A method and system for correcting matching errors based on nonlinear optimization

Abstract

The present invention relates to a matching error correction method and system based on non-linear optimization. By using the lateral distance difference of lane boundary lines sensed by a continuous multi-frame camera as a constraint condition, it can effectively solve the problem that the positioning result is unavailable when there is a mis-match between the lane boundary lines sensed by the camera and the lane boundary lines of a high-precision map during the vehicle positioning process, and the positioning trajectory is smoother; the calculated speed and attitude are corrected by a non-linear optimization method, effectively solving the problem of vehicle positioning result drift or trajectory jitter when a single mis-match occurs.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving, and particularly to a matching error correction method and system based on non-linear optimization. Background Art

[0002] When a low-cost inertial measurement unit is used in vehicle inertial navigation positioning, it is restricted by its own performance and environmental interference, and the measured state change amount is inaccurate, resulting in the accumulation of positioning errors and unable to meet the positioning accuracy requirements of the entire driving process. A relatively common low-cost fusion positioning strategy is to use the matching of the lane lines sensed by the camera and the lane boundary lines of the high-precision map as an auxiliary positioning means, which can significantly improve the positioning accuracy. This method uses the lateral distance difference of a single match for error correction. When a single mis-match occurs, the positioning result is unavailable. Summary of the Invention

[0003] Aiming at the technical problems existing in the prior art, the present invention provides a matching error correction method and system based on non-linear optimization, which uses the lateral distance difference of the lane boundary lines sensed by consecutive multi-frame cameras as a constraint condition, and corrects the calculated speed and attitude through non-linear optimization, effectively solving the problem of vehicle positioning result drift or trajectory jitter when a single mis-match occurs.

[0004] To solve the above technical problems, in the first aspect, the embodiments of the present invention provide the following technical solutions: A matching error correction method based on non-linear optimization, including:

[0005] Step S1: Obtain a sequence of measured values of the distance change from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within a time sliding window;

[0006] Step S2: Obtain a sequence of vehicle position change amounts in the carrier coordinate system at each camera sampling moment within the time sliding window, and convert them to the vehicle body coordinate system to obtain a sequence of estimated values of the distance change amounts in the vehicle body coordinate system within the time sliding window;

[0007] Step S3: Determine the distance change residual based on the sequence of measured values of the distance change amount and the sequence of estimated values of the distance change amount; obtain the vehicle speed change amount and the vehicle attitude angle change amount at each camera sampling moment within the time sliding window corresponding to the distance change residual, and correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the residual of the distance change amount. Move the time sliding window and return to Step S1.

[0008] Preferably, the Step S1 specifically includes:

[0009] Set the time length T of the time sliding window, and obtain the distance from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; based on the distance change amount between the distances from the vehicle body to the lane boundary line in the vehicle body coordinate system at every two adjacent camera sampling moments, determine the measurement value sequence of the distance change amount sensed by the camera in the vehicle body coordinate system.

[0010] Preferably, the distance change amount includes the forward distance change amount, the rightward distance change amount, and the downward distance change amount.

[0011] Preferably, in step S2, obtaining the vehicle position change amount sequence in the carrier coordinate system at each camera sampling moment within the time sliding window specifically includes:

[0012] Based on the IMU data difference, obtain the vehicle speed change amount and the vehicle angle change amount at each camera sampling moment within the time sliding window;

[0013] Based on the inertial navigation solution method, solve the vehicle speed change amount and the vehicle angle change amount to obtain the vehicle position in the carrier coordinate system at each camera sampling moment;

[0014] Based on the vehicle positions in the carrier coordinate system at every two adjacent camera sampling moments, determine the vehicle position change sequence in the carrier coordinate system.

[0015] Preferably, in step S2, and convert it to the vehicle body coordinate system to obtain the estimated value sequence of the distance change amount in the vehicle body coordinate system within the time sliding window, specifically including:

[0016] Based on the installation angle of the IMU, determine the rotation matrix for converting the carrier coordinate system to the vehicle body coordinate system; based on the rotation matrix, convert the vehicle position change sequence in the carrier coordinate system at each camera sampling moment within the time sliding window to the vehicle body coordinate system to obtain the estimated value sequence of the distance change amount in the vehicle body coordinate system within the time sliding window.

[0017] Preferably, in step S3, obtain the vehicle speed change amount and the vehicle attitude angle change amount at each camera sampling moment within the time sliding window corresponding to the distance change amount residual, and correct the vehicle speed change amount and the vehicle attitude angle change amount, specifically including:

[0018] Calculate the derivatives of the vehicle speed and the vehicle attitude at each camera sampling moment within the time sliding window corresponding to the distance change amount residual to obtain the corresponding vehicle speed change amount and vehicle attitude angle change amount;

[0019] Based on the nonlinear optimization method, iteratively correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the distance change amount residual, so as to obtain the optimized vehicle speed, vehicle attitude, and vehicle position.

[0020] In a second aspect, the embodiments of the present invention provide the following technical solution: A matching error correction system based on non-linear optimization, comprising:

[0021] A variation measurement module, which obtains a sequence of measured values of the distance variation from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within a time sliding window;

[0022] A variation estimation module, which obtains a sequence of vehicle position variations in the carrier coordinate system at each camera sampling moment within a time sliding window, and converts it to the vehicle body coordinate system to obtain a sequence of estimated values of the distance variation in the vehicle body coordinate system within the time sliding window;

[0023] A correction module, which determines the distance variation residual based on the sequence of measured values of the distance variation and the sequence of estimated values of the distance variation; obtains the vehicle speed variation and the vehicle attitude angle variation at each camera sampling moment within the time sliding window corresponding to the distance variation residual, and corrects the vehicle speed variation and the vehicle attitude angle variation to minimize the residual of the distance variation, moves the time sliding window and returns to the variation measurement module.

[0024] Preferably, the variation measurement module is specifically configured to set the time length T of the time sliding window, and obtain the distance from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; based on the distance variation between the vehicle body and the lane boundary line in the vehicle body coordinate system at every two adjacent camera sampling moments, determine the sequence of measured values of the distance variation sensed by the camera in the vehicle body coordinate system;

[0025] The distance variation includes the forward distance variation, the rightward distance variation, and the downward distance variation.

[0026] In a third aspect, the embodiments of the present invention provide the following technical solution: An electronic device, comprising:

[0027] A memory, which is used to store computer software programs;

[0028] A processor, which is used to read and execute the computer software program, and further implement the matching error correction method based on non-linear optimization described in the embodiments of the first aspect.

[0029] In a fourth aspect, the embodiments of the present invention provide the following technical solution: A non-transitory computer-readable storage medium, in which a computer software program for implementing the matching error correction method based on non-linear optimization described in the embodiments of the first aspect is stored.

[0030] The beneficial effects of the present invention are as follows: By using the lateral distance difference of the lane boundary lines sensed by a continuous multi-frame camera as a constraint condition, it can effectively solve the problem that the positioning result is unavailable when there is a mis-match between the lane boundary lines sensed by the camera and the lane boundary lines of the high-precision map during the vehicle positioning process, and the positioning trajectory is smoother. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flowchart of a matching error correction method based on non-linear optimization according to an embodiment of the present invention;

[0032] Figure 2 It is a specific flowchart of a matching error correction method based on non-linear optimization according to an embodiment of the present invention;

[0033] Figure 3 It is a schematic diagram of an embodiment of an electronic device provided by the present invention;

[0034] Figure 4 It is a schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0036] Reference to "embodiment" in this text means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0037] In vehicle inertial navigation positioning, the use of a low-cost inertial measurement unit is restricted by its own performance and environmental interference, and the measured state change amount is inaccurate, resulting in the accumulation of positioning errors and unable to meet the positioning accuracy requirements of the entire driving process. A relatively common low-cost fusion positioning strategy is to use the matching of the lane lines sensed by the camera and the lane boundary lines of the high-precision map as an auxiliary positioning means, which can significantly improve the positioning accuracy. This method uses the lateral distance difference of a single match for error correction. When a single mis-match occurs, the positioning result is unavailable.

[0038] Therefore, the embodiments of the present invention provide a matching error correction method and system based on non-linear optimization. By using the lateral distance difference of the lane boundary lines sensed by consecutive multi-frame cameras as a constraint condition, the deduced speed and attitude are corrected through non-linear optimization, effectively solving the problems of vehicle positioning result drift or trajectory jitter when a single mis-match occurs. A matching error correction method and system based on non-linear optimization are described below with reference to the accompanying drawings.

[0039] In this embodiment, the carrier coordinate system has the center of the IMU as the origin, in the front lower right direction; in the vehicle body coordinate system, the origin of the vehicle body coordinate system is fixed to the carrier at the center of mass of the carrier, and the rotation relationship with the navigation coordinate system n can represent the current attitude information of the carrier; the vehicle body is a rigid body, and the IMU is often installed in the middle of the two axles, in the middle of the rear axle, which can ensure its stability. Therefore, this point is called the origin of the vehicle. Then, by building a bounding box, the coordinates of each position of the vehicle can be known.

[0040] The vehicle body coordinate system can be matched with the local coordinate system, and then calculations can be performed. The vehicle body coordinate system needs to know its pose transformation under the navigation coordinate system and its position under the Universal Transverse Mercator (UTM) coordinate system.

[0041] The vehicle body coordinate system is fixedly connected to the carrier and moves with the carrier. It is a local coordinate system. Its rotation relationship with the n system (navigation coordinate system) or the local horizontal coordinate system can represent the current attitude of the vehicle. That is, in the local horizontal coordinate system enu (east, north, up), if the vehicle is in this coordinate system, what is its attitude. By knowing its three angles and the angle differences between the three coordinate axes of the current vehicle body coordinate system and the original coordinate system, its attitude can be determined.

[0042] In this embodiment, as Figure 1 and Figure 2 shown in, a matching error correction method based on non-linear optimization provided according to an embodiment of the present invention includes:

[0043] Step S1: Obtain a sequence of measured values of the distance change from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within a time sliding window; set the time length T of the time sliding window, and obtain the distance from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; based on the distance change between the vehicle body and the lane boundary line in the vehicle body coordinate system at every two adjacent camera sampling moments, determine a sequence of measured values of the distance change sensed by the camera in the vehicle body coordinate system. Wherein, the distance change includes the forward distance change, the rightward distance change, and the downward distance change.

[0044] Step S2: Obtain the vehicle position change amount sequence in the vehicle body coordinate system at each camera sampling moment within the time sliding window, and convert it to the vehicle body coordinate system to obtain the distance change amount estimation value sequence in the vehicle body coordinate system within the time sliding window.

[0045] In this step, based on the difference of IMU data, obtain the vehicle speed change amount and vehicle angle change amount at each camera sampling moment within the time sliding window; for the vehicle speed change amount and vehicle angle change amount at each camera sampling moment within the time sliding window obtained in the above step, solve based on the inertial navigation solution method to obtain the vehicle position in the vehicle body coordinate system at each camera sampling moment; take the difference between the vehicle positions in the vehicle body coordinate system at two consecutive adjacent camera sampling moments to obtain the vehicle position change sequence in the vehicle body coordinate system.

[0046] Determine the rotation matrix for converting the vehicle body coordinate system to the vehicle body coordinate system based on the installation angle of the IMU; based on the rotation matrix, convert the vehicle position change sequence in the vehicle body coordinate system at each camera sampling moment within the time sliding window to the vehicle body coordinate system to obtain the distance change amount estimation value sequence in the vehicle body coordinate system within the time sliding window. Obtain the forward direction distance change amount, right direction distance change amount, and downward direction distance change amount estimation value sequences in the vehicle body coordinate system within the time sliding window T.

[0047] Step S3: Determine the distance change amount residual based on the distance change amount measurement value sequence and the distance change amount estimation value sequence. Determine the distance change amount residual by taking the difference between the distance change amount estimation value sequence and the distance change amount measurement value sequence; calculate the derivatives of the vehicle speed and vehicle attitude at each camera sampling moment corresponding to the distance change amount residual to obtain the corresponding vehicle speed change amount and vehicle attitude angle change amount. Based on the nonlinear optimization method, iteratively correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the distance change amount residual, so as to obtain the optimized vehicle speed, vehicle attitude, and vehicle position; move the time sliding window and return to step S1.

[0048] The embodiment of the present invention also provides the following technical solution: A matching error correction system based on nonlinear optimization, including:

[0049] The change amount measurement module obtains the distance change amount measurement value sequence from the vehicle body to the lane edge line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; sets the time length T of the time sliding window, and obtains the distance from the vehicle body to the lane edge line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; based on the distance change amount from the vehicle body to the lane edge line in the vehicle body coordinate system at every two adjacent camera sampling moments, determine the distance change amount measurement value sequence sensed by the camera in the vehicle body coordinate system. Wherein, the distance change amount includes the forward direction distance change amount, the right direction distance change amount, and the downward direction distance change amount.

[0050] The variation estimation module obtains a sequence of vehicle position variations in the vehicle body coordinate system at each camera sampling moment within a time sliding window, and converts it to the vehicle body coordinate system to obtain a sequence of estimated values of distance variations in the vehicle body coordinate system within the time sliding window.

[0051] Based on the difference of IMU data, obtain the vehicle speed variation and vehicle angle variation at each camera sampling moment within the time sliding window; for the vehicle speed variation and vehicle angle variation at each camera sampling moment within the time sliding window obtained in the above steps, solve them based on the inertial navigation solution method to obtain the vehicle position in the vehicle body coordinate system at each camera sampling moment; find the difference between the vehicle positions in the vehicle body coordinate system at two consecutive adjacent camera sampling moments to obtain a sequence of vehicle position variations in the vehicle body coordinate system.

[0052] Determine the rotation matrix for converting the vehicle body coordinate system to the vehicle body coordinate system based on the installation angle of the IMU; based on the rotation matrix, convert the sequence of vehicle position variations in the vehicle body coordinate system at each camera sampling moment within the time sliding window to the vehicle body coordinate system to obtain a sequence of estimated values of distance variations in the vehicle body coordinate system within the time sliding window. Obtain the sequence of estimated values of the forward distance variation, rightward distance variation, and downward distance variation in the vehicle body coordinate system within the time sliding window T.

[0053] The correction module determines the distance variation residual based on the sequence of distance variation measurement values and the sequence of estimated values of distance variations; determine the distance variation residual by finding the difference between the sequence of estimated values of distance variations and the sequence of distance variation measurement values; calculate the derivatives of the vehicle speed and vehicle attitude at each camera sampling moment corresponding to the distance variation residual to obtain the corresponding vehicle speed variation and vehicle attitude angle variation, and based on the nonlinear optimization method, iteratively correct the vehicle speed variation and the vehicle attitude angle variation to minimize the distance variation residual to obtain the optimized vehicle speed, vehicle attitude, and vehicle position; move the time sliding window and return to the variation measurement module.

[0054] Please refer to Figure 3 , Figure 3 which is a schematic diagram of an embodiment of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, the embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored on the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, the following steps are implemented:

[0055] Step S1, obtain a sequence of measured values of the distance variation from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window;

[0056] Step S2: Obtain the sequence of vehicle position change amounts in the vehicle body coordinate system at each camera sampling moment within the time sliding window, and convert it to the vehicle body coordinate system to obtain the sequence of estimated distance change amounts in the vehicle body coordinate system within the time sliding window;

[0057] Step S3: Determine the distance change amount residual based on the sequence of measured distance change amounts and the sequence of estimated distance change amounts; obtain the vehicle speed change amount and the vehicle attitude angle change amount at each camera sampling moment within the time sliding window corresponding to the distance change amount residual, and correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the residual of the distance change amount, move the time sliding window and return to Step S1.

[0058] Please refer to Figure 4 , Figure 4 which is a schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. As Figure 4 shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented:

[0059] Step S1: Obtain the sequence of measured distance change amounts from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window;

[0060] Step S2: Obtain the sequence of vehicle position change amounts in the carrier coordinate system at each camera sampling moment within the time sliding window, and convert it to the vehicle body coordinate system to obtain the sequence of estimated distance change amounts in the vehicle body coordinate system within the time sliding window;

[0061] Step S3: Determine the distance change amount residual based on the sequence of measured distance change amounts and the sequence of estimated distance change amounts; obtain the vehicle speed change amount and the vehicle attitude angle change amount at each camera sampling moment within the time sliding window corresponding to the distance change amount residual, and correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the residual of the distance change amount, move the time sliding window and return to Step S1.

[0062] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0063] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0064] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented.

[0065] These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0066] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device

[0067] to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0069] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0070] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for correcting matching errors based on non - linear optimization, characterized in that, Including: Step S1: Obtain a sequence of measured values of the distance change from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; Step S2: Obtain a sequence of vehicle position change amounts in the carrier coordinate system at each camera sampling moment within the time sliding window, and convert it to the vehicle body coordinate system to obtain a sequence of estimated values of the distance change amount in the vehicle body coordinate system within the time sliding window; Step S3: Determine the distance change amount residual based on the sequence of measured values of the distance change amount and the sequence of estimated values of the distance change amount; Obtain the vehicle speed change amount and the vehicle attitude angle change amount at each camera sampling moment within the time sliding window corresponding to the distance change amount residual, and correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the residual of the distance change amount, move the time sliding window and return to Step S1.

2. The method for correcting matching errors based on non - linear optimization according to claim 1, characterized in that, The specific content of Step S1 includes: Set the time length T of the time sliding window, and obtain the distance from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; Based on the distance change amount between the distances from the vehicle body to the lane boundary line in the vehicle body coordinate system at every two adjacent camera sampling moments, determine a sequence of measured values of the distance change amount sensed by the camera in the vehicle body coordinate system.

3. The method for correcting matching errors based on non - linear optimization according to claim 2, characterized in that, The distance change amount includes the forward distance change amount, the rightward distance change amount, and the downward distance change amount.

4. The method for correcting matching errors based on non - linear optimization according to claim 1, characterized in that, In Step S2, to obtain a sequence of vehicle position change amounts in the carrier coordinate system at each camera sampling moment within the time sliding window, specifically includes: Based on the IMU data difference, obtain the vehicle speed change amount and the vehicle angle change amount at each camera sampling moment within the time sliding window; Based on the inertial navigation solution method, solve the vehicle speed change amount and the vehicle angle change amount to obtain the vehicle position in the carrier coordinate system at each camera sampling moment; Based on the vehicle positions in the carrier coordinate system at every two adjacent camera sampling moments, determine the vehicle position change sequence in the carrier coordinate system.

5. The method for correcting matching errors based on non - linear optimization according to claim 1, characterized in that, In Step S2, and convert it to the vehicle body coordinate system to obtain a sequence of estimated values of the distance change amount in the vehicle body coordinate system within the time sliding window, specifically includes: Determine the rotation matrix for converting the carrier coordinate system to the vehicle body coordinate system based on the installation angle of the IMU; Based on the rotation matrix, convert the vehicle position change sequence in the carrier coordinate system at each camera sampling moment within the time sliding window to the vehicle body coordinate system to obtain a sequence of estimated values of the distance change amount in the vehicle body coordinate system within the time sliding window.

6. The method for correcting matching errors based on non - linear optimization according to claim 1, characterized in that, In Step S3, to obtain the vehicle speed change amount and the vehicle attitude angle change amount at each camera sampling moment within the time sliding window corresponding to the distance change amount residual, and correct the vehicle speed change amount and the vehicle attitude angle change amount, specifically includes: Calculate the derivatives of the vehicle speed and the vehicle attitude at each camera sampling moment within the time sliding window corresponding to the distance change amount residual to obtain the corresponding vehicle speed change amount and vehicle attitude angle change amount; Based on the nonlinear optimization method, iteratively correct the vehicle speed change amount and the vehicle attitude angle change amount to minimize the distance change amount residual to obtain the optimized vehicle speed, vehicle attitude, and vehicle position.

7. A system for correcting matching errors based on non - linear optimization, characterized in that, Including: The change measurement module obtains a sequence of measured values of the distance change from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; The change estimation module obtains a sequence of vehicle position changes in the carrier coordinate system at each camera sampling moment within the time sliding window, and converts it to the vehicle body coordinate system to obtain a sequence of estimated values of the distance change in the vehicle body coordinate system within the time sliding window; The correction module determines the distance change residual based on the sequence of measured values of the distance change and the sequence of estimated values of the distance change; obtains the vehicle speed change and the vehicle attitude angle change at each camera sampling moment within the time sliding window corresponding to the distance change residual, and corrects the vehicle speed change and the vehicle attitude angle change to minimize the residual of the distance change, moves the time sliding window and returns to the change measurement module.

8. The system for correcting matching errors based on non - linear optimization according to claim 7, characterized in that, The change measurement module is specifically configured to set the time length T of the time sliding window, and obtain the distance from the vehicle body to the lane boundary line in the vehicle body coordinate system at each camera sampling moment within the time sliding window; based on the distance change between the vehicle body and the lane boundary line in the vehicle body coordinate system at every two adjacent camera sampling moments, determine a sequence of measured values of the distance change in the vehicle body coordinate system sensed by the camera; The distance change includes the forward distance change, the rightward distance change, and the downward distance change.

9. An electronic device, characterized in that, Comprising: A memory for storing computer software programs; A processor for reading and executing the computer software program, thereby implementing the matching error correction method based on nonlinear optimization according to any one of claims 1-6.

10. A non - transitory computer - readable storage medium, characterized in that, The computer software program for implementing the matching error correction method based on nonlinear optimization according to any one of claims 1-6 is stored in the storage medium.

Images