Image quality control method and system based on 3D camera

Abstract

The invention discloses an image quality control method and system based on a 3D camera, and relates to the technical field of image quality control, and the method comprises the steps: S1, environment illumination evaluation and preprocessing; s2, dynamic light source adjustment; s3, image acquisition and real-time processing; s4, image quality evaluation and optimization; and S5, performing feedback and iteration. According to the image quality control method and system based on the 3D camera, through the steps of environment illumination evaluation and preprocessing, dynamic light source adjustment, image acquisition and real-time processing and the like, the problem that when the 3D camera is used outdoors or in an environment with large light change, the acquisition of depth information is prone to errors is solved; the image quality of the 3D camera outdoors or in an environment with relatively large light change can be remarkably improved, so that the accuracy of image quality control is improved; and the intensity and distribution of the light source can be dynamically adjusted to adapt to shooting requirements under different illumination conditions, so that the adaptability and flexibility of the 3D camera are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of image quality control, and in particular to an image quality control method and system based on a 3D camera. Background Art

[0002] Image quality control is the operation technology or activities taken to ensure that the image quality can meet the specified quality requirements. It covers a series of activities, including quality assurance and quality control. Among them, quality assurance is all the activities of the plan and system necessary to ensure that the product production process or service quality can meet the specified quality requirements; and quality control is a part of quality assurance.

[0003] In the existing technology, since 3D cameras can obtain three-dimensional information of the surface of objects, including geometric features such as shape, size, and contour, this provides a high-precision data source for image quality control. Therefore, image quality control based on 3D cameras has gradually become one of the current mainstream directions. This method combines the high-precision ranging capability of 3D cameras and the advantages of image processing technology, and can accurately detect defects, deformations, and flaws in images, thereby ensuring that the quality of the image meets the specified requirements; it is widely used in various fields, such as manufacturing, aerospace, automobile manufacturing, medical equipment, etc. For example, in the manufacturing industry, it can be used to detect whether the product's size, shape, and position information meet the design requirements; in the aerospace field, it can be used to detect the manufacturing quality and assembly accuracy of aircraft parts; in the automobile manufacturing field, it can be used to detect the manufacturing quality and assembly accuracy of automobile bodies, etc.

[0004] However, when a 3D camera is used outdoors or in an environment with large changes in light, its performance will be significantly affected by the ambient light. For example, in direct sunlight, the depth information of some areas may be erroneous or missing; and in a dark environment, the distance measurement capability of the 3D camera will be limited. These lead to errors in the acquisition of depth information, which in turn affects the accuracy of image quality control.

[0005] Therefore, it is urgent to improve this shortcoming. The present invention studies and improves the existing technology and its shortcomings, and provides an image quality control method and system based on a 3D camera. Summary of the invention

[0006] The purpose of the present invention is to provide an image quality control method and system based on a 3D camera to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] On the one hand, a method for controlling image quality based on a 3D camera is provided, comprising the following steps:

[0009] S1. Ambient lighting assessment and preprocessing:

[0010] Before using the 3D camera to collect images, the lighting conditions of the current environment are evaluated, and the 3D camera is pre-processed and adjusted according to the environmental lighting evaluation results;

[0011] S2. Dynamic light source adjustment:

[0012] S21, light source intensity control: dynamically adjust the intensity of the built-in or external light source of the 3D camera according to the intensity of the ambient light;

[0013] S22. Light source distribution optimization: According to the changes in ambient light, optimize the distribution of light sources to improve lighting uniformity and image quality;

[0014] S3, Image acquisition and real-time processing:

[0015] Use a 3D camera that has been pre-processed and adjusted for light source to capture images, ensuring that the camera can stably capture the three-dimensional information and depth data of the object, and perform real-time processing on the captured images, including denoising, contrast enhancement, distortion correction, etc.;

[0016] S4. Image quality assessment and optimization:

[0017] Perform quality assessment on the processed images, and further optimize and adjust the images based on the quality assessment results;

[0018] S5. Feedback and iteration:

[0019] A feedback mechanism is established to feed back the image quality assessment results and optimization adjustment plans to the control system of the 3D camera. The control system will make iterative adjustments based on the feedback information to continuously improve the image quality and stability. At the same time, in actual applications, the performance and image quality of the 3D camera are continuously monitored. Based on the monitoring results, the image quality control method is continuously optimized and adjusted to adapt to different environmental conditions and application requirements.

[0020] Furthermore, in step S1, the environmental lighting condition is evaluated by measuring the intensity and stability of the ambient light using a light sensor or an algorithm, as follows:

[0021] Light sensor evaluation: Through the coordinated work of the light sensor's photosensitive element and the signal processing circuit, the light signal is converted into an electrical signal, and the electrical signal output by the light sensor is read using a data reading device (such as a digital multimeter, data acquisition card, etc.) and converted into a light intensity value; then, based on the read light intensity value, the light intensity of the current environment is evaluated, and the light intensity value over a period of time is recorded and analyzed to observe the change in the light intensity value and evaluate the stability of the light;

[0022] Algorithm evaluation: specifically adopt gray world algorithm or automatic white balance algorithm;

[0023] The evaluation process of the gray world algorithm is as follows: first, the average values ​​of the three color channels R, G, and B in the image are calculated, and then a gray value (Gray) is calculated using the arithmetic average or weighted average of the average values ​​of the three channels, and the gray value is used to adjust the brightness or color balance of the image to eliminate the influence of ambient light, and then the images before and after the adjustment are compared to evaluate the intensity and stability of the ambient light; specifically, if the color of the image after adjustment is more balanced, it means that the ambient light is relatively stable; if the color deviation is large, it means that the ambient light fluctuates.

[0024] The evaluation process of the automatic white balance algorithm is as follows: first, the white points or areas close to white in the image are identified, the R, G, and B values ​​of these white points are calculated, and the gain coefficients that need to be adjusted are determined, and then the gain coefficients are applied to adjust the R, G, and B channels of the entire image to achieve white balance, and then the adjusted image color is observed to be natural and balanced, and the intensity and stability of the ambient light are evaluated; specifically, if the image color is natural and balanced, it means that the ambient light is relatively stable; if the color is yellowish or bluish, etc., it means that there is a color temperature deviation in the ambient light.

[0025] Furthermore, in step S1, the specific operations of preprocessing adjustment include but are not limited to:

[0026] White balance adjustment: Based on the ambient light assessment, manually adjust the camera's white balance parameters to suit the current light conditions;

[0027] Exposure adjustment: adjust the camera exposure time according to the intensity of ambient light to obtain appropriate image brightness and contrast, or use multiple exposure technology to improve the camera's imaging quality for objects with different reflective characteristics;

[0028] Gain (the degree to which the camera amplifies the light signal) adjustment: When the ambient light is weak, increase the camera gain to improve the image brightness;

[0029] Filter selection: In bright light environments, use a polarizing filter to reduce the impact of glare and reflected light; in low light environments, use a brightening filter to improve the camera's light capture ability.

[0030] Furthermore, in step S21, the 3D camera is equipped with a light source controller, which can adjust the light source intensity by controlling the power or current of the light source through a software or hardware interface, and the light source intensity control logic is: when the ambient light is strong, reduce the light source intensity to avoid overexposure (overexposure will cause loss of image details and affect image quality), ensuring that the image can capture sufficient details; when the ambient light is weak, increase the light source intensity to ensure sufficient lighting, improve the brightness and contrast of the image, and make the image clearer.

[0031] Furthermore, in step S22, the light source distribution is optimized by adjusting the shape, angle and position of the light source. For example, an adjustable LED light source or fiber optic light source is used to adjust the shape and distribution area of ​​the light source as needed, or optical elements (such as lenses, reflectors, etc.) are used to change the distribution of the light source. These optical elements can focus or distribute the light of the light source to the required area to achieve more uniform lighting, and the light source distribution optimization logic is as follows: in the case of direct sunlight or interference from a strong light source, a more focused light source distribution is adopted to reduce photon noise and interference and improve image clarity and contrast; in darker or shadowed areas, the distribution area of ​​the light source is increased to improve lighting uniformity and image quality, so as to improve lighting uniformity so that the dark areas in the image can also be sufficiently illuminated, thereby reducing shadows and dark corners in the image and improving the overall image quality.

[0032] Furthermore, in step S3, the real-time processing specifically includes:

[0033] Denoising: Reduce noise and improve image clarity through denoising algorithms such as mean filtering, median filtering, and Gaussian filtering;

[0034] Enhance contrast: Improve the contrast and visual effect of the image through contrast enhancement algorithms such as histogram equalization and contrast stretching;

[0035] Distortion correction: Through radial distortion correction, tangential distortion correction and other distortion correction algorithms, barrel distortion, pincushion distortion and other distortions in the image can be eliminated or reduced to make the image more realistic and accurate.

[0036] Furthermore, in step S4, image quality assessment: a series of index tests are performed on the processed image to measure whether its quality meets the requirements, and the indexes include resolution, clarity, contrast and depth accuracy, etc., and the evaluation method of each index is as follows:

[0037] Resolution: Use a high-resolution test chart (such as the ISO 12233 test chart) to shoot, and use Imatest software to analyze the resolution and modulation transfer function (MTF) curve of the image;

[0038] Clarity: Also use high-resolution test cards for shooting, and use professional software to analyze the image clarity index;

[0039] Contrast: Use a high-contrast test card (such as a grayscale card) to shoot, and use software to analyze the image's contrast index;

[0040] Depth accuracy: Use a 3D test image or scene to shoot, and use depth measurement tools or software to analyze the depth accuracy indicators of the image.

[0041] Furthermore, in step S4, the optimization and adjustment includes adjusting image enhancement parameters, repairing image defects, improving depth accuracy, etc. The image enhancement parameters include but are not limited to contrast, brightness, and sharpness. By adjusting the image enhancement parameters, the overall visual effect of the image can be improved;

[0042] The image defect repairing method includes using a repair tool or algorithm to repair defects (such as noise, distortion, dark corners, etc.) in the image, specifically, using a denoising algorithm to reduce noise in the image, using a distortion correction algorithm to eliminate or reduce image distortion, and using a brightness uniformity adjustment algorithm to improve dark corners in the image;

[0043] The improved depth accuracy: for the depth accuracy problem in 3D images, a depth optimization algorithm is used to improve it, specifically, the depth accuracy is improved by increasing the resolution of the depth sensor or improving the depth measurement algorithm; and the accuracy of the depth information is further improved by fusing image information from multiple perspectives.

[0044] Furthermore, in step S5, the process of establishing the feedback mechanism is as follows:

[0045] Clarify feedback goals and requirements: Establish the core goal of the feedback mechanism, which is to improve the image quality and stability of the 3D camera, and analyze the specific requirements for the image quality of the 3D camera under different ambient lighting conditions;

[0046] Design feedback process and interface: define the feedback content, that is, the information content that the feedback mechanism needs to transmit, design the feedback process, plan the transmission path of the image quality evaluation results from the evaluation system to the 3D camera control system, and develop a communication interface between the 3D camera control system and the evaluation system according to the feedback content requirements to achieve seamless data transmission;

[0047] Implement feedback mechanism: Integrate the image quality assessment system into the overall architecture of the 3D camera, and deploy a control system in the 3D camera that can receive feedback and make iterative adjustments. Then test the feedback mechanism to ensure that it works stably in actual applications.

[0048] Establish a continuous monitoring and optimization system: Set monitoring indicators based on the performance and image quality requirements of the 3D camera. In actual applications, the performance and image quality data of the 3D camera are collected in real time through the monitoring system, and the monitoring results are analyzed regularly to identify potential problems and improvement points, and continuously optimize and adjust the image quality control method to adapt to different environmental conditions and application requirements;

[0049] Iterative updates and continuous improvements: Collect user feedback on the 3D camera image quality, and regularly iterate and update the feedback mechanism and control system based on user feedback and monitoring results. Continue to pay attention to technological development trends and changes in user needs, and continuously improve and optimize the feedback mechanism.

[0050] On the other hand, a 3D camera-based image quality control system is provided, which is applied to the above-mentioned 3D camera-based image quality control method, including:

[0051] Ambient lighting assessment module: used to assess the lighting conditions of the current shooting environment, including light intensity, light uniformity, etc.

[0052] Preprocessing module: used to preprocess and adjust the 3D camera according to the evaluation results;

[0053] Dynamic light source adjustment module: used to dynamically adjust the light source, including light source intensity control and light source distribution optimization;

[0054] Image acquisition module: used to acquire images using a 3D camera that has undergone preprocessing and light source adjustment;

[0055] Real-time processing module: used to process images collected by 3D cameras in real time;

[0056] Evaluation and optimization module: used to evaluate the quality of the processed image and further optimize and adjust the image according to the quality evaluation results;

[0057] Feedback iteration module: used to iteratively adjust the control system of the 3D camera according to feedback information, and continuously optimize and adjust the image quality control method.

[0058] The present invention provides a method and system for image quality control based on a 3D camera, which has the following beneficial effects:

[0059] The present invention solves the problem of errors in the acquisition of depth information when the 3D camera is used outdoors or in an environment with large light changes through steps such as environmental light evaluation and preprocessing, dynamic light source adjustment, and image acquisition and real-time processing. It can significantly improve the image quality of the 3D camera outdoors or in an environment with large light changes, thereby improving the accuracy of image quality control; and can dynamically adjust the intensity and distribution of the light source to meet the shooting requirements under different lighting conditions, thereby enhancing the adaptability and flexibility of the 3D camera. In addition, the present invention also establishes a feedback mechanism to continuously optimize the light source and image processing algorithm, reduce the 3D camera's dependence on environmental light, and enable the 3D camera to work stably in a wider range of environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 A schematic diagram of the steps of the image quality control method based on a 3D camera of the present invention;

[0061] Figure 2 Schematic diagram of step S1 of the image quality control method based on a 3D camera of the present invention;

[0062] Figure 3 A schematic flow chart of the feedback mechanism of the image quality control method based on a 3D camera of the present invention is established;

[0063] Figure 4 The figure is a logical architecture diagram of the image quality control system based on a 3D camera of the present invention. DETAILED DESCRIPTION

[0064] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0065] like Figure 1-Figure 3 As shown, the image quality control method based on the 3D camera includes the following steps:

[0066] S1. Ambient lighting assessment and preprocessing:

[0067] Before using the 3D camera to collect images, the lighting conditions of the current environment are evaluated, and the 3D camera is pre-processed and adjusted according to the environmental lighting evaluation results;

[0068] In this embodiment, the lighting condition of the environment is evaluated by measuring the intensity and stability of the ambient light using a light sensor or an algorithm, as follows:

[0069] Light sensor evaluation: Through the coordinated work of the light sensor's photosensitive element and the signal processing circuit, the light signal is converted into an electrical signal, and the electrical signal output by the light sensor is read using a data reading device (such as a digital multimeter, data acquisition card, etc.) and converted into a light intensity value; then, based on the read light intensity value, the light intensity of the current environment is evaluated, and the light intensity value over a period of time is recorded and analyzed to observe the change in the light intensity value and evaluate the stability of the light;

[0070] Algorithm evaluation: specifically adopt gray world algorithm or automatic white balance algorithm;

[0071] The evaluation process of the gray world algorithm is as follows: first calculate the average values ​​of the three color channels R, G, and B in the image, then use the arithmetic mean or weighted mean of the three channel average values ​​to calculate a gray value (Gray), and use this gray value to adjust the brightness or color balance of the image to eliminate the influence of ambient light, then compare the images before and after the adjustment to evaluate the intensity and stability of the ambient light; specifically, if the color of the image is more balanced after adjustment, it means that the ambient light is relatively stable; if the color deviation is large, it means that the ambient light fluctuates.

[0072] The evaluation process of the automatic white balance algorithm: first identify the white points or areas close to white in the image, calculate the R, G, and B values ​​of these white points, and determine the gain coefficients that need to be adjusted. Then, apply the gain coefficients to adjust the R, G, and B channels of the entire image to achieve white balance. Then, observe whether the adjusted image colors are natural and balanced, and evaluate the intensity and stability of the ambient light. Specifically, if the image colors are natural and balanced, it means that the ambient light is relatively stable. If the colors are yellowish or bluish, etc., it means that there is a color temperature deviation in the ambient light.

[0073] In this embodiment, the specific operations of preprocessing adjustment include but are not limited to:

[0074] White balance adjustment: Based on the ambient light assessment, manually adjust the camera's white balance parameters to suit the current light conditions;

[0075] Exposure adjustment: adjust the camera exposure time according to the intensity of ambient light to obtain appropriate image brightness and contrast, or use multiple exposure technology to improve the camera's imaging quality for objects with different reflective characteristics;

[0076] Gain (the degree to which the camera amplifies the light signal) adjustment: When the ambient light is weak, increase the camera gain to improve the image brightness;

[0077] Filter selection: In bright light environments, use a polarizing filter to reduce the impact of glare and reflected light; in low light environments, use a brightening filter to improve the camera's light capture ability.

[0078] S2. Dynamic light source adjustment:

[0079] S21. Light source intensity control: dynamically adjust the intensity of the built-in or external light source of the 3D camera according to the intensity of the ambient light; the 3D camera is equipped with a light source controller, which can control the power or current of the light source through software or hardware interface to adjust the light source intensity, and the light source intensity control logic: when the ambient light is strong, reduce the light source intensity to avoid overexposure (overexposure will cause loss of image details and affect image quality), ensure that the image can capture enough details; when the ambient light is weak, increase the light source intensity to ensure sufficient lighting, improve the brightness and contrast of the image, and make the image clearer;

[0080] S22. Optimization of light source distribution: According to the changes in ambient light, optimize the distribution of light sources to improve lighting uniformity and image quality; specifically, optimize the light source distribution by adjusting the shape, angle and position of the light source, for example, use an adjustable LED light source or fiber optic light source to adjust the shape and distribution area of ​​the light source as needed, or use optical elements (such as lenses, reflectors, etc.) to change the distribution of the light source. These optical elements can focus or spread the light of the light source to the required area to achieve more uniform lighting, and the light source distribution optimization logic: In the case of direct sunlight or strong light source interference, use a more focused light source distribution to reduce photon noise and interference, and improve image clarity and contrast; in dark or shadow areas, increase the distribution area of ​​the light source to improve lighting uniformity and image quality, so as to improve lighting uniformity so that the dark areas in the image can also be adequately illuminated, thereby reducing shadows and dark corners in the image and improving the overall image quality;

[0081] S3, Image acquisition and real-time processing:

[0082] Use a 3D camera that has been pre-processed and adjusted for light source to capture images, ensure that the camera can stably capture the three-dimensional information and depth data of the object, and process the captured images in real time; real-time processing specifically includes:

[0083] Denoising: Reduce noise and improve image clarity through denoising algorithms such as mean filtering, median filtering, and Gaussian filtering;

[0084] Enhance contrast: Improve the contrast and visual effect of the image through contrast enhancement algorithms such as histogram equalization and contrast stretching;

[0085] Distortion correction: Through radial distortion correction, tangential distortion correction and other distortion correction algorithms, the barrel distortion, pincushion distortion and other distortions in the image are eliminated or reduced, making the image more realistic and accurate;

[0086] S4. Image quality assessment and optimization:

[0087] Perform quality assessment on the processed images, and further optimize and adjust the images based on the quality assessment results;

[0088] In this embodiment, image quality assessment: a series of index tests are performed on the processed image to measure whether its quality meets the requirements. The indexes include resolution, clarity, contrast, depth accuracy, etc., and the evaluation method of each index is as follows:

[0089] Resolution: Use a high-resolution test chart (such as the ISO 12233 test chart) to shoot, and use Imatest software to analyze the resolution and modulation transfer function (MTF) curve of the image;

[0090] Clarity: Also use high-resolution test cards for shooting, and use professional software to analyze the image clarity index;

[0091] Contrast: Use a high-contrast test card (such as a grayscale card) to shoot, and use software to analyze the image's contrast index;

[0092] Depth accuracy: Use 3D test images or scenes to shoot, and use depth measurement tools or software to analyze the depth accuracy indicators of the image;

[0093] In this embodiment, the optimization adjustment includes adjusting image enhancement parameters, repairing image defects, improving depth accuracy, etc. The image enhancement parameters include but are not limited to contrast, brightness, and sharpness. By adjusting the image enhancement parameters, the overall visual effect of the image can be improved;

[0094] Repair image defects: Use repair tools or algorithms to repair defects in images (such as noise, distortion, dark corners, etc.). Specifically, use a denoising algorithm to reduce noise in the image, use a distortion correction algorithm to eliminate or reduce image distortion, and use a brightness uniformity adjustment algorithm to improve dark corners in the image.

[0095] Improve depth accuracy: Use depth optimization algorithms to improve the depth accuracy of 3D images. Specifically, increase the resolution of the depth sensor or improve the depth measurement algorithm to improve depth accuracy. And further improve the accuracy of depth information by fusing image information from multiple perspectives.

[0096] S5. Feedback and iteration:

[0097] Establish a feedback mechanism to feed back the image quality assessment results and optimization adjustment schemes to the control system of the 3D camera. The control system will make iterative adjustments based on the feedback information to continuously improve the image quality and stability. At the same time, in actual applications, the performance and image quality of the 3D camera will be continuously monitored. Based on the monitoring results, the image quality control method will be continuously optimized and adjusted to adapt to different environmental conditions and application requirements;

[0098] In this embodiment, the process of establishing the feedback mechanism is as follows:

[0099] Clarify feedback goals and requirements: Establish the core goal of the feedback mechanism, which is to improve the image quality and stability of the 3D camera, and analyze the specific requirements for the image quality of the 3D camera under different ambient lighting conditions, such as clarity, contrast, color reproduction, etc.;

[0100] Design feedback process and interface: define the feedback content, that is, the information content that needs to be transmitted by the feedback mechanism, including image quality evaluation results, optimization adjustment plans, etc., design the feedback process, plan the transmission path of image quality evaluation results from the evaluation system to the 3D camera control system, and develop a communication interface between the 3D camera control system and the evaluation system according to the feedback content requirements to achieve seamless data transmission;

[0101] Implement feedback mechanism: Integrate the image quality assessment system into the overall architecture of the 3D camera, and deploy a control system in the 3D camera that can receive feedback and make iterative adjustments. Then test the feedback mechanism to ensure that it works stably in actual applications.

[0102] Establish a continuous monitoring and optimization system: According to the performance and image quality requirements of the 3D camera, set monitoring indicators, such as image clarity, contrast change rate, etc. In actual applications, the performance and image quality data of the 3D camera are collected in real time through the monitoring system, and the monitoring results are analyzed regularly to identify potential problems and improvement points, and continuously optimize and adjust the image quality control method to adapt to different environmental conditions and application requirements;

[0103] Iterative updates and continuous improvements: Collect user feedback on the 3D camera image quality, and regularly iterate and update the feedback mechanism and control system based on user feedback and monitoring results. Continue to pay attention to technological development trends and changes in user needs, and continuously improve and optimize the feedback mechanism.

[0104] like Figure 4 As shown, the image quality control system based on a 3D camera is applied to the image quality control method based on a 3D camera as described above, including:

[0105] Ambient lighting assessment module: used to assess the lighting conditions of the current shooting environment, including light intensity, light uniformity, etc.

[0106] Preprocessing module: used to preprocess and adjust the 3D camera according to the evaluation results;

[0107] Dynamic light source adjustment module: used to dynamically adjust the light source, including light source intensity control and light source distribution optimization;

[0108] Image acquisition module: used to acquire images using a 3D camera that has undergone preprocessing and light source adjustment;

[0109] Real-time processing module: used to process images collected by 3D cameras in real time;

[0110] Evaluation and optimization module: used to evaluate the quality of the processed image and further optimize and adjust the image according to the quality evaluation results;

[0111] Feedback iteration module: used to iteratively adjust the control system of the 3D camera according to feedback information, and continuously optimize and adjust the image quality control method.

[0112] The embodiments of the present invention are given for the purpose of illustration and description, and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

Claims

1. An image quality control method based on a 3D camera, characterized in that: The following steps are involved: S1. Ambient lighting assessment and preprocessing: Before using the 3D camera to collect images, the lighting conditions of the current environment are evaluated, and the 3D camera is pre-processed and adjusted according to the environmental lighting evaluation results; S2. Dynamic light source adjustment: S21, light source intensity control: dynamically adjust the intensity of the built-in or external light source of the 3D camera according to the intensity of the ambient light; S22. Light source distribution optimization: optimize the distribution of light sources according to changes in ambient light; S3, Image acquisition and real-time processing: Use a 3D camera that has been pre-processed and light source adjusted to capture images, and process the captured images in real time; S4. Image quality assessment and optimization: Perform quality assessment on the processed images, and further optimize and adjust the images based on the quality assessment results; S5. Feedback and iteration: A feedback mechanism is established to feed back the image quality assessment results and optimization adjustment plans to the control system of the 3D camera. The control system will make iterative adjustments based on the feedback information. At the same time, it will continuously monitor the performance and image quality of the 3D camera and continuously optimize and adjust the image quality control method.

2. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S1, the lighting condition of the environment is evaluated by measuring the intensity and stability of the ambient light using a light sensor or an algorithm, as follows: Light sensor evaluation: The light signal is converted into an electrical signal through the light sensor, and the electrical signal output by the light sensor is read using a data reading device and converted into a light intensity value; then, based on the read light intensity value, the light intensity of the current environment is evaluated, and the change of the light intensity value is observed to evaluate the stability of the light; Algorithm evaluation: specifically adopt gray world algorithm or automatic white balance algorithm; The evaluation process of the gray world algorithm is as follows: first, the average values ​​of the three color channels R, G, and B in the image are calculated, and then a gray value is calculated using the arithmetic average or weighted average of the three channel average values, and the gray value is used to adjust the brightness or color balance of the image, and then the images before and after the adjustment are compared to evaluate the intensity and stability of the ambient light; The evaluation process of the automatic white balance algorithm is as follows: first, the white points or areas close to white in the image are identified, the R, G, and B values ​​of these white points are calculated, and the gain coefficients that need to be adjusted are determined, and then the gain coefficients are applied to adjust the R, G, and B channels of the entire image, and then the color of the adjusted image is observed to be natural and balanced, and the intensity and stability of the ambient light are evaluated.

3. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S1, the specific operations of preprocessing and adjustment include: White balance adjustment: manually adjust the camera's white balance parameters based on ambient light assessment; Exposure adjustment: adjust the camera exposure time according to the intensity of ambient light to obtain appropriate image brightness and contrast, or use multiple exposure technology to improve the camera's imaging quality for objects with different reflective characteristics; Gain adjustment: When the ambient light is weak, increase the camera gain to improve the image brightness; Filter selection: In bright light environments, use a polarizing filter to reduce the impact of glare and reflected light; in low light environments, use a brightening filter to improve the camera's light capture ability.

4. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S21, the 3D camera is equipped with a light source controller, which can adjust the light source intensity by controlling the power or current of the light source through a software or hardware interface, and the light source intensity control logic is: when the ambient light is strong, the light source intensity is reduced to avoid overexposure; when the ambient light is weak, the light source intensity is increased to ensure sufficient lighting.

5. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S22, the light source distribution is optimized by adjusting the shape, angle and position of the light source, or by using optical elements to change the distribution of the light source, and the light source distribution optimization logic is: in the case of direct sunlight or interference from a strong light source, a more focused light source distribution is used to reduce photon noise and interference and improve image clarity and contrast; in darker or shadowed areas, the light source distribution area is increased to improve lighting uniformity and image quality.

6. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S3, the real-time processing specifically includes: Denoising: Reduce noise through denoising algorithms including mean filtering, median filtering, and Gaussian filtering; Enhance contrast: Improve the contrast and visual effect of the image through contrast enhancement algorithms including histogram equalization and contrast stretching; Distortion correction: Eliminate or reduce barrel distortion and pincushion distortion in the image through distortion correction algorithms including radial distortion correction and tangential distortion correction.

7. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S4, image quality assessment: a series of index tests are performed on the processed image to measure whether its quality meets the requirements. The indexes include resolution, clarity, contrast, depth accuracy, etc., and the evaluation method of each index is as follows: Resolution: Use a high-resolution test chart to shoot, and use Imatest software to analyze the image’s resolution and modulation transfer function curve; Clarity: Also use a high-resolution test card to shoot, and use software to analyze the image clarity index; Contrast: Use a high-contrast test card to shoot and use software to analyze the image's contrast index; Depth accuracy: Use a 3D test image or scene to shoot, and use depth measurement tools or software to analyze the depth accuracy indicators of the image.

8. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S4, the optimization and adjustment includes adjusting image enhancement parameters, repairing image defects, and improving depth accuracy. The image enhancement parameters include but are not limited to contrast, brightness, and sharpness; Repairing image defects: using a repair tool or algorithm to repair defects in the image; The improved depth accuracy: To improve the depth accuracy problem in 3D images, a depth optimization algorithm is used.

9. The image quality control method based on a 3D camera according to claim 1, characterized in that: In step S5, the process of establishing the feedback mechanism is as follows: Clarify feedback goals and requirements: Establish the core goals of the feedback mechanism and analyze the specific requirements for 3D camera image quality under different ambient lighting conditions; Design feedback process and interface: define the feedback content, that is, the information content that the feedback mechanism needs to transmit, design the feedback process, plan the transmission path of the image quality evaluation results from the evaluation system to the 3D camera control system, and develop a communication interface between the 3D camera control system and the evaluation system based on the feedback content requirements; Implement feedback mechanism: Integrate the image quality assessment system into the overall architecture of the 3D camera, and deploy a control system in the 3D camera that can receive feedback and make iterative adjustments. Then test the feedback mechanism to ensure that it works stably in actual applications. Establish a continuous monitoring and optimization system: Set monitoring indicators based on the performance and image quality requirements of the 3D camera. In actual applications, the performance and image quality data of the 3D camera are collected in real time through the monitoring system, and the monitoring results are analyzed regularly to identify potential problems and improvement points, and continuously optimize and adjust the image quality control method; Iterative updates and continuous improvements: Collect user feedback on the 3D camera image quality, and regularly iterate and update the feedback mechanism and control system based on user feedback and monitoring results. Continue to pay attention to technological development trends and changes in user needs, and continuously improve and optimize the feedback mechanism.

10. An image quality control system based on a 3D camera, applied to an image quality control method based on a 3D camera as claimed in any one of claims 1 to 9, characterized in that: include: Ambient lighting assessment module: used to assess the lighting conditions of the current shooting environment, including light intensity and light uniformity; Preprocessing module: used to preprocess and adjust the 3D camera according to the evaluation results; Dynamic light source adjustment module: used to dynamically adjust the light source, including light source intensity control and light source distribution optimization; Image acquisition module: used to acquire images using a 3D camera that has undergone preprocessing and light source adjustment; Real-time processing module: used to process images collected by 3D cameras in real time; Evaluation and optimization module: used to evaluate the quality of the processed image and further optimize and adjust the image according to the quality evaluation results; Feedback iteration module: used to iteratively adjust the control system of the 3D camera according to feedback information, and continuously optimize and adjust the image quality control method.

Images