Image quality detection method and system for vehicle-mounted lens

Abstract

The invention discloses an image quality detection method and system for a vehicle-mounted lens, and the method comprises the steps: analyzing the video data shot by the vehicle-mounted lens, and judging whether a frame jitter signal is generated or not; analyzing the number of times of generating the frame jitter signal in the continuous frame image, the duration of the frame jitter signal and the jitter coefficient of the frame jitter image corresponding to the generated frame jitter signal, and judging that the vehicle-mounted lens image jitter is serious, namely generating an unstable signal; analyzing the vehicle-mounted voltage and the jitter coefficient corresponding to the continuous frame image generation unit time period based on the unstable signal, judging whether the vehicle-mounted voltage has an influence on the jitter of the vehicle-mounted lens image, and adjusting the generation frame rate of the vehicle-mounted lens image based on the vehicle-mounted voltage influence signal. According to the invention, the vehicle-mounted voltage which causes the image jitter of the vehicle-mounted lens is adjusted, so that the image jitter caused by the fluctuation of the vehicle-mounted voltage is reduced or avoided, and the improvement of the image shooting quality of the vehicle-mounted lens is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of picture quality detection, and in particular to a method and system for detecting the picture quality of a vehicle-mounted lens. Background Art

[0002] The on-board lens is an optical device installed on the car to capture visual information outside or inside the vehicle. It is a key component of the car's visual system. The on-board lens can record road conditions, traffic signs, vehicles, pedestrians and other information during the vehicle's driving. In the event of a traffic accident or traffic dispute, the video recorded by the on-board lens in the driving recorder can serve as important evidence to help restore the truth of the incident. The on-board lens can also provide visual assistance to the driver, such as displaying the situation behind the vehicle through the rearview camera when reversing to avoid collisions with obstacles; some advanced on-board lenses can also be used for lane keeping assist systems, which can remind the driver whether the vehicle has deviated from the lane by identifying lane lines, monitor the vehicle's surroundings in real time, and detect potential dangers.

[0003] However, in actual applications, the images of vehicle-mounted cameras are often affected by a variety of factors and cause jitters, among which the instability of vehicle voltage is an important reason. The fluctuation of vehicle voltage will lead to unstable power supply of vehicle-mounted cameras, thus affecting the quality of the images taken and causing image jitters. Image jitters will not only reduce the recognition accuracy of the autonomous driving system, but may also cause misjudgments, posing a threat to driving safety.

[0004] To this end, we proposed a method and system for detecting the image quality of vehicle-mounted lenses. Summary of the invention

[0005] The object of the present invention is to provide a method and system for detecting image quality of a vehicle-mounted lens, so as to solve at least one of the above-mentioned problems in the prior art.

[0006] In a first aspect, the present invention provides a method for detecting image quality of a vehicle-mounted lens, comprising the following steps:

[0007] Step 1: Analyze the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and determine whether to generate a frame jitter signal based on the jitter coefficient DX;

[0008] The video data captured by the vehicle-mounted camera includes continuous frame images;

[0009] Step 2: Analyze the number of times the frame jitter signal is generated in the continuous frame image, the duration of the frame jitter signal, and the jitter coefficient of the frame jitter image corresponding to the frame jitter signal to obtain the image jitter representation value DB. If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated;

[0010] Step 3: Based on the unstable signal, the vehicle voltage and jitter coefficient corresponding to the unit time period of the continuous frame image are analyzed to obtain the vehicle voltage influence value, and based on the vehicle voltage influence value, it is determined whether the vehicle voltage affects the jitter of the vehicle lens image, and the influence result includes the vehicle voltage influence signal;

[0011] Step 4: Based on the vehicle voltage influence signal, all slope values ​​in the slope ratio data group are processed to obtain the control coefficient. Based on the control coefficient, the vehicle voltage control value is obtained to adjust the frame rate of the vehicle lens image.

[0012] In a second aspect, the present invention provides a system for detecting the image quality of a vehicle-mounted lens, the system comprising:

[0013] Jitter signal generation module: analyzes the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and determines whether to generate a frame jitter signal based on the jitter coefficient DX;

[0014] Stability judgment module: Analyze the number of times the frame jitter signal is generated in the continuous frame image, the duration of the frame jitter signal and the jitter coefficient of the frame jitter image corresponding to the frame jitter signal to obtain the image jitter representation value DB. If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated;

[0015] Influencing factor analysis module: Based on the unstable signal, the vehicle voltage and jitter coefficient corresponding to the unit time period of the continuous frame image are analyzed to obtain the vehicle voltage impact value. Based on the vehicle voltage impact value, it is determined whether the vehicle voltage affects the jitter of the vehicle lens image. The impact result includes the vehicle voltage impact signal;

[0016] Impact control module: Based on the vehicle voltage impact signal, all slope values ​​in the slope ratio data group are processed to obtain the control coefficient. Based on the control coefficient, the vehicle voltage control value is obtained to adjust the frame rate of the vehicle lens image.

[0017] Beneficial effects of the present invention:

[0018] 1. The present invention analyzes the video data taken by the vehicle-mounted lens to obtain the jitter coefficient DX, and based on the jitter coefficient DX, determines whether to generate a frame jitter signal; analyzes the number of times the frame jitter signal is generated in continuous frame images and the duration of the frame jitter signal to obtain a picture jitter characterization value DB, if the picture jitter characterization value DB is greater than or equal to the picture jitter characterization threshold, the vehicle-mounted lens picture jitter is serious, that is, an unstable signal is generated; the present invention can more accurately determine the jitter condition of the vehicle-mounted lens picture by analyzing the video data taken by the vehicle-mounted lens, and is suitable for the situation where the vehicle-mounted lens is unqualified in production. When the picture jitter is serious, an unstable signal is generated in time.

[0019] 2. The present invention analyzes the vehicle voltage corresponding to the time period of continuous frame image generation based on the unstable signal to obtain the vehicle voltage influence value, and judges whether the vehicle voltage affects the vehicle lens image jitter based on the vehicle voltage influence value, and the influence results include the vehicle voltage influence signal and the non-vehicle voltage influence signal; based on the vehicle voltage influence signal, the voltage at each time point corresponding to the continuous frame image generation period is obtained, a decision tree model is constructed, and the frame rate of the vehicle lens image is adjusted; the present invention is also applicable to the situation where the vehicle lens image jitter is caused by abnormal vehicle voltage. By adjusting the coefficient, the vehicle voltage that causes the vehicle lens image jitter is adjusted to reduce or avoid the image jitter caused by the vehicle voltage fluctuation, which is beneficial to improving the shooting quality of the vehicle lens image. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a method for detecting image quality of a vehicle-mounted lens provided in Embodiment 1 of the present invention;

[0022] Figure 2 It is a structural schematic diagram of a vehicle-mounted lens image quality detection system provided by Embodiment 2 of the present invention;

[0023] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0024] Reference numerals: 301, processor; 302, memory; 303, computer program. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present invention.

[0026] Embodiment 1

[0027] Figure 1The flowchart of a method for detecting the image quality of a vehicle-mounted lens provided in the first embodiment of the present invention is applicable to the case where the image of the vehicle-mounted lens is shaking. The method for detecting the image quality of a vehicle-mounted lens can be executed by a system for detecting the image quality of a vehicle-mounted lens. The system for detecting the image quality of a vehicle-mounted lens can be implemented by software and hardware. The system for detecting the image quality of a vehicle-mounted lens can be configured in a device for detecting the image quality of a vehicle-mounted lens. Optionally, the device for detecting the image quality of a vehicle-mounted lens can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0028] like Figure 1 As shown, a method for detecting image quality of a vehicle-mounted lens provided by an embodiment of the present invention specifically includes the following steps:

[0029] Step 1: Analyze the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and determine whether to generate a frame jitter signal based on the jitter coefficient DX;

[0030] The video data captured by the vehicle-mounted camera includes continuous frame images;

[0031] Obtain the video data shot by the vehicle-mounted lens, use OpenCV or other image processing libraries to decode the video data shot by the vehicle-mounted lens, extract the continuous frame images within the unit time period T, and mark the continuous frame images as n in sequence, where n is 1, 2, 3, etc.;

[0032] A1: traverse and calculate the image shift ratio TPn of adjacent frame images;

[0033] Specific:

[0034] A11: Take the vertex in the first frame image as the origin and construct a spatial coordinate system, where the horizontal direction is the X-axis, the vertical direction is the Y-axis, and the Z-axis is used to arrange consecutive frame images;

[0035] A12: Divide each frame of image into a number of equal and non-overlapping blocks with a unit length of e, and mark the blocks as r, where r is 1, 2, 3, etc.; take the central pixel point of block r as the central coordinate point of block r, and mark the coordinate of block r in the XY plane in the spatial coordinate system as (x (n、r) ,y (n、r) ),

[0036] A13: traverse and calculate the offset value PY(n, r) of the same block r in two adjacent frame images n and n-1;

[0037] Specific:

[0038]

[0039] It should be noted that the value of n needs to be greater than 1;

[0040] A14: summing and averaging the offset values ​​of all blocks in the previous frame image n-1 to obtain a block offset mean, performing subtraction processing on the block offset value and the block offset mean to obtain a block relative offset value, summing and averaging all the block relative offset values ​​to obtain a block relative offset mean, performing ratio processing on the block relative offset mean and the block offset mean to obtain an image offset ratio TPn-1 of the frame image n-1;

[0041] A2: Calculate the image correlation performance value NCCn of adjacent frame images;

[0042] Specifically include:

[0043] A21: Calculate the correlation value between the blocks r with the same label in the adjacent frame images n and n-1 by traversing through the normalized cross-correlation calculation formula: including the following steps:

[0044] A211: construct a block pixel coordinate system, with the horizontal direction of the block in the frame image as the x-axis and the vertical direction of the block in the frame image as the y-axis, and mark the coordinate of each pixel in the frame image block r as (i, j);

[0045] A212: Get the pixel value of each pixel in block r in frame image n, denoted as B(i (n、r) , j (n、r) ); then calculate and obtain the pixel mean BJ(n, r) of the pixel points in block r in frame image n;

[0046] A213: Calculated by normalized cross-correlation formula:

[0047]

[0048] Calculate and obtain the block correlation value NCC(n, r) between blocks with the same label r in adjacent frame images;

[0049] A22: summing and averaging all block correlation values ​​in adjacent frame images to obtain the adjacent frame image correlation performance value NCCn;

[0050] The correlation value NCCn and the image shift ratio TP are processed by the formula: Calculate and obtain the jitter coefficient DX of adjacent frame images;

[0051] Compare the jitter coefficient DX with the jitter coefficient threshold:

[0052] If the jitter coefficient DX is less than or equal to the jitter coefficient threshold, the first frame image of two adjacent frame images is marked as a frame jitter image, and a frame jitter signal is generated corresponding to the frame jitter image;

[0053] If the jitter coefficient DX is greater than the jitter coefficient threshold, the first frame image of two adjacent frame images is marked as a non-frame jitter image, and a non-frame jitter signal is generated corresponding to the non-frame jitter image;

[0054] Step 2: Analyze the number of times the frame jitter signal is generated in the continuous frame image, the duration of the frame jitter signal, and the jitter coefficient of the frame jitter image corresponding to the frame jitter signal to obtain the image jitter representation value DB. If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated;

[0055] The number of times the frame jitter signal is generated in the continuous frame images is obtained, and the ratio is processed with the number of continuous frame images to obtain the frame jitter number ratio DC;

[0056] Mark the period when the frame jitter signal appears as the frame jitter period, obtain the duration corresponding to the frame jitter period, obtain the frame jitter duration, sum up all the jitter durations, output the total jitter duration, perform ratio processing on the total jitter duration and the total duration corresponding to the continuous frame images, and obtain the jitter duration ratio DS;

[0057] It should be noted that the duration corresponding to the generation time of a single frame jitter signal is the duration of the frame jitter signal;

[0058] Obtain the jitter coefficient of the corresponding frame jitter image generated by the frame jitter signal and perform subtraction processing with the jitter coefficient threshold to obtain the jitter deviation value, sum and average the jitter deviation values ​​of all frame jitter images in the continuous frame image to obtain the jitter deviation mean value of the vehicle-mounted lens image, perform ratio processing on the jitter deviation mean value and the jitter coefficient threshold to obtain the jitter degree ratio DD;

[0059] The frame jitter ratio DC, jitter duration ratio DS and jitter degree ratio DD are processed by the formula: The image jitter representation value DB of the continuous frame images is calculated, wherein s1, s2 and s3 are all preset proportional coefficients, s1 takes a value of 1.022, s2 takes a value of 1.145, and s3 takes a value of 1.231;

[0060] It should be noted that the image jitter representation DB is obtained by processing the frame jitter frequency ratio DC, the jitter duration ratio DS and the jitter degree ratio DD, wherein the frame jitter frequency ratio CC reflects the number of times the frame jitter signal is generated in the continuous frame image. The more times the frame jitter signal is generated in the continuous frame image, the greater the possibility that the continuous frame image jitter is serious; the jitter duration ratio DS reflects the duration of the frame jitter signal generated in the continuous frame image. The longer the duration of the frame jitter signal generated in the continuous frame image, the greater the possibility that the continuous frame image jitter is serious; the jitter degree ratio DD reflects the deviation between the jitter coefficient corresponding to the generation of the frame jitter signal in the continuous frame image and the jitter coefficient threshold. The greater the deviation, the greater the possibility that the continuous frame image jitter is serious.

[0061] Compare the image jitter characterization value DB with the image jitter characterization threshold:

[0062] If the image jitter representation value DB is less than the image jitter representation threshold, it means that the image jitter of the vehicle-mounted lens is relatively light, that is, a stable signal is generated;

[0063] If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated;

[0064] The technical solution of the embodiment of the present invention is mainly as follows: analyzing the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and judging whether to generate a frame jitter signal based on the jitter coefficient DX; analyzing the number of times the frame jitter signal is generated in continuous frame images and the duration of the frame jitter signal to obtain a picture jitter characterization value DB, if the picture jitter characterization value DB is greater than or equal to the picture jitter characterization threshold, the vehicle-mounted lens picture jitter is serious, that is, an unstable signal is generated; the present invention can more accurately judge the jitter condition of the vehicle-mounted lens picture by analyzing the video data shot by the vehicle-mounted lens, and is suitable for the situation where the vehicle-mounted lens is unqualified in production. When the picture jitter is serious, an unstable signal is generated in time.

[0065] Embodiment 2

[0066] Based on Example 1, please refer to Figure 1 As shown, when an unstable signal appears on the vehicle-mounted lens picture, it may be caused by unstable vehicle voltage. The vehicle-mounted lens picture quality detection method described in an embodiment of the present invention further includes the following steps:

[0067] Step 3: Based on the unstable signal, the vehicle voltage and jitter coefficient corresponding to the unit time period of the continuous frame image are analyzed to obtain the vehicle voltage influence value, and based on the vehicle voltage influence value, it is determined whether the vehicle voltage affects the jitter of the vehicle lens image, and the influence result includes the vehicle voltage influence signal and the non-vehicle voltage influence signal;

[0068] Obtain the vehicle voltage and jitter coefficient corresponding to the unit time period generated by the continuous frame images, mark them in the XY coordinate system respectively, connect all the vehicle voltage marking points to obtain the vehicle voltage change line, mark and connect all the jitter coefficient marking points to obtain the jitter coefficient change line;

[0069] Draw a straight line parallel to the x-axis through the rated vehicle voltage mark point and mark it as the vehicle voltage limit line;

[0070] Obtain all curve segments of the vehicle voltage change curve that are higher than the vehicle voltage limit line, mark them as out-of-bounds curves, obtain the time period corresponding to the out-of-bounds curve on the X-axis, and obtain the out-of-bounds time period;

[0071] Perform overlap analysis on the out-of-bounds period and the frame jitter period to obtain the overlap period between the out-of-bounds period and the frame jitter period, and sum the durations corresponding to all the overlap periods to obtain the overlap duration;

[0072] The overlap duration is processed by ratio processing with the total duration corresponding to the continuous frame images to obtain the overlap duration ratio, which is marked as CH;

[0073] It should be noted that there is a corresponding time period when the frame jitter image is generated in the continuous frame images;

[0074] Based on the overlap period, the overlap period is divided into a number of time points of equal length;

[0075] Respectively obtain the vehicle voltage change sub-line and the jitter coefficient change sub-line corresponding to two adjacent time points, and integrate the obtained vehicle voltage change sub-line and jitter coefficient change sub-line into a sub-line group;

[0076] The vehicle voltage change sub-line is a line connecting two adjacent vehicle voltage value marking points in the vehicle voltage change line, and the jitter coefficient change sub-line is a line connecting two adjacent jitter coefficient marking points in the jitter coefficient change line;

[0077] Obtaining the slopes of the vehicle voltage change sub-line and the jitter coefficient change sub-line in the sub-line group respectively, and performing ratio processing on them to obtain the slope ratio of the sub-line group;

[0078] The slope ratios corresponding to all sub-polyline groups are integrated into a slope ratio data group, and the variance of the slope ratios in the slope ratio data group is calculated to obtain a change synchronization value, which is marked as FC;

[0079] The obtained change synchronization value FC and overlap time ratio CH are processed by the formula: The vehicle voltage impact value CYx is calculated, where c1 and c2 are preset proportional coefficients, c1 is 1.268, and c2 is 1.989;

[0080] Compare the vehicle voltage impact value with the vehicle voltage impact value threshold:

[0081] If the vehicle voltage impact value is greater than or equal to the vehicle voltage impact value threshold, it means that the vehicle voltage has a greater impact on the vehicle lens image jitter, and a vehicle voltage impact signal is generated;

[0082] If the vehicle voltage impact value is less than the vehicle voltage impact value threshold, it means that the vehicle voltage has little effect on the jitter of the vehicle lens picture, and further analysis is needed on other factors that affect the quality of the vehicle lens picture;

[0083] Step 4: Based on the vehicle voltage influence signal, all slope values ​​in the slope ratio data group are processed to obtain a control coefficient, and based on the control coefficient, a vehicle voltage control value is obtained to adjust the frame rate of the vehicle lens image;

[0084] All slope values ​​in the slope ratio data group are summed and averaged to obtain the control coefficient;

[0085] Continuously monitor the video frames of the vehicle-mounted camera to obtain the jitter coefficient;

[0086] Compare the jitter coefficient to the jitter coefficient threshold:

[0087] If the jitter coefficient is greater than or equal to the jitter coefficient threshold, the corresponding jitter coefficient is subtracted from the jitter coefficient threshold to obtain a jitter coefficient deviation value, and the control coefficient is multiplied by the jitter coefficient deviation value to obtain the vehicle voltage control value;

[0088] If the jitter coefficient is less than the jitter coefficient, no processing is performed.

[0089] The technical solution of the embodiment of the present invention is mainly as follows: based on the unstable signal, the vehicle voltage corresponding to the time period of continuous frame image generation is analyzed to obtain the vehicle voltage influence value, and based on the vehicle voltage influence value, it is judged whether the vehicle voltage affects the vehicle lens picture jitter, and the influence result includes the vehicle voltage influence signal and the non-vehicle voltage influence signal; based on the vehicle voltage influence signal, the voltage at each time point corresponding to the continuous frame image generation period is obtained, a decision tree model is constructed, and the frame rate of the vehicle lens picture is adjusted; the present invention is also applicable to the situation where the vehicle lens picture jitter is caused by abnormal vehicle voltage. By adjusting the coefficient, the vehicle voltage that causes the vehicle lens picture jitter is adjusted to reduce or avoid the picture jitter caused by the vehicle voltage fluctuation, which is beneficial to improving the shooting quality of the vehicle lens picture.

[0090] Embodiment 3

[0091] Based on Example 1, please refer to Figure 2 As shown, the image quality detection system of a vehicle-mounted lens according to an embodiment of the present invention further includes the following steps:

[0092] Jitter signal generation module: analyzes the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and determines whether to generate a frame jitter signal based on the jitter coefficient DX;

[0093] Stability judgment module: Analyze the number of times the frame jitter signal is generated in the continuous frame image, the duration of the frame jitter signal and the jitter coefficient of the frame jitter image corresponding to the frame jitter signal to obtain the image jitter representation value DB. If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated;

[0094] Influencing factor analysis module: Based on the unstable signal, the vehicle voltage and jitter coefficient corresponding to the unit time period of the continuous frame image are analyzed to obtain the vehicle voltage impact value. Based on the vehicle voltage impact value, it is determined whether the vehicle voltage affects the jitter of the vehicle lens image. The impact result includes the vehicle voltage impact signal;

[0095] Impact control module: Based on the vehicle voltage impact signal, all slope values ​​in the slope ratio data group are processed to obtain the control coefficient. Based on the control coefficient, the vehicle voltage control value is obtained to adjust the frame rate of the vehicle lens image.

[0096] Embodiment 4

[0097] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a method for detecting the image quality of a vehicle lens as described in any one of the above methods is implemented.

[0098] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that

[0099] Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0100] The processor 301 may be a central processing unit (CPU), or 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. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0101] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0102] Embodiment 5

[0103] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for detecting the image quality of a vehicle-mounted lens as described in any one of the above methods is implemented.

[0104] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0107] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0110] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for detecting the image quality of a vehicle-mounted lens, characterized in that: The following steps are involved: Step 1: Analyze the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and determine whether to generate a frame jitter signal based on the jitter coefficient DX; The video data captured by the vehicle-mounted camera includes continuous frame images; Step 2: Analyze the number of times the frame jitter signal is generated in the continuous frame image, the duration of the frame jitter signal, and the jitter coefficient of the frame jitter image corresponding to the frame jitter signal to obtain the image jitter representation value DB. If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated; Step 3: Based on the unstable signal, the vehicle voltage and jitter coefficient corresponding to the unit time period of the continuous frame image are analyzed to obtain the vehicle voltage influence value, and based on the vehicle voltage influence value, it is determined whether the vehicle voltage affects the jitter of the vehicle lens image, and the influence result includes the vehicle voltage influence signal; Step 4: Based on the vehicle voltage influence signal, all slope values ​​in the slope ratio data group are processed to obtain the control coefficient. Based on the control coefficient, the vehicle voltage control value is obtained to adjust the frame rate of the vehicle lens image.

2. The image quality detection method of a vehicle-mounted lens according to claim 1, characterized in that: The jitter coefficient DX is obtained as follows: Obtain video data shot by the vehicle-mounted lens, and analyze and obtain the image correlation performance value NCCn and image shift ratio TP of adjacent frame images; The correlation value NCCn and the image shift ratio TP are processed by the formula: The jitter coefficient DX of adjacent frame images is calculated.

3. The image quality detection method of a vehicle-mounted lens according to claim 2, characterized in that: The image shift ratio TP of adjacent frame images is obtained as follows: Taking the vertex in the first frame image as the origin, a spatial coordinate system is constructed, wherein the horizontal direction is the X-axis, the vertical direction is the Y-axis, and the Z-axis direction is used to arrange consecutive frame images; Each frame of image is divided into several equal and non-overlapping blocks with unit length e, and the blocks are marked as r in sequence, where r is 1, 2, 3, etc.; the central pixel point of block r is the central coordinate point of block r, and the coordinate of block r in the XY plane in the spatial coordinate system is marked as (x (n、r) ,y (n、r) ), Traverse and calculate the offset value PY(n, r) of the same block r marked in two adjacent frame images n and n-1; The offset values ​​of all blocks in the previous frame image n-1 are summed and averaged to obtain the block offset mean, the block offset value is subtracted from the block offset mean to obtain the block relative offset value, all the block relative offset values ​​are summed and averaged to obtain the block relative offset mean, the block relative offset mean is compared with the block offset mean to obtain the image offset degree ratio TPn-1 of the frame image n-1.

4. The method for detecting image quality of a vehicle-mounted lens according to claim 2, characterized in that: The method for obtaining the image correlation performance value NCCn of the adjacent frame images is as follows: The correlation value between the blocks r with the same label in the adjacent frame images n and n-1 is calculated by traversing the normalized cross-correlation calculation formula, including the following steps: Construct a block pixel coordinate system, with the horizontal direction of the block in the frame image as the x-axis and the vertical direction of the block in the frame image as the y-axis, and mark the coordinate of each pixel in the frame image block r as (i, j); Get the pixel value of each pixel in block r in frame image n, denoted as B(i (n、r) , j (n、r) ); then calculate and obtain the pixel mean BJ(n, r) of the pixel points in block r in frame image n; The normalized cross-correlation formula is: Calculate and obtain the block correlation value NCC(n, r) between blocks with the same label r in adjacent frame images; All block correlation values ​​in adjacent frame images are summed and averaged to obtain the adjacent frame image correlation performance value NCCn.

5. The method for detecting image quality of a vehicle-mounted lens according to claim 1, characterized in that: The image jitter characterization value DB of the continuous frame images is obtained as follows: The number of times the frame jitter signal is generated in the continuous frame images, the time period when the frame jitter signal appears, and the jitter coefficient of the frame jitter image generated by the frame jitter signal are obtained, and the frame jitter number ratio DC, the jitter duration ratio DS, and the jitter degree ratio DD are obtained by analysis; The frame jitter ratio DC, jitter duration ratio DS and jitter degree ratio DD are processed by the formula: The image jitter characterization value DB of the continuous frame images is calculated, wherein s1, s2 and s3 are all preset proportional coefficients, s1 takes a value of 1.022, s2 takes a value of 1.145, and s3 takes a value of 1.

231.

6. The method for detecting the image quality of a vehicle-mounted lens according to claim 5, characterized in that: The frame jitter frequency ratio DC, jitter duration ratio DS and jitter degree ratio DD are obtained as follows: The number of times the frame jitter signal is generated in the continuous frame images is obtained, and the ratio is processed with the number of continuous frame images to obtain the frame jitter number ratio DC; Mark the period when the frame jitter signal appears as the frame jitter period, obtain the duration corresponding to the frame jitter period, obtain the frame jitter duration, sum up all the jitter durations, output the total jitter duration, perform ratio processing on the total jitter duration and the total duration corresponding to the continuous frame images, and obtain the jitter duration ratio DS; The jitter coefficient of the corresponding frame jitter image generated by the frame jitter signal is obtained and subtracted from the jitter coefficient threshold to obtain the jitter deviation value. The jitter deviation values ​​of all frame jitter images in the continuous frame images are summed and averaged to obtain the jitter deviation mean of the vehicle-mounted lens image. The jitter deviation mean is compared with the jitter coefficient threshold to obtain the jitter degree ratio DD.

7. The method for detecting image quality of a vehicle-mounted lens according to claim 5, characterized in that: The vehicle voltage impact value CYx is obtained in the following manner: The vehicle voltage and jitter coefficient corresponding to the unit time period generated by the continuous frame images are obtained, and the vehicle voltage change line and the jitter coefficient change line are constructed respectively. The vehicle voltage change line and the jitter coefficient change line are analyzed to obtain the change synchronization value FC and the overlap time ratio CH; The obtained change synchronization value FC and overlap time ratio CH are processed by the formula: The vehicle voltage impact value CYx is calculated, where c1 and c2 are both preset proportional coefficients, c1 takes a value of 1.268, and c2 takes a value of 1.

989.

8. The method for detecting image quality of a vehicle-mounted lens according to claim 7, characterized in that: The change synchronization value FC and the overlap time ratio CH are obtained as follows: Obtain the vehicle voltage and jitter coefficient corresponding to the unit time period generated by the continuous frame images, mark them in the XY coordinate system respectively, connect all the vehicle voltage marking points to obtain the vehicle voltage change line, mark and connect all the jitter coefficient marking points to obtain the jitter coefficient change line; Draw a straight line parallel to the x-axis through the rated vehicle voltage mark point and mark it as the vehicle voltage limit line; Obtain all curve segments of the vehicle voltage change curve that are higher than the vehicle voltage limit line, mark them as out-of-bounds curves, obtain the time period corresponding to the out-of-bounds curve on the X-axis, and obtain the out-of-bounds time period; Perform overlap analysis on the out-of-bounds period and the frame jitter period to obtain the overlap period between the out-of-bounds period and the frame jitter period, and sum the durations corresponding to all the overlap periods to obtain the overlap duration; The overlap duration is processed by ratio processing with the total duration corresponding to the continuous frame images to obtain the overlap duration ratio, which is marked as CH; Based on the overlap period, the overlap period is divided into a number of time points of equal length; Respectively obtain the vehicle voltage change sub-line and the jitter coefficient change sub-line corresponding to two adjacent time points, and integrate the obtained vehicle voltage change sub-line and jitter coefficient change sub-line into a sub-line group; The vehicle voltage change sub-line is a line connecting two adjacent vehicle voltage value marking points in the vehicle voltage change line, and the jitter coefficient change sub-line is a line connecting two adjacent jitter coefficient marking points in the jitter coefficient change line; Obtaining the slopes of the vehicle voltage change sub-line and the jitter coefficient change sub-line in the sub-line group respectively, and performing ratio processing on them to obtain the slope ratio of the sub-line group; The slope ratios corresponding to all sub-polyline groups are integrated into a slope ratio data group, and the variance of the slope ratios within the slope ratio data group is calculated to obtain a change synchronization value, which is marked as FC.

9. The method for detecting image quality of a vehicle-mounted lens according to claim 8, characterized in that: The vehicle voltage control value is obtained in the following manner: All slope values ​​in the slope ratio data group are summed and averaged to obtain the control coefficient; Continuously monitor the video frames of the vehicle-mounted camera to obtain the jitter coefficient; Compare the jitter coefficient to the jitter coefficient threshold: If the jitter coefficient is greater than or equal to the jitter coefficient threshold, the corresponding jitter coefficient is subtracted from the jitter coefficient threshold to obtain a jitter coefficient deviation value, and the control coefficient is multiplied by the jitter coefficient deviation value to obtain the vehicle voltage control value; If the jitter coefficient is less than the jitter coefficient, no processing is performed.

10. A vehicle-mounted lens image quality detection system, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Jitter signal generation module: analyzes the video data shot by the vehicle-mounted lens to obtain the jitter coefficient DX, and determines whether to generate a frame jitter signal based on the jitter coefficient DX; Stability judgment module: Analyze the number of times the frame jitter signal is generated in the continuous frame image, the duration of the frame jitter signal and the jitter coefficient of the frame jitter image corresponding to the frame jitter signal to obtain the image jitter representation value DB. If the image jitter representation value DB is greater than or equal to the image jitter representation threshold, the image jitter of the vehicle-mounted lens is serious, that is, an unstable signal is generated; Influencing factor analysis module: Based on the unstable signal, the vehicle voltage and jitter coefficient corresponding to the unit time period of the continuous frame image are analyzed to obtain the vehicle voltage impact value. Based on the vehicle voltage impact value, it is determined whether the vehicle voltage affects the jitter of the vehicle lens image. The impact result includes the vehicle voltage impact signal; Impact control module: Based on the vehicle voltage impact signal, all slope values ​​in the slope ratio data group are processed to obtain the control coefficient. Based on the control coefficient, the vehicle voltage control value is obtained to adjust the frame rate of the vehicle lens image.

Images