coefficient in the lane line coefficient, please refer to the following formulas (3) and (4):

[0066] L left =cos(θ left )×C0 left Formula (3);

[0067] L right =cos(θ right )×C0 right Formula (4);

[0068] Where, θ left and θ right are the left lane line orientation angle and the right lane line orientation angle respectively. C0 left and C0 right are the first coefficient of the left lane line and the first coefficient of the right lane line respectively. L left is the distance between the center of the rear axle of the vehicle and the left lane line. L right is the distance between the center of the rear axle of the vehicle and the right lane line.

[0069] Specifically, for the process of determining the difference between the target distance and the historical target distance, please refer to the following formulas (5) and (6):

[0070] ΔL left =fabs(L left -L_pre left ) Formula (5);

[0071] ΔL right =fabs(L right -L_preright ) Formula (6);

[0072] Where, L left is the target distance between the center of the vehicle's rear axle and the left lane line. L right is the target distance between the center of the vehicle's rear axle and the right lane line. L_pre left is the historical target distance between the center of the vehicle's rear axle and the left lane line. L_pre right is the historical target distance between the center of the vehicle's rear axle and the right lane line. ΔL left is the difference between the target distance corresponding to the left lane line and the historical target distance. ΔL right is the difference between the target distance corresponding to the right lane line and the historical target distance. fabs may refer to the absolute value.

[0073] It can be understood that the distance between the center of the vehicle's rear axle and the lane line is the displacement of the center of the vehicle's rear axle from the lane line as described above. Exemplarily, calculating the change in the distance between the center of the vehicle's rear axle and the lane line is also whether the difference between the above target distance and the historical target distance is within the limit range L max Therein, L max has the unit of m. L max can be used to represent the third constraint condition corresponding to the third constraint parameter. When ΔL left ≤L max , the left lane line coefficient is considered valid. When ΔL right ≤L max , the right lane line coefficient is considered valid. That is, the above step S13 may be to determine that the lane line detection result of the target vehicle is in an effective state in response to the third constraint parameter satisfying the third constraint condition, and the third constraint condition is related to the target distance and / or the historical target distance.

[0074] It can be considered that by comparing the third constraint parameter with the third constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result. In addition, by setting different historical moments, the accuracy of the lane line detection can be controlled.

[0075] In some other applications, a target distance between a preset part of a target vehicle and a lane line is determined according to a second coefficient in a lane line coefficient. Among them, according to the second coefficient in the lane line coefficient, a lane line orientation angle is determined. Based on the lane line orientation angle and a first coefficient in the lane line coefficient, the target distance between the preset part of the target vehicle and the lane line is determined. Based on the target distance, a lane width is determined. The method for determining the target distance can refer to the above formulas (1) to (4), which will not be elaborated here. Specifically, the process of determining the lane width based on the target distance can refer to formulas (7) and (8):

[0076] Lwidth = L left -L right Formula (7);

[0077] A = L width -VehWidth Formula (8);

[0078] Among them, L left is the distance between the center of the rear axle of the vehicle and the left lane line. L right is the distance between the center of the rear axle of the vehicle and the right lane line. L width is used to represent the lane line width. VehWidth is used to represent the vehicle width of the target vehicle, that is, the vehicle width of the own vehicle. A is used to represent the lane width. The lane width A is used as the fourth constraint parameter.

[0079] According to the lane width and considering that the vehicle width VehWidth (unit: m) of the own vehicle satisfies within the set threshold L_min width range. Among them, L_min width has the unit of m. The set threshold L_min width is used to represent the fourth constraint condition corresponding to the fourth constraint parameter. For example, the lane width A ≥ L_min width , which means that the lane width meets the function activation requirement. That is, the above step S13 can be to determine that the lane line detection result of the target vehicle is in an effective state in response to the fourth constraint parameter satisfying the fourth constraint condition, and the fourth constraint condition is related to the lane width.

[0080] It can be considered that by comparing the fourth constraint parameter with the fourth constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result. In addition, the vehicle widths of different vehicle models may be different. Considering the vehicle width of the own vehicle when considering the lane width can be applicable to different vehicle models. Furthermore, under different vehicle models, the detection results of the lane line detection in this application have high accuracy.

[0081] Please refer to Figure 2 , Figure 2Schematic flow of an embodiment of the lane line detection method of the present application Figure 2 。

[0082] In some embodiments, the lane line information includes the lane line starting point distance, at least one constraint parameter includes a fifth constraint parameter, the constraint condition includes the constraint condition corresponding to the fifth constraint parameter, and the above step S12 may include the following steps: Step S21: Obtain the wheelbase of the target vehicle. Step S22: Use the difference between the lane line starting point distance and the wheelbase as the fifth constraint parameter.

[0083] Specifically, the process of the difference between the lane line starting point distance and the wheelbase can be referred to the following formula (9):

[0084] B = Startpointx - Vehbase Formula (9);

[0085] Where, Startpointx is used to represent the above lane line starting point distance. Vehbase is used to represent the wheelbase of the target vehicle. B is used to represent the difference between the lane line starting point distance and the wheelbase.

[0086] Exemplarily, calculate whether the lane line starting point and the lane line length meet the function activation requirement Xmax. Wherein, the unit of Xmax is m. The threshold Xmax is used to represent the fifth constraint condition corresponding to the fifth constraint parameter.

[0087] According to the lane line starting point distance sent by the lane line (i.e., the lane line starting point distance with the center of the rear axle of the vehicle as the origin), since the lane keeping function uses the image acquisition device in front of the vehicle, that is, the front view camera, it is necessary to calculate whether the result of subtracting the vehicle wheelbase Vehbase (unit: m) from the lane line starting point meets the requirement. When Startpointx - Vehbase ≤ Xmax, it means that the lane line starting point meets the function activation requirement. That is, the above step S13 may be to determine that the lane line detection result of the target vehicle is in an effective state in response to the fifth constraint parameter meeting the fifth constraint condition, and the fifth constraint condition is related to the lane line starting point distance.

[0088] It can be considered that by comparing the fifth constraint parameter with the fifth constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result. In addition, the wheelbases corresponding to different vehicle models may be different. Considering the constraint parameter by adding the wheelbase of the target vehicle can be applicable to different vehicle models. Furthermore, under different vehicle models, the detection result of the lane line detection of the present application has a high accuracy.

[0089] Please refer to Figure 3 , Figure 3 Schematic flow of an embodiment of the lane line detection method of the present applicationFigure 3 。

[0090] In some embodiments, the motion information includes the current vehicle speed, the lane line information includes the lane line coefficients in the target lane line equation corresponding to the target vehicle, at least one constraint parameter includes a sixth constraint parameter, and the constraint condition includes the constraint condition corresponding to the sixth constraint parameter. The above step S12 may include the following steps: Step S31: Determine a target speed based on the current vehicle speed and the second coefficient in the lane line coefficients. The target speed is used to represent the relative speed between the target vehicle and the lane line. Step S32: Use the difference between the target speed and the historical target speed as the sixth constraint parameter. The historical target speed is used to represent the target speed determined at a historical moment before the current moment.

[0091] The target speed is used to represent the relative speed between the target vehicle and the lane line. Specifically, the target speed may be the lateral speed of the target vehicle based on the lane line. Among them, the target speed includes the lateral speed of the vehicle based on the left lane line and / or the lateral speed of the vehicle based on the right lane line.

[0092] Specifically, the process of the above step S31 may refer to the following formulas (10) and (11):

[0093] Vlat left =V×sin(θ left ) Formula (10);

[0094] Vlat right =V×sin(θ right ) Formula (11);

[0095] Among them, θ left and θ right are the left lane line orientation angle and the right lane line orientation angle respectively. The process of determining the lane line orientation angle may refer to the above formulas (1) and (2), which will not be elaborated here. V is used to represent the current speed of the target vehicle, and the unit may be m / s. Vlat left is used to represent the lateral speed of the vehicle based on the left lane line. Vlat right is used to represent the lateral speed of the vehicle based on the right lane line.

[0096] In the above step S32, the target speed includes the lateral speed of the vehicle based on the left lane line and / or the lateral speed of the vehicle based on the right lane line. The difference between the target speed and the historical target speed is used as the third constraint parameter. The historical target speed is determined based on the current vehicle speed in the historical motion information and the second coefficient in the historical lane line coefficient after collecting the historical motion information and historical lane line information at the historical moment. In some application scenarios, the historical moment can be the previous moment before the current moment. In other application scenarios, the historical moment can be a moment before the current moment and in the same traffic scenario as the current moment. The traffic scenario can be scenarios such as elevated roads, flat ground, tunnels, etc.

[0097] Specifically, the process of determining the difference between the target distance and the historical target distance can refer to the following formulas (12) and (13):

[0098] ΔVlat left =fabs(Vlat left -Vlat_pre left ) Formula (12);

[0099] ΔVlat right =fabs(Vlat right -Vlat_pre right ) Formula (13);

[0100] Where, Vlat left is used to represent the current lateral speed of the vehicle based on the left lane line at the current moment. Vlat right is used to represent the current lateral speed of the vehicle based on the right lane line at the current moment. Vlat_pre left is used to represent the historical lateral speed of the vehicle based on the left lane line at the historical moment. Vlat_pre right is used to represent the historical lateral speed of the vehicle based on the right lane line at the historical moment. ΔVlat left is the difference between the target distance of the left lane line and the historical target distance. ΔVlat right is the difference between the target distance of the right lane line and the historical target distance. fabs can refer to the absolute value.

[0101] Exemplarily, calculate whether the change in the current vehicle lateral speed is within the range of the set threshold Vlat max (unit: m / s). Where, Vlat max has the unit of m / s. The set threshold Vlat maxUsed to represent the sixth constraint condition corresponding to the sixth constraint parameter. According to the current vehicle speed V (unit: m / s), the lateral speed of the vehicle based on the left lane line and the lateral speed of the vehicle based on the right lane line are obtained. The lateral speed of the vehicle is calculated based on the lane line signal of the previous frame to obtain the historical target speed. The target speed and the historical target speed are subjected to a difference calculation, and the obtained difference is used as the sixth constraint parameter and compared with the sixth constraint condition. When ΔVlat left ≤Vlat max , it is considered that the left lane line is valid. When ΔVlat right ≤Vlat max , it is considered that the right lane line is valid. That is, the above step S13 may be to determine that the lane line detection result of the target vehicle is in a valid state in response to the sixth constraint parameter satisfying the sixth constraint condition, and the sixth constraint condition is related to the change in the lateral speed of the vehicle.

[0102] It can be considered that by comparing the sixth constraint parameter with the sixth constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result. In addition, by setting different historical moments, the accuracy of lane line detection can be controlled.

[0103] In some embodiments, the lane line information includes the lane line coefficients in the target lane line equation corresponding to the target vehicle, at least one constraint parameter includes a seventh constraint parameter, and the constraint condition includes the constraint condition corresponding to the seventh constraint parameter. The above step S12 may include the following steps: Based on the third coefficient in the lane line coefficients, determine the lane line curvature. Based on the lane line curvature, determine the change in the lane line curvature and use the change in the lane line curvature as the seventh constraint parameter.

[0104] The third coefficient in the lane line coefficients may be the above C2.

[0105] Specifically, for the process of determining the lane line curvature based on the third coefficient in the lane line coefficients, please refer to formulas (14) and (15):

[0106] Curve left =C2 left ×D Formula (14);

[0107] Curve right =C2 right ×D Formula (15);

[0108] Among them, C2 left and C2 right are the third coefficients of the left lane line and the right lane line respectively. Curve leftis the lane curvature of the left lane line at the current moment. Curve right is the lane curvature of the right lane line at the current moment. D can represent a preset value other than 0. For example, D can be set to 2.

[0109] Specifically, based on the lane curvature, the process of determining the change in lane curvature refers to the following formulas (16) and (17):

[0110] ΔCurve left = fabs(Curve left - Curve_pre left ) Formula (16);

[0111] ΔCurve right = fabs(Curve right - Curve_pre right ) Formula (17);

[0112] where Curve left is the lane curvature of the left lane line at the current moment. Curve right is the lane curvature of the right lane line at the current moment. Curve_pre left is the lane curvature of the left lane line at the historical moment. Curve_pre right is the lane curvature of the right lane line at the historical moment. ΔCurve left can represent the change in the lane curvature of the left lane line. ΔCurve right can represent the change in the lane curvature of the left lane line. In some application scenarios, the historical moment can be the previous moment before the current moment. In other application scenarios, the historical moment can be a moment before the current moment and in the same traffic scenario as the current moment. The traffic scenario can be scenarios such as elevated roads, flat ground, tunnels, etc.

[0113] Exemplarily, calculate whether the change in the current lane curvature is within the set range Curve max . The set range Curve max is used to represent the seventh constraint condition corresponding to the seventh constraint parameter. According to the third coefficient C2 left and / or C2 right in the lane line coefficients corresponding to the current moment, calculate the lane curvature of the left lane line and / or the right lane line of the lane where the current vehicle is located. According to the left and right lane curvatures Curve_pre left and / or Curve_pre right calculated based on the previous frame of perception signal。Calculate the difference between the curvature calculated for the previous frame and the curvature calculated at the current moment to obtain the change in the lane line curvature. Compare the lane line curvature change with the set range Curve in the seventh constraint condition max to determine whether the lane line curvature is valid. When ΔCurve left ≤Curve m2x , it indicates that the left lane line curvature is valid. When ΔCurve right ≤Curve max , it indicates that the right lane line curvature is valid. That is, the above step S13 can be to determine that the lane line detection result of the target vehicle is in a valid state in response to the seventh constraint parameter satisfying the seventh constraint condition, and the seventh constraint condition is related to the change in the lane line curvature.

[0114] It can be considered that by comparing the seventh constraint parameter with the seventh constraint condition, it is possible to avoid misjudgment caused by environmental interference when determining the lane line detection result with a single judgment factor, thereby improving the accuracy of the lane line detection result. In addition, by setting different historical moments, the accuracy of lane line detection can be controlled.

[0115] It can be understood that at least one of the constraint parameters determined in the above step S12 can be any one or any combination of the above first constraint parameter to the above seventh constraint parameter, or all of them.

[0116] For the above step S13, the satisfaction of each constraint parameter with the constraint condition can mean that any one or any combination of the above first constraint parameter to the above seventh constraint parameter satisfies its corresponding constraint condition, or all satisfy their corresponding constraint conditions.

[0117] Exemplarily, after the above step S11, when the first constraint parameter satisfies the first constraint condition, the above step S12 can be to determine the target constraint parameter. The target constraint parameter includes but is not limited to any one or more of the above second constraint parameter, the above fifth constraint parameter, the above sixth constraint parameter, and the constraint parameter corresponding to the vehicle lateral position change range. When at least some of the constraint parameters in the target constraint parameter satisfy their respective constraint conditions, the lane line detection result of the target vehicle is determined to be in a valid state.

[0118] Based on the motion information and lane line information collected for the target vehicle at the current moment, the above solution determines at least one constraint parameter, and determines the lane line detection result of the target vehicle through the relationship between the constraint parameter related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line and the constraint condition, which can avoid misjudgment caused by environmental interference when determining the lane line detection result with a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0119] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of an embodiment of the lane line detection device of the present application. The lane line detection device 40 includes an acquisition module 41, a first determination module 42, and a second determination module 43; the acquisition module 41 is configured to acquire motion information and lane line information collected for a target vehicle at a current moment; the first determination module 42 is configured to determine at least one constraint parameter based on the motion information and / or the lane line information, where the at least one constraint parameter is related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line; the second determination module 43 is configured to determine that the lane line detection result of the target vehicle is in an effective state in response to each constraint parameter satisfying a constraint condition.

[0120] In the above solution, at least one constraint parameter is determined based on the motion information and lane line information collected for the target vehicle at the current moment, and the lane line detection result of the target vehicle is determined by the relationship between the constraint parameter related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line and the constraint condition, which can avoid misjudgment caused by environmental interference when determining the lane line detection result by a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0121] For the functions executed by each module, please refer to the lane line detection method, which will not be elaborated here.

[0122] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an embodiment of the electronic device of the present application. The electronic device 50 includes a memory 51 and a processor 52. The processor 52 is configured to execute program instructions stored in the memory 51 to implement the steps in the above embodiment of the lane line detection method. In a specific implementation scenario, the electronic device 50 may include, but is not limited to, a microcomputer, a server. In addition, the electronic device 50 may also include mobile devices such as a laptop computer and a tablet computer, which are not limited here.

[0123] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps in the above-described embodiment of the lane line detection method. The processor 52 may also be referred to as a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with the ability to process signals. The processor 52 may also be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Additionally, the processor 52 may be implemented jointly by integrated circuit chips.

[0124] Based on the motion information and lane line information collected for the target vehicle at the current moment, the above solution determines at least one constraint parameter, and determines the lane line detection result of the target vehicle through the relationship between the constraint parameter related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line, and the constraint condition, which can avoid misjudgment caused by environmental interference when determining the lane line detection result with a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0125] Please refer to Figure 6 , Figure 6 is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. The computer-readable storage medium 60 stores program instructions 601 thereon, and when the program instructions 601 are executed by the processor, the steps in any of the above-described embodiments of the lane line detection method are implemented.

[0126] Based on the motion information and lane line information collected for the target vehicle at the current moment, the above solution determines at least one constraint parameter, and determines the lane line detection result of the target vehicle through the relationship between the constraint parameter related to the speed information of the target vehicle and / or the distance information between the target vehicle and the same lane line, and the constraint condition, which can avoid misjudgment caused by environmental interference when determining the lane line detection result with a single judgment factor, thereby improving the accuracy of the lane line detection result.

[0127] In some embodiments, the functions or modules included in the system provided by the embodiments of the present disclosure can be used to execute the methods described in the above method embodiments, and the specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0128] The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments. For the same or similar parts, reference can be made to each other. For the sake of brevity, they will not be elaborated herein again.

[0129] In several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0130] In addition, each functional unit in the various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks and other various media that can store program codes.

Claims

1. A lane line detection method, characterized in that: The method comprises: Obtain the motion information and lane line information collected from the target vehicle at the current moment; Based on the motion information and / or the lane line information, determining at least one constraint parameter, wherein the at least one constraint parameter is related to the speed information of the target vehicle and / or the distance information between the target vehicle and the lane line; In response to each of the constraint parameters satisfying a constraint condition, the lane line detection result of the target vehicle is determined as the lane line of the target vehicle being in a valid state.

2. The method according to claim 1, characterized in that The lane line information includes a lane line confidence, the at least one constraint parameter includes a first constraint parameter corresponding to the lane line confidence in the lane line information, and in response to each constraint parameter satisfying a constraint condition, determining the lane line detection result of the target vehicle as the lane line of the target vehicle being in a valid state, including: In response to the first constraint parameter satisfying a first constraint condition, the lane line detection result of the target vehicle is determined as the lane line of the target vehicle being in a valid state, and the first constraint condition is related to the lane line confidence.

3. The method according to claim 1, characterized in that: The motion information includes the current vehicle speed, the at least one constraint parameter includes a second constraint parameter, the constraint condition includes a constraint condition corresponding to the second constraint parameter, and determining at least one constraint parameter based on the motion information and / or the lane line information includes: The length of the lane line within a preset time is determined according to the current vehicle speed, and the lane line length is used as the second constraint parameter.

4. The method according to claim 1, characterized in that The lane line information includes a lane line coefficient in a target lane line equation corresponding to the target vehicle, the at least one constraint parameter includes a third constraint parameter and / or a fourth constraint parameter, the constraint condition includes a constraint condition corresponding to the third constraint parameter and / or the fourth constraint parameter, and determining at least one constraint parameter based on the motion information and / or the lane line information includes: Determine a target distance and / or lane width between a preset position of the target vehicle and the lane line according to a first coefficient and a second coefficient in the lane line coefficient; The difference between the target distance and the historical target distance is used as the third constraint parameter, and the historical target distance is used to represent the target distance determined at a historical moment before the current moment; and / or, the lane width is used as the fourth constraint parameter.

5. The method according to claim 1, characterized in that The lane line information includes a lane line starting point distance, the at least one constraint parameter includes a fifth constraint parameter, the constraint condition includes a constraint condition corresponding to the fifth constraint parameter, and determining at least one constraint parameter based on the motion information and / or the lane line information includes: Obtaining the wheelbase of the target vehicle; The difference between the lane line starting point distance and the wheelbase is used as the fifth constraint parameter.

6. The method according to claim 1, characterized in that The motion information includes the current vehicle speed, the lane line information includes the lane line coefficient in the target lane line equation corresponding to the target vehicle, the at least one constraint parameter includes a sixth constraint parameter, the constraint condition includes the constraint condition corresponding to the sixth constraint parameter, and determining at least one constraint parameter based on the motion information and / or the lane line information includes: Determine a target speed based on the current vehicle speed and a second coefficient in the lane line coefficient, wherein the target speed is used to represent a relative speed between the target vehicle and the lane line; The difference between the target speed and the historical target speed is used as the sixth constraint parameter, and the historical target speed is used to represent the target speed determined at a historical moment before the current moment.

7. The method according to claim 1, characterized in that The lane line information includes a lane line coefficient in a target lane line equation corresponding to the target vehicle, the at least one constraint parameter includes a seventh constraint parameter, the constraint condition includes a constraint condition corresponding to the seventh constraint parameter, and determining at least one constraint parameter based on the motion information and / or the lane line information includes: Determining a lane line curvature based on a third coefficient among the lane line coefficients; Based on the lane line curvature, a lane line curvature change is determined, and the lane line curvature change is used as the seventh constraint parameter.

8. A lane line detection device, characterized in that: include: An acquisition module is used to acquire the motion information and lane line information collected from the target vehicle at the current moment; A first determination module, configured to determine at least one constraint parameter based on the motion information and / or the lane line information, wherein the at least one constraint parameter is related to the speed information of the target vehicle and / or the distance information between the target vehicle and the lane line; The second determination module is used to determine the lane line detection result of the target vehicle as the lane line of the target vehicle being in a valid state in response to each of the constraint parameters satisfying the constraint condition.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores program instructions, and the processor retrieves the program instructions from the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 7.

Images