252 results about "Region growing algorithm" patented technology

The invention relates to the technical field of image detection, in particular to a PCBA board defect detection method and system based on image processing, and the method comprises the following steps: carrying out the meshing calculation of a gray scale deviation after a gray scale image is subjected to Gaussian filtering denoising, generating change rate data, carrying out the statistics of a frequency number, constructing a histogram, combining with an Otsu algorithm, and generating a candidate mask; extracting pixels based on a mask, calculating a gradient modulus, screening edge candidate points, carrying out gradient direction connection and morphological processing to generate a complete edge structure, expanding a connected domain through a region growing algorithm, aligning the connected domain with a template contour, and outputting defect coordinates. According to the method, the defect identification sensitivity is improved through combination of gray level image gridding processing and dynamic threshold calculation, a candidate mask is generated through grid gray level change rate statistics and an Otsu algorithm to avoid over-segmentation missing detection, and the contour precision is improved through combination of gradient modulus difference screening and morphological closed operation optimization. The region growing algorithm and template dynamic alignment reduce deformation misjudgment, and staged dimension reduction and feature enhancement reduce calculation complexity and solve resource waste.

The invention discloses a point cloud data rapid processing system based on 3D vision, and relates to the technical field of point cloud data processing. The binocular acquisition module generates an anti-interference high-precision point cloud; the preprocessing module is used for reducing noise and dimensionality and retaining key geometric features; the hierarchical feature extraction module fuses curvature weight and a non-maximum suppression strategy, and improves the robustness of an ORB algorithm in rotation, scale and noise scenes; the industrial scene segmentation module accurately separates stacked objects through normal vector clustering and a dynamic region growing algorithm, and secondarily verifies boundaries in combination with a lightweight semantic model; the two-stage registration module dynamically adjusts a threshold value based on error feedback to realize pose optimization from coarse registration to fine registration; the coordinate mapping module establishes a space mapping model through multi-attitude calibration and robot multi-axis linkage trajectory optimization. The problem that in the prior art, a 3D machine vision algorithm is high in time delay is solved, the real-time performance and rapidity of 3D model recognition and feature extraction are improved, and the efficiency requirement of industrial production is met.

The invention provides an engineering construction defect automatic detection and classification method based on deep learning, and the method comprises the steps: obtaining a welding seam surface image through the shooting of an unmanned plane, and carrying out the denoising and illumination normalization processing of the welding seam surface image, and obtaining a standardized image; welding seam surface texture features are extracted from the standardized image, a convolutional neural network is adopted to analyze the spatial distribution characteristics of textures, and vectorization processing is carried out to obtain texture feature vectors; segmenting a weld surface corresponding to abnormal region distribution by adopting a region growing algorithm, and analyzing pore and weld discontinuity in combination with the texture feature vector to obtain a defect candidate region; performing threshold division on the sizes and the numbers of the defects according to the defect types and the feature vectors of the candidate regions to obtain a severity grading result of each type of defects; and severity features are extracted from a grading result, and a Bayesian network is adopted to fuse texture feature vectors and defect type labels to obtain a welding quality evaluation score.

The present invention belongs to the technical field of digital mine safety, and particularly relates to a blasting area surface morphology inversion method based on an unmanned aerial vehicle. The method comprises: S01, on-site data collection; S02, blasting area morphology inversion; S03, a muck pile throw distance; and S04, a muck pile surface fragmentation distribution. In the present invention, oblique photography by an unmanned aerial vehicle is used, and three-dimensional model reconstruction is performed by capturing a blasting area image, so that a feasible aerial survey scheme is formulated, and the integrity of collected data is good; and reverse modeling of the blasting area is performed by means of the steps of feature point extraction, spatial information conversion, point cloud generation, grid generation, etc.; voxel grid downsampling, point cloud matching and error detection are used to perform registration on point clouds of a target area before and after blasting, so that a good effect is achieved; and a color-based region growing algorithm is used to perform coarse segmentation of point cloud features on an ore-rock block on the surface of a muck pile, and a PointNet++ algorithm is used to perform fine segmentation of point cloud features on the ore-rock block on the surface of the muck pile, so that the muck pile throw distance and the muck pile surface fragmentation distribution are calculated.

The invention discloses a method and a system for rapidly screening peanut endophytic mildew, particularly relates to the technical field of nondestructive testing of agricultural products, and is used for solving the problems of false detection and missing detection caused by low contrast and gradient boundary in an initial mildew stage and an internal diffusion sample in an existing detection method. Based on a hyperspectral imaging technology, a filtering kernel size is dynamically adjusted through conjoint analysis of frequency domain energy distribution and spatial local variance, and detail features of a gradient boundary in an image are enhanced; verifying and screening high-confidence candidate regions by adopting spectrum and spatial feature consistency, analyzing and extracting principal component features representing a mildew diffusion trend in combination with a texture direction, and dynamically splicing the principal component features with a spectrum gradient direction to construct a fusion feature vector; quantizing boundary confidence through a Bayesian probability classification model, combining with a neighborhood similarity constraint region growing algorithm to generate a mildewed mark graph with continuous space and consistent features, and introducing a dynamic threshold correction mechanism to adaptively optimize a segmentation standard; and the detection precision and the anti-interference capability of the fuzzy boundary are improved.

The invention discloses an intelligent pest and disease damage identification and targeted spraying method and system based on machine vision, and the method comprises the steps: inputting a multispectral image sequence and environment sensing data into a processing system, and obtaining a high-quality fusion image through spectrum-space joint correction and environment adaptive compensation; constructing a region growing algorithm based on a topological flow theory, and realizing accurate extraction of a target region in combination with curvature flow boundary optimization; integrating the spatial features, the time sequence features and the context information by adopting a multi-modal feature fusion method, and establishing a pest state evaluation and behavior prediction model; and according to an evaluation result, a spraying track is optimized through an environment constraint field, a self-adaptive parameter control system is adopted to adjust spraying parameters, and closed-loop optimization is realized through real-time monitoring. The technical problems of low pest and disease identification precision, poor spraying effect and the like in a complex environment are solved, and the accuracy and efficiency of prevention and treatment are improved.

The invention discloses an SMT welding spot defect detection method based on image data. The method comprises the following steps: S1, acquiring an image of an SMT welding spot area; s2, carrying out image preprocessing; s3, carrying out welding spot region segmentation by adopting a self-adaptive region growing algorithm, and carrying out modeling on a welding spot region contour in combination with a boundary fitting optimization algorithm to generate a welding spot contour model; s4, multi-level comprehensive features are extracted from the welding spot area, and the multi-level comprehensive features are constructed into a feature vector set; and S5, inputting the feature vector set into a welding spot defect detection network, predicting a defect mode existing in the current batch of welding spots by adopting an improved ProtoNet model, and completing classification and identification of welding spot defects by adopting adaptive feature filtering. According to the method, the adaptive region growing algorithm and the improved ProtoNet model are adopted, accurate detection of the welding spot defects is achieved, and the method has the advantages of being high in detection precision, high in adaptability and good in robustness.

The invention relates to the technical field of foamed silicone rubber surface detection, and discloses a foamed silicone rubber surface detection method based on image visual identification, which comprises the following steps: acquiring a color image of a foamed silicone rubber surface, carrying out graying and normalization processing, and generating a diffuse reflection effective detection area by using a polarization filter difference technology; color abnormity is detected based on an image gridding and gray statistical method, meanwhile, pore and microbubble defects are detected in combination with minimum value seed point extraction and an eight-neighborhood region growing algorithm, finally, various masks are fused, the defect area and number are counted, and a quality inspection report is generated; the method can effectively inhibit highlight interference and accurately identify uneven colors and pore microbubbles, the detection process does not need external training, calculation is efficient, and the method is suitable for rapid detection and quality control of surface defects of foamed silicone rubber.

The invention provides a strain clamp crimping quality intelligent diagnosis method based on infrared thermal imaging, and the method comprises the steps: carrying out the noise reduction and enhancement processing of a thermal image data set through employing a wavelet transform and morphological filtering algorithm, highlighting the temperature distribution characteristics of a crimping part, segmenting a thermal image through employing a region growing algorithm, extracting a region of interest, and carrying out the segmentation of a region of interest. Calculating characteristic parameters such as a temperature mean value, a variance and a gradient of the region, and constructing a crimping quality characteristic vector; in order to solve the problem of crimp quality defect sample scarcity, a generative adversarial network algorithm is adopted, through adversarial learning of a generator and a discriminator, defect samples are synthesized, a data set is expanded, a transfer learning technology is utilized, a convolutional neural network model is pre-trained on a crimp quality normal sample, general feature representation is extracted, and fine tuning is performed on defect data. And the model generalization ability is improved.

The invention relates to an ancient character image recognition and semantic analysis method, which comprises the following steps of: firstly, acquiring an original image containing irregular deformation and material diversity characteristics from the surface of a cultural relic, and eliminating noise and illumination interference through adaptive filtering; calculating a main inclination angle based on stroke feature distribution, and executing inclination angle correction to obtain a processed image; thirdly, separating independent characters by adopting a region growing algorithm based on stroke features, and extracting feature vectors by utilizing a deep convolutional network for identification; and finally, matching context information in combination with an ancient text corpus, and optimizing sequence labeling by adopting a conditional random field algorithm to obtain semantic output. And if the result is not ideal, the inclination angle correction parameter is adjusted through backtracking and iterative optimization is carried out, so that the overall identification accuracy is improved. According to the method, the problems of irregular deformation and material diversity in the ancient character image can be effectively solved, and the recognition precision and the semantic analysis reliability are improved.

The invention discloses a molybdenum-rhenium alloy pipe fitting defect identification method and system based on a high-definition microscopic image. The method comprises the following operation steps that high-definition microscopic equipment is used for collecting the high-definition image of a molybdenum-rhenium alloy pipe fitting; preprocessing the high-definition image of the molybdenum-rhenium alloy pipe fitting to obtain a molybdenum-rhenium image to be detected; performing execution processing of a region growing algorithm on the molybdenum-rhenium image to be detected to obtain a defect region to be detected; performing defect identification on the to-be-detected defect area to obtain type defects; and judging the defect problem of the molybdenum-rhenium alloy pipe fitting according to the type defect.

An unsupervised region-growing network (RGN) is trained to perform object segmentation on video data degraded by atmospheric turbulence. The method includes obtaining input data containing turbulence-degraded video, extracting a video frame sequence, and training the RGN using a selected algorithm incorporating a region-growing algorithm and a grouping loss function. A bidirectional optical flow sequence is computed for multiple reference frames within the video sequence. Pixel-level masks are generated for detected moving objects, followed by applying the region-growing algorithm to create coarse masks. A grouping loss function refines these masks to ensure consistency across consecutive frames. The trained RGN outputs refined masks as object segmentation data for the received video, improving segmentation accuracy in turbulent environments. This approach enables robust object detection and segmentation without requiring prior video restoration, maintaining fidelity to the original turbulence-distorted input.

The invention discloses a desertification monitoring method and system based on multi-source remote sensing data fusion, and the method comprises the steps: carrying out the weighted scoring of multi-source satellite remote sensing data according to the spectrum, cloud coverage and time resolution, and automatically switching to a data source with a higher priority when the score is lower than a threshold value. Thirdly, performing initial segmentation on the image by using a multi-scale segmentation algorithm in combination with spectrum and texture features, optimizing boundaries through a region growing algorithm, and merging regions with small spectrum differences into desertification plaques; and extracting construction land expansion and agricultural activity intensity indexes from the time series data, and establishing a quantitative relation model with desertification plaque change. And adopting a Kriging space-time interpolation algorithm for missing data to generate a continuous curved surface. And finally, fusing a multi-period segmentation result and human factor data, and outputting a desertification boundary dynamic change diagram and a human influence weight distribution diagram. According to the invention, accurate monitoring of the desertification process and quantitative evaluation of human influence are realized, and a scientific basis is provided for desertification control.

The invention provides a prefabricated dish semi-finished product defect identification method and system with an AI algorithm, and the method comprises the steps: extracting semantic features from a refined defect candidate region set, carrying out the feature mapping of each region through a deep convolutional network according to the demands of atypical defect identification, and obtaining the defect description represented by a high-dimensional feature vector; marking original image data through a final defect identification result, and for inhibition of complex background interference, performing outward expansion from defect edge features by adopting a region growing algorithm to obtain complete defect region boundary information; after complete defect area boundary information is obtained, defect distribution changes of continuous batches of images are compared through a time sequence analysis method according to the monitoring requirement of production process fluctuation, and the quantitative basis of process adjustment is determined.

The invention discloses a multispectral petroleum leakage detection method. The method comprises the following steps: S1, acquiring a multispectral image of a petroleum leakage area by using spectral imaging equipment; s2, the multispectral image is preprocessed, and noise in multispectral data is removed; s3, reducing data dimensions of the multispectral data by using a principal component analysis method, and removing redundant wavebands; s4, extracting a potential petroleum leakage characteristic region from the multispectral image based on an optimized SAM method, and performing ROI recognition through a region growing algorithm; s5, inputting the multispectral image into the optimized YOLO model, and carrying out entry detection and classification; and S6, optimizing a detection result by using an NMS, removing redundant detection through non-maximum suppression, and reserving an optimal detection result. The invention further discloses multispectral petroleum leakage detection equipment and a storage medium. The multispectral petroleum leakage detection method provided by the embodiment of the invention has the characteristics of high precision and high robustness, and is suitable for petroleum leakage detection under a complex background.

The invention relates to the technical field of remote sensing geological prediction, in particular to a slope support stability prediction method and system based on remote sensing data, and the method comprises the steps: obtaining a multispectral remote sensing image of a target slope region, and generating a vegetation mask through employing a normalized vegetation index; removing interference pixels of a vegetation coverage area in combination with morphological filtering and connected area analysis, then identifying support structure features through an improved edge detection algorithm, delimiting an influence area by adopting a region growing algorithm based on machine learning, inputting an area image into a convolutional neural network model, and obtaining an image of the support structure; a deformation probability graph is output by using a data enhancement technology and a weight optimization layer, finally, a threshold value is determined according to historical data, slope support stability categories are divided in combination with spatial neighborhood information and a voting mechanism, vegetation interference is effectively eliminated, a support structure is accurately recognized, prediction precision is improved, slope support stability can be accurately judged in time, and the method is suitable for popularization and application. And a reliable basis is provided for early warning and protection of slope disasters.

The invention relates to a historical building disease diagnosis method and device assisted by artificial intelligence, equipment and a medium. The method comprises the steps of obtaining a multi-angle image sequence of a historical building and performing preprocessing to obtain a standardized building structure image, performing edge feature extraction on the standardized image to identify dislocation feature points to generate an edge information graph, and segmenting a dislocation region through a region growing algorithm based on the edge information graph to generate an initial dislocation region distribution graph. Performing deformation degree and displacement calculation on each region in the distribution diagram to determine a dislocation severity level, comparing dislocation region changes in each period through a time sequence analysis algorithm by combining an image sequence to generate a dynamic change mode, and optimizing boundary division according to the severity level and the dynamic change mode to generate a diagnosis report; automatic identification and evolution tracking of historical building dislocation diseases are realized, the problems of high subjectivity, fuzzy boundary judgment and lack of disease evolution prediction of traditional manual investigation are solved, and the scientificity and long-term effectiveness of repair decision are improved.

The invention provides a circuit board component accurate positioning and mounting method and system based on visual guidance, and relates to the technical field of mounting, and the method comprises the steps: obtaining the multi-angle image information of a to-be-mounted component, determining a three-dimensional point cloud model and a depth map sequence, and determining the type information; segmenting the point cloud model through a region growing algorithm to extract features for pose estimation; the mounting parameters are called and combined with the posture deviation information to control a mechanical arm; and motion parameters are optimized based on a self-adaptive optical flow algorithm until the precision requirement is met. According to the invention, the component mounting precision and efficiency are improved, and the mounting failure rate is reduced.

The invention discloses a tortoise-shell glue transparency detection method and system based on multispectrum, and the method comprises the steps: S1, obtaining a multispectral image sequence of a tortoise-shell glue sample, carrying out the wave band correction, constructing a multispectral image data cube, and carrying out the spatial registration; s2, generating a spectral angle mapping graph according to the registered multispectral image data cube; s3, extracting a tortoise-shell glue region through spectral angle mapping and a region growing algorithm, and constructing a spectral feature matrix; s4, based on the spectral feature matrix and a cross validation method, obtaining an optimal tortoise-shell glue transparency qualified product identification model, and performing qualification judgment on the transparency of the tortoise-shell glue sample to be detected; and S5, constructing a transparency quality evaluation model, and carrying out quality grade division on the transparency of the tortoise-shell glue. And carrying out quality grading on the transparency of the tortoise-shell glue. According to the method, objective and comprehensive evaluation of the transparency quality of the tortoise-shell glue can be realized by acquiring the image information of the tortoise-shell glue sample in a plurality of spectral bands and combining an intelligent analysis algorithm.

The invention provides an explosion-proof safety cabinet intelligent control method and system based on deep learning, and relates to the technical field of explosion-proof safety cabinet control, and the method comprises the steps: collecting multi-dimensional state data and environment image data in a cabinet, carrying out the state prediction through employing a multi-layer causal convolutional network of dynamic discrete wavelet transform and a segmented recursive structure, and obtaining a state prediction result; abnormal target detection is carried out by adopting a twin neural network and a local similarity region growing algorithm, and a control track is extracted from an expert strategy library in combination with a Gaussian kernel function and is optimized, so that intelligent control of the explosion-proof safety cabinet is realized. According to the method, the state prediction accuracy, the anomaly detection sensitivity and the control strategy adaptability are improved, and the system safety is enhanced.

The invention belongs to the technical field of three-dimensional model modeling, and particularly relates to a method for constructing a foreign body model of a nuclear power plant foreign body digital museum. Comprising the following steps: step 1, collecting close-range image data of a target foreign body, generating point cloud data by using feature matching and a neural radiation field, calculating a normal vector of each point, and segmenting the point cloud data through a region growing algorithm to obtain a point cloud model of the target foreign body; 2, generating a surface grid model of the foreign matter by adopting a Poisson reconstruction algorithm, and finishing and optimizing the grid model by analyzing the solid structure of the foreign matter to obtain a refined foreign matter fine model; and 3, generating high-fidelity texture mapping by adopting a method based on texture reconstruction and rendering in combination with foreign matter surface features and close-range image data, and rendering illumination and reflection effects for the model to realize visual optimization. The method has the beneficial effects that the high-fidelity three-dimensional model of the foreign matter can be efficiently generated, and the damaged area can be effectively repaired.

The invention relates to a welding quality detection method and system for a high-order computing power automatic driving FPC sensing module, and the method comprises the following steps: carrying out the feature extraction of a multi-dimensional spectral image set, obtaining a welding feature vector of a welding region, and constructing a welding feature map based on the welding feature vector; performing dynamic feature mapping on the welding feature spectrum through a spectrum transformation network to obtain a welding feature descriptor; based on the welding feature descriptors, topological structure analysis is conducted on the welding area, and a welding association diagram is obtained; and inputting the welding association diagram into a preset region growing algorithm for quality detection and grading to obtain a welding quality evaluation report, thereby solving the problems that the traditional method generally depends on manual inspection, the efficiency is low, the influence of operator experience and subjective judgment is easy to cause, and the working efficiency is low. And the requirements of the modern manufacturing industry on automation and precision cannot be met.

The invention discloses a three-dimensional reconstruction method, system and device for an extra-high voltage power transmission and transformation line, and belongs to the technical field of point cloud reconstruction. The three-dimensional reconstruction method comprises the following steps: placing a laser radar along the extra-high voltage power transmission and transformation line to obtain point cloud data of the extra-high voltage power transmission and transformation line; rTK positioning software is placed at the laser radar and the selected reference point to obtain longitude, latitude and height coordinate data; correcting and filtering the obtained point cloud data and longitude and latitude coordinate data of the extra-high voltage power transmission and transformation line; splicing the filtered extra-high voltage power transmission and transformation line point cloud data, and constructing a preliminary reconstruction model; performing point cloud segmentation on the preliminary reconstruction model by using a region growing algorithm, and extracting incomplete power transmission tower point clouds in the preliminary reconstruction model; acquiring three-dimensional models of different types of required power transmission towers, and constructing a standard model library; and matching the incomplete point cloud of the power transmission tower with the constructed standard model library, and placing a matched three-dimensional model in a scene to realize complete point cloud reconstruction.

The invention relates to an insulator image segmentation method based on an infrared enhancement image of an unmanned aerial vehicle, and relates to the technical field of image processing, and the method comprises the steps: collecting an infrared image sequence through an infrared enhancement camera, obtaining a standard infrared image sequence, and carrying out the state recognition through an image perception prior engine, outputting a predicted insulator attention heat map and a predicted boundary confidence map; optimizing and adjusting the initial threshold segmentation algorithm and the initial region growing algorithm, and obtaining an adaptive threshold segmentation algorithm and an adaptive region growing algorithm; and carrying out image segmentation on the standard infrared image sequence to output an insulator image sequence, and carrying out early warning judgment on the insulator image sequence based on an adaptive early warning mechanism. The method solves the problems that a traditional insulator image segmentation method cannot effectively deal with the problems of low infrared image temperature contrast ratio, large noise interference and complex background, so that the insulator segmentation is easy to cause mistaken segmentation and missing segmentation, and the high-precision requirement of fault detection is difficult to meet.

The invention belongs to the technical field of image processing, and particularly relates to an urban garden insect pest early warning method and an early warning system thereof, which can automatically identify an insect pest area in an image by collecting a plant surface image and sequentially carrying out de-noising processing, image enhancement, edge detection, texture analysis, feature extraction and mode matching. And a region growing algorithm is adopted to extract an insect pest influence range, and an insect pest area proportion is calculated, so that quantitative judgment of the insect pest degree is realized. And on the basis, early warning data is generated in combination with the geographical position information and is pushed to the terminal equipment through the network, so that a manager can timely obtain the occurrence position and severity of the insect pests, and the insect pest response efficiency and management precision are improved. Therefore, according to the scheme, the problems that in the prior art, insect pest recognition depends on manpower, the recognition accuracy is low, and early warning is not timely are solved, and intelligent and automatic monitoring and early warning of urban garden insect pests are achieved.

The invention discloses an image processing method and system for extrusion shaping of a wood-plastic plate, and the method comprises the steps: carrying out the multi-scale analysis of an image of the wood-plastic plate, and recognizing the local features in the image; on the basis of multi-scale image feature extraction, a deformation mode in an image sequence is recognized through a time sequence image data association and dynamic correction method, and image processing parameters are adjusted in real time; according to the dynamically corrected image, processing the image by using morphological operation, and extracting a surface defect area of the wood-plastic plate; after morphological operation, identifying a defect area based on an image gradient optimization method; and on the basis of the sharpened image, analyzing the local flatness in the image by using a region growing algorithm. According to the method, the feature points are extracted from the image sequence and matched, the deformation mode between the images is recognized, and the local surface flatness is accurately analyzed in combination with the region growing algorithm, so that accurate detection of the surface defects and irregular regions of the wood-plastic plate is realized.

The invention relates to the technical field of medical imaging, and discloses an image processing method and system for a dual-energy X-ray bone mineral densitometer, and the method comprises the steps: collecting a dual-energy X-ray image, and carrying out the light and dark field correction of original projection data; based on the corrected projection data, using an aluminum sheet to simulate bones and glass to simulate tissues, carrying out data fitting to obtain a bone mineral density value, and fitting a bone-aluminum conversion coefficient; preprocessing the image, wherein the preprocessing comprises Gaussian smooth filtering, threshold processing and corrosion operation; segmenting the image by using a region growing algorithm, and carrying out edge detection by using a Canny operator; extracting an ROI (Region of Interest), and determining the boundary of the ROI by searching coordinates meeting a preset threshold condition within a preset proportion range in the vertical direction of the image; and calculating the area of the ROI, the bone mineral density BMD and the bone mineral salt content. The accuracy of bone mineral density measurement is improved, the influence of noise and artifacts can be effectively reduced, and the target area is accurately extracted.

The invention relates to the technical field of image processing, and particularly discloses a titanium rod surface defect detection method, which comprises the following steps of: acquiring a grayscale image of a titanium rod; segmenting the grayscale image by using a region growing algorithm to obtain a plurality of segmented regions; and inputting all the segmented regions into a support vector machine, and outputting the defect type of each segmented region. According to the titanium rod surface defect detection method provided by the invention, the growth criterion of the region growth algorithm is improved, so that the segmented region is more reasonable, and the titanium rod surface defect detection is more accurate.

The invention discloses an electronic screen film surface dust detection method based on photometric stereo. The method comprises the following steps: image acquisition: acquiring 4-8 grayscale images in different incident directions; image preprocessing: carrying out edge-preserving noise reduction processing on the original image by adopting a bilateral filter, improving the smoothness by combining a Gaussian filter, and converting the filtered image into a floating point type; normal reconstruction: calculating a surface normal vector corresponding to each pixel point through a least square method or robust estimation according to a photometric stereo principle by utilizing a multi-light source matrix form, and generating a normal distribution diagram; curvature calculation: estimating a local curved surface of each pixel neighborhood based on the reconstructed normal graph; and dust identification: through setting a dynamic threshold and a region growing algorithm, extracting a continuous and significant normal disturbance region, and carrying out classification, marking and visual output in combination with characteristics such as area, length, boundary curvature and the like.

The invention belongs to the technical field of material lumpiness statistics, and particularly discloses a material lumpiness statistics method based on multi-view three-dimensional laser point clouds, which comprises the following steps of: obtaining point cloud data of materials through a three-dimensional laser scanner, preprocessing the obtained point cloud data of the materials, and storing the preprocessed point cloud data in a tree structure; determining point cloud groups of all surfaces of the material blocks by using a point cloud region growth algorithm, dividing the relationship between adjacent point cloud groups by using spatial feature normal vectors of the point cloud groups, and obtaining all point cloud groups of each material block in combination with a nearest neighbor algorithm so as to judge the spatial relationship of adjacent materials; according to the method, the point cloud data are preprocessed to reduce illumination variation, shielding objects, noise interference and the like, and the material identification precision and accuracy are improved, so that the problems of low material identification precision and poor accuracy caused by factors such as illumination variation, shielding objects, noise interference and the like in a complex environment during statistics of different forms of materials are solved.