Dynamic calibration method and system for vehicle-mounted image acquisition sensor

Abstract

The invention relates to the technical field of image processing, and provides a dynamic calibration method and system for a vehicle-mounted image acquisition sensor, and the method comprises the steps: obtaining the initial image information and the operation state information of a vehicle in real time; preprocessing the initial image information to obtain first intermediate image information; inputting the running state information into a vibration model of the vehicle to obtain vibration information of the vehicle; generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; and optimizing the second intermediate image information based on a preset image optimization method to obtain target image information. The method can adapt to vibration characteristics under different road conditions and driving conditions, dynamically adjust calibration parameters, and ensure that high-quality images can be obtained in various complex environments.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a dynamic calibration method and system for a vehicle-mounted image acquisition sensor. Background Art

[0002] With the rapid development of intelligent driving technology, on-board image acquisition sensors play a vital role in the fields of vehicle environmental perception, navigation assistance and autonomous driving. On-board image acquisition sensors can capture the environmental information around the vehicle in real time and provide high-precision visual data support for the vehicle. However, during driving, the vehicle will inevitably be affected by factors such as uneven road surface and vehicle vibration, which will cause the image captured by the image acquisition sensor to be blurred and distorted, seriously affecting the image quality. Therefore, how to improve the dynamic calibration capability of on-board image acquisition sensors and overcome the impact of vehicle vibration on image quality has become a key technical problem that needs to be solved in the field of intelligent driving. Summary of the invention

[0003] The present application provides a dynamic calibration method and system for a vehicle-mounted image acquisition sensor to solve the problems raised by the above background technology.

[0004] In a first aspect, the present application provides a dynamic calibration method for a vehicle-mounted image acquisition sensor, comprising: Acquire initial image information and vehicle operation status information in real time; Preprocessing the initial image information to obtain first intermediate image information; Inputting the operating state information into the vibration model of the vehicle to obtain vibration information of the vehicle; generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; The second intermediate image information is optimized based on a preset image optimization method to obtain target image information.

[0005] In a possible implementation manner, preprocessing the initial image information to obtain first intermediate image information includes: Performing wavelet decomposition on the initial image information to obtain a low-frequency component and a high-frequency component; Performing threshold processing on the high frequency component, and performing wavelet reconstruction on the low frequency component and the high frequency component after the threshold processing, to obtain first processed image information; Performing Gaussian filtering on the first processed image information to obtain second processed image information; calculating the gradient magnitude and direction of the second processed image information, and detecting the edge of the second processed image information based on the Sobel operator and the gradient magnitude and direction of the second processed image information to obtain an initial image edge; The initial image edge is optimized based on a non-maximum suppression algorithm to obtain an intermediate image edge, and the intermediate image edge is optimized based on a double threshold algorithm to obtain the first intermediate image information.

[0006] In one possible implementation, the method for constructing the vibration model includes: Acquire a training data set; the training data set includes a plurality of mapping relationships, wherein the mapping relationship is a mapping relationship between operating state information and its corresponding vibration information; Dividing the training data set into a training set and a calibration set; For the running state information in the training data set, the running state information is used as the input of the preset neural network, and the vibration information corresponding to the running state information is used as the output of the preset neural network to train the preset neural network to obtain an initial vibration model; For the operating status information in the correction set, the operating status information is input into the initial vibration model to obtain the predicted vibration information corresponding to the operating status information, and the error loss value between the predicted vibration information corresponding to the operating status information and the vibration information is obtained, and the model parameters of the initial vibration model are optimized based on the error loss value to obtain the vibration model.

[0007] In a possible implementation manner, generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information includes: Determine position change information and angle change information of the vehicle-mounted image acquisition sensor based on the vibration information; generating position calibration parameter information based on the position change information, and generating rotation calibration parameter information based on the angle change information; Generate scaling parameter information based on the reference distance of the vehicle-mounted image acquisition sensor and the position calibration parameter information; generating an affine transformation matrix based on the position calibration parameter information, the rotation calibration parameter information and the scaling parameter information; Performing geometric calibration on the first intermediate image information based on the affine transformation matrix to obtain geometrically calibrated image information; Based on the scaling parameter information, a bicubic interpolation algorithm is used to scale the geometric calibration image information to obtain the second intermediate image information.

[0008] In a possible implementation manner, optimizing the second intermediate image information based on a preset multi-scale optimization method to obtain target image information includes: For each pixel of the second intermediate image information, analyzing the illumination component and the reflection component of the pixel to obtain a logarithmic domain target pixel value of the pixel; The logarithmic domain target pixel value corresponding to each of the pixels is converted into the RGB color space to obtain the target image information.

[0009] In a possible implementation manner, performing illumination component and reflection component analysis on the pixel to obtain a logarithmic domain target pixel value of the pixel includes: Convert the pixel from the RGB color space to the logarithmic domain space to obtain the logarithmic domain pixel value of the pixel; Performing multi-scale Gaussian filtering on the pixel to obtain multiple blurred pixel values ​​of the pixel; generating a log-domain illumination component of the pixel based on each of the blurred pixel values; Generate a reflection component of the pixel based on a logarithmic domain pixel value and a logarithmic domain illumination component of the pixel, and perform enhancement processing on the reflection component to obtain an enhanced reflection component; A logarithmic domain target pixel value is generated based on the enhanced reflection component and the logarithmic domain illumination component corresponding to the pixel.

[0010] In a second aspect, the present application provides a dynamic calibration system for a vehicle-mounted image acquisition sensor, comprising: An acquisition module, used for acquiring initial image information and vehicle operation status information in real time; A preprocessing module, used for preprocessing the initial image information to obtain first intermediate image information; An input module, used for inputting the operating state information into the vibration model of the vehicle to obtain vibration information of the vehicle; a calibration module, configured to generate image calibration parameter information based on the vibration information, and calibrate the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; The image optimization module is used to optimize the second intermediate image information based on a preset image optimization method to obtain target image information.

[0011] The present application provides a dynamic calibration method and system for a vehicle-mounted image acquisition sensor, the method comprising: acquiring initial image information and vehicle operating status information in real time; preprocessing the initial image information to obtain first intermediate image information; inputting the operating status information into a vibration model of the vehicle to obtain vibration information of the vehicle; generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; optimizing the second intermediate image information based on a preset image optimization method to obtain target image information. This method, on the one hand, by acquiring the vehicle's operating status information in real time and combining it with a pre-trained vibration model, the system can dynamically generate image calibration parameters to achieve real-time calibration and meet the high real-time requirements of intelligent driving. On the other hand, the vibration model is used to calculate the vehicle's vibration displacement information and vibration angle information, and an affine transformation matrix is ​​generated based on the vibration displacement information and vibration angle information. The affine transformation matrix and the bicubic interpolation algorithm are combined to perform geometric calibration and scaling on the image, which can accurately correct image blur and distortion caused by vehicle vibration and significantly improve image clarity and detail expression. On the other hand, by combining the vehicle's operating status information and vibration model, the system can adapt to the vibration characteristics under different road conditions and driving conditions, dynamically adjust the calibration parameters, and ensure that high-quality images can be obtained in various complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0013] Figure 1 A schematic diagram of a flow chart of a dynamic calibration method for a vehicle-mounted image acquisition sensor provided in an embodiment of the present application; Figure 2 A schematic block diagram of the structure of a dynamic calibration system for a vehicle-mounted image acquisition sensor provided in an embodiment of the present application; Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0016] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0017] It should be further understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0018] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0019] See also Figure 1 , Figure 1 A schematic diagram of a flow chart of a dynamic calibration method for a vehicle-mounted image acquisition sensor provided in an embodiment of the present application, such as Figure 1 As shown, the dynamic calibration method of the vehicle-mounted image acquisition sensor provided in the embodiment of the present application includes steps S1 to S5.

[0020] Step S1, acquiring initial image information and vehicle operation status information in real time.

[0021] Step S2: preprocess the initial image information to obtain first intermediate image information.

[0022] Step S3: input the operating status information into the vibration model of the vehicle to obtain vibration information of the vehicle.

[0023] Step S4: Generate image calibration parameter information based on the vibration information, and calibrate the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information.

[0024] Step S5: Optimize the second intermediate image information based on a preset image optimization method to obtain target image information.

[0025] In this embodiment, it specifically includes: In the above step S1, during the operation of the vehicle, initial image information is acquired in real time through the on-board image acquisition sensor provided on the vehicle, and the operating status information is acquired through the on-board inertial measurement unit, vehicle speed sensor and other equipment provided on the vehicle, wherein the acquisition time of the initial image information is consistent with the acquisition time of the operating status information, and the operating status information includes but is not limited to the vehicle's three-axis acceleration, three-axis angular velocity, vehicle speed, steering angle, pitch angle, roll angle, etc.

[0026] In the above step S2, the initial image information is subjected to noise reduction processing and edge detection processing in sequence to obtain the first intermediate image information.

[0027] In the above step S3, the operating state information is input into the vibration model of the vehicle to obtain the vibration information of the vehicle; wherein the vibration model is a pre-trained neural network model, and the vibration information includes vibration displacement information and vibration angle information.

[0028] In the above step S4, first, the position change information, angle change information and scaling parameter information of the vehicle-mounted image acquisition sensor are determined based on the vibration information, then, an affine transformation matrix is ​​generated based on the position change information and the angle change information, and the first intermediate image information is geometrically calibrated based on the affine transformation matrix to obtain geometrically calibrated image information, and finally, based on the scaling parameter information, a bicubic interpolation algorithm is used to scale the geometrically calibrated image information to obtain the second intermediate image information.

[0029] In the above step S5, first, for each pixel of the second intermediate image information, the illumination component and the reflection component of the pixel are analyzed to obtain the logarithmic domain target pixel value of the pixel, and then the logarithmic domain target pixel value corresponding to each pixel is converted into the RGB color space to obtain the target image information.

[0030] The method provided in this embodiment, on the one hand, by acquiring the vehicle's operating status information in real time and combining it with a pre-trained vibration model, the system can dynamically generate image calibration parameters to achieve real-time calibration and meet the high real-time requirements of intelligent driving. On the other hand, the vibration model is used to calculate the vehicle's vibration displacement information and vibration angle information, and an affine transformation matrix is ​​generated based on the vibration displacement information and vibration angle information, and the affine transformation matrix and the bicubic interpolation algorithm are combined to perform geometric calibration and scaling processing on the image, which can accurately correct image blur and distortion caused by vehicle vibration and significantly improve the image clarity and detail expression. On the other hand, by combining the vehicle's operating status information and the vibration model, the system can adapt to the vibration characteristics under different road conditions and driving conditions, dynamically adjust the calibration parameters, and ensure that high-quality images can be obtained in various complex environments.

[0031] In some embodiments, the preprocessing of the initial image information to obtain the first intermediate image information comprises the following steps: Performing wavelet decomposition on the initial image information to obtain a low-frequency component and a high-frequency component; Performing threshold processing on the high frequency component, and performing wavelet reconstruction on the low frequency component and the high frequency component after the threshold processing, to obtain first processed image information; Performing Gaussian filtering on the first processed image information to obtain second processed image information; calculating the gradient magnitude and direction of the second processed image information, and detecting the edge of the second processed image information based on the Sobel operator and the gradient magnitude and direction of the second processed image information to obtain an initial image edge; The initial image edge is optimized based on a non-maximum suppression algorithm to obtain an intermediate image edge, and the intermediate image edge is optimized based on a double threshold algorithm to obtain the first intermediate image information.

[0032] The method provided in this embodiment, firstly, can effectively separate and remove noise in the image through wavelet decomposition and threshold processing, while retaining the detailed information of the image and significantly improving the clarity of the image; secondly, Gaussian filtering processing further smoothes the image and reduces residual noise, thereby providing clean input data for subsequent edge detection; finally, edge detection based on the Sobel operator combined with non-maximum suppression and dual threshold algorithm can accurately extract the edge information of the image, avoid the interference of pseudo-edges, and enhance the detail expression of the image.

[0033] In some embodiments, the vibration model construction method includes: Acquire a training data set; the training data set includes a plurality of mapping relationships, wherein the mapping relationship is a mapping relationship between operating state information and its corresponding vibration information; Dividing the training data set into a training set and a calibration set; For the running state information in the training data set, the running state information is used as the input of the preset neural network, and the vibration information corresponding to the running state information is used as the output of the preset neural network to train the preset neural network to obtain an initial vibration model; For the operating status information in the correction set, the operating status information is input into the initial vibration model to obtain the predicted vibration information corresponding to the operating status information, and the error loss value between the predicted vibration information corresponding to the operating status information and the vibration information is obtained, and the model parameters of the initial vibration model are optimized based on the error loss value to obtain the vibration model.

[0034] In some embodiments, generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information includes the following steps: Based on the vibration information, the position change information and angle change information of the vehicle-mounted image acquisition sensor are determined; specifically, the vibration information includes vibration displacement information , Angle change information , is the displacement of the vehicle on the X axis, is the displacement of the vehicle on the Y axis, is the displacement of the vehicle on the Z axis, is the rotation angle of the vehicle along the X axis, is the rotation angle of the vehicle along the Y axis, is the rotation angle of the vehicle along the Z axis. It can be understood that since the vehicle-mounted image sensor is installed on the vehicle, the vehicle-mounted image sensor vibrates with the vibration of the vehicle. Therefore, the position change information is , the angle change information is ; Generate position calibration parameter information based on the position change information, and generate rotation calibration parameter information based on the angle change information; wherein the position calibration parameter information is , the rotation calibration parameter information is ; The scaling parameter information is generated based on the reference distance of the vehicle-mounted image acquisition sensor and the position calibration parameter information; specifically, by , , ,in, is the scaling parameter corresponding to the X-axis, is the scaling parameter corresponding to the Y axis, is the scaling parameter corresponding to the Z axis, is the distance between the vehicle-mounted image acquisition sensor and the ground; Generate an affine transformation matrix A based on the position calibration parameter information, the rotation calibration parameter information and the scaling parameter information; Performing geometric calibration on the first intermediate image information based on the affine transformation matrix to obtain geometrically calibrated image information; Based on the scaling parameter information, a bicubic interpolation algorithm is used to scale the geometric calibration image information to obtain the second intermediate image information.

[0035] The method provided in this embodiment, firstly, can accurately reflect the influence of vehicle vibration on image acquisition by accurately calculating the position change information and angle change information of the vehicle-mounted image acquisition sensor, and provide high-precision input data for image calibration; secondly, the affine transformation matrix generated based on the position calibration parameters, rotation calibration parameters and scaling parameters can comprehensively correct the distortion of the image in three dimensions of translation, rotation and scaling, and significantly improve the geometric accuracy of the image; finally, the bicubic interpolation algorithm is used to scale the geometrically calibrated image, which can effectively retain the detailed information of the image and avoid artifacts or blurring introduced during the image scaling process.

[0036] In some embodiments, optimizing the second intermediate image information based on a preset multi-scale optimization method to obtain target image information includes the following steps: For each pixel of the second intermediate image information, analyzing the illumination component and the reflection component of the pixel to obtain a logarithmic domain target pixel value of the pixel; The logarithmic domain target pixel value corresponding to each of the pixels is converted into the RGB color space to obtain the target image information.

[0037] The step of analyzing the illumination component and the reflection component of the pixel to obtain the logarithmic domain target pixel value of the pixel comprises the following steps: The pixel is converted from the RGB color space to the logarithmic domain space to obtain the logarithmic domain pixel value of the pixel; specifically, by The pixels are converted from the RGB color space to the logarithmic domain space, where: is the logarithmic domain pixel value, is the pixel value corresponding to the pixel in the RGB color space; Performing multi-scale Gaussian filtering on the pixel to obtain multiple blurred pixel values ​​of the pixel; Generate the logarithmic domain illumination component of the pixel based on each blurred pixel value; first, by Generate a linear domain illumination component for the pixel, where is the linear domain illumination component, For the Fuzzy pixel values, For the The weight coefficient corresponding to the fuzzy pixel value is For the The standard deviation of the Gaussian kernel corresponding to the blurred pixel value, Indicates that there is The blurred pixel values ​​are then Generate a log-domain illumination component of the pixel, where is the logarithmic domain illumination component; The reflection component of the pixel is generated based on the logarithmic domain pixel value and the logarithmic domain illumination component of the pixel, and the reflection component is enhanced to obtain the enhanced reflection component; specifically, first, the logarithmic domain pixel value is subtracted from the logarithmic domain illumination component to obtain the reflection component, and then, The reflection component is enhanced to obtain an enhanced reflection component, wherein: is the enhanced reflection component, is the preset enhancement factor; A logarithmic domain target pixel value is generated based on the enhanced reflection component and the logarithmic domain illumination component corresponding to the pixel; specifically, the enhanced reflection component is added to the logarithmic domain illumination component to obtain the logarithmic domain target pixel value.

[0038] The method provided in this embodiment, firstly, by converting the image from the RGB color space to the logarithmic domain space and combining it with multi-scale Gaussian filtering processing, it is possible to effectively separate the illumination component and the reflection component of the image, thereby eliminating the influence of uneven illumination on the image quality; secondly, by enhancing the reflection component, it is possible to significantly improve the detail information and contrast of the image, making the texture and edges of the image clearer; finally, by combining the enhanced reflection component with the illumination component to generate a logarithmic domain target pixel value, and converting it back to the RGB color space, it is possible to retain the natural color and realism of the image and avoid color distortion.

[0039] See also Figure 2 , Figure 2 The structure schematic block diagram of the dynamic calibration system 100 of the vehicle-mounted image acquisition sensor provided in the embodiment of the present application is as follows: Figure 2 As shown, the dynamic calibration system 100 of the vehicle-mounted image acquisition sensor provided in the embodiment of the present application includes: The acquisition module 110 is used to acquire the initial image information and the running status information of the vehicle in real time.

[0040] The preprocessing module 120 is used to preprocess the initial image information to obtain first intermediate image information.

[0041] The input module 130 is used to input the operating state information into the vibration model of the vehicle to obtain the vibration information of the vehicle.

[0042] The calibration module 140 is configured to generate image calibration parameter information based on the vibration information, and calibrate the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information.

[0043] The image optimization module 150 is used to optimize the second intermediate image information based on a preset image optimization method to obtain target image information.

[0044] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the process in the aforementioned dynamic calibration method embodiment of the vehicle-mounted image acquisition sensor, and will not be repeated here.

[0045] The dynamic calibration system 100 of the vehicle-mounted image acquisition sensor provided in the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 3 The system is run on the terminal device 200 shown.

[0046] See also Figure 3 , Figure 3 The present invention provides a schematic block diagram of the structure of a terminal device 200 according to an embodiment of the present application. The terminal device 200 includes a processor 201 and a memory 202. The processor 201 and the memory 202 are connected via a device bus 203, wherein the memory 202 can include a non-volatile storage medium and an internal memory.

[0047] The non-volatile storage medium can store a computer program. The computer program includes program instructions, and when the program instructions are executed by the processor 201, the processor 201 can execute any of the above-mentioned dynamic calibration methods for the vehicle-mounted image acquisition sensor.

[0048] The processor 201 is used to provide computing and control capabilities to support the operation of the entire terminal device 200.

[0049] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 201, the processor 201 can execute any of the above-mentioned dynamic calibration methods for the vehicle-mounted image acquisition sensor.

[0050] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the terminal device 200 involved in the scheme of the present application. The specific terminal device 200 can include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0051] It should be understood that the processor 201 can be a central processing unit (CPU), and the processor 201 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0052] In some embodiments, the processor 201 is used to run a computer program stored in the memory to implement the following steps: Acquire initial image information and vehicle operation status information in real time; Preprocessing the initial image information to obtain first intermediate image information; Inputting the operating state information into the vibration model of the vehicle to obtain vibration information of the vehicle; generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; The second intermediate image information is optimized based on a preset image optimization method to obtain target image information.

[0053] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the terminal device 200 described above can refer to the process of the dynamic calibration method of the aforementioned vehicle-mounted image acquisition sensor, and will not be repeated here.

[0054] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the one or more processors implement the dynamic calibration method of the vehicle-mounted image acquisition sensor provided in the embodiment of the present application.

[0055] The computer-readable storage medium can be an internal storage unit of the terminal device 200 in the aforementioned embodiment, such as a hard disk or memory of the terminal device 200. The computer-readable storage medium can also be an external storage device of the terminal device 200, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped with the terminal device 200.

[0056] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A dynamic calibration method for a vehicle-mounted image acquisition sensor, characterized in that: include: Acquire initial image information and vehicle operation status information in real time; Preprocessing the initial image information to obtain first intermediate image information; Inputting the operating state information into the vibration model of the vehicle to obtain vibration information of the vehicle; generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; The second intermediate image information is optimized based on a preset image optimization method to obtain target image information.

2. The dynamic calibration method of the vehicle-mounted image acquisition sensor according to claim 1, characterized in that: The preprocessing of the initial image information to obtain the first intermediate image information includes: Performing wavelet decomposition on the initial image information to obtain a low-frequency component and a high-frequency component; Performing threshold processing on the high frequency component, and performing wavelet reconstruction on the low frequency component and the high frequency component after the threshold processing, to obtain first processed image information; Performing Gaussian filtering on the first processed image information to obtain second processed image information; calculating the gradient magnitude and direction of the second processed image information, and detecting the edge of the second processed image information based on the Sobel operator and the gradient magnitude and direction of the second processed image information to obtain an initial image edge; The initial image edge is optimized based on a non-maximum suppression algorithm to obtain an intermediate image edge, and the intermediate image edge is optimized based on a double threshold algorithm to obtain the first intermediate image information.

3. The dynamic calibration method of the vehicle-mounted image acquisition sensor according to claim 1, characterized in that: The method for constructing the vibration model comprises: Acquire a training data set; the training data set includes a plurality of mapping relationships, wherein the mapping relationship is a mapping relationship between operating state information and its corresponding vibration information; Dividing the training data set into a training set and a calibration set; For the running state information in the training data set, the running state information is used as the input of the preset neural network, and the vibration information corresponding to the running state information is used as the output of the preset neural network to train the preset neural network to obtain an initial vibration model; For the operating status information in the correction set, the operating status information is input into the initial vibration model to obtain the predicted vibration information corresponding to the operating status information, and the error loss value between the predicted vibration information corresponding to the operating status information and the vibration information is obtained, and the model parameters of the initial vibration model are optimized based on the error loss value to obtain the vibration model.

4. The dynamic calibration method of the vehicle-mounted image acquisition sensor according to claim 1, characterized in that: The step of generating image calibration parameter information based on the vibration information, and calibrating the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information includes: Determine position change information and angle change information of the vehicle-mounted image acquisition sensor based on the vibration information; generating position calibration parameter information based on the position change information, and generating rotation calibration parameter information based on the angle change information; Generate scaling parameter information based on the reference distance of the vehicle-mounted image acquisition sensor and the position calibration parameter information; generating an affine transformation matrix based on the position calibration parameter information, the rotation calibration parameter information and the scaling parameter information; Performing geometric calibration on the first intermediate image information based on the affine transformation matrix to obtain geometrically calibrated image information; Based on the scaling parameter information, a bicubic interpolation algorithm is used to scale the geometric calibration image information to obtain the second intermediate image information.

5. The dynamic calibration method of the vehicle-mounted image acquisition sensor according to claim 1, characterized in that: The step of optimizing the second intermediate image information based on a preset multi-scale optimization method to obtain target image information includes: For each pixel of the second intermediate image information, analyzing the illumination component and the reflection component of the pixel to obtain a logarithmic domain target pixel value of the pixel; The logarithmic domain target pixel value corresponding to each of the pixels is converted into the RGB color space to obtain the target image information.

6. The dynamic calibration method of the vehicle-mounted image acquisition sensor according to claim 5, characterized in that: The step of analyzing the illumination component and the reflection component of the pixel to obtain a logarithmic domain target pixel value of the pixel includes: Convert the pixel from the RGB color space to the logarithmic domain space to obtain the logarithmic domain pixel value of the pixel; Performing multi-scale Gaussian filtering on the pixel to obtain multiple blurred pixel values ​​of the pixel; generating a log-domain illumination component of the pixel based on each of the blurred pixel values; Generate a reflection component of the pixel based on a logarithmic domain pixel value and a logarithmic domain illumination component of the pixel, and perform enhancement processing on the reflection component to obtain an enhanced reflection component; A logarithmic domain target pixel value is generated based on the enhanced reflection component and the logarithmic domain illumination component corresponding to the pixel.

7. A dynamic calibration system for a vehicle-mounted image acquisition sensor, characterized in that: include: An acquisition module, used for acquiring initial image information and vehicle operation status information in real time; A preprocessing module, used for preprocessing the initial image information to obtain first intermediate image information; An input module, used for inputting the operating state information into the vibration model of the vehicle to obtain vibration information of the vehicle; a calibration module, configured to generate image calibration parameter information based on the vibration information, and calibrate the first intermediate image information based on the image calibration parameter information to obtain second intermediate image information; The image optimization module is used to optimize the second intermediate image information based on a preset image optimization method to obtain target image information.

Images