A method, device and medium for correcting image transmission of a vehicle-mounted lens

Abstract

The application provides a vehicle-mounted lens transmission image correction method and device and medium, and relates to the technical field of image processing. The method comprises the following steps: taking a transmission image photographed by a vehicle-mounted lens, obtaining target speed information of the vehicle-mounted lens within an exposure time of photographing the transmission image, obtaining N, uniformly dividing the exposure time into N target time slices, obtaining a target vehicle-mounted lens pose corresponding to each target time slice based on the target speed information, determining a target point spread matrix based on the target vehicle-mounted lens pose corresponding to each target time slice, processing the transmission image by using the target point spread matrix, and obtaining a target clear image. The method balances the calculation efficiency and the clarity of the transmission image.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, device and medium for correcting images transmitted by a vehicle-mounted camera. Background Technology

[0002] In autonomous driving, vehicle navigation, and driver assistance systems, the image quality acquired by vehicle cameras directly affects the accuracy of critical tasks such as target detection and environmental perception. However, during vehicle operation, due to the possibility of traveling on various routes such as straight lines and curves, the vehicle camera experiences rapid acceleration and angular velocity changes within the exposure time, resulting in nonlinear characteristics in the point spread function of the image during deblurring, posing a challenge to traditional deblurring methods. Existing technologies, global deblurring algorithms based on uniform motion struggle to accurately model the vehicle's point spread matrix, and dividing the exposure time into a fixed number of time slices ignores the dynamic changes in motion intensity. Patent application number 202110280229.5 discloses a system and method for image deblurring in vehicles, but this patent only discloses using velocity and acceleration information to obtain the point spread matrix, without addressing angular velocity. Therefore, an adaptive time slice division mechanism based on comprehensive velocity is still needed to achieve a balance between efficiency and image clarity accuracy. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0004] According to a first aspect of the present invention, a method for correcting images transmitted by a vehicle-mounted camera is provided, the method comprising the following steps:

[0005] The system acquires transmitted images captured by a vehicle-mounted camera and obtains target velocity information within the exposure time of the transmitted images captured by the vehicle-mounted camera. The target velocity information includes at least the target linear acceleration and the target angular velocity.

[0006] Obtain N, and divide the exposure time evenly into N target time slices, and obtain the target vehicle lens pose corresponding to each target time slice based on the target speed information;

[0007] Based on the target vehicle camera pose corresponding to each target time slice, the target point diffusion matrix is ​​determined, and the transmitted image is processed using the target point diffusion matrix to obtain a clear target image;

[0008] N is obtained through the following steps:

[0009] Determine the target's combined velocity cv based on the target's linear acceleration and angular velocity;

[0010] If cv is greater than v0, obtain N, where N satisfies the following condition: N is equal to the average of all time slices greater than N0 in the time slice quantity list, where the time slice quantity list includes several time slice quantities, v0 is the velocity threshold, and N0 is the time slice quantity threshold.

[0011] If cv is not greater than v0, obtain N, where N satisfies the following condition: N is equal to the average number of all time slices not greater than N0 in the time slice count list.

[0012] According to a second aspect of the present invention, a non-transitory computer-readable storage medium is provided, wherein a computer program is stored in the storage medium, and the computer program is loaded and executed by a processor to implement the aforementioned method.

[0013] According to a third aspect of the present invention, an electronic device is provided, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned method.

[0014] The present invention has at least the following beneficial effects: acquiring a transmission image captured by a vehicle-mounted lens, acquiring target velocity information of the vehicle-mounted lens within the exposure time of capturing the transmission image, acquiring N, and uniformly dividing the exposure time into N target time slices, acquiring the target vehicle-mounted lens pose corresponding to each target time slice based on the target velocity information, determining the target point diffusion matrix based on the target vehicle-mounted lens pose corresponding to each target time slice, and using the target point diffusion matrix to process the transmission image to obtain a clear target image. The present invention dynamically optimizes the segmentation granularity within the exposure time by using a velocity threshold and a time slice number threshold, thereby achieving a balance between computational efficiency and the clarity of the transmission image. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0016] Figure 1 A flowchart illustrating a method for correcting images transmitted via a vehicle-mounted camera, as provided in an embodiment of the present invention.

[0017] Figure 2 A flowchart of S200 provided in an embodiment of the present invention;

[0018] Figure 3 A flowchart of S220 provided in an embodiment of the present invention;

[0019] Figure 4 A flowchart of one embodiment of S227 provided in this invention;

[0020] Figure 5 A flowchart of another embodiment of S227 provided in this invention;

[0021] Figure 6 A flowchart of S300 provided in an embodiment of the present invention;

[0022] Figure 7 A flowchart of S320 provided in an embodiment of the present invention;

[0023] Figure 8 A flowchart of another embodiment of S220 provided in this invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar tasks and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0026] This invention provides a method for correcting images transmitted by a vehicle-mounted camera, such as... Figure 1 As shown, the method includes the following steps:

[0027] S100: Acquire the transmitted image captured by the vehicle-mounted camera, and acquire the target velocity information within the exposure time of the image capture and transmission. The target velocity information includes at least the target linear acceleration and the target angular velocity. Specifically, the target velocity information also includes the vehicle speed. Further, the target angular velocity and target linear acceleration are acquired through the vehicle-mounted IMU. Specifically, based on the IMU acquisition frequency, the target velocity information includes the target linear acceleration and target angular velocity acquired by the IMU each time within the exposure time.

[0028] S200, obtain N, and evenly divide the exposure time into N target time slices, and obtain the target vehicle-mounted lens pose corresponding to each target time slice based on the target speed information. Specifically, for each target time slice t i The rotation matrix R(t) is obtained by integrating the target angular velocity data from the target time slice. i The displacement T(t) is obtained by quadratic integration of the target acceleration data from the target time slice. i ), thereby obtaining the target vehicle camera pose [R(t)] for the target time slice ti. i ), T(t) i )).

[0029] S300 determines the target point diffusion matrix based on the target vehicle camera pose corresponding to each target time slice, and uses the target point diffusion matrix to process the transmitted image to obtain a clear target image.

[0030] Among them, such as Figure 2 As shown in S200, N is obtained through the following steps:

[0031] S210, based on the target's linear acceleration and angular velocity, determine the target's overall velocity cv.

[0032] In one embodiment of the present invention, the target integrated velocity is the average value of the first sum value collected by the IMU each time, and the first sum value is equal to the sum of the target angular velocity and the target linear acceleration.

[0033] In another embodiment of the invention, the target synthesis is the average of the second sum values ​​collected by the IMU each time, where the second sum value is equal to v. cm +w×b,v cm Let w be the sum of the integral of the target linear acceleration over one IMU acquisition time interval and the initial velocity, w be the target angular velocity, and b be the position vector of the vehicle-mounted camera relative to the vehicle's center of mass.

[0034] S220, if cv is greater than v0, obtain N, where N satisfies the following condition: N equals the average of all time slice counts greater than N0 in the time slice count list, where the time slice count list includes several time slice counts, v0 is the velocity threshold, and N0 is the time slice count threshold. Specifically, the time slice list A = {A1, A2, ..., A...} r A s}, A r+1 Greater than A r If A r Not less than N0, and A r-1 If the value is less than N0, obtain A. r To A s The average value is taken as N.

[0035] S230, if cv is not greater than v0, obtain N, where N satisfies the following condition: N equals the average number of all time slices in the time slice count list that is not greater than N0. Specifically, if A r+1 Greater than N0, and A r If not greater than N0, obtain A1 to A s The average value is taken as N.

[0036] In summary, this invention acquires the transmitted image captured by the vehicle-mounted camera and obtains the target velocity information of the vehicle-mounted camera within the exposure time of capturing the transmitted image. N is then obtained, and the exposure time is evenly divided into N target time slices. Based on the target velocity information, the target vehicle-mounted camera pose corresponding to each target time slice is obtained. Based on the target vehicle-mounted camera pose corresponding to each target time slice, a target point diffusion matrix is ​​determined. The target point diffusion matrix is ​​then used to process the transmitted image to obtain a clear target image. This invention dynamically optimizes the segmentation granularity within the exposure time by using velocity thresholds and time slice number thresholds, thereby achieving a balance between computational efficiency and the clarity of the transmitted image.

[0037] Specifically, such as Figure 3 As shown, in S220, v0 and N0 are obtained through the following steps:

[0038] S221, Obtain the sample comprehensive velocity list v = {v1, v2, ..., v...} j , ..., v n}, v j It is the composite velocity of the j-th sample, where j ranges from 1 to n, and n is the number of composite velocities. The composite velocity is determined based on the sample velocity information of the sample vehicle during the exposure time of a sample. The sample velocity information includes at least the sample linear acceleration and the sample angular velocity.

[0039] Specifically, the sample velocity information includes the sample linear acceleration and sample angular velocity collected by the IMU of the sample vehicle each time during the exposure time of the sample. In one embodiment of the present invention, the sample linear acceleration and sample angular velocity collected each time during the exposure time of the sample are summed to obtain the sample sum value, and the average value of the sample sum value is used as the sample comprehensive velocity.

[0040] In one embodiment of the present invention, v j Not equal to v j+1 .

[0041] In one embodiment of the present invention, the exposure time of a sample is equal to the exposure time of the vehicle-mounted lens when capturing and transmitting the image.

[0042] S222, the exposure time of the sample is evenly divided into A r Each sample time slice, and based on v j Obtaining the corresponding sample velocity information v j Corresponding to A r Sample pose list B jr ={B jr，1 B jr，2 B jr，g B jr，Ar}, thereby obtaining v j The corresponding sample pose list B j ={B j1 B j2 B jr B js}, B jr，g It is v j Corresponding to A r The sample pose of the g-th time slice, where the value of g ranges from 1 to A. r , positive integer A r This represents the number of the r-th time slice in the list of time slice counts, where r ranges from 1 to s, and s is the total number of time slices. Specifically, for each sample time slice, based on v... j The sample rotation matrix is ​​obtained by integrating the sample angular velocity of the sample time slice, based on v. j The sample displacement is obtained by quadratic integration of the linear acceleration of the sample in the sample time slice, and the sample pose is obtained based on the sample rotation matrix and the sample displacement.

[0043] S223, based on v j The corresponding sample pose list B j ={B j1 B j2 B jr B js Generate a list C of sample point diffusion matrices. j ={C j1C j2 C jr C js}, and use C jr For v j The corresponding sample transmission image is processed to obtain a clear sample image D. jr Thus obtain v j The corresponding list of clear sample images D j ={D j1 D j2 D jr D js}, C jr It is v j The exposure time is divided into A r The diffusion matrix of sample points obtained from each sample time slice.

[0044] Specifically, as those skilled in the art will know, any existing method for obtaining a point diffusion matrix based on pose is within the scope of protection of this invention, and will not be elaborated further here.

[0045] Specifically, the clear sample image is obtained by convolving the sample point diffusion matrix with noise. Therefore, after obtaining the sample point diffusion matrix, the sample transmission image is deconvolved using the sample point diffusion matrix to obtain the clear sample image.

[0046] S224, obtain D jr The corresponding image quality value E jr Specifically, the image quality value is the peak signal-to-noise ratio (PSNR) of the image. PSNR is used to quantify the difference between a sharp sample image and a transmitted sample image. It uses the maximum value of the image pixels and the mean square error value to measure the quality of the sharp sample image, making the sharp sample image have better sharpness at the processor level, even though the PSNR value may not be consistent with human visual perception.

[0047] S225. Establish a coordinate system with sample aggregation speed as the X-axis, time slice number as the Y-axis, and image quality value as the Z-axis.

[0048] S226, generate a three-dimensional image based on the sample synthesis velocity list v, the time slice number list, and the image quality value.

[0049] Specifically, based on v j A r and E jr As those skilled in the art know, any method for generating three-dimensional images in the prior art falls within the scope of protection of this invention, such as using Python tools to generate three-dimensional images.

[0050] S227, obtain the inflection point value of the 3D image on the X-axis as v0, and obtain the inflection point value of the 3D image on the Y-axis as N0.

[0051] In summary, by obtaining a comprehensive list of sample speeds, the exposure time of the samples is evenly divided into A... r Each sample time slice, and based on v j Obtaining the corresponding sample velocity information v j Corresponding to A r From the list of sample poses, obtain D jr The corresponding image quality value E jr A coordinate system is established with sample aggregation speed as the X-axis, time slice number as the Y-axis, and image quality value as the Z-axis. The inflection point value of the 3D image on the X-axis is obtained as v0, and the inflection point value of the 3D image on the Y-axis is obtained as N0. This invention obtains the corresponding PSNR value by using different time slice numbers for different sample aggregation speeds. The speed threshold and time slice number threshold are determined by the inflection point, thus obtaining the speed threshold and time slice number threshold more accurately.

[0052] Specifically, such as Figure 4 As shown, in one embodiment of the present invention, S227, obtaining the inflection point value of the three-dimensional image on the X-axis as v0, further includes:

[0053] S2271, for A r Obtain the image quality value E jr With sample aggregation speed v j The first change curve F r Those skilled in the art will understand that any existing method for obtaining a change curve based on coordinate values ​​falls within the scope of protection of this invention, and will not be elaborated further here.

[0054] S2272, Obtain the first change curve F r The first inflection point AP r Get the X-axis coordinate value of AP1 to AP s The average X-axis coordinate value is obtained and used as v0.

[0055] Specifically, such as Figure 5 As shown, in one embodiment of the present invention, S227, obtaining the inflection point value of the three-dimensional image on the Y-axis as N0, further includes:

[0056] S2273, for v j Obtain the image quality value E jr Number of slices A over time r The second change curve H j .

[0057] S2274, Obtain the second change curve H j The second inflection point BP j Get the Y-axis coordinate value of BP1 to BP n The average Y-axis coordinate value is obtained, and this Y-axis coordinate value is taken as N0.

[0058] Specifically, such as Figure 6 As shown, in S300, the target point diffusion matrix is ​​determined based on the target vehicle-mounted camera pose corresponding to each target time slice, and the process also includes:

[0059] S310, the pose of the target vehicle-mounted camera is projected onto a 2D image plane to obtain the projection point. Specifically, those skilled in the art will know that any method in the prior art for projecting a pose onto a 2D image plane to obtain the projection point falls within the protection scope of this invention, and will not be elaborated here.

[0060] S320: Create a blank point diffusion matrix of size M×M. Based on the blank point diffusion matrix, quantize the projected points to pixel coordinates, and generate the target point diffusion matrix based on the pixel coordinates. Specifically, round the projected points to integer pixel positions and perform a quick check to ensure that the integer pixels are within the image. Draw the trajectory so that the values ​​at the trajectory points accumulate to 1. Then, normalize the PSF matrix to obtain the target point diffusion matrix.

[0061] Furthermore, such as Figure 7 As shown, M is obtained in S320 through the following steps:

[0062] S321, obtain the first standard deviation α1 and the second standard deviation α2, where α1 satisfies the following condition: α1=(f×(ra×T+1 / 2×a×T)) 2 )) / (z×s); α2 satisfies the following conditions: α2=s0×w×T, f is the focal length of the vehicle lens, ra is the vehicle speed, T is the exposure time, s0 is the maximum number of pixels from the center to the edge of the transmitted image, z is the preset object distance, w is the target angular velocity, s is the pixel resolution, and a is the target linear acceleration.

[0063] S322, obtain the composite standard deviation α0, where α0 satisfies the following condition: α0=[k1×(α1)] 2 +k2×(α2) 2 ] 1 / 2 k1 is the preset first weight, and k2 is the preset second weight.

[0064] In one embodiment of the present invention, k1 = f × (T) 2 / 2) / (z×s), k2=f×(d x 2 +d y2 ) 1 / 2 ×T / (z×s). d x d represents the size of the vehicle-mounted lens relative to the vehicle center along a preset X-axis. y The size of the vehicle-mounted lens relative to the center of the vehicle along the preset Y-axis.

[0065] S323, obtain M, M satisfies the following condition: M=ceil(α0+k0×α3), ceil() is the floor function, k0 is the preset third weight, and α3 is the preset size of the Gaussian kernel.

[0066] Specifically, the actual PSF matrix size needs to include a Gaussian kernel that is expanded by k0 times around the path points to avoid stage errors.

[0067] In one embodiment of the present invention, k0 = 3, and the preset Gaussian kernel is 1.5.

[0068] In summary, by obtaining the first standard deviation α1 and the second standard deviation α2, obtaining the composite standard deviation α0, and obtaining M, the method of obtaining M through the first and second standard deviations makes the acquisition of M more reasonable.

[0069] Furthermore, such as Figure 8 As shown, in S200, after obtaining N, it also includes:

[0070] S201, Obtain the target prediction function. Input cv and N into the target prediction function and obtain the prediction result.

[0071] In one embodiment of the present invention, the target prediction function is γ / (1+e -f(cv,N) ), where γ is a preset parameter. In one embodiment of the present invention, f(cv, N) = N+1 / (cv).

[0072] S202, if the prediction result does not meet the preset prediction requirements, update N based on the prediction result.

[0073] In one embodiment of the present invention, if γ / (1+e -f(cv,N) If the threshold is less than the preset threshold, N is manually updated. The preset threshold ranges from 0 to 1.

[0074] Embodiments of the present invention also provide a non-transitory computer-readable storage medium that can be disposed in an electronic device to store a computer program related to implementing a method in the method embodiments, the computer program being loaded and executed by the processor to implement the method provided in the above embodiments.

[0075] Embodiments of the present invention also provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method provided in the above embodiments.

[0076] While specific embodiments of the invention have been described in detail by way of examples, those skilled in the art should understand that the examples are for illustrative purposes only and are not intended to limit the scope of the invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the invention.

Claims

1. A method for correcting a vehicle-mounted lens-transmitted image, characterized by, The method comprises the following steps: acquiring a transmission image photographed by a vehicle-mounted lens, and acquiring target speed information of the vehicle-mounted lens within an exposure time of photographing the transmission image, the target speed information comprising at least a target linear acceleration and a target angular velocity; acquiring N and dividing the exposure time into N target time slices uniformly, and acquiring a target vehicle-mounted lens pose corresponding to each target time slice based on the target speed information; determining a target point spread matrix based on the target vehicle-mounted lens pose corresponding to each target time slice, and processing the transmission image using the target point spread matrix to acquire a target sharp image; wherein N is acquired by the following steps: determining a target comprehensive speed cv based on the target linear acceleration and the target angular velocity; if cv is greater than v0, acquiring N, N satisfying the following condition: N is equal to the average of all time slice quantities greater than N0 in a time slice quantity list, wherein the time slice quantity list comprises a plurality of time slice quantities, v0 is a speed threshold, and N0 is a time slice quantity threshold; if cv is not greater than v0, acquiring N, N satisfying the following condition: N is equal to the average of all time slice quantities not greater than N0 in the time slice quantity list.

2. The method of claim 1, wherein, v0 and N0 are acquired by the following steps: Obtain the sample comprehensive velocity list v = {v1, v2, ..., v j , ..., v n }, v j It is the composite velocity of the j-th sample, where j ranges from 1 to n, and n is the number of composite velocities. The composite velocity is determined based on the sample velocity information of the sample vehicle during the exposure time of a sample. The sample velocity information includes at least the sample linear acceleration and the sample angular velocity. The exposure time of the sample is evenly divided into A r sample time slices, and the corresponding sample speed information v j is obtained j The sample pose list B r corresponding to A jr is obtained jr，1 ={B jr，2 , B jr，g , …, B jr，Ar , …, B j}, so as to obtain the corresponding sample pose list B j ={B j1 , B j2 , …, B jr , …, B js}, B jr，g is the pose of the gth sample time slice corresponding to A j v r , and g ranges from 1 to A r , which is a positive integer A r is the rth time slice number in the time slice number list, and r ranges from 1 to s, where s is the number of time slice numbers. Based on v j The corresponding sample pose list B j ={B j1 B j2 B jr B js Generate a list C of sample point diffusion matrices. j ={C j1 C j2 C jr C js }, and use C jr For v j The corresponding sample transmission image is processed to obtain a clear sample image D. jr Thus obtain v j The corresponding list of clear sample images D j ={D j1 D j2 D jr D js }, C jr It is v j The exposure time is divided into A r The diffusion matrix of sample points obtained from each sample time slice; Acquisition D jr Corresponding image quality value E jr ; establishing a coordinate system with a sample comprehensive speed as the X axis, a time slice quantity as the Y axis, and an image quality value as the Z axis; generating a three-dimensional image based on a sample comprehensive speed list v, a time slice quantity list, and an image quality value; acquiring a turning point value of the three-dimensional image on the X axis as v0, and acquiring a turning point value of the three-dimensional image on the Y axis as N0.

3. The method of claim 2, wherein the correction is performed by a camera lens distortion correction algorithm. acquiring the turning point value of the three-dimensional image on the X axis as v0 further comprises: To A r , the image quality value E jr is obtained j with the first curve F r of the sample integrated speed v ; acquiring a first change curve F r of a first inflection point AP r , acquiring an X-axis average coordinate value from an X-axis coordinate value of AP1 to an X-axis coordinate value of AP s , and taking the X-axis average coordinate value as v0.

4. The method of claim 2, wherein, acquiring the turning point value of the three-dimensional image on the Y axis as N0 further comprises: to v j , the image quality value E jr is acquired r , a second curve H j of the number A of slices over time is acquired acquiring a second change curve H j of a second inflection point BP j , acquiring a Y-axis average coordinate value from a Y-axis coordinate value of BP1 to a Y-axis coordinate value of BP n , and taking the Y-axis coordinate value as N0.

5. The method of claim 1, wherein, determining the target point spread matrix based on the target vehicle-mounted lens pose corresponding to each target time slice further comprises: projecting each target vehicle-mounted lens pose onto a 2D image plane to acquire a projection point; creating a blank point spread matrix with a size of MxM, quantifying the projection point to a pixel coordinate point based on the blank point spread matrix, and generating the target point spread matrix based on the pixel coordinate point.

6. The method of claim 5, wherein, M is acquired by the following steps: Obtain the first standard deviation α1 and the second standard deviation α2, where α1 satisfies the following condition: α1=(f×(ra×T+1 / 2×a×T)) 2 )) / (z×s); α2 satisfies the following conditions: α2=s0×w×T, f is the focal length of the vehicle lens, ra is the vehicle speed, T is the exposure time, s0 is the maximum number of pixels from the center to the edge of the transmitted image, z is the preset object distance, w is the target angular velocity, s is the pixel resolution, and a is the target linear acceleration. The synthetic standard deviation a0 is obtained, and a0 satisfies the following condition: a0 = [k1 x (a1) 2 +k2 x (a2) 2 ] 1 / 2 , k1 is a preset first weight, and k2 is a preset second weight. M is acquired, M satisfying the following condition: M = ceil (a0 + k0x a3), ceil () is a rounding up function, k0 is a preset third weight, and a3 is a size of a preset Gaussian kernel.

7. The method of claim 1, wherein the method is performed by a vehicle-mounted camera. after acquiring N, further comprising: acquiring a target prediction function, inputting cv and N into the target prediction function to acquire a prediction result; if the prediction result does not satisfy a preset prediction requirement, updating N based on the prediction result.

8. The method of claim 2, wherein, the image quality value is a peak signal-to-noise ratio value of the image.

9. A non-transitory computer-readable storage medium, comprising: The storage medium stores a computer program, which is loaded and executed by the processor to implement the vehicle-mounted lens transmission image correction method according to any one of claims 1-8.

10. An electronic device comprising: The processor, the memory, and the computer program stored on the memory and executable on the processor, wherein the processor implements the vehicle-mounted lens transmission image correction method according to any one of claims 1-8 when executing the computer program.

Images