Parameter compensation method and device of vehicle-mounted camera device and auxiliary driving equipment

Abstract

The embodiment of the invention discloses a parameter compensation method and device of a vehicle-mounted camera device and auxiliary driving equipment, relates to the technical field of auxiliary driving, and can effectively improve the accuracy of course angle parameters of the vehicle-mounted camera device and effectively improve the vehicle performance. The method comprises the steps that in the driving process of a target vehicle, driving information of the target vehicle is obtained, the driving information comprises motion state information and first lane information of a lane where the target vehicle is located, and the first lane information is provided by a camera device installed on the target vehicle; determining that the target vehicle is in a linear running scene under the condition that the driving information meets a preset condition, acquiring second lane information of a lane where the target vehicle is located, and determining a compensation value of a course angle parameter of the camera device according to the second lane information; and adjusting the course angle parameter of the camera device according to the compensation value of the course angle parameter to obtain a target course angle parameter.

Description

Technical Field

[0001] This invention relates to the field of driver assistance, and more particularly to a parameter compensation method, device, and driver assistance equipment for an in-vehicle camera device. Background Technology

[0002] In recent years, with the increasing number of autonomous driving projects being implemented, the impact of end-of-line (EOL) calibration assistance on vehicle control has become increasingly important. However, during the EOL calibration process, factors such as target placement, the adjustment of vehicle attitude by the aligner, and deviations between the theoretical parameters input to the camera production line and the actual conditions can all lead to discrepancies between the calibrated and actual values ​​of the camera's extrinsic yaw parameter. Deviations in the yaw parameter can affect the accuracy of vehicle perception and recognition functions, thereby impacting vehicle performance. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a parameter compensation method, device, and driver assistance equipment for an in-vehicle camera device, which can effectively improve the accuracy of the heading angle parameters of the in-vehicle camera device, thereby effectively improving vehicle performance.

[0004] In a first aspect, embodiments of the present invention provide a parameter compensation method for an in-vehicle camera device, comprising: during the driving of a target vehicle, acquiring driving information of the target vehicle, the driving information including motion state information and first lane information of the lane where the target vehicle is located, the first lane information being provided by a camera device installed on the target vehicle; when the driving information meets preset conditions, determining that the target vehicle is in a straight-line driving scenario, and acquiring second lane information of the lane where the target vehicle is located, and determining a compensation value for the heading angle parameter of the camera device based on the second lane information; wherein the second lane information is provided by the camera device; adjusting the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain a target heading angle parameter.

[0005] In one embodiment, the motion state information includes: vehicle yaw rate, vehicle speed, and vehicle centerline position; the first lane information includes: lane curvature radius at the current point, lane curvature radius at the pre-aiming point, lane width, presence of lane lines, lane line deflection angle at the current point, and lane line deflection angle at the pre-aiming point, wherein the current point is the current location of the target vehicle, the pre-aiming point is a preset distance away in the forward direction under the current self-coordinate system of the target vehicle, and the lane line deflection angle is the angle formed by the tangent at any point on the lane and the forward direction under the current self-coordinate system.

[0006] In one embodiment, obtaining the first lane information includes: acquiring a lane line image of the lane where the target vehicle is located through the camera device; fitting the lane line image into a lane line curve using a cubic polynomial; determining the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point based on the first derivative of the lane line curve; and determining the lane curvature radius of the current point and the lane curvature radius of the pre-aiming point based on the second derivative of the lane line curve.

[0007] In one embodiment, the preset conditions include: a first preset condition, a second preset condition, and a third preset condition; the step of determining that the target vehicle is in a straight-line driving scenario when the driving information meets the preset conditions, and determining the compensation value of the heading angle parameter of the camera device based on the lane information, includes: determining that the target vehicle is in a straight-line driving scenario when the driving information meets the first preset condition, and determining whether the driving information meets the second preset condition; when the driving information meets the second preset condition, starting a timer for the time when the driving information simultaneously meets the first and second preset conditions, and determining that the driving information meets the third preset condition when the timer duration is greater than a preset duration threshold; when the driving information meets the third preset condition, acquiring the second lane information and determining the compensation value of the heading angle parameter of the camera device based on the second lane information.

[0008] In one implementation, the first preset condition includes: the vehicle yaw rate is less than a preset angular velocity value, the vehicle speed is greater than a preset speed value, the distance between the vehicle centerline and the lane centerline is less than a preset distance threshold, the lane curvature radius at the current point and the lane curvature radius at the pre-aiming point are both greater than a preset radius threshold, and the lane width is greater than a preset width threshold with both left and right lane lines present; the second preset condition includes: the lane line deflection angle at the current point and the lane line deflection angle at the pre-aiming point are both greater than a first deflection angle threshold; the absolute value of the difference between the lane line deflection angle at the current point and the lane line deflection angle at the pre-aiming point is less than a preset deflection angle difference value; and the flag of the preset calibration operation of the target vehicle is a preset value.

[0009] In one embodiment, the second lane information includes the lane deflection angle at the current point; the step of acquiring the second lane information and determining the compensation value of the heading angle parameter of the camera device based on the second lane information includes: acquiring the lane deflection angle at the current point once at a preset time interval during the driving of the target vehicle; adjusting the compensation value of the heading angle parameter from the initial value according to a preset slope to obtain an adjusted value; if the difference between the adjusted value and the lane deflection angle at the current point is less than a preset adjustment threshold, determining the adjusted value as a preliminary compensation value; jumping back to the step of acquiring the lane deflection angle at the current point once at a preset time interval during the driving of the target vehicle and continuing to execute, iterating N times to obtain N preliminary compensation values, and averaging the N preliminary compensation values ​​to obtain the compensation value of the heading angle parameter, where N is a positive integer.

[0010] In one embodiment, adjusting the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter includes: subtracting the original heading angle parameter of the camera device from the compensation value of the heading angle parameter, and using the difference as the target heading angle parameter.

[0011] In one embodiment, after adjusting the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter, the method further includes: jumping back to the step of acquiring the lane line deviation angle of the current point at a preset time interval during the driving process of the target vehicle and continuing to execute, iterating M times to obtain M preliminary compensation values; where M is a positive integer; if all M preliminary compensation values ​​are greater than a preset compensation threshold, re-determining the compensation value of the heading angle parameter of the camera device according to the second lane information, wherein the preset compensation threshold is greater than the first deviation angle threshold.

[0012] In one embodiment, after re-determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: summing the compensation values ​​of the heading angle in each iteration to obtain a compensation accumulation value; if the compensation accumulation value is greater than a preset accumulation threshold, setting the compensation accumulation value to 0 and restoring the heading angle parameter to the factory settings of the target vehicle.

[0013] In one implementation, after the target vehicle returns to the production line for calibration, the accumulated compensation value is set to 0, and the factory settings of the heading angle parameter are updated.

[0014] In one embodiment, after determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: using the compensation value of the heading angle parameter to perform lateral centering control on the target vehicle.

[0015] In one embodiment, after determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: jumping back to the step of acquiring the driving information of the target vehicle during its driving process and continuing to execute the step, iterating in a loop to obtain multiple compensation values ​​of the heading angle parameter; accumulating the compensation values ​​of the multiple heading angle parameters to obtain a compensation accumulation value; if the compensation accumulation value is greater than a preset accumulation threshold, setting the compensation accumulation value to 0 and restoring the heading angle parameter to the factory settings of the target vehicle.

[0016] Secondly, embodiments of the present invention also provide a parameter compensation device for a vehicle-mounted camera, comprising: an acquisition unit, configured to acquire driving information of the target vehicle during its driving process, the driving information including motion state information and first lane information of the lane where the target vehicle is located, the first lane information being provided by a camera installed on the target vehicle; a determination unit, configured to determine that the target vehicle is in a straight-line driving scenario when the driving information meets preset conditions, and acquire second lane information of the lane where the target vehicle is located, and determine a compensation value for the heading angle parameter of the camera based on the second lane information; wherein the second lane information is provided by the camera; and an adjustment unit, configured to adjust the heading angle parameter of the camera based on the compensation value of the heading angle parameter to obtain a target heading angle parameter.

[0017] In one embodiment, the motion state information includes: vehicle yaw rate, vehicle speed, and vehicle centerline position; the first lane information includes: lane curvature radius at the current point, lane curvature radius at the pre-aiming point, lane width, presence of lane lines, lane line deflection angle at the current point, and lane line deflection angle at the pre-aiming point, wherein the current point is the current location of the target vehicle, the pre-aiming point is a preset distance away in the forward direction under the current self-coordinate system of the target vehicle, and the lane line deflection angle is the angle formed by the tangent at any point on the lane and the forward direction under the current self-coordinate system.

[0018] In one embodiment, the acquisition unit is specifically configured to: acquire a lane line image of the lane where the target vehicle is located through the camera device; fit the lane line image into a lane line curve using a cubic polynomial; determine the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point based on the first derivative of the lane line curve; and determine the lane curvature radius of the current point and the lane curvature radius of the pre-aiming point based on the second derivative of the lane line curve.

[0019] In one embodiment, the preset conditions include: a first preset condition, a second preset condition, and a third preset condition; the determining unit includes: a first determining module, configured to determine that the target vehicle is in a straight-line driving scenario when the driving information meets the first preset condition, and to determine whether the driving information meets the second preset condition; a second determining module, configured to start timing for the time when the driving information simultaneously meets the first and second preset conditions when the driving information meets the second preset condition, and to determine that the driving information meets the third preset condition when the timing duration is greater than a preset duration threshold; and a third determining module, configured to acquire the second lane information and determine the compensation value of the heading angle parameter of the camera device based on the second lane information when the driving information meets the third preset condition.

[0020] In one embodiment, the first preset conditions include: the vehicle yaw rate is less than a preset angular velocity value, the vehicle speed is greater than a preset speed value, the distance between the vehicle centerline and the lane centerline is less than a preset distance threshold, the lane curvature radius of the current point and the lane curvature radius of the pre-aiming point are both greater than a preset radius threshold, and the lane width is greater than a preset width threshold and both left and right lane lines exist.

[0021] In one embodiment, the second preset condition includes: the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point are both greater than a first deflection angle threshold; and the absolute value of the difference between the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point is less than a preset deflection angle difference value.

[0022] In one embodiment, the second preset condition further includes: the flag bit of the preset calibration operation of the target vehicle is a preset value.

[0023] In one embodiment, the second lane information includes the lane deflection angle at the current point; the third determining module includes: an acquisition submodule, configured to acquire the lane deflection angle at the current point at preset time intervals during the driving of the target vehicle; an adjustment submodule, configured to adjust the compensation value of the heading angle parameter from an initial value according to a preset slope to obtain an adjusted value; a determining submodule, configured to determine the adjusted value as a preliminary compensation value if the difference between the adjusted value and the lane deflection angle at the current point is less than a preset adjustment threshold; and a triggering submodule, configured to trigger the acquisition submodule to continue acquiring the lane deflection angle at the current point at preset time intervals during the driving of the target vehicle, iterating N times to obtain N preliminary compensation values, and averaging the N preliminary compensation values ​​to obtain the compensation value of the heading angle parameter, where N is a positive integer.

[0024] In one embodiment, the adjustment unit is specifically used to: subtract the original heading angle parameter of the camera device from the compensation value of the heading angle parameter, and use the difference as the target heading angle parameter.

[0025] In one embodiment, the device further includes: a first triggering unit, configured to, after adjusting the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter, trigger the acquisition submodule to continue acquiring the lane line deflection angle of the current point once at a preset time interval during the driving process of the target vehicle, iterating M times to obtain M of the preliminary compensation values; wherein M is a positive integer; the determining unit is further configured to, if all M of the preliminary compensation values ​​are greater than a preset compensation threshold, re-determine the compensation value of the heading angle parameter of the camera device according to the second lane information, wherein the preset compensation threshold is greater than the first deflection angle threshold.

[0026] In one embodiment, the device further includes: an accumulation unit, configured to accumulate the compensation values ​​of the heading angle in each iteration after re-determining the compensation value of the heading angle parameter of the camera device based on the second lane information, to obtain a compensation accumulation value; and a recovery unit, configured to set the compensation accumulation value to 0 and restore the heading angle parameter to the factory settings of the target vehicle if the compensation accumulation value is greater than a preset accumulation threshold.

[0027] In one embodiment, the device further includes an update unit, configured to set the compensation accumulation value to 0 and update the factory settings of the heading angle parameter after the target vehicle returns to the production line for off-line calibration.

[0028] In one embodiment, the device further includes a control unit, configured to perform lateral centering control on the target vehicle using the compensation value of the heading angle parameter after determining the compensation value of the heading angle parameter of the camera device based on the second lane information.

[0029] In one embodiment, the device further includes: a second triggering unit, configured to, after determining the compensation value of the heading angle parameter of the camera device based on the second lane information, trigger the acquisition unit to continue acquiring the driving information of the target vehicle during its driving process, iteratively obtaining multiple compensation values ​​of the heading angle parameter; an accumulation unit, configured to accumulate the compensation values ​​of the multiple heading angle parameters to obtain a compensation accumulation value; and a recovery unit, configured to, if the compensation accumulation value is greater than a preset accumulation threshold, set the compensation accumulation value to 0 and restore the heading angle parameter to the factory settings of the target vehicle.

[0030] Thirdly, embodiments of the present invention also provide a driver assistance device, including a processor, a memory, and an in-vehicle camera device. The processor is coupled to the memory and the in-vehicle camera device respectively. The memory stores executable program code. The processor reads the executable program code stored in the memory to run the program corresponding to the executable program code, and executes any parameter compensation method for an in-vehicle camera device provided by the embodiments of the present invention to perform parameter compensation for the in-vehicle camera device.

[0031] The parameter compensation method, device, and driver assistance equipment for the vehicle-mounted camera device provided in the embodiments of the present invention can acquire the driving information of the target vehicle during the driving process of the target vehicle. When the driving information meets preset conditions, it is determined that the target vehicle is in a straight-line driving scenario, and the second lane information of the lane where the target vehicle is located is acquired. The compensation value of the heading angle parameter of the camera device is determined according to the second lane information, and the heading angle parameter of the camera device is adjusted according to the compensation value of the heading angle parameter to obtain the target heading angle parameter. Since the target vehicle's driving information can include motion state information and the first lane information of the lane in which the target vehicle is located, the motion state information and the first lane information can be combined to more accurately determine whether the vehicle is currently in a straight-line driving scenario. If it is determined that the target vehicle is in a straight-line driving scenario, then the lane in which the target vehicle is traveling should theoretically also be straight. By further obtaining the second lane information, the actual situation of the lane in which the vehicle is traveling can be known. Since the second lane information is obtained by the camera device, if there is an error in the heading angle parameter of the camera device, then the actual situation of the second lane information obtained by the camera device will differ from the theoretical straight situation. Conversely, this difference can also reflect the error of the heading angle parameter of the camera device. In this way, the compensation value of the heading angle parameter of the camera device can be determined. After compensating the heading angle parameter according to the compensation value, the obtained target heading angle parameter can make the camera device's perception more accurate, thereby effectively improving vehicle performance. Attached Figure Description

[0032] 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A flowchart of a parameter compensation method for a vehicle-mounted camera device provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the lanes corresponding to the current point and the preview point in an embodiment of the present invention; Figure 3 A detailed flowchart of a parameter compensation method for a vehicle-mounted camera device provided in an embodiment of the present invention; Figure 4 A schematic diagram of a parameter compensation device for a vehicle-mounted camera provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of a driver assistance device provided in an embodiment of the present invention. Detailed Implementation

[0034] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0035] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0036] In a first aspect, embodiments of the present invention provide a parameter compensation method for an in-vehicle camera device, such as... Figure 1 As shown, it may include: Step S101: During the driving process of the target vehicle, the driving information of the target vehicle is acquired. The driving information includes motion state information and first lane information of the lane where the target vehicle is located. The first lane information is provided by a camera device installed on the target vehicle.

[0037] The target vehicle can be equipped with an on-board camera device, and the target vehicle can be in motion. That is to say, the target vehicle has completed the off-line calibration, and the various external parameters of the camera device have been configured and are in use.

[0038] During the movement of the target vehicle, its driving information can be acquired. This driving information can include both the vehicle's motion state information and information about the lane in which the target vehicle is located, i.e., first lane information. Both motion state information and first lane information can include one or more different subcategories. Depending on the type of information, different sensors can be used to acquire the corresponding driving information. For example, in one embodiment, motion state information can be acquired using a speed sensor, attitude sensor, etc., while first lane information can be acquired using an image sensor, such as an onboard camera device. The camera device can include various imaging devices; for example, in one instance, it can include a camera device that images in the visible light and / or infrared light bands.

[0039] Step S102: When the driving information meets the preset conditions, determine that the target vehicle is in a straight-line driving scenario, and obtain the second lane information of the lane where the target vehicle is located. Determine the compensation value of the heading angle parameter of the camera device based on the second lane information; wherein, the second lane information is provided by the camera device.

[0040] In this step, it can be determined whether the acquired driving information meets preset conditions. If the preset conditions are met, it is determined that the target vehicle is in a straight-line driving scenario, and the second lane information is further acquired. Based on the second lane information, the compensation value of the camera device's heading angle parameter is determined. It should be noted that the second lane information is different from the first lane information. The first lane information is a part of the driving information. The second lane information is acquired only after the driving information is acquired and it is determined that the driving information meets the preset conditions. The second lane information can also be acquired by a camera device installed on the target vehicle.

[0041] The heading angle parameter of the camera device is an external parameter of the camera device. After the camera device is installed in the vehicle, it is calibrated before the vehicle leaves the factory to determine the specific value of the heading angle parameter. In this step, a compensation value can be determined for the calibrated heading angle parameter based on the second lane information obtained during vehicle operation, in order to compensate for the error of the calibrated heading angle parameter.

[0042] Step S103: Adjust the heading angle parameters of the camera device according to the compensation value of the heading angle parameters to obtain the target heading angle parameters.

[0043] In this step, the heading angle parameter can be corrected using the compensation value of the heading angle parameter determined in the previous step to obtain the target heading angle parameter. The corrected target heading angle parameter will be closer to the actual situation than the factory value of the uncorrected heading angle parameter, thereby enabling the camera device to perceive more accurately and effectively improve vehicle performance.

[0044] The parameter compensation method for a vehicle-mounted camera device provided in the embodiments of the present invention can acquire the driving information of the target vehicle during its driving process. When the driving information meets preset conditions, it can determine that the target vehicle is in a straight-line driving scenario and acquire the second lane information of the lane where the target vehicle is located. Based on the second lane information, it can determine the compensation value of the heading angle parameter of the camera device and adjust the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter. Since the target vehicle's driving information can include motion state information and the first lane information of the lane in which the target vehicle is located, the motion state information and the first lane information can be combined to more accurately determine whether the vehicle is currently in a straight-line driving scenario. If it is determined that the target vehicle is in a straight-line driving scenario, then the lane in which the target vehicle is traveling should theoretically also be straight. By further obtaining the second lane information, the actual situation of the lane in which the vehicle is traveling can be known. Since the second lane information is obtained by the camera device, if there is an error in the heading angle parameter of the camera device, then the actual situation of the second lane information obtained by the camera device will differ from the theoretical straight situation. Conversely, this difference can also reflect the error of the heading angle parameter of the camera device. In this way, the compensation value of the heading angle parameter of the camera device can be determined. After compensating the heading angle parameter according to the compensation value, the obtained target heading angle parameter can make the camera device's perception more accurate, thereby effectively improving vehicle performance.

[0045] Specifically, in step S101, the acquired driving information of the target vehicle may include the target vehicle's motion state information and the first lane information of the lane in which the target vehicle is located. Both the motion state information and the first lane information may include one or more subdivisions. For example, in some embodiments, the motion state information may include: vehicle yaw rate, vehicle speed, and vehicle centerline position; the first lane information may include: the lane curvature radius at the current point, the lane curvature radius at the preview point, the lane width, whether the lane line exists, the lane line deviation angle at the current point, and the lane line deviation angle at the preview point.

[0046] Here, vehicle yaw rate, also known as vehicle heading angular velocity or yaw rate, refers to the angular velocity of the target vehicle's longitudinal axis around the instantaneous steering center, reflecting the rotational dynamics of the target vehicle during lateral movement. Vehicle speed refers to the displacement of the target vehicle per unit time. Vehicle centerline position refers to the location of the target vehicle's longitudinal axis.

[0047] The "current point" mentioned here can refer to the current location of the target vehicle (e.g., the center point of the rear axle of the target vehicle). In the target vehicle's current auto-coordinate system, the coordinate of the current point in the vehicle's current forward direction is 0. The "pre-aiming point" mentioned here can be a preset distance in the forward direction in the target vehicle's current auto-coordinate system. For example, if the preset distance is L, then in the target vehicle's current auto-coordinate system, the coordinate of the pre-aiming point in the vehicle's current forward direction is L. The "lane line deviation angle" mentioned here can refer to the angle formed by the tangent at any point on the lane line and the forward direction in the current auto-coordinate system. In the embodiments of the present invention, when both left and right lane lines exist in the lane where the target vehicle is located, the lane line deviation angle of the current point can include the lane line deviation angle of the left lane line at the current point and the lane line deviation angle of the right lane line at the current point. Similarly, the lane line deviation angle of the pre-aiming point can also include the lane line deviation angle of the left lane line at the pre-aiming point and the lane line deviation angle of the right lane line at the pre-aiming point. For example, the lane curvature radius R1 of the current point, the lane curvature radius R2 of the preview point, the lane line deviation angle θ1 of the current point, and the lane line deviation angle θ2 of the preview point can be illustrated as follows: Figure 2 As shown.

[0048] In some embodiments, step S101 of obtaining the first lane information may include: acquiring a lane line image of the lane where the target vehicle is located through the camera device; fitting the lane line image into a lane line curve using a cubic polynomial; determining the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point based on the first derivative of the lane line curve; and determining the lane curvature radius of the current point and the lane curvature radius of the pre-aiming point based on the second derivative of the lane line curve.

[0049] In this embodiment of the invention, an in-vehicle camera, such as a video camera, can be used to record the road conditions in front of the target vehicle in real time, capturing lane line images of the lane where the target vehicle is located. The lane lines are then modeled based on these images. Specifically, a cubic polynomial can be used to fit the lane line curve, thereby characterizing the extension of the lane lines. For example, in the target vehicle's own coordinate system, with the forward direction as the x-axis and the direction perpendicular to the forward direction as the y-axis, the following equation can be established: y=C0+C1 x+C2 x 2 +C3 x 3 (1) Where C0, C1, C2, and C3 are the coefficients of each term of the cubic polynomial, and all of them are real numbers.

[0050] The first derivative of the above cubic polynomial is: y'=C1+2 C2 x +3 C3 x 2 (2) The second derivative of the above cubic polynomial is: y''=2 C2 +6 C3 x (3) Substituting the coordinates of the current point x=0 into the first derivative of the cubic polynomial (2), we can obtain the slope of the lane line at the current point as C1. Since the slope is the tangent of the angle, we can determine the angle between the tangent of the lane line at the current point and the x-axis, i.e., the lane line deflection angle θ1, based on the arctangent function. Similarly, substituting the coordinates of the aiming point x=L into the first derivative of the cubic polynomial (2), we can obtain the slope of the lane line at the aiming point as C1+2. C2 Since the slope is the tangent of the angle, the angle between the tangent of the lane line at the aiming point and the x-axis can be determined by the arctangent function, which is the lane line deflection angle θ2.

[0051] Similarly, substituting the coordinates of the current point x=0 into the second derivative of the cubic polynomial (3), we can obtain the second derivative of the lane line at the current point as 2. C2, based on the relevant known information, when the lane line is approximately a straight line, the first derivative of the lane line is very small (close to 0, much less than 1). Therefore, the second derivative is approximately equal to the curvature of the lane line. Since curvature is equal to the reciprocal of the radius of curvature, we can determine that the radius of curvature of the lane line at the current point is 1 / (2π√3 / 2π√3 / 2). C2). Similarly, substituting the coordinates x=L of the pre-aiming point into the second derivative of the cubic polynomial (3), we can obtain the second derivative of the lane line at the pre-aiming point as 2. C2+6 C3 L, thus determining the radius of curvature of the lane line at the pre-aiming point as 1 / (2 C2+6 C3 L).

[0052] After obtaining the driving information of the target vehicle, it can be determined in step S102 whether the driving information meets the preset conditions. If the preset conditions are met, it is determined that the target vehicle is in a straight-line driving scenario, and the second lane information is obtained. The compensation value of the heading angle parameter of the vehicle-mounted camera device of the target vehicle is determined based on the second lane information.

[0053] Specifically, in one embodiment of the present invention, the preset conditions may include: a first preset condition, a second preset condition, and a third preset condition. Based on this, step S102, when the driving information meets the preset conditions, determines that the target vehicle is in a straight-line driving scenario, and determines the compensation value of the heading angle parameter of the camera device according to the lane information, which may include: when the driving information meets the first preset condition, determining that the target vehicle is in a straight-line driving scenario, and determining whether the driving information meets the second preset condition; when the driving information meets the second preset condition, starting a timer for the time when the driving information simultaneously meets the first and second preset conditions, and determining that the driving information meets the third preset condition when the timer duration is greater than a preset duration threshold; when the driving information meets the third preset condition, acquiring the second lane information and determining the compensation value of the heading angle parameter of the camera device according to the second lane information.

[0054] In this embodiment of the invention, after acquiring the driving information of the target vehicle, it can be sequentially determined whether the driving information meets the first preset condition, the second preset condition, and the third preset condition. The first preset condition determines whether the target vehicle is in a straight-line driving scenario. This is because in straight-line driving, the learning of the target vehicle's heading angle parameters can minimize other interfering factors. For example, in non-straight-line driving, the learning of heading angle parameters based on lane information will be affected by the current non-straight-line environment, preventing the correct learning of the heading angle parameters. If the first preset condition is met, the second preset condition can be used to further determine whether it is suitable to use the current driving conditions to determine the compensation value of the heading angle parameters. If both the first and second preset conditions are met, a timer can be started for the duration when the driving information simultaneously meets both conditions. If the timer duration exceeds a preset threshold, the driving information is determined to meet the third preset condition. That is, if the state of the driving information simultaneously meeting both conditions continues for more than the preset duration, the third preset condition is considered met. If the duration of this state is insufficient, the third preset condition is not considered met. The specific value of the preset duration threshold can be set and adjusted as needed, and the embodiments of the present invention do not limit this. Since the target vehicle is in motion, if the third preset condition is met, the second lane information can be further obtained, and the compensation value of the heading angle parameter can be learned based on the second lane information.

[0055] In one implementation, the first preset condition may include: the vehicle yaw rate is less than a preset angular velocity value; the vehicle speed is greater than a preset speed value; the distance between the vehicle centerline and the lane centerline is less than a preset distance threshold; the lane curvature radius at the current point and the lane curvature radius at the pre-aiming point are both greater than a preset radius threshold; and the lane width is greater than a preset width threshold, with both left and right lane lines present. When the first preset condition is met, it can be determined that the current target vehicle is in a straight-line driving scenario. The second preset condition may include: the lane line deflection angle at the current point and the lane line deflection angle at the pre-aiming point are both greater than a first deflection angle threshold; and the absolute value of the difference between the lane line deflection angle at the current point and the lane line deflection angle at the pre-aiming point is less than a preset deflection angle difference value.

[0056] The second preset condition is to compare whether the lane line deviation angle is greater than a threshold, including the lane line deviation angle of the current point and the preview point. It can be that both the lane line deviation angle of the current point and the lane line deviation angle of the preview point are greater than the first deviation angle threshold, and the absolute value of the difference between the lane line deviation angle of the current point and the lane line deviation angle of the preview point is less than the preset deviation angle difference. It can be determined that the lane line deviation angle has deviated from the position of the target vehicle during the operation of the target vehicle, and then the second preset condition is met.

[0057] Furthermore, based on the above-mentioned content, in some embodiments, the second preset condition may further include: the flag bit of the preset calibration operation of the target vehicle is a preset value. Specifically, after the target vehicle is powered on, it can perform some preset calibration operations, such as automatic start-up sensing self-calibration or dynamic calibration. If the sensing self-calibration or dynamic calibration is completed, the corresponding calibration type MCU2Func_CamCaliType can be set to 0. After detecting the flag indicating that the calibration is completed, the learning of the heading angle parameter compensation value of the vehicle-mounted camera device is not required. If the vehicle system detects that the calibration type MCU2Func_CamCaliType is set to 1, the preset calibration operation is not completed, and the second preset condition is met. The learning of the heading angle parameter compensation value of the vehicle-mounted camera device can then be performed to determine the compensation value.

[0058] Specifically, in some embodiments, the second lane information may include the lane deflection angle of the current point. Therefore, step S102, which involves obtaining the second lane information and determining the compensation value of the heading angle parameter of the camera device based on the second lane information, may include: acquiring the lane deflection angle of the current point at preset time intervals during the driving of the target vehicle; adjusting the compensation value of the heading angle parameter from its initial value according to a preset slope to obtain an adjusted value; determining the adjusted value as a preliminary compensation value if the difference between the adjusted value and the lane deflection angle of the current point is less than a preset adjustment threshold; and continuing execution of the step of acquiring the lane deflection angle of the current point at preset time intervals during the driving of the target vehicle, iterating N times to obtain N preliminary compensation values, and averaging the N preliminary compensation values ​​to obtain the compensation value of the heading angle parameter, where N is a positive integer.

[0059] In this embodiment, as the target vehicle moves, its relative position to the lane lines changes continuously. During this process, the lane line deflection angle at the current point can be acquired at preset intervals, and multiple lane line deflection angles at the current point can be acquired to complete the sampling of the lane line deflection angle. The difference between the lane line deflection angle at the current point and the theoretical value of the lane line deflection angle (the theoretical value of the lane line deflection angle in a straight-line driving scenario is 0) can be used as the compensation value for the heading angle parameter. For example, in one example, in the second lane information, the lane line deflection angle at the current point is 0.02 degrees, while the theoretical value of the lane line deflection angle is 0 degrees. Therefore, the compensation value for the heading angle parameter is 0.02 - 0 = 0.02 degrees.

[0060] It should be noted that since the target vehicle is in motion, the current position is constantly changing, and the lane lines are also constantly changing. Therefore, the lane deflection angle at the current point is also fluctuating slightly. To obtain a more stable and accurate compensation value for the heading angle parameter, in one embodiment of the invention, the compensation value of the heading angle parameter can be adjusted from its initial value with a preset slope to obtain an adjusted value. This adjusted value is then gradually made closer to the newly determined target value. If the difference between the adjusted value and the target value is less than a preset adjustment threshold, this adjusted value can be considered a preliminary compensation value, thus completing one round of preliminary compensation value determination. This process is iterated N times to determine N corresponding preliminary compensation values. The average of these N preliminary compensation values ​​yields the compensation value for the heading angle parameter. For example, N can be 8, and the average of the 8 preliminary compensation values ​​yields the compensation value for the heading angle parameter.

[0061] After obtaining the compensation value of the heading angle parameter, the heading angle parameter of the camera device can be adjusted in step S103 according to the compensation value to obtain the target heading angle parameter. Specifically, in one embodiment, adjusting the heading angle parameter of the camera device according to the compensation value to obtain the target heading angle parameter in step S103 may include: subtracting the original heading angle parameter of the camera device from the compensation value of the heading angle parameter, and using the difference as the target heading angle parameter.

[0062] This invention provides a specific implementation of adjusting the target heading angle parameter in the parameter compensation method. The original heading angle parameter and the compensation value of the acquired heading angle parameter are subtracted, and the difference is used as the target heading angle parameter. The compensation value of the heading angle parameter can be positive or negative, corresponding to a leftward or rightward correction of the heading angle parameter. For example, in one example, if the original heading angle parameter of the camera device is 1 degree and the compensation value is 0.2 degrees, then the target heading angle parameter is 1 degree - 0.2 degrees = 0.8 degrees.

[0063] Further, in some embodiments, after step S103 adjusts the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter, the parameter compensation method provided by the embodiments of the present invention may further include: jumping back to the step of obtaining the lane line deviation angle of the current point once at a preset time interval during the driving process of the target vehicle and continuing to execute, iterating M times to obtain M preliminary compensation values; where M is a positive integer; if all M preliminary compensation values ​​are greater than a preset compensation threshold, the compensation value of the heading angle parameter of the camera device is re-determined according to the second lane information, wherein the preset compensation threshold is greater than the first deviation angle threshold.

[0064] In other words, after determining the compensation value of the heading angle parameter, multiple preliminary compensation values ​​can be determined and compared with the preset compensation threshold. If M consecutive preliminary compensation values ​​are greater than the preset compensation threshold, the compensation value of the previously determined heading angle parameter is cleared to zero, and the current lane angle is collected and the compensation value of the heading angle parameter is determined again based on the cubic polynomial fitted by the second lane information.

[0065] Furthermore, in some embodiments, after re-determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the parameter compensation method provided by the embodiments of the present invention may further include: summing the compensation values ​​of the heading angle in each iteration to obtain a compensation accumulation value; if the compensation accumulation value is greater than a preset accumulation threshold, setting the compensation accumulation value to 0, and restoring the heading angle parameter to the factory settings of the target vehicle.

[0066] In this embodiment of the invention, the compensation accumulation value represents the cumulative effect of multiple compensations. For example, if the compensation value of the heading angle obtained from the first compensation is 0.2 and the compensation value of the heading angle obtained from the second compensation is 0.3, then the compensation accumulation value is 0.2 + 0.3 = 0.5. If the preset accumulation threshold is 0.4, then the compensation accumulation value has exceeded the threshold. Accordingly, the compensation accumulation value can be set to 0 to avoid large errors caused by continuous compensation of the heading angle parameter in one direction.

[0067] In one implementation, after the target vehicle returns to the production line for calibration, the accumulated compensation value is set to 0, and the factory setting of the heading angle parameter is updated. In this embodiment of the invention, since the target vehicle has already returned to the production line for recalibration, the factory value of the heading angle parameter will also be reset. Therefore, the original accumulated compensation value is meaningless and can be set to 0.

[0068] In the foregoing embodiments, after obtaining the compensation value of the heading angle parameter, the heading angle parameter can be adjusted using this compensation value to obtain the target heading angle parameter. However, the embodiments of the present invention are not limited to this. In other embodiments of the present invention, the target heading angle parameter can be stored when the power is off and used the next time it is powered on. That is to say, after determining the compensation value of the heading angle parameter, it may not be possible to immediately improve vehicle performance by correcting the heading angle parameter of the camera device. Therefore, in one embodiment of the present invention, after determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the compensation value of the heading angle parameter can also be used to perform lateral centering control on the target vehicle, thereby immediately correcting the problem of failure to center laterally due to the error of the heading angle parameter, effectively improving the lateral control performance of the vehicle and the user experience.

[0069] This invention provides an implementation of the heading angle parameter of the camera device in the parameter compensation method. After obtaining a cubic polynomial by fitting lane information, the heading angle parameter in the polynomial is collected and compensation learning is performed to obtain the compensation value of the heading angle parameter. The compensation value of the heading angle parameter can correct the heading angle parameter for use in the control module of the target vehicle to control lateral centering. The compensation value can be positive or negative, and the corresponding control of the target vehicle can be adjusted to the left or right to meet the lateral centering of the target vehicle.

[0070] In some embodiments, after determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: jumping to the step of acquiring the driving information of the target vehicle during the driving process of the target vehicle and continuing to execute, iterating in a loop to obtain multiple compensation values ​​of the heading angle parameter; and summing the multiple compensation values ​​of the heading angle parameter to obtain a compensation sum value. If the accumulated compensation value is greater than a preset accumulated threshold, the accumulated compensation value is set to 0, and the heading angle parameter is restored to the factory settings of the target vehicle.

[0071] This invention provides further implementations of the parameter compensation method after determining the compensation value of the heading angle parameter for the second lane information. Based on the driving information of the target vehicle, a cubic polynomial of the lane is fitted, and the current lane angle is continuously collected. The method is iteratively learned to obtain multiple compensation values ​​for the heading angle parameter. The iterative learning of the compensation value of the heading angle parameter is to update the heading angle parameter of the target vehicle to obtain a more accurate heading angle parameter. The compensation values ​​of the learned heading angle parameter are accumulated to obtain a compensation accumulation value. It is determined whether the compensation accumulation value is within the range of a preset accumulation threshold. If it exceeds the preset accumulation threshold, the compensation accumulation value is set to 0, and the heading angle parameter is restored to the factory settings of the target vehicle.

[0072] The parameter compensation method for the vehicle-mounted camera device provided in the present invention will be described in detail below through a specific embodiment.

[0073] like Figure 3 As shown, the parameter compensation method for the vehicle-mounted camera device provided in the embodiments of the present invention may include: S201. During the driving process of the target vehicle, the driving information of the target vehicle is obtained, including motion state information and first lane information; The acquisition of the first lane information may include: The lane line image of the target vehicle's lane is acquired using a camera device, and determined based on the lane line image. The lane line image is fitted into a lane line curve using a cubic polynomial. The lane line deflection angle of the current point and the lane line deflection angle of the preview point are determined based on the first derivative of the lane line curve, and the lane curvature radius of the current point and the lane curvature radius of the preview point are determined based on the second derivative of the lane line curve.

[0074] S202. If the driving information meets the first preset condition, determine that the target vehicle is in a straight-line driving scenario, and determine whether the driving information meets the second preset condition. S203. When the driving information meets the second preset condition, start timing for the time when the driving information simultaneously meets the first preset condition and the second preset condition. If the timing duration is greater than a preset duration threshold, determine that the driving information meets the third preset condition. S204. When the driving information meets the third preset condition, during the driving process of the target vehicle, the lane line deviation angle of the current point is acquired once at a preset time interval. S205. Adjust the compensation value of the heading angle parameter from the initial value according to the preset slope to obtain the adjusted value; S206. If the difference between the adjustment value and the lane line deviation angle at the current point is less than a preset adjustment threshold, the adjustment value is determined to be a pre-compensation value. S207. Jump to step S204 and continue execution. Iterate N times to obtain N preliminary compensation values. Calculate the average of the N preliminary compensation values ​​to obtain the compensation value of the heading angle parameter, where N is a positive integer.

[0075] S208. Subtract the original heading angle parameter of the camera device from the compensation value of the heading angle parameter, and use the difference as the target heading angle parameter.

[0076] S209. Jump to step S201 and continue execution, iterating in a loop to obtain compensation values ​​for multiple heading angle parameters; S210. The compensation values ​​of the multiple heading angle parameters are summed to obtain the compensation sum value; S211. If the accumulated compensation value is greater than the preset accumulated threshold, the accumulated compensation value is set to 0, and the heading angle parameter is restored to the factory setting of the target vehicle.

[0077] Secondly, embodiments of the present invention also provide a parameter compensation device for a vehicle-mounted camera, which can effectively improve the accuracy of the heading angle parameters of the vehicle-mounted camera, thereby effectively improving vehicle performance.

[0078] like Figure 4 As shown, the parameter compensation device for the vehicle-mounted camera provided in the embodiments of the present invention may include: The acquisition unit 31 is used to acquire the driving information of the target vehicle during the driving process of the target vehicle. The driving information includes motion state information and first lane information of the lane where the target vehicle is located. The first lane information is provided by a camera device installed on the target vehicle. The determining unit 32 is configured to determine that the target vehicle is in a straight-line driving scenario when the driving information meets preset conditions, and to obtain the second lane information of the lane where the target vehicle is located, and to determine the compensation value of the heading angle parameter of the camera device based on the second lane information; wherein the second lane information is provided by the camera device; The adjustment unit 33 is used to adjust the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter.

[0079] The parameter compensation device for the vehicle-mounted camera provided in the embodiments of the present invention can acquire the driving information of the target vehicle during the driving process of the target vehicle. When the driving information meets preset conditions, it determines that the target vehicle is in a straight-line driving scenario and acquires the second lane information of the lane where the target vehicle is located. Based on the second lane information, it determines the compensation value of the heading angle parameter of the camera device and adjusts the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter. Since the target vehicle's driving information can include motion state information and the first lane information of the lane in which the target vehicle is located, the motion state information and the first lane information can be combined to more accurately determine whether the vehicle is currently in a straight-line driving scenario. If it is determined that the target vehicle is in a straight-line driving scenario, then the lane in which the target vehicle is traveling should theoretically also be straight. By further obtaining the second lane information of the lane in which the target vehicle is located, the actual situation of the lane in which the vehicle is traveling can be known. Since the second lane information is obtained by the camera device, if there is an error in the heading angle parameter of the camera device, then the actual situation of the second lane information obtained by the camera device will differ from the theoretical straight situation. Conversely, this difference can also reflect the error of the heading angle parameter of the camera device. In this way, the compensation value of the heading angle parameter of the camera device can be determined. After compensating the heading angle parameter according to the compensation value, the obtained target heading angle parameter can make the camera device's perception more accurate, thereby effectively improving vehicle performance.

[0080] In one embodiment, the motion state information includes: vehicle yaw rate, vehicle speed, and vehicle centerline position; the first lane information includes: lane curvature radius at the current point, lane curvature radius at the pre-aiming point, lane width, presence of lane lines, lane line deflection angle at the current point, and lane line deflection angle at the pre-aiming point, wherein the current point is the current location of the target vehicle, the pre-aiming point is a preset distance away in the forward direction under the current self-coordinate system of the target vehicle, and the lane line deflection angle is the angle formed by the tangent at any point on the lane and the forward direction under the current self-coordinate system.

[0081] In one embodiment, the acquisition unit 31 may be specifically used to: acquire a lane line image of the lane where the target vehicle is located through the camera device; fit the lane line image into a lane line curve using a cubic polynomial; determine the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point based on the first derivative of the lane line curve; and determine the lane curvature radius of the current point and the lane curvature radius of the pre-aiming point based on the second derivative of the lane line curve.

[0082] In one embodiment, the preset conditions include: a first preset condition, a second preset condition, and a third preset condition; the determining unit 32 may include: a first determining module, configured to determine that the target vehicle is in a straight-line driving scenario when the driving information meets the first preset condition, and to determine whether the driving information meets the second preset condition; a second determining module, configured to start timing for the time when the driving information simultaneously meets the first and second preset conditions when the driving information meets the second preset condition, and to determine that the driving information meets the third preset condition when the timing duration is greater than a preset duration threshold; and a third determining module, configured to acquire the second lane information and determine the compensation value of the heading angle parameter of the camera device based on the second lane information when the driving information meets the third preset condition.

[0083] In one embodiment, the first preset conditions include: the vehicle yaw rate is less than a preset angular velocity value, the vehicle speed is greater than a preset speed value, the distance between the vehicle centerline and the lane centerline is less than a preset distance threshold, the lane curvature radius of the current point and the lane curvature radius of the pre-aiming point are both greater than a preset radius threshold, and the lane width is greater than a preset width threshold and both left and right lane lines exist.

[0084] In one embodiment, the second preset condition includes: the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point are both greater than a first deflection angle threshold; and the absolute value of the difference between the lane line deflection angle of the current point and the lane line deflection angle of the pre-aiming point is less than a preset deflection angle difference value.

[0085] In one embodiment, the second preset condition further includes: the flag bit of the preset calibration operation of the target vehicle is a preset value.

[0086] In one embodiment, the second lane information includes the lane deflection angle at the current point; the third determining module includes: an acquisition submodule, configured to acquire the lane deflection angle at the current point at preset time intervals during the driving of the target vehicle; an adjustment submodule, configured to adjust the compensation value of the heading angle parameter from an initial value according to a preset slope to obtain an adjusted value; a determining submodule, configured to determine the adjusted value as a preliminary compensation value if the difference between the adjusted value and the lane deflection angle at the current point is less than a preset adjustment threshold; and a triggering submodule, configured to trigger the acquisition submodule to continue acquiring the lane deflection angle at the current point at preset time intervals during the driving of the target vehicle, iterating N times to obtain N preliminary compensation values, and averaging the N preliminary compensation values ​​to obtain the compensation value of the heading angle parameter, where N is a positive integer.

[0087] In one embodiment, the adjustment unit 33 is specifically used to: subtract the original heading angle parameter of the camera device from the compensation value of the heading angle parameter, and use the difference as the target heading angle parameter.

[0088] In one embodiment, the device may further include: a first triggering unit, configured to, after adjusting the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter, trigger the acquisition submodule to continue acquiring the lane line deviation angle of the current point once at a preset time interval during the driving process of the target vehicle, iterating M times to obtain M of the preliminary compensation values; wherein M is a positive integer; and a determining unit 32, configured to, if all M of the preliminary compensation values ​​are greater than a preset compensation threshold, re-determine the compensation value of the heading angle parameter of the camera device according to the second lane information, wherein the preset compensation threshold is greater than the first deviation angle threshold.

[0089] In one embodiment, the device may further include: an accumulation unit, configured to accumulate the compensation values ​​of the heading angle in each iteration after re-determining the compensation value of the heading angle parameter of the camera device based on the second lane information, to obtain a compensation accumulation value; and a recovery unit, configured to set the compensation accumulation value to 0 and restore the heading angle parameter to the factory settings of the target vehicle if the compensation accumulation value is greater than a preset accumulation threshold.

[0090] In one embodiment, the device may further include: an update unit, configured to set the compensation accumulation value to 0 and update the factory settings of the heading angle parameter after the target vehicle returns to the production line for off-line calibration.

[0091] In one embodiment, the device may further include: a control unit, configured to perform lateral centering control on the target vehicle using the compensation value of the heading angle parameter after determining the compensation value of the heading angle parameter of the camera device based on the second lane information.

[0092] In one embodiment, the device may further include: a second triggering unit, configured to, after determining the compensation value of the heading angle parameter of the camera device based on the second lane information, trigger the acquisition unit to continue acquiring the driving information of the target vehicle during its driving process, iteratively obtaining multiple compensation values ​​of the heading angle parameter; an accumulation unit, configured to accumulate the compensation values ​​of the multiple heading angle parameters to obtain a compensation accumulation value; and a recovery unit, configured to, if the compensation accumulation value is greater than a preset accumulation threshold, set the compensation accumulation value to 0 and restore the heading angle parameter to the factory settings of the target vehicle.

[0093] Thirdly, such as Figure 5As shown, embodiments of the present invention also provide a driver assistance device, including a processor 41, a memory 42, and an in-vehicle camera device 43. The processor 41 is coupled to the memory 42 and the in-vehicle camera device 43 respectively. The memory 42 stores executable program code. The processor 41 reads the executable program code stored in the memory 42 to run the program corresponding to the executable program code, which is used to execute any of the parameter compensation methods for the in-vehicle camera device provided in the embodiments of the present invention, so as to perform parameter compensation for the in-vehicle camera device. Therefore, it can also achieve the corresponding beneficial technical effects, which have been described in detail above and will not be repeated here.

[0094] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A parameter compensation method for a vehicle-mounted camera device, characterized in that, include: During the driving process of the target vehicle, the driving information of the target vehicle is acquired. The driving information includes motion state information and first lane information of the lane in which the target vehicle is located. The first lane information is provided by a camera device installed on the target vehicle. When the driving information meets preset conditions, it is determined that the target vehicle is in a straight-line driving scenario, and the second lane information of the lane where the target vehicle is located is obtained. The compensation value of the heading angle parameter of the camera device is determined based on the second lane information; wherein, the second lane information is provided by the camera device. The heading angle parameters of the camera device are adjusted according to the compensation value of the heading angle parameters to obtain the target heading angle parameters.

2. The parameter compensation method according to claim 1, characterized in that, The motion status information includes: vehicle yaw rate, vehicle speed, and vehicle centerline position; The first lane information includes: the lane curvature radius of the current point, the lane curvature radius of the preview point, the lane width, whether the lane line exists, the lane line deflection angle of the current point, and the lane line deflection angle of the preview point. The current point is the current location of the target vehicle, the preview point is a preset distance away in the forward direction in the current self-coordinate system of the target vehicle, and the lane line deflection angle is the angle formed by the tangent at any point on the lane and the forward direction in the current self-coordinate system.

3. The parameter compensation method according to claim 2, characterized in that, Obtaining the information of the first lane includes: The camera device acquires an image of the lane lines in the lane where the target vehicle is located. The lane line image is fitted into a lane line curve using a cubic polynomial. The lane deflection angle of the current point and the lane deflection angle of the preview point are determined based on the first derivative of the lane curve, and the lane curvature radius of the current point and the lane curvature radius of the preview point are determined based on the second derivative of the lane curve.

4. The parameter compensation method according to claim 3, characterized in that, The preset conditions include: a first preset condition, a second preset condition, and a third preset condition; The step of determining that the target vehicle is in a straight-line driving scenario when the driving information meets preset conditions, and determining the compensation value of the heading angle parameter of the camera device based on the lane information, includes: If the driving information meets the first preset condition, it is determined that the target vehicle is in a straight-line driving scenario, and it is determined whether the driving information meets the second preset condition; If the driving information meets the second preset condition, the time when the driving information simultaneously meets the first preset condition and the second preset condition is started to count. If the counting time is greater than the preset time threshold, it is determined that the driving information meets the third preset condition. When the driving information meets the third preset condition, the second lane information is acquired and the compensation value of the heading angle parameter of the camera device is determined based on the second lane information.

5. The parameter compensation method according to claim 4, characterized in that, The first preset conditions include: the vehicle yaw rate is less than a preset angular velocity value, the vehicle speed is greater than a preset speed value, the distance between the vehicle centerline and the lane centerline is less than a preset distance threshold, the lane curvature radius at the current point and the lane curvature radius at the preview point are both greater than a preset radius threshold, and the lane width is greater than a preset width threshold and both left and right lane lines exist. The second preset condition includes: Both the lane line deflection angle at the current point and the lane line deflection angle at the preview point are greater than the first deflection angle threshold. The absolute value of the difference between the lane line deviation angle at the current point and the lane line deviation angle at the pre-aiming point is less than a preset deviation angle difference value; The flag for the preset calibration operation of the target vehicle is a preset value.

6. The parameter compensation method according to claim 5, characterized in that, The second lane information includes the lane deflection angle at the current point; The step of acquiring the second lane information and determining the compensation value of the heading angle parameter of the camera device based on the second lane information includes: During the driving process of the target vehicle, the lane line deviation angle at the current point is acquired once at preset time intervals; The compensation value of the heading angle parameter is adjusted from the initial value according to the preset slope to obtain the adjusted value; If the difference between the adjusted value and the lane deflection angle at the current point is less than a preset adjustment threshold, the adjusted value is determined to be a pre-compensation value. The process jumps to the step of obtaining the lane deflection angle of the current point at a preset time interval during the driving of the target vehicle and continues to execute. This process is repeated N times to obtain N preliminary compensation values. The average of the N preliminary compensation values ​​is then calculated to obtain the compensation value of the heading angle parameter, where N is a positive integer.

7. The parameter compensation method according to claim 6, characterized in that, The step of adjusting the heading angle parameters of the camera device according to the compensation value of the heading angle parameters to obtain the target heading angle parameters includes: The difference between the original heading angle parameter of the camera device and the compensation value of the heading angle parameter is used as the target heading angle parameter.

8. The parameter compensation method according to claim 6, characterized in that, After adjusting the heading angle parameters of the camera device according to the compensation value of the heading angle parameters to obtain the target heading angle parameters, the method further includes: The process jumps to the step of acquiring the lane deflection angle at the current point at preset intervals during the driving of the target vehicle and continues to execute, iterating M times to obtain M preliminary compensation values; where M is a positive integer; If all M of the proposed compensation values ​​are greater than the preset compensation threshold, the compensation value of the heading angle parameter of the camera device is re-determined based on the second lane information, wherein the preset compensation threshold is greater than the first deflection angle threshold.

9. The parameter compensation method according to claim 8, characterized in that, After re-determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: The compensation values ​​of the heading angles from each iteration are summed to obtain the cumulative compensation value. If the accumulated compensation value is greater than a preset accumulated threshold, the accumulated compensation value is set to 0, and the heading angle parameter is restored to the factory settings of the target vehicle.

10. The parameter compensation method according to claim 9, characterized in that, Also includes: After the target vehicle returns to the production line for calibration, the compensation accumulation value is set to 0, and the factory settings of the heading angle parameter are updated.

11. The parameter compensation method according to claim 1, characterized in that, After determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: The target vehicle is laterally centered using the compensation value of the heading angle parameter.

12. The parameter compensation method according to claim 1, characterized in that, After determining the compensation value of the heading angle parameter of the camera device based on the second lane information, the method further includes: The process jumps to the step of acquiring the driving information of the target vehicle during its driving process and continues to execute, iterating in a loop to obtain compensation values ​​for multiple heading angle parameters; The compensation values ​​of multiple heading angle parameters are summed to obtain the compensation sum value; If the accumulated compensation value is greater than a preset accumulated threshold, the accumulated compensation value is set to 0, and the heading angle parameter is restored to the factory settings of the target vehicle.

13. A parameter compensation device for a vehicle-mounted camera, characterized in that, include: The acquisition unit is used to acquire the driving information of the target vehicle during the driving process of the target vehicle. The driving information includes motion state information and first lane information of the lane in which the target vehicle is located. The first lane information is provided by a camera device installed on the target vehicle. The determining unit is configured to determine that the target vehicle is in a straight-line driving scenario when the driving information meets preset conditions, and to obtain the second lane information of the lane where the target vehicle is located, and to determine the compensation value of the heading angle parameter of the camera device based on the second lane information; wherein the second lane information is provided by the camera device; The adjustment unit is used to adjust the heading angle parameter of the camera device according to the compensation value of the heading angle parameter to obtain the target heading angle parameter.

14. A driver assistance device, characterized in that, The device includes a processor, a memory, and an in-vehicle camera. The processor is coupled to the memory and the in-vehicle camera respectively. The memory stores executable program code. The processor reads the executable program code stored in the memory to run the program corresponding to the executable program code, which is used to execute the parameter compensation method of the in-vehicle camera according to any one of claims 1-12, so as to perform parameter compensation on the in-vehicle camera.

Images