System and method for intelligently adjusting and optimizing white balance of multi-view camera equipment

Abstract

The invention discloses a white balance intelligent adjustment and optimization system and method for multi-view camera equipment, and the system comprises a multi-view image collection unit which is used for capturing images of an environment where the multi-view camera equipment is located from different angles, and forming a multi-angle view; the ambient light detection module is used for evaluating the illumination condition of the environment where the multi-view camera is located and providing measurement data of illumination intensity, color temperature and direction; the ambient light color temperature analysis algorithm is used for calculating the color temperature value of the current environment; and the intelligent white balance adjusting unit is used for automatically adjusting the white balance setting of the multi-view camera according to a result calculated by the ambient light color temperature analysis algorithm. The light condition and the shooting environment of the multi-view camera equipment are detected in real time through the environment light detection module, and the white balance parameters of the multi-view camera are intelligently adjusted according to the factors, so that the white balance adjustment precision and efficiency of the multi-view camera equipment can be greatly improved, and more accurate and real images are obtained.

Description

Technical Field

[0001] The invention relates to a multi-camera, and in particular to a multi-camera equipment white balance intelligent adjustment and optimization system and method. Background Art

[0002] Currently, there are applications in many fields for collecting images from multiple different cameras at the same time, such as multi-cameras for security monitoring and multi-camera products for consumer electronics.

[0003] In existing multi-camera equipment, accurate white balance adjustment is crucial to obtain high-quality images. However, due to differences in hardware design, device selection, shooting angles, etc., traditional white balance adjustment methods often cannot meet the accuracy and efficiency requirements of multi-camera equipment for white balance adjustment. It is easy for the images captured by different cameras to have large color differences, and it is impossible to accurately and objectively display the color effects of the actual scene, which brings a lot of trouble to users.

[0004] The defects of the existing technology mainly include:

[0005] Low accuracy: The color temperature of the environment in which the multi-camera is located is detected by external sensors, which has accuracy deviation and cannot meet the detection and distinction of a wide dynamic range.

[0006] High cost: To match multiple cameras, the hardware sensor to collect the ambient color temperature hardware implementation requires additional costs.

[0007] System complexity: The solution of detection through external sensors requires multiple components to work together to produce an effect. The system complexity is high, and the number of related variables affecting system performance increases, which in turn increases the risk of abnormal system performance.

[0008] If the environment is detected and identified through respective pictures, different color displays will be shown in similar scenes, affecting the user's judgment of the actual environment scene. Summary of the invention

[0009] In view of the problems existing in the prior art, the present invention provides a white balance intelligent adjustment and optimization system and method for a multi-camera device. The system of the present invention can automatically detect factors such as the lighting conditions and shooting environment of the multi-camera device, and intelligently adjust the white balance parameters of multiple images according to these factors to obtain more realistic and accurate images.

[0010] In order to achieve the above object, the present invention provides a multi-camera device white balance intelligent adjustment and optimization system, comprising:

[0011] A multi-camera image acquisition unit, used to capture images of the environment where the multi-camera device is located from different angles to form a multi-angle view;

[0012] Ambient light detection module, used to evaluate the lighting conditions of the environment where the multi-camera is located, and provide measurement data of light intensity, color temperature and direction;

[0013] Ambient light color temperature analysis algorithm, used to process and analyze the image data captured by the multi-eye image acquisition unit and the measurement data of the light environment detection module, and calculate the color temperature value of the current environment;

[0014] Intelligent white balance adjustment unit, which automatically adjusts the white balance settings of multi-cameras according to the results calculated by the ambient light color temperature analysis algorithm;

[0015] The user interaction module provides a user interaction interface, allowing users to easily set and fine-tune white balance parameters, monitor shooting effects in real time, and optimize image white balance as needed.

[0016] Preferably, the ambient light detection module includes detection components for light source type, light intensity and direction;

[0017] The ambient light detection module also includes an ambient light intensity dynamic adjustment component for dynamically adjusting detection parameters according to changes in ambient light intensity.

[0018] Preferably, the ambient light color temperature analysis algorithm includes an image preprocessing module, a color space conversion module, a color temperature estimation module, a color histogram analysis module, a machine learning model module, an ambient light source recognition module and a color temperature calibration module;

[0019] The image preprocessing module is used to perform denoising, white balance pre-adjustment and contrast enhancement on the images collected by the multi-eye image acquisition unit;

[0020] A color space conversion module, used to convert image data from RGB color space to CIELAB or HSV color space;

[0021] A color temperature estimation module, used to estimate the color temperature based on the chromaticity of white or neutral gray areas in the image;

[0022] Color histogram analysis module, used to analyze the distribution of colors in an image;

[0023] A machine learning model module for predicting color temperature based on image features;

[0024] Ambient light source recognition module, used to identify the main light source type in the environment;

[0025] The color temperature calibration module is used to calibrate the estimated color temperature according to the identified light source type and environmental characteristics.

[0026] Preferably, the image preprocessing module further includes: an automatic exposure control module, an automatic white balance control module, and an edge enhancement algorithm;

[0027] Among them, the automatic exposure control module is used to dynamically adjust the exposure of the image to adapt to different lighting conditions;

[0028] Automatic white balance control module, used to preliminarily adjust the color temperature of the image;

[0029] Edge enhancement algorithms are used to improve the clarity of edges in images;

[0030] The color temperature estimation module includes: a chromaticity value mapping function and a color temperature estimation algorithm;

[0031] Wherein, the chromaticity value mapping function is used to convert the chromaticity value into the corresponding color temperature value;

[0032] Color temperature estimation algorithm, used to calculate the color temperature of multiple areas in the image;

[0033] The ambient light source recognition module is capable of recognizing at least two or more light source types and adjusting the color temperature estimation algorithm according to the light source type;

[0034] The color temperature calibration module adopts an adaptive algorithm to adjust the color temperature estimation value according to real-time feedback to adapt to the color temperature changes under different environmental conditions.

[0035] Preferably, the intelligent white balance adjustment unit further includes a gain control mechanism, which ensures that white objects present their true color by finely adjusting the gains of the three primary colors of red, green and blue.

[0036] Preferably, the user interaction interface also has a real-time feedback function, which intuitively displays the white balance adjustment effect of the system to the user, so that the user can monitor the shooting effect in real time and make corresponding adjustments as needed.

[0037] The present invention also provides an intelligent adjustment and optimization method for white balance of multi-camera equipment images, which is characterized by comprising the following steps:

[0038] Step a: using a multi-camera image acquisition unit to capture images of the environment where the multi-camera device is located from different angles to form a multi-angle view;

[0039] Step b: Evaluate the lighting conditions of the environment where the multi-camera is located through the ambient light detection module to obtain measurement data of light intensity, color temperature and direction;

[0040] Step c: using an ambient light color temperature analysis algorithm to process and analyze the image data captured by the multi-eye image acquisition unit and the measurement data provided by the ambient light detection module to calculate the color temperature value of the current environment;

[0041] Step d: According to the calculation result of the ambient light color temperature analysis algorithm, the white balance setting of the multi-camera is automatically adjusted by the intelligent white balance adjustment unit;

[0042] Step e: Provide user operation and parameter adjustment functions through the user interaction module.

[0043] Preferably, the ambient light color temperature analysis algorithm in step c comprises the following steps:

[0044] Step c01: preprocessing the images collected by the multi-eye image acquisition unit, including denoising, white balance pre-adjustment, and contrast enhancement, to improve the accuracy of subsequent analysis;

[0045] Step c02: converting the image data from the RGB color space to the CIELAB or HSV color space;

[0046] Step c03: estimating the color temperature in the image, including analyzing the chromaticity of white or neutral gray areas in the image;

[0047] Step c04: Analyze the color histogram of the image to determine the distribution of colors in the image;

[0048] Step c05: Predict color temperature using a machine learning model;

[0049] Step c06: Identify the main light source type in the environment to adapt to the color temperature characteristics under different light sources;

[0050] Step c07: Perform color temperature calibration according to the identified light source type and environmental characteristics, and automatically adjust the white balance setting of the multi-view camera based on the color temperature calibration result, by finely adjusting the gains of the three primary colors of red, green, and blue.

[0051] Preferably, the machine learning model module in step c05 adopts a well-trained model, support vector machine (SVM) or neural network to improve the accuracy of color temperature prediction.

[0052] The technical solution of the present invention has the following beneficial effects:

[0053] The present invention uses an ambient light detection module to detect the light conditions and shooting environment of a multi-camera device in real time, and intelligently adjusts the white balance parameters of the multi-camera according to these factors. This technical solution can greatly improve the white balance adjustment accuracy and efficiency of the multi-camera device, thereby obtaining a more accurate and realistic image.

[0054] The present invention can detect and analyze the lighting conditions and color temperature of a multi-camera device in real time through an ambient light detection module and an ambient light color temperature analysis algorithm, thereby achieving higher-precision white balance adjustment.

[0055] The present invention can improve the accuracy of color temperature estimation: the ambient light color temperature analysis algorithm adopts advanced image processing technology and machine learning models to improve the accuracy and efficiency of color temperature measurement and reduce the need for manual intervention; through comprehensive image preprocessing, color space conversion, color temperature estimation, color histogram analysis, machine learning model prediction, ambient light source identification and color temperature calibration, the present invention can more accurately estimate the ambient color temperature, thereby improving the accuracy of white balance adjustment.

[0056] The intelligent white balance adjustment unit of the present invention automatically adjusts the white balance settings according to the analysis results, ensuring that white objects can present their true colors under different lighting conditions, enhancing the authenticity and reliability of the image, and can instantly optimize the white balance parameters according to the dynamic changes of ambient light to adapt to the changes in color temperature under different environmental conditions.

[0057] The user interaction module of the present invention provides real-time feedback and intuitive parameter adjustment functions, so that users can conveniently perform personalized settings and optimizations according to the shooting effects monitored in real time.

[0058] The method of the present invention can adapt to the color temperature changes under different light sources and lighting conditions, automatically adjust the white balance setting, and ensure that high-quality images can be obtained in various environments. The images captured by the multi-camera device of the present invention at different angles can achieve color consistency through the method of the present invention, avoiding color deviation caused by inconsistent white balance, allowing the system to increase or decrease camera modules as needed, and improving the flexibility and scalability of the system.

[0059] The present invention effectively eliminates the color difference problem that may exist between different cameras by synchronously adjusting the white balance settings of multiple camera modules, thereby ensuring the overall consistency of the image; the present invention is suitable for processing an environment where multiple light sources are mixed, and can effectively identify and adapt to the color temperature characteristics of different light sources.

[0060] The present invention reduces the need for manual white balance adjustment through an automated intelligent adjustment process, improves operating efficiency, and reduces operating difficulty for users.

[0061] The present invention uses real-time feedback and self-adaptive adjustment mechanisms, and the method of the present invention can ensure long-term stable operation and improve the reliability of the system.

[0062] The method of the present invention is not only applicable to professional photography, but also to various application scenarios requiring high-quality image output, such as security monitoring, video conferencing, and live broadcasting.

[0063] The machine learning model integrated in the present invention is capable of continuous learning and optimization, and improves the intelligence level of white balance adjustment over time.

[0064] When performing image processing and analysis, the method of the present invention ensures the security and privacy of user data and does not involve the leakage of any sensitive information. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 Schematic diagram of the control module of the present invention. DETAILED DESCRIPTION

[0066] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments.

[0067] Reference Figure 1 The present invention provides a multi-camera device white balance intelligent adjustment and optimization system, comprising:

[0068] The multi-camera image acquisition unit is used to capture images of the multi-camera device environment and integrate multi-angle views. These images are then transmitted to the back-end processing system for further analysis and processing.

[0069] Ambient light detection module, used to evaluate the lighting conditions of the environment where the multi-camera is located, and provide measurement data of light intensity, color temperature and direction;

[0070] Ambient light color temperature analysis algorithm, used to process and analyze the image data captured by the multi-eye image acquisition unit and the measurement data of the light environment detection module, and calculate the color temperature value of the current environment;

[0071] Intelligent white balance adjustment unit, which automatically adjusts the white balance settings of multi-cameras according to the results calculated by the ambient light color temperature analysis algorithm;

[0072] The user interaction module is used for users to set and fine-tune white balance parameters, allowing users to easily set and fine-tune white balance parameters, monitor shooting effects in real time, and optimize image white balance as needed.

[0073] The present invention can improve the accuracy of white balance adjustment: the system can accurately calculate the color temperature value of the current environment by real-time evaluation of the lighting conditions of the environment in which the multi-camera is located, and adopts an advanced ambient light color temperature analysis algorithm, thereby significantly improving the accuracy of white balance adjustment. The present invention can enhance the adaptability of the system: the intelligent white balance adjustment unit can instantly optimize the white balance parameters according to the dynamically changing ambient light conditions, so that the system can adapt to various complex lighting environments and ensure image quality. The present invention can reduce costs and complexity: compared with the traditional white balance adjustment method that relies on external sensors, the present system reduces hardware requirements and costs, while simplifying the system structure and reducing system complexity. The present invention can enhance user experience: the user interaction module provides intuitive white balance parameter setting and fine-tuning functions, as well as the ability to provide real-time feedback on the system white balance adjustment effect, which enhances the user's operational convenience and satisfaction. The present invention can optimize image quality: through intelligent white balance adjustment, the system ensures the authenticity and accuracy of the color of the image captured under different lighting conditions, significantly optimizing the overall quality of the image.

[0074] The present invention can expand the scope of application: the system can be applied not only to the field of security monitoring, but also to multiple fields requiring high-quality images, such as consumer electronics, industrial detection, and medical imaging.

[0075] The present invention can improve the stability and reliability of the system: since the dependence on external sensors is reduced, the system can maintain stable white balance adjustment performance in various environments, thereby improving the reliability of the system.

[0076] The present invention can support personalized settings: users can adjust white balance parameters according to their own needs and preferences, and the system supports personalized settings to meet the specific needs of different users.

[0077] Further, the multi-eye image acquisition unit includes multiple camera modules and an image synchronization module, wherein each camera module independently captures images at different angles; the image synchronization module is used to synchronize image data captured by different camera modules. The camera modules of this embodiment have independence: each camera module is designed to operate independently and can capture scene images from their own angles. This independence allows the system to perform a full range of visual analysis of complex scenes and capture more details and information. The image synchronization module of this embodiment has a coordination function: the image synchronization module is responsible for coordinating the work of each camera module to ensure the temporal consistency of all captured image data. The image synchronization module synchronizes image data through a high-precision timestamp or synchronization signal to avoid errors introduced by timing differences. The image synchronization module of this embodiment also includes a data fusion algorithm that can integrate image data from multiple angles into a single, comprehensive view or multiple useful views. This fusion not only improves the coverage of the scene, but also enhances the depth and details of the image data, providing richer information for white balance analysis; in order to achieve precise synchronization, the image synchronization module may include or access a high-precision clock management system to ensure the accuracy of synchronization. The clock management system can be an independent hardware device or a high-precision time source integrated in the system. The image synchronization module is designed with the fault tolerance of the system in mind. Even if some camera modules fail, the system can continue to operate. Through redundant design, the image synchronization module can automatically switch to the backup camera module to ensure data continuity and stability. The image synchronization module in this embodiment works closely with the intelligent white balance adjustment unit. The precise synchronization data provided by the synchronization module is a prerequisite for the accurate execution of the white balance adjustment algorithm. This collaborative work ensures that the white balance adjustment can be performed based on the latest and most accurate image data.

[0078] Furthermore, the ambient light detection module includes detection components for light source type, light intensity and direction; accurate measurement of these parameters enables the system to evaluate the intensity and color temperature of the ambient light, providing necessary data support for subsequent white balance adjustment. The ambient light detection module also includes an ambient light intensity dynamic adjustment component, which is used to dynamically adjust the detection parameters according to changes in ambient light intensity. The light source type detection component in this embodiment is used to identify the type of light source in the environment, such as natural light, incandescent lamp, fluorescent lamp or LED lamp, etc. By analyzing the spectral characteristics of light, the light source type detection component can provide key information for white balance adjustment. The light intensity detection component is responsible for measuring the brightness level of the ambient light and providing the necessary light intensity data for white balance adjustment. The light intensity detection component uses a highly sensitive light sensor that can cover a wide range from low illumination to high illumination. The light direction detection component is used to determine the orientation and angle of the light source, which is crucial to understanding how light is distributed in the scene. By accurately measuring the light direction, the system can better simulate and adjust the white balance in a natural light environment. Ambient light intensity dynamic adjustment component: According to the real-time detected changes in ambient light intensity, the detection parameters of the ambient light detection module are dynamically adjusted. The dynamic adjustment mechanism ensures that the system can maintain high-accuracy white balance adjustment under different lighting conditions. The ambient light intensity dynamic adjustment component uses an adaptive algorithm to adjust the sensitivity or measurement range of the sensor in real time according to the changes in light intensity. This adaptive capability enables the system to quickly respond to sudden changes in lighting conditions, such as walking from indoors to outdoors. The data collected by the ambient light detection module needs to be fused and processed to provide consistent and accurate lighting condition information. The data fusion algorithm of the image synchronization module comprehensively considers the information of light source type, light intensity and direction to provide comprehensive data support for white balance adjustment. The ambient light detection module works closely with the intelligent white balance adjustment unit to ensure that the white balance adjustment is based on the latest and most accurate ambient light detection data. This collaborative working mechanism enables the system to achieve fast and accurate white balance adjustment.

[0079] Furthermore, the ambient light color temperature analysis algorithm includes an image preprocessing module, a color space conversion module, a color temperature estimation module, a color histogram analysis module, a machine learning model module, an ambient light source identification module and a color temperature calibration module; wherein the image preprocessing module is used to perform denoising, white balance pre-adjustment and contrast enhancement on the collected image; these processing steps improve the image quality and provide more accurate image data for subsequent color analysis and color temperature estimation. The color space conversion module is used to convert the image data from the RGB color space to the CIELAB or HSV (hue, saturation, brightness) color space; this conversion makes the mathematical processing of color more intuitive and effective, and facilitates color temperature estimation and color histogram analysis. The color temperature estimation module is used to estimate the color temperature based on the chromaticity of the white or neutral gray area in the image, providing basic data for white balance adjustment. The color histogram analysis module is used to analyze the distribution of colors in the image, especially the proportion of red and blue components; the color histogram provides statistical information on the image color distribution, which helps to further calibrate the color temperature. The machine learning model module is used to predict color temperature based on image features; this module can learn and adapt to different images and lighting conditions to improve the accuracy and robustness of color temperature prediction. The ambient light source recognition module is used to identify the main light source types in the environment, such as daylight, incandescent lamps, fluorescent lamps, etc. By identifying the light source type, the system can apply the corresponding color temperature characteristics to optimize the color temperature estimation results. The color temperature calibration module is used to calibrate the estimated color temperature based on the identified light source type and environmental characteristics. The calibration process takes into account the color temperature characteristics and environmental factors of different light sources to ensure the accuracy of white balance adjustment.

[0080] Further, the image preprocessing module further includes: an automatic exposure control module, an automatic white balance control module, and an edge enhancement algorithm; wherein the automatic exposure control module is used to dynamically adjust the exposure of the image to adapt to different lighting conditions, and adjust the exposure parameters of the image in real time to ensure that the image can maintain optimal brightness and details under different lighting conditions; the automatic white balance control module is used to preliminarily adjust the color temperature of the image to reduce the need for manual adjustment and provide a basis for subsequent accurate color temperature estimation; the edge enhancement algorithm is used to improve the clarity of the edge in the image, and by enhancing the contrast of the edge in the image, the clarity of the image is improved, which helps the subsequent modules to more accurately identify objects and contours in the image. In this embodiment, the edge enhancement algorithm works in conjunction with the automatic exposure and white balance control modules to ensure that the color and brightness of the image are balanced while enhancing the edge. The user can adjust the parameters of the image preprocessing module through the user interaction module to adapt to specific shooting requirements or personal preferences. The image preprocessing module can integrate a scene recognition function to automatically select the most appropriate preprocessing parameters according to the characteristics of different scenes. The preprocessing module ensures the consistency of the image data and provides high-quality input for the entire system, thereby improving the accuracy of color temperature analysis.

[0081] Further, the color temperature estimation module includes: a chromaticity value mapping function and a color temperature estimation algorithm; wherein the chromaticity value mapping function is used to convert the chromaticity value into the corresponding color temperature value; responsible for converting the color information in the image into the chromaticity value, and then mapping it to the specific color temperature value. By analyzing the white or neutral gray area in the image sample, the chromaticity value mapping function can quantify the chromaticity characteristics of the image and correspond it to the known color temperature value. The color temperature estimation algorithm is used to calculate the color temperature of multiple areas in the image; the algorithm uses the output of the chromaticity value mapping function to calculate the color temperature of multiple areas in the image to obtain a comprehensive color temperature distribution. The color temperature estimation algorithm comprehensively considers the chromaticity values ​​of different areas in the image to reduce the influence of local outliers and improve the accuracy of color temperature estimation. Further, the design of the color temperature estimation module also considers the following aspects: multi-region analysis: the color temperature estimation algorithm does not only analyze a single area of ​​the image, but segments the image and analyzes multiple areas to obtain a more accurate average color temperature. Adaptive threshold determination: the algorithm can adaptively determine the color threshold used for color temperature calculation to distinguish between white, neutral gray and other color areas in the image. Consistency of color space: Before chromaticity value mapping, ensure that the image data is in a unified color space to maintain the consistency and accuracy of color temperature estimation. Adaptability to lighting conditions: The color temperature estimation algorithm takes into account the color performance under different lighting conditions and can adapt to strong light, weak light or mixed light environments. Real-time performance: The algorithm optimizes the calculation process to achieve fast color temperature estimation and meet the needs of real-time processing. Collaboration with ambient light source recognition module: The color temperature estimation module works closely with the ambient light source recognition module to adjust the parameters of the color temperature estimation algorithm according to the identified light source type. User interaction: Users can adjust certain parameters of the color temperature estimation module through the user interaction module to adapt to specific shooting needs or personal preferences. The ambient light source recognition module can identify at least two or more light source types and adjust the color temperature estimation algorithm according to the light source type; the module has a strong recognition ability and can detect and distinguish at least two or more light source types, such as daylight, incandescent lamps, fluorescent lamps and LED lamps. By analyzing the spectral characteristics of the light source or specific color signs in the image, the module can accurately identify the light source type and use its information for subsequent color temperature estimation. The color temperature calibration module adopts an adaptive algorithm to adjust the color temperature estimation value according to real-time feedback to adapt to the color temperature changes under different environmental conditions. The color temperature calibration module improves the accuracy of color temperature estimation through continuous learning and optimization to ensure accurate white balance adjustment under different lighting conditions. The design of the ambient light source recognition module and the color temperature calibration module also takes into account the following aspects: Adaptive learning mechanism: The color temperature calibration module has the ability of self-learning and adjustment, and can continuously optimize the color temperature estimation algorithm based on historical data and user feedback. The ambient light source recognition module and the color temperature calibration module are closely integrated and work together with other system modules (such as the image preprocessing module and the color temperature estimation module) to form an efficient overall system.

[0082] Furthermore, the intelligent white balance adjustment unit also includes a gain control mechanism, which ensures that white objects present their true colors by finely adjusting the gains of the three primary colors of red, green and blue. By precisely controlling the gains of each primary color, the module can eliminate color deviation and ensure that white objects maintain their natural colors under different lighting conditions. The gain control mechanism provides fine adjustment capabilities, allowing the system to make small step adjustments to achieve a smoother and more natural white balance transition. This fine adjustment helps to avoid color jumps and ensure the continuity and visual comfort of the image during the adjustment process; the gain control mechanism has real-time response capabilities and can quickly adapt to dynamic changes in lighting conditions, such as the switching of indoor lighting or the changes in brightness and darkness of outdoor lighting. This unit ensures that white objects can present their true colors under various lighting conditions. In addition, the intelligent white balance adjustment unit has real-time response capabilities and can instantly optimize white balance parameters according to dynamic changes in ambient lighting to maintain the color accuracy and authenticity of the image. The intelligent white balance adjustment unit can identify different shooting scenes and automatically adjust the gain control parameters according to the characteristics of the scene to achieve the best white balance effect. Multi-zone white balance: When different areas of the image may have different color temperature conditions, the gain control mechanism can adjust these areas separately to achieve a harmonious unity of the overall image. The gain control mechanism works in conjunction with the image preprocessing module (including automatic exposure and automatic white balance control) to ensure effective white balance adjustment in the early stages of image capture. The intelligent white balance adjustment unit is designed with a feedback loop to self-optimize based on the effect of the intelligent white balance adjustment, continuously improving the accuracy and efficiency of white balance adjustment. When designing the gain control mechanism, special consideration was given to system stability to ensure reliable white balance adjustment during long-term operation or under extreme conditions.

[0083] Furthermore, the user interaction interface also has a real-time feedback function, which can intuitively display the white balance adjustment effect of the system to the user, so that the user can monitor the shooting effect in real time and make corresponding adjustments as needed. The user interaction module is a key bridge connecting the user and the system, providing an intuitive and easy-to-use control method, and enabling the user to monitor and adjust the shooting effect through the real-time feedback function. The user interaction module has a real-time feedback function, which can instantly display the white balance adjustment effect of the system to the user; the user can intuitively see the comparison before and after the white balance adjustment, as well as the real-time image effect under the current settings.

[0084] The user interaction module provides real-time image preview, allowing users to monitor the current shooting effect, including color accuracy and overall image quality. Users can judge whether further adjustment of white balance settings is needed based on the real-time preview image effect. The user interaction module provides intuitive control options, allowing users to adjust white balance parameters such as gain control, color temperature offset, etc. as needed.

[0085] The design of the user interaction module in this embodiment also takes into account the following aspects: users can set the layout of the interface and the type of information displayed, such as color temperature value, gain level, etc., according to their personal preferences. The interface provides a variety of preset white balance modes, suitable for different shooting environments, such as daylight, cloudy days, indoors, etc. Users can switch between automatic white balance adjustment and manual adjustment as needed. The interface records the user's adjustment history, allowing users to trace back and compare the effects under different settings. The interface integrates auxiliary tools, such as color analyzer, exposure meter, etc., to help users better understand the current image status. Online help and user guidance are provided to help users understand how to use the interface and adjust the white balance. The user interaction module design takes into account multi-platform use, providing a good user experience whether on professional monitors, laptops or mobile devices. Users can provide feedback through the interface, and the system is optimized based on the user's feedback to improve the intelligence and accuracy of white balance adjustment. The interface uses data visualization technology to display complex white balance data in a graphical way to improve the readability of information.

[0086] The present invention also provides an intelligent adjustment and optimization method for white balance of multi-camera equipment images, comprising the following steps:

[0087] Step a: using a multi-camera image acquisition unit to capture images of the environment where the multi-camera device is located from different angles and integrate the environment images from multiple angles;

[0088] Multi-eye image acquisition units are used to synchronously capture environmental images from different angles to obtain comprehensive lighting and color information. These images are integrated to form a comprehensive view, providing a data basis for subsequent lighting condition evaluation and color temperature analysis.

[0089] Step b: Use the ambient light detection module to evaluate the lighting conditions of the environment in which the multi-camera is located, including the type of light source, light intensity and direction; the evaluation results provide key environmental parameters for intelligent white balance adjustment to ensure that the white balance adjustment can adapt to actual lighting conditions.

[0090] Step c: The ambient light color temperature analysis algorithm is used to process and analyze the image data captured by the multi-camera image acquisition unit and the measurement data provided by the ambient light detection module to calculate the color temperature value of the current environment; the algorithm can provide a more accurate ambient color temperature value by analyzing the image data and the light measurement data, thereby improving the accuracy of the white balance adjustment. The automated algorithm reduces the need for manual intervention, saves time and reduces the possibility of operating errors. Combining image data and light measurement data, the algorithm can more comprehensively understand the ambient light conditions and improve the reliability of color temperature estimation. The algorithm can adapt to different lighting environments and condition changes to ensure good white balance adjustment in various environments. The ambient light color temperature analysis algorithm is designed to process data quickly and realize real-time or near real-time color temperature calculation to meet the needs of rapid response. Accurate color temperature calculation helps to optimize the overall quality of the image, especially in a multi-camera system, ensuring color consistency and authenticity. The use of advanced image processing and analysis techniques, including machine learning models, ensures the advancement and accuracy of the algorithm in color temperature estimation. By providing accurate color temperature measurement and adjustment, the algorithm enhances the user experience when using multi-camera equipment. Applicable to various scenarios: The flexibility and adaptability of the algorithm make it applicable to various shooting scenarios from indoor to outdoor, from daylight to artificial light. The ambient light color temperature analysis algorithm is used to calculate the color temperature value of the current environment based on the lighting condition data obtained in step b. The ambient light color temperature analysis includes sub-steps such as image preprocessing, color space conversion, and color temperature estimation to ensure the accuracy of the color temperature value.

[0091] Step d: Based on the calculation result of the ambient light color temperature analysis algorithm, the intelligent white balance adjustment unit automatically adjusts the white balance setting; the adjustment includes gain control, color temperature compensation, etc. to ensure the color authenticity of white objects under different lighting conditions.

[0092] Step e provides user operation and parameter adjustment functions through the user interaction module. The user interaction module provides an intuitive operation interface, allowing users to perform manual operations and parameter adjustments. The real-time feedback function enables users to monitor the shooting effect and make corresponding adjustments as needed to achieve the best image quality.

[0093] Furthermore, the ambient light color temperature analysis algorithm in step c comprises the following steps:

[0094] Step c01: Preprocess the captured image, including denoising, white balance pre-adjustment, and contrast enhancement, to improve the accuracy of subsequent analysis; denoise the captured image to reduce image noise and improve image quality. Perform white balance pre-adjustment to perform preliminary color temperature correction on the image to provide a basis for subsequent color temperature estimation. Contrast enhancement to improve the contrast between light and dark areas in the image, making color edges clearer.

[0095] Step c02: Convert the image data from the RGB color space to the CIELAB or HSV color space; these color spaces are more suitable for color analysis and color temperature estimation.

[0096] Step c03: Estimating the color temperature in the image, including analyzing the chromaticity of white or neutral gray areas in the image; the chromaticity of these areas is directly related to the ambient color temperature.

[0097] Step c04: Analyze the color histogram of the image to determine the distribution of colors in the image and provide statistical data support for color temperature estimation.

[0098] Step c05: Use a machine learning model to predict color temperature; predict color temperature based on image features to improve the accuracy of color temperature estimation. The machine learning model module uses a trained model, support vector machine (SVM) or neural network to improve the accuracy of color temperature prediction.

[0099] Step c06: Identify the main light source type in the environment to adapt to the color temperature characteristics under different light sources; ， Such as natural light, incandescent lamps, etc., because different light sources have different color temperature characteristics.

[0100] Step c07: Perform color temperature calibration according to the identified light source type and environmental characteristics, and automatically adjust the white balance setting of the multi-view camera based on the color temperature calibration result, by finely adjusting the gains of the three primary colors of red, green, and blue.

[0101] As can be seen from the above embodiments, the present invention detects the light conditions and shooting environment of the multi-camera device in real time through the ambient light detection module, and intelligently adjusts the white balance parameters of the multi-camera according to these factors. This technical solution can greatly improve the white balance adjustment accuracy and efficiency of the multi-camera device, thereby obtaining a more accurate and realistic image.

[0102] The present invention can detect and analyze the lighting conditions and color temperature of a multi-camera device in real time through an ambient light detection module and an ambient light color temperature analysis algorithm, thereby achieving higher-precision white balance adjustment.

[0103] The present invention can improve the accuracy of color temperature estimation: the ambient light color temperature analysis algorithm adopts advanced image processing technology and machine learning models to improve the accuracy and efficiency of color temperature measurement and reduce the need for manual intervention; through comprehensive image preprocessing, color space conversion, color temperature estimation, color histogram analysis, machine learning model prediction, ambient light source identification and color temperature calibration, the present invention can more accurately estimate the ambient color temperature, thereby improving the accuracy of white balance adjustment.

[0104] The intelligent white balance adjustment unit of the present invention automatically adjusts the white balance settings according to the analysis results, ensuring that white objects can present their true colors under different lighting conditions, enhancing the authenticity and reliability of the image, and can instantly optimize the white balance parameters according to the dynamic changes of ambient light to adapt to the changes in color temperature under different environmental conditions.

[0105] The user interaction module of the present invention provides real-time feedback and intuitive parameter adjustment functions, so that users can conveniently perform personalized settings and optimizations according to the shooting effects monitored in real time.

[0106] The method of the present invention can adapt to the color temperature changes under different light sources and lighting conditions, automatically adjust the white balance setting, and ensure that high-quality images can be obtained in various environments. The images captured by the multi-camera device of the present invention at different angles can achieve color consistency through the method of the present invention, avoiding color deviation caused by inconsistent white balance, allowing the system to increase or decrease camera modules as needed, and improving the flexibility and scalability of the system.

[0107] The present invention effectively eliminates the color difference problem that may exist between different cameras by synchronously adjusting the white balance settings of multiple camera modules, thereby ensuring the overall consistency of the image; the present invention is suitable for processing an environment where multiple light sources are mixed, and can effectively identify and adapt to the color temperature characteristics of different light sources.

[0108] The present invention reduces the need for manual white balance adjustment through an automated intelligent adjustment process, improves operating efficiency, and reduces operating difficulty for users.

[0109] The present invention uses real-time feedback and self-adaptive adjustment mechanisms, and the method of the present invention can ensure long-term stable operation and improve the reliability of the system.

[0110] The method of the present invention is not only applicable to professional photography, but also to various application scenarios requiring high-quality image output, such as security monitoring, video conferencing, and live broadcasting.

[0111] The machine learning model integrated in the present invention is capable of continuous learning and optimization, and improves the intelligence level of white balance adjustment over time.

[0112] When performing image processing and analysis, the method of the present invention ensures the security and privacy of user data and does not involve the leakage of any sensitive information.

[0113] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A multi-camera white balance intelligent adjustment and optimization system, characterized in that: include: A multi-camera image acquisition unit, used to capture images of the environment where the multi-camera device is located from different angles to form a multi-angle view; Ambient light detection module, used to evaluate the lighting conditions of the environment where the multi-camera is located, and provide measurement data of light intensity, color temperature and direction; Ambient light color temperature analysis algorithm, used to process and analyze the image data captured by the multi-eye image acquisition unit and the measurement data of the light environment detection module, and calculate the color temperature value of the current environment; Intelligent white balance adjustment unit, which automatically adjusts the white balance settings of multi-cameras according to the results calculated by the ambient light color temperature analysis algorithm; The user interaction module provides a user interaction interface, allowing users to easily set and fine-tune white balance parameters, monitor shooting effects in real time, and optimize image white balance as needed.

2. The multi-camera device white balance intelligent adjustment and optimization system according to claim 1, characterized in that: The multi-eye image acquisition unit includes a plurality of camera modules and an image synchronization module, wherein each camera module independently captures images at different angles, and the image synchronization module is used to synchronize image data captured by different camera modules.

3. The multi-camera device white balance intelligent adjustment and optimization system according to claim 1, characterized in that: The ambient light detection module includes detection components for light source type, light intensity and direction; The ambient light detection module also includes an ambient light intensity dynamic adjustment component for dynamically adjusting detection parameters according to changes in ambient light intensity.

4. The multi-camera device white balance intelligent adjustment and optimization system according to claim 1, characterized in that: The ambient light color temperature analysis algorithm includes an image preprocessing module, a color space conversion module, a color temperature estimation module, a color histogram analysis module, a machine learning model module, an ambient light source recognition module and a color temperature calibration module; The image preprocessing module is used to perform denoising, white balance pre-adjustment and contrast enhancement on the images collected by the multi-eye image acquisition unit; A color space conversion module, used to convert image data from RGB color space to CIELAB or HSV color space; A color temperature estimation module, used to estimate the color temperature based on the chromaticity of white or neutral gray areas in the image; Color histogram analysis module, used to analyze the distribution of colors in an image; A machine learning model module for predicting color temperature based on image features; Ambient light source recognition module, used to identify the main light source type in the environment; The color temperature calibration module is used to calibrate the estimated color temperature according to the identified light source type and environmental characteristics.

5. The multi-camera device white balance intelligent adjustment and optimization system according to claim 4, characterized in that: The image preprocessing module further includes: an automatic exposure control module, an automatic white balance control module, and an edge enhancement algorithm; Among them, the automatic exposure control module is used to dynamically adjust the exposure of the image to adapt to different lighting conditions; Automatic white balance control module, used to preliminarily adjust the color temperature of the image; Edge enhancement algorithms are used to improve the clarity of edges in images; The color temperature estimation module includes: a chromaticity value mapping function and a color temperature estimation algorithm; Wherein, the chromaticity value mapping function is used to convert the chromaticity value into the corresponding color temperature value; Color temperature estimation algorithm, used to calculate the color temperature of multiple areas in the image; The ambient light source recognition module is capable of recognizing at least two or more light source types and adjusting the color temperature estimation algorithm according to the light source type; The color temperature calibration module adopts an adaptive algorithm to adjust the color temperature estimation value according to real-time feedback to adapt to the color temperature changes under different environmental conditions.

6. The multi-camera device white balance intelligent adjustment and optimization system according to claim 1, characterized in that: The intelligent white balance adjustment unit also includes a gain control mechanism, which ensures that white objects present their true color by finely adjusting the gains of the three primary colors of red, green and blue.

7. The multi-camera device white balance intelligent adjustment and optimization system according to claim 1, characterized in that: The user interaction interface also has a real-time feedback function, which intuitively displays the white balance adjustment effect of the system to the user, so that the user can monitor the shooting effect in real time and make corresponding adjustments as needed.

8. A method for intelligently adjusting and optimizing the white balance of images of a multi-camera device, characterized in that The following steps are involved: Step a: using a multi-camera image acquisition unit to capture images of the environment where the multi-camera device is located from different angles to form a multi-angle view; Step b: Evaluate the lighting conditions of the environment where the multi-camera is located through the ambient light detection module to obtain measurement data of light intensity, color temperature and direction; Step c: using an ambient light color temperature analysis algorithm to process and analyze the image data captured by the multi-eye image acquisition unit and the measurement data provided by the ambient light detection module to calculate the color temperature value of the current environment; Step d: According to the calculation result of the ambient light color temperature analysis algorithm, the white balance setting of the multi-camera is automatically adjusted by the intelligent white balance adjustment unit; Step e: Provide user operation and parameter adjustment functions through the user interaction module.

9. The method for intelligently adjusting and optimizing the white balance of images of a multi-camera device according to claim 8, characterized in that: The ambient light color temperature analysis algorithm in step c comprises the following steps: Step c01: preprocessing the images collected by the multi-eye image acquisition unit, including denoising, white balance pre-adjustment, and contrast enhancement, to improve the accuracy of subsequent analysis; Step c02: converting the image data from the RGB color space to the CIELAB or HSV color space; Step c03: estimating the color temperature in the image, including analyzing the chromaticity of white or neutral gray areas in the image; Step c04: Analyze the color histogram of the image to determine the distribution of colors in the image; Step c05: Predict color temperature using a machine learning model; Step c06: Identify the main light source type in the environment to adapt to the color temperature characteristics under different light sources; Step c07: Perform color temperature calibration according to the identified light source type and environmental characteristics, and automatically adjust the white balance setting of the multi-view camera based on the color temperature calibration result, by finely adjusting the gains of the three primary colors of red, green, and blue.

10. The method for intelligently adjusting and optimizing the white balance of images of a multi-camera device according to claim 9, characterized in that: The machine learning model module in step c05 uses a well-trained model, support vector machine or neural network to improve the accuracy of color temperature prediction.

Images