A multi-resolution camera imaging quality automatic evaluation method, system, electronic device and storage medium

Abstract

The application discloses a kind of multi-resolution under Camera imaging quality automation evaluation method, system, electronic equipment and storage medium, belong to imaging quality evaluation technical field, including S10: carry out relevant processing, preset imaging sample before carrying out relevant processing, imaging sample, for the imaging sample of target Camera device under multi-resolution gear;Relevant processing includes: the imaging sample is distinguished, including distinguishing into imaging sample I, imaging sample II and imaging sample III, and the resolution corresponding to each imaging sample distinguished is obtained;The difference of the resolution corresponding to each imaging sample distinguished is obtained, and relevant extraction is carried out according to the difference, and relevant extraction includes extracting quality difference.The present application can effectively determine the pros and cons of imaging quality by mechanisms such as presetting critical value, color accuracy calculation and risk color region identification, and predict the trend of quality change, providing technical support for the optimization of imaging quality of Camera device.

Description

Technical Field

[0001] This invention relates to the field of imaging quality assessment technology, and in particular to an automated method, system, electronic device, and storage medium for assessing the imaging quality of a camera under multiple resolutions. Background Technology

[0002] In today's digital age, images have become an indispensable element in fields such as information dissemination, entertainment consumption, and scientific research, and the assessment of image quality has become a key link in quality assurance in related fields.

[0003] Regarding this research, application CN202211231813.2 provides a method, apparatus, device, and readable storage medium for lens resolution quality detection. The technical solution includes: acquiring an original image of the lens to be tested and extracting a region of interest (ROI) from the original image; determining a segmentation threshold based on the grayscale distribution statistics of the ROI, wherein the grayscale distribution statistics include the number of pixels corresponding to each grayscale level. This technical solution can automatically complete the quantitative analysis of lens resolution quality, improving the efficiency and accuracy of lens resolution quality detection to a certain extent.

[0004] Another application, CN202610378101.5, provides an image processing method, storage medium, and electronic device. This technical solution acquires spatiotemporally aligned visible light images and infrared thermal imaging images of a target scene, performs cross-modal pixel-level semantic analysis, generates understanding information containing the semantic category of each pixel, determines differentiated image fusion strategies corresponding to different semantic categories based on this semantic information, and uses this strategy to fuse the two types of images to generate a target fused image, thereby effectively suppressing noise and artifacts in complex environments to improve image detail and visual coherence.

[0005] However, the above technical solutions only test basic indicators such as signal-to-noise ratio and sharpness at a specific resolution (such as the default output level), ignoring the continuity of image quality when switching between different resolutions. For example, when the device automatically reduces the resolution due to bandwidth fluctuations during recording, the image often shows obvious color abrupt changes or artifacts, and the single-point evaluation of the above technical solutions cannot capture the image quality loss during this dynamic adaptation process. Summary of the Invention

[0006] In view of the problems existing in the field of existing imaging quality assessment technology, the present invention is proposed.

[0007] Therefore, one of the objectives of this invention is to provide an automated method, system, electronic device, and storage medium for evaluating camera image quality under multiple resolutions. Through mechanisms such as preset thresholds, color accuracy calculation, and risk color region identification, it can effectively determine the quality of the image and predict the trend of image quality changes, providing technical support for optimizing the image quality of camera devices.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] On the one hand, the present invention provides an automated method for evaluating camera imaging quality under multiple resolutions, comprising the following steps:

[0010] S10: Perform related processing. Before performing the related processing, a preset imaging sample is established. The imaging sample is an imaging sample of the target camera device at multiple resolution levels. The related processing includes:

[0011] The imaging samples are distinguished into imaging sample I, imaging sample II and imaging sample III, and the resolution corresponding to each of the distinguished imaging samples is obtained;

[0012] Obtain the resolution difference corresponding to each distinguished imaging sample, and perform correlation extraction based on the difference. The correlation extraction includes extracting image quality differences, and the extraction steps are as follows:

[0013] The resolutions corresponding to imaging sample I, imaging sample II, and imaging sample III are respectively regarded as resolution I, resolution II, and resolution III, and the image quality corresponding to resolution I, resolution II, and resolution III is obtained;

[0014] The acquired image quality is further differentiated into different levels, including differentiation based on color levels, as shown below:

[0015] Obtain the colors contained in each image quality, and based on the colors contained, obtain the color regions corresponding to each color;

[0016] Within each color region, the color region is divided into three equal-height upper, middle, and lower steps;

[0017] Relevant calculations are performed on the divided steps, including color accuracy;

[0018] S20: Based on the calculated color accuracy preset threshold, including a threshold value of ΔE < 6.5, if the color accuracy of the target camera device exceeds the threshold value at a future time, the image quality is determined to be poor; otherwise, the image quality is not determined to be poor.

[0019] S30: When the image quality is determined to be poor, the resolution corresponding to this image is obtained, and the resolution is regarded as a reference resolution. Among the I resolution, II resolution and III resolution, the resolution closest to the reference resolution is obtained and the resolution is regarded as a comparison resolution. When the resolution of the target camera device's image changes towards the comparison resolution in the future, it is determined that the image quality is on the trend of improvement.

[0020] S40: When the image quality is determined to be poor, the color region with the highest color accuracy exceeding the threshold value is counted in each color region and regarded as the reference color region. When the resolution of the image does not change towards the reference resolution, the color accuracy of the reference color region is calculated. If the color accuracy is lower than the threshold value, the image quality is not determined to be poor.

[0021] On the other hand, the present invention provides a system for an automated assessment method of camera imaging quality under multiple resolutions as described above, comprising:

[0022] The data processing module is used to perform related processing. Before performing the related processing, an imaging sample is preset. The imaging sample is an imaging sample of the target camera device at multiple resolution levels. The data processing module includes a differentiation unit, an extraction unit, and a calculation unit.

[0023] The distinguishing unit is used to distinguish the imaging samples, including distinguishing them into imaging sample I, imaging sample II and imaging sample III, and obtaining the resolution corresponding to each distinguished imaging sample;

[0024] The extraction unit is used to obtain the resolution difference corresponding to each distinguished imaging sample, and to perform correlation extraction based on the difference. The correlation extraction includes extracting image quality differences, and the extraction steps are as follows:

[0025] The resolutions corresponding to imaging sample I, imaging sample II, and imaging sample III are respectively regarded as resolution I, resolution II, and resolution III, and the image quality corresponding to resolution I, resolution II, and resolution III is obtained;

[0026] The acquired image quality is further differentiated into different levels, including differentiation based on color levels, as shown below:

[0027] Obtain the colors contained in each image quality, and based on the colors contained, obtain the color regions corresponding to each color;

[0028] Within each color region, the color region is divided into three equal-height upper, middle, and lower steps;

[0029] The computing unit is used to perform relevant calculations in the divided steps, including color accuracy;

[0030] An imaging fusion evaluation module, comprising evaluation unit I, evaluation unit II, and evaluation unit III;

[0031] The evaluation unit I is used to preset a critical value based on the calculated color accuracy, including a critical value of ΔE < 6.5. When the color accuracy of the target camera device exceeds the critical value at a future time, the image quality is determined to be poor; otherwise, the image quality is not determined to be poor.

[0032] The evaluation unit II is used to obtain the resolution corresponding to the image when the image quality is determined to be poor, and to take the resolution as a reference resolution. Among the I resolution, II resolution and III resolution, the resolution closest to the reference resolution is obtained and taken as the control resolution. When the resolution of the target camera device's image changes toward the control resolution in the future, it is determined that the image quality is on the trend of improvement.

[0033] The evaluation unit III is used to, when the image quality is determined to be poor, count the color regions in each color region where the color accuracy exceeds the critical value the most, and regard the color regions as reference color regions. When the resolution of the image does not change towards the reference resolution, the color accuracy of the reference color regions is calculated. If the color accuracy is lower than the critical value, the image quality is not determined to be poor.

[0034] An electronic device includes a processor, an input interface, an output interface, and a memory, wherein the processor, the input interface, the output interface, and the memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the method described above.

[0035] A computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described above.

[0036] Beneficial effects:

[0037] 1. This invention achieves fine differentiation of image quality by pre-setting imaging samples and further distinguishing the imaging samples in detail (imaging samples I, II, III), and obtaining the resolution and image quality information corresponding to each sample, which can more accurately identify the differences in image quality at different resolutions.

[0038] 2. This invention utilizes quantitative calculation of color accuracy. By calculating parameters such as color difference value, brightness axis, red / green axis, and yellow / blue axis, it can accurately measure the difference between the image color and the reference color. This quantitative evaluation makes the image quality evaluation more objective and comparable.

[0039] 3. When determining poor image quality, this invention can further analyze the relationship between resolution changes and image quality improvement. By obtaining reference resolution and comparison resolution, it can predict the future trend of image quality changes, providing guidance for image quality optimization. Furthermore, by identifying the risk color areas most affected by resolution and paying special attention to these areas in future imaging, if the image contains risk color areas and the color accuracy is not up to standard, it is determined to be poor image quality, which helps to discover and solve potential image quality problems in a timely manner.

[0040] 4. Furthermore, in addition to the risky color areas, the present invention also considers other color areas affected by resolution. By statistically analyzing the number of affected color groups and calculating color accuracy, the image quality is comprehensively evaluated to meet the image quality evaluation needs in different scenarios. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of the modular structure of an automated camera imaging quality evaluation system under multiple resolutions according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the method flow for step S10 in an embodiment of the present invention;

[0042] The diagram is labeled as follows: 110 - Data processing module; 1101 - Differentiation unit; 1102 - Extraction unit; 1103 - Calculation unit; 120 - Imaging fusion evaluation module; 1201 - Evaluation unit I; 1202 - Evaluation unit II; 1203 - Evaluation unit III. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0044] Because existing technologies only test basic indicators such as signal-to-noise ratio and sharpness at specific resolutions (such as the default output level), they ignore the continuity of image quality when switching between different resolutions, making it impossible to capture the image quality loss during this dynamic adaptation process.

[0045] Based on this, the present invention proposes an automated evaluation method, system, electronic device and storage medium for camera imaging quality under multiple resolutions. Through mechanisms such as preset threshold values, color accuracy calculation and risk color area identification, it can effectively determine the quality of the image and predict the trend of image quality changes.

[0046] The present solution will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0047] Reference Figures 1 to 3 This is one embodiment of the present invention, which provides an automated method for evaluating camera imaging quality under multiple resolutions, including the following steps:

[0048] S10: Perform relevant processing. Before performing relevant processing, preset imaging samples. The imaging samples are imaging samples of the target camera device at multiple resolution levels (all imaging samples mentioned are imaging samples with good image quality); the relevant processing includes:

[0049] The imaging samples are distinguished into imaging sample I, imaging sample II and imaging sample III, and the resolution corresponding to each imaging sample is obtained.

[0050] The system presets imaging samples of the target camera device at multiple resolution levels, distinguishes and processes these samples, and obtains the resolution of each sample and its corresponding image quality, making the evaluation results more comprehensive and improving the evaluation efficiency.

[0051] Obtain the resolution difference between the identified imaging samples and the target samples. Then, perform correlation extraction based on the differences. Correlation extraction includes extracting image quality differences. The extraction steps are as follows:

[0052] The resolutions corresponding to imaging sample I, imaging sample II, and imaging sample III are respectively regarded as resolution I, resolution II, and resolution III, and the image quality corresponding to resolution I, resolution II, and resolution III is obtained (i.e., the image quality corresponding to resolution I, resolution II, and resolution III).

[0053] The acquired image quality is then differentiated into different levels, including differentiation based on color levels, as shown below:

[0054] Obtain the colors contained in each image quality, and based on the colors contained, obtain the color regions corresponding to each color;

[0055] Within each color area, the color area is divided into three equal-height upper, middle, and lower tiers.

[0056] Relevant calculations are performed on the defined steps, including color accuracy.

[0057] In one feasible implementation, the images at different resolutions are subdivided vertically in the color space (upper, middle, and lower three-tiered steps) to compare the ability of different resolutions to reproduce different brightness or saturation levels within the same color area.

[0058] By distinguishing samples at different resolutions, the imaging quality at each resolution can be evaluated more accurately.

[0059] S20: Based on the calculated color accuracy preset threshold, including a preset threshold of ΔE value < 6.5, if the color accuracy of the target camera device's image exceeds the threshold at a future time, the image quality is judged to be poor; otherwise, the image quality is not judged to be poor.

[0060] ΔE (Delta-E) is a unit of measurement for color difference as perceived by the human eye. In reality, if the ΔE value is greater than 6.5, it is considered a serious color deviation, and users can clearly perceive that the color is "wrong," such as appearing greenish or purplish.

[0061] Quantifying color accuracy makes the evaluation results more objective and comparable, while setting thresholds can promptly identify imaging quality problems and provide a basis for improvement.

[0062] S30: When the image quality is determined to be poor, the resolution corresponding to this image is obtained and regarded as the reference resolution. Among the I resolution, II resolution and III resolution, the resolution closest to the reference resolution is obtained and regarded as the comparison resolution. When the resolution of the target camera device's image changes towards the comparison resolution in the future, it is determined that the image quality is on the trend of improvement.

[0063] This embodiment can predict future trends in image quality, providing guidance for device optimization and upgrades. Furthermore, based on trend analysis, it can specifically improve image quality at a particular resolution.

[0064] S40: When the image quality is determined to be poor, the color region with the highest color accuracy exceeding the threshold is counted in each color region and regarded as the reference color region. When the resolution of the image does not change towards the reference resolution, the color accuracy of the reference color region is calculated. If the color accuracy is lower than the threshold, the image quality is not determined to be poor.

[0065] In one feasible implementation, this embodiment takes into account the image quality judgment under special circumstances, avoiding the one-sidedness of a single standard.

[0066] Furthermore, by statistically analyzing and comparing the color accuracy of different color regions, image quality issues can be analyzed in more detail.

[0067] In S10, relevant calculations (color accuracy) are performed on the divided steps, as shown below:

[0068] ;

[0069] In the formula, Indicates the color difference value;

[0070] Indicates the brightness axis; represents the lightness or darkness of that step level.

[0071] This represents the red / green axis (positive values ​​tend towards red, negative values ​​tend towards green).

[0072] This indicates the yellow / blue axis (positive values ​​tend towards yellow, negative values ​​tend towards blue).

[0073] Subscript , representing the baseline reference value (i.e., the imaging sample);

[0074] Subscript , represents the measured value (i.e., the data measured by the target camera device at resolutions I, II, and III).

[0075] Furthermore, it also includes calculations based on the following formula:

[0076] ;

[0077] In the formula, This represents the difference in saturation (a positive result indicates a more vibrant color, while a negative result indicates a paler color).

[0078] It represents chroma (the distance of a color from the central gray axis).

[0079] Because the color areas are divided into equal height sections, the saturation can be extracted separately to determine the impact of resolution on color purity.

[0080] Based on the calculation results, relevant data is obtained, including the degree to which each color region is affected by resolution, as shown below:

[0081] ;

[0082] In the formula, This indicates the color fluctuation index (the higher the value, the worse the color stability of the camera device at different resolutions).

[0083] Indicates the first Color difference values ​​at various resolutions;

[0084] This represents the average color difference across three resolutions.

[0085] This indicates the total number of resolution levels ( =3).

[0086] In one feasible implementation, due to the use of a three-tiered division, different weighting coefficients can be assigned to each tier during calculation (e.g., the weight of the central tier is set to 0.5, and the weight of the edge tier is set to 0.25). The resulting weighted average score can better reflect the true image quality observed by the human eye.

[0087] It can identify color areas that may have imaging quality problems in advance, providing a basis for risk prevention and control. At the same time, it clarifies the key areas for optimizing imaging quality and improves optimization efficiency.

[0088] Based on the calculation results, the color regions most affected by resolution are obtained from each color region. These color regions are considered as risk color regions. If a risk color region is present in the image at a future time, the image quality is judged to be poor; otherwise, the image quality is not judged to be poor.

[0089] In S30, when it is determined that the image quality is on an improving trend, if the image contains a risky color area, the color accuracy of the risky color area is calculated. If the color accuracy exceeds the threshold value, the image quality is determined to be poor; otherwise, the image quality is not determined to be poor.

[0090] In one feasible implementation, the imaging of areas containing risky colors can be more strictly controlled, ensuring an overall improvement in imaging quality and preventing the overall evaluation results from being affected by poor imaging quality in local areas.

[0091] In addition to the risky color areas, other color areas affected by resolution are acquired, the number of color areas is counted, and affected color groups are generated. When it is determined that the image quality is on the trend of improvement, if the image does not contain risky color areas, but the color areas corresponding to the affected color groups account for one-third of the color areas of the image, then the color accuracy of the color areas (the color areas that are the same as the color areas corresponding to the affected color groups) is calculated; otherwise, it is not calculated, and the image quality is judged based on the calculation (judged according to whether it exceeds the critical value).

[0092] In one feasible implementation, in addition to the risky color areas, other color areas affected by resolution are also considered. The number of these areas is counted to generate affected color groups. When the image does not contain risky color areas but the proportion of affected color groups reaches a certain level, the color accuracy of these areas is calculated to determine the image quality.

[0093] This embodiment comprehensively considers all color regions affected by resolution, avoiding the one-sidedness of the evaluation. Through statistics and calculations, it is possible to understand the performance of image quality in different color regions in greater detail.

[0094] As can be seen from the above, this application can effectively determine the quality of the image and predict the trend of image quality changes by means of preset threshold values, color accuracy calculation and risk color area identification, thus providing technical support for the optimization of the image quality of camera devices.

[0095] This embodiment, in conjunction with the above-described automated assessment method for camera imaging quality under multiple resolutions, also proposes a system applied to this method, as follows:

[0096] The data processing module 110 is used to perform related processing. Before performing related processing, it presets an imaging sample. The imaging sample is an imaging sample of the target camera device at multiple resolution levels. The data processing module 110 includes a differentiation unit 1101, an extraction unit 1102, and a calculation unit 1103.

[0097] The differentiation unit 1101 is used to differentiate the imaging samples, including differentiating them into imaging sample I, imaging sample II and imaging sample III, and to obtain the resolution corresponding to each differentiated imaging sample.

[0098] The extraction unit 1102 is used to obtain the resolution difference between each distinguished imaging sample and the resolution difference, and to perform correlation extraction based on the difference. The correlation extraction includes extracting image quality differences. The extraction steps are as follows:

[0099] The resolutions corresponding to imaging sample I, imaging sample II, and imaging sample III are respectively regarded as resolution I, resolution II, and resolution III, and the image quality corresponding to resolution I, resolution II, and resolution III is obtained;

[0100] The acquired image quality is then differentiated into different levels, including differentiation based on color levels, as shown below:

[0101] Obtain the colors contained in each image quality, and based on the colors contained, obtain the color regions corresponding to each color;

[0102] Within each color area, the color area is divided into three equal-height upper, middle, and lower tiers.

[0103] The calculation unit 1103 is used to perform relevant calculations in the divided steps, including color accuracy;

[0104] The imaging fusion evaluation module 120 includes evaluation unit I 1201, evaluation unit II 1202 and evaluation unit III 1203;

[0105] Evaluation unit I1201 is used to preset a threshold value based on the calculated color accuracy, including a threshold value of ΔE value < 6.5. If the color accuracy of the target camera device exceeds the threshold value at a future time, the image quality is judged to be poor; otherwise, the image quality is not judged to be poor.

[0106] Evaluation unit II 1202 is used to obtain the resolution corresponding to the image when the image quality is determined to be poor, and to take the resolution as a reference resolution. Among resolution I, resolution II and resolution III, the resolution closest to the reference resolution is obtained and taken as the control resolution. When the resolution of the target camera device's image changes towards the control resolution in the future, it is determined that the image quality is on the trend of improvement.

[0107] Evaluation unit Ⅲ1203 is used to identify the color region with the highest color accuracy exceeding the threshold when the image quality is determined to be poor. This color region is then regarded as a reference color region. When the resolution of the image does not change towards the reference resolution, the color accuracy of the reference color region is calculated. If the color accuracy is lower than the threshold, the image quality is not determined to be poor.

[0108] An electronic device includes a processor, an input interface, an output interface, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the method described above.

[0109] A computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the methods described above.

[0110] In summary, this invention, through mechanisms such as preset threshold values, color accuracy calculation, and risk color region identification, can effectively determine the quality of image images and predict the trend of image quality changes. It has high trend prediction, risk identification, flexibility, and adaptability, and can provide technical support for optimizing the image quality of camera devices.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An automated method for evaluating camera image quality under multiple resolutions, characterized in that, Includes the following steps: S10: Perform related processing. Before performing the related processing, a preset imaging sample is established. The imaging sample is an imaging sample of the target camera device at multiple resolution levels. The related processing includes: The imaging samples are distinguished into imaging sample I, imaging sample II and imaging sample III, and the resolution corresponding to each of the distinguished imaging samples is obtained; Obtain the resolution difference corresponding to each distinguished imaging sample, and perform correlation extraction based on the difference. The correlation extraction includes extracting image quality differences, and the extraction steps are as follows: The resolutions corresponding to imaging sample I, imaging sample II, and imaging sample III are respectively regarded as resolution I, resolution II, and resolution III, and the image quality corresponding to resolution I, resolution II, and resolution III is obtained; The acquired image quality is further differentiated into different levels, including differentiation based on color levels, as shown below: Obtain the colors contained in each image quality, and based on the colors contained, obtain the color regions corresponding to each color; Within each color region, the color region is divided into three equal-height upper, middle, and lower steps; Relevant calculations are performed on the divided steps, including color accuracy; S20: Based on the calculated color accuracy preset threshold, including a threshold value of ΔE < 6.5, if the color accuracy of the target camera device exceeds the threshold value at a future time, the image quality is determined to be poor; otherwise, the image quality is not determined to be poor. S30: When the image quality is determined to be poor, the resolution corresponding to this image is obtained, and the resolution is regarded as a reference resolution. Among the I resolution, II resolution and III resolution, the resolution closest to the reference resolution is obtained and the resolution is regarded as a comparison resolution. When the resolution of the target camera device's image changes towards the comparison resolution in the future, it is determined that the image quality is on the trend of improvement. S40: When the image quality is determined to be poor, the color region with the highest color accuracy exceeding the threshold value is counted in each color region and regarded as the reference color region. When the resolution of the image does not change towards the reference resolution, the color accuracy of the reference color region is calculated. If the color accuracy is lower than the threshold value, the image quality is not determined to be poor.

2. The automated assessment method for camera imaging quality under multiple resolutions as described in claim 1, characterized in that, In step S10, relevant calculations are performed on the divided steps, as shown below: ； In the formula, Indicates the color difference value; Indicates the brightness axis; Indicates the red / green axis; Indicates yellow / blue axis; Subscript , indicating the baseline reference value; Subscript , represents the measured value.

3. The automated assessment method for camera imaging quality under multiple resolutions as described in claim 2, characterized in that, It also includes calculations based on the following formula: ； In the formula, Indicates the difference in saturation; Indicates chroma.

4. The automated assessment method for camera imaging quality under multiple resolutions as described in any one of claims 2 to 3, characterized in that, Based on the calculation results, relevant data is obtained, including the degree to which each color region is affected by resolution, as shown below: ； In the formula, Indicates color fluctuation index; Indicates the first Color difference values ​​at various resolutions; This represents the average color difference across three resolutions. This indicates the total number of resolution levels.

5. The automated assessment method for camera imaging quality under multiple resolutions as described in claim 4, characterized in that, Based on the calculation results, the color regions most affected by resolution are obtained from each color region. These color regions are considered as risk color regions. If the image contains these risk color regions in future imaging, the image quality is determined to be poor. Conversely, if the image quality is poor, it is not considered poor.

6. The automated assessment method for camera imaging quality under multiple resolutions as described in claim 5, characterized in that, In S30, when it is determined that the image quality is on an improving trend, if the image contains the risk color area, the color accuracy of the risk color area is calculated. If the color accuracy exceeds the threshold value, the image quality is determined to be poor. Conversely, if the image quality is poor, it is not considered poor.

7. The automated assessment method for camera imaging quality under multiple resolutions as described in claim 6, characterized in that, In addition to the risky color regions, other color regions affected by resolution are obtained, the number of these color regions is counted, and affected color groups are generated. When it is determined that the image quality is on an improving trend, if the image does not contain the risky color regions, but the color regions corresponding to the affected color groups account for one-third of the color regions of the image, then the color accuracy of the color regions is calculated; otherwise, it is not calculated, and the image quality is judged based on the calculation.

8. A system applied to the automated assessment method for camera imaging quality under multiple resolutions as described in claim 1, characterized in that, include: The data processing module is used to perform related processing. Before performing the related processing, an imaging sample is preset. The imaging sample is an imaging sample of the target camera device at multiple resolution levels. The data processing module includes a differentiation unit, an extraction unit, and a calculation unit. The distinguishing unit is used to distinguish the imaging samples, including distinguishing them into imaging sample I, imaging sample II and imaging sample III, and obtaining the resolution corresponding to each distinguished imaging sample; The extraction unit is used to obtain the resolution difference corresponding to each distinguished imaging sample, and to perform correlation extraction based on the difference. The correlation extraction includes extracting image quality differences, and the extraction steps are as follows: The resolutions corresponding to imaging sample I, imaging sample II, and imaging sample III are respectively regarded as resolution I, resolution II, and resolution III, and the image quality corresponding to resolution I, resolution II, and resolution III is obtained; The acquired image quality is further differentiated into different levels, including differentiation based on color levels, as shown below: Obtain the colors contained in each image quality, and based on the colors contained, obtain the color regions corresponding to each color; Within each color region, the color region is divided into three equal-height upper, middle, and lower steps; The computing unit is used to perform relevant calculations in the divided steps, including color accuracy; An imaging fusion evaluation module, comprising evaluation unit I, evaluation unit II, and evaluation unit III; The evaluation unit I is used to preset a critical value based on the calculated color accuracy, including presetting the critical value with ΔE value < 6.

5. When the color accuracy of the target camera device exceeds the critical value at a future time, the image quality is determined to be poor. Conversely, if the image quality is poor, it is not considered poor. The evaluation unit II is used to obtain the resolution corresponding to the image when the image quality is determined to be poor, and to take the resolution as a reference resolution. Among the I resolution, II resolution and III resolution, the resolution closest to the reference resolution is obtained and taken as the control resolution. When the resolution of the target camera device's image changes toward the control resolution in the future, it is determined that the image quality is on the trend of improvement. The evaluation unit III is used to, when the image quality is determined to be poor, count the color regions in each color region where the color accuracy exceeds the critical value the most, and regard the color regions as reference color regions. When the resolution of the image does not change towards the reference resolution, the color accuracy of the reference color regions is calculated. If the color accuracy is lower than the critical value, the image quality is not determined to be poor.

9. An electronic device, characterized in that, The device includes a processor, an input interface, an output interface, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1 to 7.

Images