199 results about "Computer image" patented technology

The invention discloses an industrial surface defect image classification method based on hybrid query strategy active learning, and belongs to the technical field of computer image processing and machine learning. The invention aims to solve the technical problems of high cost, long period and low rare defect recognition rate caused by category imbalance due to dependence on large-scale manual labeling. The core of the method is to execute a hybrid query strategy in an iterative loop: firstly, screening out a candidate sample set of model cognitive ambiguity through uncertainty measurement of prediction entropy; secondly, in the candidate set, a core set and hierarchical thought diversity sampling method is adopted to select a final to-be-labeled sample with both characteristic representativeness and category balance. And the query batch is manually annotated and then is used for carrying out iterative updating and optimization on the model. According to the method, the recognition precision and generalization ability of the classification model on various defects can be remarkably improved with extremely low manual labeling cost, and the model development period is greatly shortened.

The invention discloses a ginseng seed lossless classification method and a ginseng seed lossless classification system, relates to the technical field of computer image detection, and solves the problem that in the prior art, a ginseng seed classification method based on image and spectral characteristics of ginseng seeds is lacked. Respectively collecting image data of the ginseng seeds and hyperspectral data of the ginseng seeds; respectively preprocessing the image data of the ginseng seeds and the hyperspectral data of the ginseng seeds; respectively carrying out feature screening on the preprocessed image data of the ginseng seeds and the preprocessed hyperspectral data of the ginseng seeds; fusing the image data of the ginseng seeds after feature screening and the hyperspectral data of the ginseng seeds; after the RBMO algorithm is improved, the RBMO algorithm is combined with the RF model to construct an ORBMO-RF model; and respectively inputting the fused image data of the ginseng seeds and the fused hyperspectral data of the ginseng seeds into an ORBMO-RF model for processing, thereby completing classification of the ginseng seeds.

The invention discloses an unmanned aerial vehicle small target detection method based on feature enhancement and selective attention and a related device, and relates to the technical field of computer image target detection, and the method comprises the steps: obtaining an aerial image of an unmanned aerial vehicle, adjusting the image to a preset resolution, and obtaining an adjusted image; inputting the image into a backbone network of a network architecture, extracting a multi-level feature representation through a plurality of CALBlock feature extraction modules, and enhancing features of the multi-level feature representation through an EMIT edge enhancement architecture to obtain an enhanced multi-level feature representation; inputting the enhanced multi-level feature representation into a neck network of the network architecture, and performing cross-scale feature fusion and enhancement through an FSAFPN structure to obtain a multi-scale enhanced feature map; and inputting the multi-scale enhanced feature maps into a detection network of a network architecture, and performing target detection by using a decoder to obtain target category probability distribution and bounding box coordinates.

The present invention relates to the technical field of computer image processing, and in particular to an agent-based image analysis and processing method and system, and a storage medium. Image quality analysis and estimation is performed by means of a pre-trained image quality analysis model, and a corresponding processing strategy and a corresponding image processing sequence are generated, thereby achieving automatic image quality analysis and evaluation and facilitating selection of different processing strategies based on different image content, so as to satisfy processing requirements of various application scenarios. A corresponding image processing model is retrieved on the basis of the result of matching between the processing strategy and basic information of each image processing model in a knowledge base, and then called according to the image processing sequence, and an automatic image processing flow control model automatically controls the image processing model to execute image processing according to the image processing sequence and performs monitoring, thereby achieving automatic image processing, reducing the requirement of manual intervention, and saving the time and cost.

The invention provides an efficient image super-resolution method and device based on dual guidance semantic enhancement, and relates to the technical field of image super-resolution, visual content generation and the like in computer image process.The method comprises the steps that an image super-resolution model containing a pre-training diffusion model backbone structure is constructed, and a pre-training diffusion model is constructed; a trainable LoRA module is inserted into a U-Net structure and a VAE encoder of the image super-resolution model; calculating the perception image loss of the generated image and the real image by adopting a dual-guidance quality enhancement training strategy; based on a semantic alignment method of score matching, performing semantic feature constraint on the generated image through a condition vector of a pre-training diffusion model to form semantic consistency loss aligned with real image distribution; and carrying out end-to-end training on the image super-resolution model under joint optimization of perceptual image loss and semantic consistency loss, and after the training is finished, realizing high-resolution generation of a low-resolution image only through one-time U-Net reasoning.

The invention belongs to the field of tunnel wall surface deformation monitoring, and particularly relates to a tunnel wall surface deformation monitoring method based on computer image recognition, which comprises the following steps: acquiring expandable data and accessing the expandable data to a subsystem; image stabilization operation is carried out on the edge side, and a standardized preprocessing subsystem is constructed to process data; constructing a multi-modal fusion architecture of a structural topological graph and a space-time diagram neural network; constructing a hierarchical alarm judgment mechanism of an uncertainty-driven risk score and a sectionalized adaptive threshold, and linking the BIM and work order circulation to form a closed loop; according to the invention, millimeter-level displacement resolution can be realized, false alarm and missing alarm can be obviously reduced, and long-term online traceable tunnel wall surface deformation monitoring and graded early warning closed loop can be supported.

The invention relates to the technical field of computer image processing and medical image analysis, in particular to a cervical cancer MRI (Magnetic Resonance Imaging) image segmentation method for improving a U-Net structure based on a feed-forward channel double-attention mechanism. In order to solve the problems that a traditional U-Net structure is weak in multi-scale information extraction capability, inaccurate in boundary fuzzy region recognition and the like in processing female abdominal cervical cancer MRI images, the method proposes that a feedforward connection mechanism and a double-attention mechanism are embedded into an encoder and a bottleneck module to form a novel U-Net segmentation model; the recognition and segmentation precision of the cervical cancer focus area is improved, and a high-quality image basis is provided for subsequent clinical diagnosis and treatment. A double-attention mechanism is integrated into a plurality of key nodes of the model, a joint channel-space attention module is added to the tail of each convolution module in an encoder, a cavity space pyramid pooling structure is introduced to a bottleneck position, a channel attention mechanism is embedded, and joint modeling of cross-scale, multi-channel and space context information is achieved.

The invention discloses a large-scale rotary equipment blade three-dimensional profile measurement and point cloud splicing method and system based on line laser, and belongs to the technical field of precision measurement and computer image processing. Reading a CAD model of a to-be-measured blade, extracting geometric features of the blade by a system, and analyzing the geometric features to generate a plurality of measurement path candidate sets; a measured blade is fixed on a rotary table, a multi-dimensional measurement movement mechanism is adopted to carry a line laser sensor to scan the surface of the blade step by step according to a planned final path, and accurate three-dimensional point cloud data is obtained; the method comprises the following steps: after acquiring point cloud data of a blade, initially aligning the scanned point cloud data in combination with position information of equipment; the optimized ICP algorithm is used, a transformation matrix between the point clouds is continuously adjusted through an iteration mode, the distance between the point clouds is minimized, mismatching and noise influences are further reduced, and therefore accurate registration is achieved. The invention aims to solve the problems of low precision and poor efficiency of aero-engine blade three-dimensional profile measurement.

The invention discloses a cast-in-place pile pouring process quality detection method capable of sensing ERT on the inner side and the outer side. The cast-in-place pile pouring process quality detection method comprises the steps that conductivity information of the inner side and the outer side of a cast-in-place pile is collected through an electrical resistance tomography electrode array arranged at the bottom of a cast-in-place pile feeding guide pipe; the two-dimensional position information of the electrical resistance tomography electrode array in the pile hole in the horizontal direction is positioned through an ultrasonic transducer array arranged at the bottom of the feeding guide pipe; the depth information of the electrical resistance tomography electrode array is acquired through an incremental encoder and a roller which move along with the feeding guide pipe in the vertical direction; transmitting the obtained conductivity information, the two-dimensional position information and the depth information to a computer imaging system to obtain a three-dimensional conductivity distribution image of the cast-in-place pile, and analyzing the obtained image to realize quality detection of the cast-in-place pile. Total cross-section imaging of concrete and a reinforcement cage can be achieved, and the positions and sizes of karst caves and collapse possibly existing in the pile hole wall can be accurately measured.

The invention discloses a garden disease and pest identification method and system based on computer image processing, and belongs to the technical field of disease and pest monitoring, and the method specifically comprises the steps: collecting a visible light image, an infrared image and environment parameters of vegetation; performing space-time registration on the visible light image and the infrared image and generating a three-dimensional temperature field model; the three-dimensional space is divided into grid units, and the temperature statistical characteristics and the vertical direction temperature gradient of each unit are extracted; obtaining an expected temperature gradient direction through a preset standard three-dimensional radiation field reference model; and when the actual gradient direction is consistent with the expected gradient direction, calculating a gradient direction deviation value of each grid unit, calibrating the grid unit with the deviation exceeding a threshold value as an abnormal region, and extracting a corresponding visible light image to carry out pest recognition. According to the invention, early-stage accurate identification of diseases and insect pests is realized, systematic diseases and local insect pests are effectively distinguished, interference of environmental factors is overcome, and the reliability of insect pest monitoring is improved.

The embodiment of the invention discloses an image rendering display method and device, equipment, a medium and a product, and relates to the technical field of computer image processing. The method comprises the following steps: rendering a scene where a three-dimensional model object is located to obtain a scene basic graph; determining a screen space coordinate of a preset virtual light source and a first distance between the preset virtual light source and the three-dimensional model object, and constructing a first light shade based on the screen space coordinate and the first distance; obtaining a first outer stroke effect picture of the three-dimensional model object, and obtaining a second outer stroke effect picture of an outer stroke located in the first light shade illuminated by a preset virtual light source based on the first outer stroke effect picture and the first light shade; the post-processing effect picture is obtained based on the scene basic picture and the second outer stroking effect picture, and the post-processing effect picture is displayed, so that the picture coordination degree and the style flexibility are improved, the problem of visual separation of light and stroking is solved, and the quality, controllability and efficiency of the post-processing effect are improved.

The invention relates to the technical field of computer image processing, and particularly discloses a multi-image intelligent compression splicing method and splicing system capable of configuring the column number, and the splicing method comprises the following steps: 1, achieving the intelligent compression of images through the iteration quality attenuation, and balancing the image quality and storage space; step 2, dynamically calculating an image layout size based on the number of columns configured by a user; 3, keeping the aspect ratio of the image by adopting a cell centering strategy; and 4, realizing multi-image splicing by a dynamic canvas synthesis technology. The method has the advantages that intelligent image compression is achieved, and mass and storage space are balanced; a compression strategy can be dynamically adjusted according to the number of images; maintaining the original aspect ratio of the image; flexible multi-column image arrangement is supported; and splicing parameters can be dynamically configured.

The invention relates to the technical field of computer image processing, and particularly provides a space-frequency domain pedestrian gait feature extraction method based on spiking neural network driving, and the method comprises the steps: carrying out the gait feature extraction of a gait image through employing a space-frequency domain pedestrian gait feature extraction model; the space-frequency domain pedestrian gait feature extraction model comprises a backbone network, a multi-stage time domain global feature interaction enhancement module and a distinguishing feature aggregation module; the backbone network comprises N stages which are connected in sequence, and each stage comprises a space-frequency feature fusion module for fusing space-domain features and frequency-domain features; a multi-stage time domain global feature interaction enhancement module extracts and enhances spatial domain global features and time domain global features; and the distinguishing feature aggregation module aggregates the output of the backbone network and the output of the multi-stage time domain global feature interaction enhancement module. According to the method, the capturing capability of the model on gait micro-detail features can be improved, and the adaptability to complex scenes is enhanced.

The invention relates to a vaulting horse mark-free image processing and intelligent motion capturing system based on a computer vision technology, and belongs to the field of computer image processing, and the system comprises a plurality of cameras which are used for collecting vaulting horse motion video images of a moving target at a fixed point; the image processing and intelligent motion capture device respectively extracts feature points from different camera video images, adopts machine vision and deep learning technology to automatically identify human body articulation points in motion, tracks motions in motion, analyzes the motions in real time, reconstructs and obtains three-dimensional space coordinate information of a moving target, and carries out real-time tracking on the three-dimensional space coordinate information of the moving target. And performing optimization processing on the three-dimensional space coordinate information to obtain motion capture data. The system provided by the invention can realize integrated operation of video acquisition, motion capture and key data extraction under a large-view-field complex background.

The invention relates to the technical field of computer image restoration, in particular to a frequency domain and spatial domain adaptive collaborative modeling image defogging method, which comprises the following steps: acquiring a foggy image, and inputting the foggy image into a trained image defogging model to obtain a defogged image; the training process of the image defogging model comprises the following steps: inputting a foggy image into the shallow feature extraction module to obtain a preliminary feature; inputting the preliminary features into a frequency domain enhanced attention encoder to obtain advanced features; inputting the advanced features into a frequency domain enhanced attention decoder to obtain residual features; adding the foggy image and the residual features of the foggy image to obtain a defogged image; calculating a loss function value according to the fogless image and the defogged image of the foggy image, updating parameters of the model according to the loss function value, and obtaining a trained model when the loss function value is minimum; according to the method, a frequency domain attention enhancement module is introduced in the encoding and decoding processes, a defogging model for frequency domain and space domain adaptive collaborative modeling is constructed, and the defogging stability and definition are improved.

The invention relates to the crossing field of image processing and artificial intelligence, and discloses a computer image recognition method and system based on machine learning, and the method comprises the steps: fusing a convolutional neural network with a self-adaptive attention mechanism, and constructing a multi-scale feature extraction network; a dynamic adversarial data enhancement strategy is adopted to process the input image to generate an adversarial sample, and the adversarial sample and the style migration image jointly form an enhanced data set; adopting a hierarchical transfer learning framework, initializing source domain pre-training model parameters based on meta learning, and learning a feature mapping relationship between a source domain and a target domain through a domain adaptive network; constructing a probability prediction model based on a variational auto-encoder and a Bayesian Transform, and outputting an image recognition result and a corresponding confidence index; carrying out incremental learning by adopting a federal learning algorithm based on differential privacy, and regularly issuing updated knowledge to the edge model; according to the invention, the image recognition performance and practicability are significantly improved.

The invention relates to the field of computer image processing, in particular to a millimeter-level tea pest detection method and device based on improved YOLOv8. According to the method provided by the invention, an existing method for detecting pests by utilizing YOLOv8 is improved, and the feature significance of millimeter-level tea pests in a target detection method based on machine learning is effectively improved by adopting a slice-assisted reasoning SAHI strategy; gating convolution additive self-attention (GCAS) is adopted, the capacity of an existing network for capturing key information of small target tea pests is enhanced, and the detection precision is further improved. Aiming at the special problems of insect state postures, shielding and the like in the field of tea pest detection, the fine-grained feature extraction capability of multiple small target tea pests of a network is improved by using space depth conversion convolution (SPD)-Conv, and all-kernel modules OKM of different receptive fields are adopted to respectively pay attention to tea pest features of different scales; effective detection of pests with different postures and overlapped sheltered pests is realized.

The embodiment of the invention discloses an image segmentation method and device, electronic equipment and a storage medium, and belongs to the technical field of computer image processing. The method comprises the following steps: inputting an obtained initial image into a pre-trained segmentation network model, and outputting an initial feature map of the initial image through a target processing layer of the segmentation network model; performing cross-channel pooling processing on the plurality of initial channel features in each preset channel group, and splicing pooling processing results to obtain target channel features; performing convolution processing on the target channel features through a plurality of different preset convolution kernels, and determining a weight attention feature map according to a convolution processing result; and performing feature enhancement on the initial feature map according to the weight attention feature map to obtain a target feature map, inputting the target feature map into a processing layer behind a target processing layer of the segmentation network model for processing, and outputting a target segmentation result of the initial image. The accuracy of the image segmentation result can be improved.

The invention discloses a computer image feature extraction intelligent classification system, which relates to the technical field of image classification and comprises an image preprocessing module, a multi-scale parallel feature extraction module, a node pixel feature vector generation module, a proximity distribution coefficient acquisition module, a feature classification interval acquisition module and a classification module. The method comprises the following steps: extracting small-scale, medium-scale and large-scale pixel features, fusing to form a multi-scale fused pixel vector, generating a node pixel feature vector through a pixel multi-scale feature mean value in a grid, and meanwhile, calculating a cosine similarity mean value of each node and adjacent nodes in four directions of the node as adjacent pixel feature proximity; and by taking the standard deviation of all adjacent pixel feature closeness as a closeness distribution system, after a plurality of feature classification intervals are obtained by counting the closeness distribution coefficients of a large number of known category images, any new image can quickly fall into the corresponding interval only by calculating the closeness distribution coefficient once, so that accurate classification is realized.

The invention provides an unmanned aerial vehicle track rendering method and device, electronic equipment and a storage medium, and belongs to the technical field of computer imageology, and the method comprises the steps: constructing a geographic space background; the real-time data stream of the unmanned aerial vehicle is received and then analyzed to obtain the operation state data of the unmanned aerial vehicle, and the operation state data comprises the distance between the unmanned aerial vehicle and the observation point; based on the distance, using a corresponding model to render the unmanned aerial vehicle on the geographic space background; the farther the distance is, the simpler the model is. The rendering details of the unmanned aerial vehicle are dynamically adjusted according to the distance between the unmanned aerial vehicle and the observer, so that unnecessary picture rendering is reduced, picture fluency is guaranteed, GPU / CPU load is reduced, memory occupation is reduced, and large-scale unmanned aerial vehicle trajectory stability and flow field display are achieved.

The application discloses a handwriting corner point determination method and device, a storage medium and a terminal, and relates to the technical field of computer image recognition. First, the writing speed of each trajectory point in handwriting and the final curvature of each trajectory point are calculated, and the final curvature is the average of all curvatures of vectors formed by the trajectory point and other trajectory points in a preset range. Then, a trajectory point meeting a condition is selected as a first corner point. Finally, pseudo corner points in the first corner point are removed. Since the average of all curvatures of the trajectory point in the preset range is taken as the final curvature of the trajectory point, that is, the average of the cumulative curvatures of the sliding window is taken as the curvature of the window center trajectory point, the misleading of curvature mutation to corner point selection is reduced, the curvature mutation can be effectively smoothed, more accurate corner points can be selected, line segment fitting of handwriting is performed, pseudo corner points in the first corner point are removed, the pseudo corner points in the corner points can be effectively removed, and finally, correct corner points in the handwriting are determined.

The application discloses a graphical interface testing method and device, and relates to the technical field of computer image processing. The method comprises the following steps: constructing an intelligent region screenshot system by adopting a three-layer event-driven architecture, and performing screenshot and screenshot information processing by using the intelligent region screenshot system; wherein the three-layer event-driven architecture comprises an event listening layer, a coordinate processing layer and a service integration layer; the event listening layer is used for capturing a screenshot signal and an event triggered by a user operation, and recording associated original boundary coordinate points; the coordinate processing layer is used for loading correction parameters from a configuration file, correcting the original boundary coordinate points, and determining boundary coordinates of a screenshot region; the service integration layer is used for performing screenshot saving and size acquisition operations according to the determined screenshot region coordinates; and the operation of the intelligent region screenshot system is integrated into an automatic test system to perform graphical interface testing. The problems of how to realize efficient screenshot operation and how to realize content backtracking of the screenshot are solved.

The application discloses a kind of based on multi-constraint priori's bayesian Retinex deep-sea image enhancement method, it is related to computer image processing method, the method is first by a kind of based on statistics color correction method to image color correction processing;Then according to Retinex principle, original deep-sea image is divided into illumination map and reflection map, in illumination map estimation, it is carried out smooth priori, structure priori and non-uniform illumination highlight area priori, and three kinds of priori conditions are combined into bayesian model;Through the method of gamma correction, illumination map and reflection map are handled, and finally output enhanced deep-sea image;Various evaluation standards and algorithm comparison show that the method proposed is more suitable for image enhancement work under deep-sea harsh environment, and the deep-sea image obtained by processing has better observation effect.

This invention discloses a growth reference method, apparatus, and medium for rosewood trees, applicable to the fields of computer image processing and virtual reality technology. The method employs a parallel approach to the splicing process. After obtaining the coordinate information of each segment based on measurement data, image blocks for each segment are determined. The corresponding branch splicing state is then determined based on each image block. The image blocks are obtained in parallel and spliced ​​together, improving the efficiency of the generated model. Due to the parallel approach, each image block is generated solely from the coordinate information of its segment, avoiding the existing problem of cascading errors. This prevents significant deviations caused by splicing another segment if one segment is misaligned. In this invention, even if one segment is misaligned, the next segment is generated based on its own coordinate information, avoiding large deviations during the splicing process. This results in a growth model with smaller deviations, providing a more valuable reference for the growth of rosewood.

The invention discloses a confocal microscopic image longitudinal distortion correction method based on an electromagnetic drive MEMS micromirror, and the method comprises the steps: sampling a piezoresistive feedback signal of a micromirror slow axis drive signal through a high-speed data collection card, fitting sampling data through a polynomial, carrying out the linear fitting of data points in a left-right interval of a midpoint of a sampling data time sequence, and carrying out the linear fitting of data points in a left-right interval of a midpoint of the sampling data time sequence; and mapping the polynomial fitting curve and the linear fitting curve according to the actual position of the corresponding micromirror, and finally realizing longitudinal distortion correction of the confocal microscopic image by utilizing upper computer imaging software through a mapping relation. According to the invention, the longitudinal distortion of the electromagnetic drive MEMS micromirror confocal microscope can be effectively corrected, and the image quality is improved.

The application provides an image fusion method and device, electronic equipment and storage medium, which are applied to the field of computer images. The method comprises the following steps: performing pixel sampling on an initial insertion image to obtain original color channel values of each pixel point in the initial insertion image; determining color parameters of each pixel point; determining spatial dispersion degrees of each pixel point; determining a reference pixel point among each pixel point based on the color parameters and the spatial dispersion degrees; determining a background pixel point and a foreground pixel point among each pixel point based on the chroma difference values between each pixel point and the reference pixel point; correcting the transparency of the background pixel point to a target transparency, and generating a target insertion image based on the background pixel point and the foreground pixel point of the target transparency; and inserting the target insertion image into a preset insertion position of a target image, thereby improving the adaptability and instantaneity of image fusion.

The invention discloses a neural signal extraction self-supervised learning method and system based on sparse decomposition, belongs to the technical field of deep learning computer image processing, and solves the problems that in an existing traditional neural signal extraction method, calculation time is long, and in an existing deep learning neural signal extraction method, calculation time is short. Signals need to be labeled manually; and the extraction accuracy is low. Comprising the following steps: obtaining a denoised neural microscopic image as a data set; constructing a sparse decomposition network, and training the sparse decomposition network by adopting a loss function; inputting the denoised neural microscopic image into the trained sparse decomposition network for reasoning to obtain a sparse part image representing neuron information; drawing an F / F image, performing threshold segmentation processing, and extracting spatial positions of neurons; according to the spatial positions of the neurons, F / F time sequence signals of each neuron are extracted, and the spatial position and starting and ending time of each neuron event are recorded; the method is suitable for a neural imaging technical scene.

The invention relates to the technical field of computer images, and provides a spatial weak moving target detection method and system driven by time sequence image registration, and the method comprises the steps: obtaining a time sequence image short sequence of spatial weak moving target detection; inter-frame registration is carried out on the time sequence image short sequence to obtain a registration transformation matrix, and geometric correction is carried out on subsequent frames to complete space registration; double labeling is carried out based on the time sequence data after space registration is completed; and inputting the time sequence image short sequence subjected to spatial registration into a trained target detection model to obtain a detection result, and performing inter-frame registration on the time sequence image short sequence and constructing double annotations based on a motion sequence frame and coordinate points. The weak moving target can still keep feature alignment and track consistency under the conditions of cross-frame background disturbance and low signal-to-noise ratio; in combination with a cooperative structure of the encoder and the two-stage detection head, detection and high-precision positioning of weak targets such as space debris and microsatellites are realized, and the detection stability and accuracy of the weak and small moving targets in the space are improved.

This invention discloses a method for displaying medical images and a readable storage medium, belonging to the field of computer image processing. The display method includes the following steps: in response to interface operations, constructing multiple sub-windows under the same window, and constructing at least one sub-display area in each of the multiple sub-windows, wherein the multiple sub-windows do not overlap and display registered magnetic resonance images of different modalities; displaying a preset section layer of at least one type of anatomical view from the registered magnetic resonance images of the same modality in at least one sub-display area of ​​the same sub-window; in response to interface operations on the multiple sub-windows, updating the section index global variable in the global parameter pool, and updating the section layer displayed in each of the at least one sub-display areas according to the updated section index global variable.

The present application relates to a kind of point cloud color denoising methods based on L0 norm minimization, belong to computer image graphics processing technical field.This method, first decoupling position and color information, respectively create the point cloud RGB vector of length N using extracted color information.Then see the RGB value of position modification point, if the color value of this point and the gradient difference of its neighborhood point color value is larger, then prove that this point is located in the position of color mutation.Form a color smooth surface with this point and its k nearest neighbors, modify the color value of point by L0 norm minimization, and along the position of color smooth point, to sequentially denoise the color value of other points in point cloud.Repeat the process until convergence.This method optimizes color denoising on three-dimensional point cloud model with position information, effectively solves the color mutation problem on the basis of preserving color and geometric features.At the same time, L0 norm minimization method solves the color denoising problem in three-dimensional point cloud denoising.