4014 results about "Lightness" patented technology

The invention relates to the technical field of defect detection, in particular to a special equipment defect automatic identification method and system, and the method comprises the following steps: marking a continuous path based on an image gray scale gradient and adjacent differences, identifying the pixel connection intensity to obtain a contour image layer, extracting continuous pixels, analyzing gray scale and gradient features, and expanding a texture direction to generate a defect image block. And marking and connecting the small regions to obtain a closed layer, analyzing texture and edge differences, matching classification tags, and clustering and coding to generate a defect identification tag set. According to the method, boundary structure recognition is enhanced through gray gradient and direction continuity analysis, a texture aggregation area is expanded in combination with gray consistency and edge direction stability, brightness abrupt change points are removed, contour extraction precision is improved, micro crack continuity is recovered, and pseudo defects are eliminated; and multi-dimensional image attributes are fused to identify key region feature differences, so that the classification precision and the spatial mapping consistency are improved, and efficient and accurate defect identification and stable classification are realized.

The invention discloses a low-illumination image enhancement method based on a Retinex theory, and belongs to the field of low-illumination image enhancement. According to the method, on the basis of the Retinex theory, three aspects of innovations are developed: a double-branch decomposition network DecomNet is established, and precise decoupling of illumination and reflection components is realized; a diffusion model is introduced to denoise reflection components, and noise suppression and detail retention are both considered by means of a self-constraint consistency loss function; reLumenNet is constructed, an LIT module and a CBAM mechanism are fused, and illumination is regulated and controlled in a self-adaptive mode. By means of a series of innovative designs, the low-illumination image enhancement effect is greatly improved, and the problems of brightness distortion, noise interference, detail missing and the like are effectively solved. The method has high practical value in the scenes of night monitoring, automatic driving and the like, and a novel low-illumination image enhancement method is provided on the technical level.

The invention relates to the technical field of display control, in particular to a display self-monitoring method and system and a display, and the method comprises the following steps: collecting light intensity data, comparing and classifying ambient light as low light, strong light or reflected light with a preset standard, judging whether a real-time color temperature and a standard color temperature difference value exceed a threshold value, if yes, adjusting the color temperature and the brightness, and if not, adjusting the brightness; pixel RGB channel proportions are extracted frame by frame, a color gamut distribution diagram is generated, restoration instruction time features are recorded, the color temperature adjustment trend is counted, and a backlight gradient compensation mode is generated. In the invention, the light intensity around the display is monitored in real time, the light intensity is compared with the preset illumination condition, and the ambient light condition is automatically classified, so that the display can adjust the color temperature and the brightness according to different illumination environments, and the backlight drive of the display is adjusted in time by analyzing the coverage areas of the red, green and blue channels in the display frame frame by frame; the adaptive capacity and the long-term stability of the display under variable illumination conditions are improved, and more optimized visual experience is provided for users.

The invention provides a self-adaptive nonlinear image enhancement method and system for a low-light scene of a mobile terminal, and relates to the technical field of image enhancement, and the method comprises the steps: carrying out the image preprocessing and noise reduction, and carrying out the graying and noise suppression of an input color image through a local variance self-adaptive algorithm; adaptive down-sampling is carried out, and the down-sampling proportion is dynamically adjusted according to the image resolution and the content complexity, so that the processing efficiency is improved; brightness adaptive enhancement is carried out, and the overall brightness of the image is rapidly improved by adopting an Otsu method and a lookup table; contrast nonlinear enhancement: enhancing image details and contrast in combination with a Laplace operator and local mean adjustment; and color restoration: restoring the resolution through bilinear interpolation and performing weighted fusion to realize natural color reconstruction. And finally, a high-quality image of which the brightness, the contrast ratio and the color are remarkably improved is output. According to the invention, the recognition accuracy and processing efficiency of the low-illumination image are improved.

The invention relates to the technical field of image recognition, in particular to an image monitoring system for traditional village heritage risk assessment, and the system comprises a heritage image collection module which is used for obtaining an image data stream of a target traditional village building surface, carrying out the geometric correction of original heritage image data, carrying out the image brightness equalization processing, and obtaining an image data stream of the target traditional village building surface; and establishing a calibrated image set. According to the method, image distortion and local overexposure caused by shooting angle difference or uneven illumination on the surface of a traditional village building are eliminated through geometric correction and brightness equalization processing, and the input data quality of subsequent feature analysis is improved. The consistency degree of crack textures in a neighborhood range is quantified based on gray gradient direction field data, the gray contrast of continuous crack edges is enhanced in combination with a dynamic threshold adjustment mechanism, non-structural texture interference is inhibited, and separability of micro cracks and background materials is enhanced.

The invention discloses a waste plastic classification method and system based on visual identification, and particularly relates to the technical field of plastic classification. Reflection suppression is realized through an industrial camera equipped with a polarization filter and a multi-angle cross polarization light source, and the structure and color characteristics of a shielded area are effectively restored by combining brightness equalization, reflection area detection and image restoration technologies; and then semantic segmentation and target classification are completed by using an improved deep neural network model, a control signal is generated based on an identification result, and an execution mechanism is driven to realize accurate sorting of multiple types of plastics, so that the identification robustness and the sorting efficiency of the system under a complex illumination condition are improved.

The invention discloses a panoramic image real-time splicing algorithm and system based on multi-sensor fusion, and particularly relates to the technical field of panoramic image real-time splicing, and the algorithm comprises the following steps: constructing a structured fusion sequence based on multi-source images, postures and position information, optimizing a matching effect through high-density feature extraction and repeated texture recognition, and obtaining a multi-source image fusion sequence; a dynamic foreground and a static background are distinguished by using sparse optical flow so as to improve the visual angle estimation precision, pose fusion optimization is realized in combination with a multi-mode residual error, and the continuity and stability of a spliced image are improved through edge smoothing, brightness tuning and color correction; according to the method, the structured fusion sequence is constructed through multi-source data alignment, so that the data synchronization and splicing stability is improved; identifying repeated regions based on texture direction features, and optimizing feature matching accuracy; and through edge smoothing, brightness harmonizing and color consistency processing, the visual coherence and output quality of the panoramic image are enhanced.

The invention discloses a complex material-oriented global full-frequency illumination neural rendering method and system, and belongs to the technical field of computer graphics, and the method comprises the steps: querying and extracting a primary frequency feature and a secondary frequency feature in a neural feature field according to the primary geometric buffer and the reflection geometric buffer of a rendering pixel; performing weighted combination on the primary frequency features and the secondary frequency features through a double-frequency fusion module to form full-frequency fusion features; inputting the full-frequency fusion feature and the initial geometric buffer into a decoder to obtain a pixel radiation brightness value; and optimizing the network by adopting a double-stage training strategy of low-frequency data and multi-frequency data, and then using the optimized network for neural drawing of global full-frequency illumination. The method can improve the accuracy and stability of global illumination simulation in a complex dynamic scene, and is suitable for modeling a multi-frequency global illumination effect in a dynamic three-dimensional scene.

The invention provides an aluminum film sealing defect real-time detection method and system based on multi-algorithm fusion, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: triggering an industrial camera at a detection station to collect an original image of a pesticide aluminum film sealing on a conveyor belt; performing adaptive equalization operation on the original image through pixel brightness distribution data, eliminating light fluctuation and surface reflection interference, and outputting a standardized image; three types of defect detection are synchronously executed based on the standardized image, a dynamic threshold segmentation algorithm is combined with local area brightness analysis to detect edge damage, a contour extraction algorithm is adopted to calculate bottleneck center offset to recognize seal offset, wrinkle defects are recognized based on a surface texture feature analysis algorithm, and a primary detection result is output. The aluminum film sealing defect detection method is based on multi-algorithm fusion, has strong anti-interference capability, real-time detection performance and data traceability, and provides an efficient and reliable automatic solution for aluminum film sealing quality management and control.

The invention provides a computer visual defect detection system and method on an electric control board production line, and relates to the technical field of data processing.The method comprises the steps that according to collected multi-angle images, the overall area of an electric control board is partitioned in combination with illumination conditions and visual angle information; performing image partitioning processing to generate a plurality of image sub-regions, and extracting texture features, brightness distribution features and geometric edge features in each image sub-region; rare defect feature enhancement processing is executed, multi-scale repeated superposition is carried out on low-frequency abnormal textures, and directional extension is carried out on edge fractures; performing difference comparison with the corresponding normal area combination features, and performing normalization correction in combination with the illumination condition and the visual angle information; multi-angle reproducibility analysis is executed, when the same suspected defect is detected at different angles, a reliable defect area is formed, otherwise, an interference area is removed, and an electric control board defect detection result is generated; according to the invention, the accuracy of defect detection is improved.

The invention discloses a heat shrink tube detection method based on image recognition, particularly relates to the technical field of electric power material defect detection, and is used for solving the problems of defect contour distortion, positioning deviation and insufficient classification precision caused by optical ghost interference in heat shrink tube detection. A mapping relation of light refraction paths is established based on brightness gradient difference and refractive index difference, theoretical ghost interference fringes are generated by dynamically adjusting optical path difference of an interferometer, and abnormal areas deviating from theoretical distribution are screened; meanwhile, light source incident angle optimization and defect displacement calculation are combined, residual ghost interference is eliminated, finally, accurate classification and positioning of defects are achieved through multi-dimensional matching of geometric parameters and historical defect data, complex algorithm dependence is reduced while the detection precision is improved, and the real-time detection requirement of an industrial production line is met.

The invention provides a hull surface defect detection system based on machine vision, and relates to the technical field of data processing. The image correction module is used for carrying out illumination equalization processing and geometric distortion correction; the region construction module is used for identifying a defect-free stable region and generating reference region data which comprises a brightness model and a texture model; the candidate generation module is used for detecting a region where texture interruption or abnormal bright spots exist locally to form candidate defect data, and the candidate defect data comprise pixel positions and local contrast parameters; the stability judgment module is used for carrying out projection matching in the multiple frames of images and simultaneously carrying out joint comparison with the brightness model and the texture model of the reference area data to form real defect data and false defect data; the result output module is used for generating a detection result containing defect coordinates, defect contours, image frame numbers and interference sample prompts; the accuracy of hull surface defect detection is improved.

The invention discloses a stainless steel tube surface defect detection method and system. The method comprises the following steps: S1, collecting stainless steel tube scanning images under dark field and bright field illumination; s2, splicing the line scanning images into dark field and bright field cylindrical expanded images, and executing brightness equalization and reflection suppression processing; s3, carrying out pixel-level fusion on the dark field and bright field cylindrical expansion images according to a set weight; s4, inputting the fusion cylinder expansion image into a YOLO network trunk of an integrated Swin Transform module, and extracting a multi-scale feature map; s5, performing feature fusion and bounding box prediction, and outputting a bounding box, confidence and a category label of the defect; s6, performing semantic segmentation, gray segmentation and weighted fusion in the detection frame area to generate a final defect mask; and S7, calculating the area, length, width and centroid coordinates of the defect, and converting the actual size and the spatial position. The stainless steel tube surface defect recognition accuracy and stability are improved.

The invention discloses a dark light enhancement method under the view angle of an unmanned aerial vehicle, and relates to the technical field of image processing and enhancement, and the method comprises the steps: collecting a continuous frame dark light image sequence of a target when the unmanned aerial vehicle flies, carrying out the preprocessing operation including denoising and normalization, and forming a dark light image set; and estimating the motion between adjacent frames by using an image recognition algorithm. According to the invention, through dynamic range compression and detail enhancement processing, the image definition and visibility in a dark light environment are improved, the brightness difference of the image is balanced by adopting a dynamic range compression algorithm, local overexposure or underexposure is avoided, the image can keep a good visual effect under different illumination conditions, and the image quality is improved. And the detail enhancement processing highlights texture and edge information in the image through multi-scale gradient fusion and adaptive sharpening, and improves the detail definition in dark light, so that the unmanned aerial vehicle can recognize a target more clearly when executing a task at night or in a low-light environment, and the task execution efficiency and accuracy are improved.

The invention discloses an image enhancement method for brightness gain self-adaptive regulation and control under low illumination, and relates to the technical field of image data processing. The image enhancement method for brightness gain adaptive regulation and control under low illumination comprises the following steps: S1, acquiring original image data and auxiliary processing data under a low illumination environment for preprocessing, and constructing an image processing database after storing the original image data and the auxiliary processing data; s2, performing illumination distribution optimization and brightness correction operation through brightness deviation analysis, and outputting an illumination enhancement component; s3, performing de-noising and detail enhancement processing according to a noise color deviation result, and outputting a corrected reflectivity component; s4, through image quality enhancement analysis, using a loss function to guide a double U-Net architecture to carry out detail reconstruction and color optimization on the image; and S5, based on the quality feedback and the difficult sample, adjusting processing parameters and driving algorithm closed-loop optimization. The problems of insufficient image brightness, noise interference, color distortion and detail missing multiple degradation in a low-light environment are solved.

The invention relates to the technical field of computer vision, in particular to a defect segmentation positioning method and system for an inorganic mineral casting image, and the method comprises the following steps: calling an illumination image to analyze brightness, matching exposure parameters, splicing the image, analyzing a gradient, recognizing a defect, screening an effective region, calculating a gray variance, and constructing roughness weight recognition texture features. According to the method, the high-reflection area identification, the brightness gradient analysis, the pixel-level roughness weight and the structure tensor analysis are combined, the exposure interval can be dynamically adjusted when the casting image is processed, the defect type information is output in the direction, and the positioning information is generated by correcting the recognition position in combination with the actual coordinate of the target spot. The method has the advantages that the high-reflection area identification, the brightness gradient analysis, the pixel-level roughness weight and the structure tensor analysis are combined; the method has the advantages that the method is simple and easy to implement, detail loss of overexposure areas is reduced, the recognition precision of defect areas is improved, accurate area segmentation and classification processing are achieved, roughness weight calculation combining gray variance and pixel density is combined, the sensitivity to surface fine defects is enhanced, and the precision and reliability of defect positioning are improved.

The invention discloses a circuit board surface coating quality detection method and device, and the method comprises the steps: obtaining an image of a coating surface, and removing noise interference; brightness gradient information is extracted, and when the brightness gradient information exceeds a preset brightness threshold value, it is judged that defects exist, and a potential defect area is obtained; a potential defect area is separated from the background, image brightness distribution is mapped into plating depth data, and surface topography parameters are calculated; the defect areas are classified, edge optical characteristics are extracted from coating edge areas in the image, the coating thickness difference is calculated, the thickness difference and the edge optical characteristics are fused to obtain fusion characteristics, and an image is generated through an algorithm; and calculating the brightness dispersion degree of the plating layer edge and the local thickness difference of each edge region, carrying out weighted average on the corresponding pixel gray value to obtain a fused comprehensive defect region image, and calculating to obtain the comprehensive quality score of the plating layer. The method can accurately detect the quality of the circuit board.

Embodiments of the present application disclose an ambient light compensation method and apparatus, an electronic device, a storage medium, and a program product. The method comprises: capturing an ambient image in response to the distance between an object and a distance sensor being less than a preset threshold; determining an original light color and a color cast value of current ambient light on the basis of color information in the ambient image, wherein the color cast value represents a color distribution state of the original light color in a color gamut; on the basis of the original light color and a preset target light color of target ambient light, determining a compensation light color corresponding to the current ambient light; determining light brightness adjustment parameters on the basis of the compensation light color and the color cast value; and on the basis of the light brightness adjustment parameters, using the compensation light color to perform light compensation on the current ambient light.

The invention relates to the technical field of optical detection, in particular to an AOI automatic optical detector calibration method and system, and the method comprises the following steps: obtaining a standard color palette RGB reflection reference, collecting a measured value, calculating an offset contrast, extracting image brightness, generating a correction ratio, converting gray level, extracting abrupt change, screening anomalies, and analyzing a brightness trend to generate a finishing record. And formulating a rule matching correction output comparison table. According to the method, the accuracy and reliability of image detection are enhanced through detailed analysis and accurate correction of color offset and brightness difference, the scheme combines real-time light source data and image information, fine changes are effectively identified, the misjudgment rate is reduced, the accuracy of gray and color correction is improved through comprehensive analysis of light intensity offset and regional brightness trend, and the accuracy of image detection is improved. The detection efficiency and quality of a high-density circuit are ensured, the detailed calibration mechanism remarkably reduces detection errors especially in a high-precision environment, and product quality control and the stability of a production process are optimized.

The invention provides a low-light large dynamic image enhancement method based on dynamic weight and pyramid fusion. The low-light large dynamic image enhancement method is suitable for complex illumination imaging in security monitoring. According to the method, the global weight and the detail weight of an image are obtained according to the global average brightness, the local brightness and the gradient of an image sequence, and the total weight is obtained through weighting. And the halo phenomenon easily occurring in the fusion process is reduced through guide filtering. And combining Gaussian pyramid and ratio pyramid decomposition and weighting to obtain a final fusion image. According to the method, the problems of detail loss and limited dynamic range in the low-light scene are effectively solved. Experiments show that the method is superior to the prior art in information entropy, average gradient, edge strength, spatial frequency and other key indexes. The technology has an all-time adaptive capability, is suitable for the fields of intelligent transportation, urban security and protection, low-illumination monitoring and the like, and has a wide market prospect.

A visual defect detection method, device, medium and product relate to the field of visual detection, and the method comprises the following steps: firstly, recording brightness changes of pixel points in different illumination directions by constructing an illumination response matrix, and establishing a complete mapping of surface reflection characteristics; secondly, performing joint calculation by using the light source direction matrix and the illumination response matrix to obtain normal vector data and reflectivity data, and representing spatial geometric features and material optical features of the surface respectively; thirdly, calculating a gradient feature map, a curvature feature map and a deformation feature map based on the normal vector data, generating a reflectivity map by using the reflectivity data, and forming a multi-dimensional feature representation system; and finally, in a defect detection stage, a strategy of combining gradient feature pre-screening with multi-feature verification is adopted, and final judgment is carried out by calculating a comprehensive defect feature value, so that the technical problem of insufficient micro defect detection precision of a visual detection method in the prior art is solved.

The invention provides a multi-scale polarization data fusion method based on a 4K polarization imaging detector, and relates to the technical field of image processing, and the method comprises the steps: carrying out the adaptive edge detection of four original polarization images, generating a comprehensive edge image, and carrying out the definition scoring; performing color calibration on each original polarization image based on the ambient light intensity and the color temperature, and outputting a polarization image after color calibration and a color deviation score; combining definition scores, color deviation scores and global brightness information entropies of the four polarization images after color calibration to construct a multi-objective optimization function, and solving the multi-objective optimization function in a multi-exposure parameter space to obtain an optimal exposure parameter combination; applying the optimal exposure parameter combination to image capture of the next period, and calculating global quality reward values of four newly collected polarization images; when the global quality reward value meets a preset condition, wavelet decomposition and frequency division multi-scale fusion are carried out on the polarization images after color correction, a fused image is generated, and the quality of the polarization images is effectively improved.

The invention relates to the field of illumination control, and discloses a regional illumination control method and system, and the method comprises the steps: obtaining the equipment state information, illumination intensity and personnel image information of each sub-region of a target region; the sub-regions are determined based on the building layout and function purpose division of the target region; identifying a personnel activity type and a personnel position based on the personnel image data; obtaining a static illumination demand of each sub-region of the target region; the static illumination demand comprises a brightness value and a color temperature; inputting the personnel position, the personnel activity type, the illumination intensity and the static illumination demand of each sub-region into an illumination demand prediction model; the illumination demand prediction model outputs an expected illumination demand of each sub-region; and generating a lighting control strategy for an optimization target based on the expected lighting demand of each sub-region in combination with the lighting comfort and the service life of the lighting equipment. The method has the following effect that the light requirements of people in different activity scenes are met.

The invention discloses an RGB LED light source calibration mode optimization method and system, and the method comprises the steps: collecting the color coordinates and brightness data of a three-primary-color light source of an RGB LED, and recording the actual optical characteristics; based on the collected data, establishing a physical model of the light mixing effect of the RGB LED light source, and calculating an initial PWM duty ratio corresponding to a target color coordinate and brightness; inputting the initial PWM duty ratio into the intelligent calibration algorithm model, and optimizing and calculating the optimal PWM duty ratio; the optimized PWM duty ratio is written into an MCU, and the MCU controls mixed light output of the RGB LED according to the written duty ratio; and testing and verifying the calibration effect of the RGB LED light source, and adjusting the parameters of the intelligent calibration algorithm model according to the test result. According to the invention, the PWM duty ratio can be dynamically optimized to realize high-precision light mixing output, and rapid repair and real-time adjustment are supported. The invention belongs to the technical field of photoelectricity, and aims to solve the core problem of the existing RGB LED light source calibration technology and improve the consistency of the light source performance and the production efficiency.

The invention discloses a road scene recognition method and system based on modal information evaluation, and belongs to the technical field of road scene recognition, and the method comprises the steps: constructing a scene recognition multi-task model based on modal information evaluation based on extracted multi-modal features; the multi-modal features comprise audio features and video image frame features; the scene identification multi-task model comprises a collaborative network and a backbone classification network, the collaborative network uses visual feature extraction VGG16-places365 as a modal quality evaluation network, and uses a BRISQUE algorithm based on a local normalized brightness coefficient as a teacher model to provide a learning reference label for the modal quality evaluation network; the backbone classification network uses a multi-modal DBN network to carry out unsupervised joint representation on visual and audio modal scene information. According to the method, the image quality is associated with the brightness information, and the modal information quality evaluation factor is provided to evaluate the video image frame quality, so that the modal information weight can be dynamically adjusted according to the illumination change, and the purpose of identifying the robustness of the model is achieved.

The invention relates to the technical field of optic nerve detection, in particular to a plastic particle quality detection method and system based on optic nerves, and the method comprises the following steps: capturing a plastic particle image through an industrial camera, carrying out the balance processing of the image contrast, extracting the brightness and color features of the image, and removing the noise interference; and adjusting the image brightness and optimizing the particle edge to obtain a particle optimization image. According to the invention, the accuracy and automation level of plastic particle quality detection are greatly enhanced by using the visual neural network and the image processing technology, and the edge and shape features of the particles can be accurately extracted from a complex background by automatically adjusting the image contrast and brightness and applying an advanced edge detection algorithm. According to the method, the visual quality of the image is optimized, tiny flaws such as cracks and bubbles of the particles can be effectively recognized and analyzed, and more detailed data support can be provided compared with a traditional method by accurately calculating the surface roughness and texture uniformity of the particles.

The invention relates to the technical field of image recognition, in particular to a bridge pier underwater structure image intelligent analysis method and system, and the method comprises the following steps: obtaining RGB channel values of all pixels of a bridge underwater structure image region, converting a main color temperature, generating a color temperature map, dividing the region in a vertical direction, extracting a main color temperature track, and carrying out the linear fitting. And comparing the residual error with a continuity threshold, and marking a color temperature continuous section. According to the method, a two-dimensional map is constructed through fusion of main color temperature and space coordinates, spatial distribution expression of a structural region is enhanced, a stable region is extracted by combining residual and continuity discrimination, interval judgment and RGB finishing are introduced into gray scale lifting, image brightness balance and color consistency are enhanced, a gray scale trend model is constructed through radial chain grouping, and light attenuation interference stripping is achieved. Feature point continuous frame tracking is combined with disturbance vector mapping, structure dynamic changes are captured, abnormal behaviors are recognized through cross analysis of tension differences and response terms, and efficient recognition and interference isolation under multi-dimensional feature fusion are achieved.

The invention relates to the field of intelligent illumination, in particular to a brightness AI adaptive adjustment method and system for an illumination system, and the method comprises the steps: obtaining the light environment parameters of an illumination region in real time; determining an interference parameter of the reflection light source to the target area based on the spatial distribution characteristics and the intensity of the reflection light source, and generating a compensation trigger signal when the interference parameter exceeds a preset interference threshold value; in response to the compensation trigger signal, acquiring environment data of the illumination area; calculating a reflection interference compensation amount according to the environment data, wherein the environment data comprises a mobile object reflection characteristic, a high reflection object position and an environment light fluctuation trend; generating an illumination adjustment strategy according to the reflection interference compensation amount, wherein the strategy comprises a cooperative control parameter for the target area illumination unit; and dynamically adjusting the brightness output of the target area illumination unit based on the illumination adjustment strategy. And the reflection interference compensation amount is dynamically calculated, so that a targeted illumination adjustment strategy is generated, and cooperative control of the illumination unit is realized.

The invention discloses a low-illumination image enhancement method based on a YCbCr space and a Fourier frequency domain, and the method comprises the steps: extracting a brightness component of a low-illumination image in the YCbCr space, and constructing a training set together with a normal-illumination image and the low-illumination image; constructing a low-illumination image enhancement network model, and inputting the training set into the model for training; constructing a loss function between the amplitude enhancement network branch and the normal illumination image as well as between the phase enhancement network branch and the normal illumination image, and adjusting model parameters by minimizing the loss function to obtain an optimization model; and inputting a to-be-enhanced low-illumination image into the optimization model for image enhancement. According to the method, the YCbCr brightness component and the amplitude information of the Fourier frequency domain are combined, and the Transform is utilized to enhance the phase information, so that the visual quality of the low-illumination image is remarkably improved, the visibility and definition of the image are improved, and the method has wide application prospects in tasks of image enhancement, denoising, super-resolution recovery and the like.

The invention discloses a low-light image enhancement method based on a YUV color space, and relates to the technical field of image processing. According to the method, a color space illumination enhancement network (CSLNet is established, brightness (Y) and chrominance (U, V) information is separated, and brightness and chrominance channels are respectively subjected to targeted processing, so that the image brightness and details are improved, the problems of color distortion and noise amplification are avoided, the CSLNet makes full use of the advantages of a YUV color space, and the image quality is improved. Wherein the Y channel represents brightness information, the U and V channels represent chrominance information, brightness enhancement and color correction can be more accurately controlled through separation processing and the CSLNet, a color space enhancement module CSE Block (Color Space Enhancement Block) is introduced into the CSLNet, the CSE Block is fused with a U-shaped network structure and a multi-head self-attention mechanism, and optimization processing is specially carried out on chrominance channels U and V of a low-illumination image.