964 results about "Edge maps" patented technology

The present invention discloses an edge-guided RGBD underwater salient object detection method with multi-attention, which includes the steps of: S1 performing channel-dimension preprocessing on RGB image and depth map and serially connecting them to obtain an RMD image; S2 inputting the RMD image into a trained salient object detection model including an encoder structure and a decoder structure; and S3 obtaining salient images and edge images output from the salient object detection model as object detection results, in which the encoder generates feature maps with reduced resolution layer by layer using the RMD image based on a residual neural network, and the decoder structure includes an edge detection branch used to fuse the feature maps layer by layer, and a saliency detection branch used to fuse the feature maps and edge feature maps layer by layer. The present invention preprocesses the input image with underwater imaging features, and uses an edge prediction image to guide multi-layer salient object detection, thereby enhancing edge details of the salient image.

The invention relates to the technical field of image processing, and discloses a backlight effect image edge enhancement method based on intelligent identification, which comprises the following steps of: judging a field environment type; performing global optimization on the original image based on a set environment perception type enhancement mechanism according to the judged field environment type, and outputting a global pre-processing image; constructing a backlight area segmentation model for the globally preprocessed image; outputting a local enhanced image; designing a structure perception type local adaptive threshold algorithm for the local enhanced image, and outputting a binary image keeping structural continuity; extracting an edge image of the binarized image through an edge detection algorithm, and optimizing a topological structure of a contour in the binarized image; and comparing with a wood template processing standard feature library, outputting an edge quality evaluation result and feeding back to a processing control system. Defect detection and machining control depth linkage is achieved, passive detection is changed into active optimization, and the production efficiency and the yield are improved.

The invention provides a PCBA circuit board defect detection method, apparatus and device, and a storage medium. The method comprises the steps of obtaining three-dimensional point cloud data of the surface of a circuit board by projecting multispectral composite structured light; performing feature fusion on the multi-modal image of the circuit board according to the three-dimensional point cloud data to generate a fused multi-channel feature map; performing non-rigid registration on the acoustic impedance distribution data and the three-dimensional point cloud data to generate an acousto-optic fusion defect probability distribution diagram; performing multi-scale edge detection on the fused multi-channel feature map to generate an optimized binary edge map; and performing scattering transformation on the optimized binary edge graph, and determining the defect type of the circuit board according to the acousto-optic fusion defect probability distribution graph. Through implementation of the scheme, non-rigid registration is performed by using the acoustic impedance distribution data and the three-dimensional point cloud data, the acousto-optic fusion defect probability distribution diagram is generated, the surface three-dimensional information and the internal acoustic impedance data are combined, internal hidden defects are effectively identified, and comprehensive detection of surface and internal defects is realized.

The invention discloses a method for identifying impurities and bubbles in a wine bottle based on multi-feature comprehensive judgment, and belongs to the technical field of image processing and computer vision, and the method comprises the steps: employing a high-resolution industrial camera to be combined with an LED light source, and continuously shooting multiple frames of images of the wine bottle under the consistent shooting angle and illumination condition; carrying out the preprocessing of the collected image through employing a self-adaptive histogram equalization and Gaussian blur method; extracting the edges of impurities and bubbles in the wine bottle on the image by adopting a Canny edge detection algorithm to obtain an edge image; segmenting the edge image into a plurality of target areas by using a contour detection technology, and extracting possible bubble and impurity areas from the edge image; extracting target area features including circularity, gray average, gray uniformity, texture features and color space; and according to the extracted features, bubbles and impurities are distinguished by applying a comprehensive judgment rule. According to the method, the bubbles and the impurities are comprehensively judged by adopting multi-feature combination, so that the accuracy and the robustness of detection are greatly improved.

The invention belongs to the technical field of computer vision, and relates to a dynamic scene online calibration method and system for three-dimensional target detection. The method comprises the following steps: firstly, acquiring a 3D point cloud around a vehicle, an initial external parameter and a synchronous image, and processing the 3D point cloud, the initial external parameter and the synchronous image by a bimodal static mask generation module to obtain a static region probability graph; calculating a multi-scale residual error of the image and the LiDAR edge image in a static region through a static region fusion module; a historical time sequence modeling module is used to generate time sequence fusion features; performing external parameter correction through a coarse-fine multi-stage external parameter correction module; and finally, according to the predicted external parameters, performing three-dimensional target detection through an image-point cloud bidirectional enhancement module in combination with Transform. Full-scene self-adaptive calibration is achieved, the invalid calibration rate is reduced by 67%, permanent deformation and temporary interference of the sensor can be effectively distinguished, the diagnosis accuracy rate reaches 92%, the false alarm rate is lower than 0.5%, and the three-dimensional target detection performance is improved.

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 discloses a traditional Chinese medicinal material condition feature extraction and classification processing method and system, and the method comprises the following operation steps: collecting a medicinal material image of gastrodia elata, and carrying out the preprocessing of the medicinal material image of gastrodia elata to obtain a to-be-detected medicinal material image; performing edge detection on the to-be-detected medicinal material image to extract contour information to obtain a to-be-detected edge image; and extracting multi-scale mildew features of the to-be-detected edge image, and identifying abnormal defects of the rhizoma gastrodiae medicinal material image through the multi-scale mildew features. According to the invention, multiple features are extracted from the abnormal region of the to-be-detected edge image, so that mildew can be judged, and missing detection can be prevented according to recognition of holes.

The invention relates to the field of image processing, in particular to an automobile part processing burr detection method, which comprises the following steps of: positioning an automobile part, acquiring an edge image to define an ROI (Region of Interest), performing sub-pixel extraction on an edge in the ROI, and performing multi-scale decomposition by applying discrete wavelet transform to obtain detail coefficients. The fractal dimension of the edge local contour is calculated, the expected detail energy of the edge local contour under the corresponding wavelet scale is deduced, then the adaptive threshold adjustment amount is obtained through calculation, the final local adaptive threshold is generated in combination with the basic threshold, and the threshold is used for judging the actual detail coefficient to accurately position burrs. And then carrying out feature quantification on the positioned burrs. And finally, comparing the quantized burr characteristics with a preset quality standard, judging whether the part is qualified or not, and outputting a result. According to the method, the wavelet threshold is adaptively adjusted by introducing fractal features, so that the accuracy and robustness of burr detection under different edge conditions are improved.

The invention discloses a welding spot defect detection method, electronic equipment and a storage medium. The mode relates to the field of image detection, and the method comprises the following steps: obtaining a to-be-detected image of a to-be-detected welding spot; edge detection is carried out on the to-be-detected image, a welding spot edge image of the to-be-detected welding spot is obtained, and the welding spot edge image is used for representing contour features of the to-be-detected welding spot in the image space; parameter extraction is conducted on the welding spot edge image, welding spot shape information of the to-be-detected welding spot is obtained, and the welding spot shape information is used for representing shape features of the to-be-detected welding spot in a parameter space; welding spot defect detection is conducted on the to-be-detected welding spot based on the welding spot shape information, a defect detection result is obtained, and the defect detection result is used for representing whether the to-be-detected welding spot has welding defects or not. According to the invention, the technical problem of low efficiency of detecting the welding spot defect in the prior art is solved.

The invention discloses a strain culture dish positioning method and system based on monocular vision. The positioning method comprises the following steps: acquiring an edge image of a culture dish by a monocular vision camera, and presetting a grabbing point in the edge image; the edge image and the template image are matched based on an improved SIFT algorithm, and two-dimensional coordinates of the grabbing points are obtained; acquiring depth information of the culture dish by a laser triangulation ranging method, and combining the depth information with the two-dimensional coordinates to form three-dimensional coordinates; according to the coordinate system conversion relation between the camera and the manipulator, the three-dimensional coordinates are converted into a manipulator coordinate system, and the manipulator is controlled to grab the culture dish at the grabbing point. The defect that a traditional monocular vision system is difficult to obtain depth information is overcome, the improved SIFT algorithm is used for matching images and obtaining two-dimensional coordinates, the depth information of the system is obtained in combination with a laser triangulation ranging method, and therefore three-dimensional coordinate information of a target is obtained, the detection efficiency and positioning precision of the monocular vision system are improved, and the detection precision of the monocular vision system is improved. The method has the characteristics of accuracy and rapidness.

The invention belongs to the technical field of image data processing, and particularly relates to a quality detection method and system for metal pipe fitting forming, and the method comprises the steps: obtaining a plurality of groups of matched gap regions of a port edge image according to the gray scale difference of the neighborhood of each gap of the port edge image in a corresponding metal pipe fitting image; obtaining a suspected defect area of the port edge image according to curvature change of edge pixel points of the port edge image; acquiring similar arc segments of each suspected defect area according to the change of the distance from the arc segment on the ellipse of the metal pipe edge image to the ellipse center; obtaining the abnormal degree of each suspected defect region according to the deformation difference between the suspected defect region and the similar arc section and the gray difference between the suspected defect region and the corresponding suspected defect region of the same group of matched gap regions; and screening to obtain a final defect area. According to the invention, the accuracy of quality forming detection of the metal pipe fitting is improved.

The invention relates to the technical field of mining area safety monitoring, in particular to a mining area settlement monitoring method and system based on image data, and the method comprises the steps: collecting a mine hole image in a mining area, and carrying out the edge detection of the mine hole image, and obtaining an edge image; high-definition images and to-be-enhanced images are screened out according to the definition degree of the edge images, and the definition degree reflects the pixel value and the position change degree of pixel points at the same position of two adjacent frames of edge images. According to the method, the supplementary coefficient of each pixel point is calculated by utilizing the characteristics between the high-definition image and the to-be-enhanced image, the to-be-enhanced image is enhanced, so that a complete mine hole edge can be obtained in the to-be-enhanced image, and finally, the time when the mine hole edge is abruptly changed is calculated. According to the difference value between the area of the mine hole edge at the sudden change moment and the area of the mine hole edge at the current moment and the change time, the settlement coefficient of the mine area can be accurately calculated so as to monitor the safety of the mine hole.

The invention provides a disaster site satellite communication blind area image acquisition and transmission method of a low-altitude unmanned aerial vehicle relay. The method comprises the following steps: acquiring disaster area information and executing adaptive multi-modal image acquisition; establishing a low-altitude unmanned aerial vehicle relay network; performing feature extraction and semantic analysis on the marked image data set, generating non-uniform image fragments and calculating a transmission priority; and monitoring a communication environment state, and dynamically adjusting a transmission strategy through a dual-cycle feedback mechanism. According to the method, semantic integrity is ensured, transmission window perception is realized, parameter adjustment is stabilized through a double-loop feedback mechanism, and the problem of efficient transmission of the satellite communication blind area edge image in a disaster site is solved.

The invention discloses an impregnated paper surface uniformity detection method based on texture image analysis, and particularly relates to the field of image enhancement and texture analysis, and the method comprises the steps: obtaining an impregnated paper image, constructing an edge image based on a gray difference value, extracting an image region with an edge value lower than a first threshold value in the edge image, and defining the image region as a fuzzy region; and edge value difference calculation between adjacent pixels is carried out on the fuzzy region to form a difference chart, and a pixel region with an edge change value greater than a second threshold value is extracted from the difference chart and is defined as a fracture region. According to the scheme, the weak boundary between the adhesive film and the fiber is extracted by recognizing the fuzzy region with the low edge value and tracking the direction path of the fuzzy region, the problem that the low-contrast edge cannot be recognized through a traditional method is solved, and the detection precision of the non-uniform region is improved.

A method for evaluating edge quality in an image includes receiving an image from a camera of a vehicle, detecting an edge in the image captured by the camera, fitting a polynomial curve to the edge in the image captured by the camera, executing a numerical optimizer to determine a minimum distance from each pixel in the image of the edge to the polynomial curve, determining a modulation transfer function (MTF) value using the minimum distance, determining whether the MTF value is greater than predetermined threshold, and providing an alert in response to determining that the MTF value is not greater than the predetermined threshold.

The invention discloses a broken rock granularity identification method based on machine vision. The method comprises the following steps: S1, obtaining a broken rock pile image in a quarry; s2, based on the lightweight edge segmentation model, combining a deformable convolution module fusing attention and an attention residual shrinkage unit, and replacing a maximum pooling layer with a cavity convolution layer to obtain an improved lightweight edge segmentation model; s3, segmenting the macadam pile image, and distinguishing macadam edges and backgrounds in the macadam pile image to obtain a macadam edge graph; s4, carrying out edge refinement on the broken stone edge graph by adopting a table look-up method, and carrying out area filtering by combining an area filter so as to refine edges and eliminate interference edges; and S5, carrying out macadam edge contour extraction on the macadam edge graph, calculating the area and perimeter of the macadam, and finally obtaining the granularity distribution condition of the macadam. According to the detection method, the calculation amount is remarkably reduced while high accuracy is kept.

The invention provides a deep learning fusion feature-based workpiece edge detection method. The method comprises the steps of obtaining a to-be-detected workpiece image; performing noise reduction processing on the to-be-detected workpiece image to obtain a noise-reduced image and a noise probability; inputting the noise reduction image and the noise probability into an edge enhancement model based on deep learning for identification, and obtaining an identified enhanced edge image and an edge probability; performing feature fusion on the noise probability and the edge probability by adopting a feature fusion algorithm based on machine learning, and converting a two-dimensional vector into a one-dimensional residual feature to form a residual vector; and inputting the enhanced edge image and the residual vector into an edge enhancement model based on deep learning for identification, carrying out clustering processing on the identified image, and outputting a target edge detection result and non-target features. The method can reduce the influence of irrelevant noise on target edge detection, and achieves the accurate recognition of the target edge.

The invention relates to the technical field of rock mass fracture recognition, in particular to a rock mass fracture recognition method based on a boundary detection neural network model. According to the method, an innovative deep learning framework is provided for boundary recognition, the characteristics of a refinement strategy and sub-pixel convolution are combined, and a leading result is obtained on a data set. The research shows that the CED model can improve the performance of middle-level and high-level visual tasks including optical flow estimation, target suggestion generation, semantic segmentation and the like. According to the method, a novel architecture is provided to solve the precision problem of a CED algorithm, a reverse refining path is supplemented for an HED network to improve the recognition precision, and the path uses efficient sub-pixel convolution to merge features step by step; the CED provided by the invention can generate an edge image which is well aligned with an image boundary.

The embodiments of the present disclosure disclose a method and apparatus for identifying a wafer edge defect type, a medium and a wafer processing method. The method for identifying a wafer edge defect type comprises: receiving a collected edge image of a wafer under test; according to image features of the edge image, determining an area to be identified having a defect; acquiring morphology features of the defect present in said area; and, according to the morphology features and features of said area, determining the type of the defect present in said area.

The invention discloses an image edge cutting method and device based on boundary detection, equipment and a storage medium, and relates to the technical field of image boundary detection, and the method comprises the steps: carrying out the preprocessing of an original image, and obtaining a target image; determining a scene type of the target image; based on an edge detection strategy corresponding to the scene type, performing edge detection on the target image to obtain an edge image; performing straight line detection on the edge image to obtain a plurality of candidate straight line segments; and based on a boundary positioning rule, determining a target boundary line segment from the plurality of candidate straight line segments, so as to carry out edge cutting on the original image according to the target boundary line segment. According to the invention, a more reliable image edge cutting effect can be generated.

The invention provides a contour information extraction method and device, and a storage medium. The method comprises the steps of obtaining a to-be-processed original image of a target object; performing edge detection on the original image to obtain an edge image of the target object; skeleton extraction is carried out on the edge image to obtain a morphological image of the target object, and the morphological image comprises skeleton information of the target object; and performing contour extraction on the morphological image according to the skeleton information to obtain contour information of the target object. According to the method, the morphological lines of the target object in the original image are enhanced before contour extraction, so that the contour extraction result is more accurate, and the precision of the contour extraction result is improved.

The invention relates to the technical field of flood prevention management, in particular to a hydraulic engineering system real-time scheduling method based on a neural network technology, and the method comprises the steps: obtaining the real-time data of a hydraulic engineering system at a fixed time interval; performing image recognition on the satellite cloud picture by adopting a CNN model to obtain a rain cloud region map and a rain cloud region edge map; edge roughness coefficients, internal density coefficients and rain cloud thickness coefficients of the rain cloud area map and the rain cloud area edge map are calculated, so that rainfall coefficients are obtained; analyzing the rain cloud area map at continuous time intervals by using an optical flow method, obtaining the moving speed and direction of the rain cloud and the shortest distance between the rain cloud and the water conservancy project area, and obtaining a rain cloud influence coefficient; predicting the future water level of the reservoir by using a deep learning model, and calculating a vulnerability coefficient according to the flood control data; the flood control coefficient is calculated according to the rainfall coefficient, the rain cloud influence coefficient and the vulnerability coefficient, and the flood control regulation and control model is constructed, so that the flexibility of real-time scheduling of the hydraulic engineering system is effectively improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an image segmentation method, device, equipment and medium based on multi-channel edge superposition. Only the mask decoder and the expansion module are updated; obtaining a target image and prompt information, and obtaining an initial mask image; generating a multi-channel edge image set, and superposing the multi-channel edge image set with the target image and the initial mask image channel to form a multi-channel input image; and processing by a gating convolution unit, a channel compression convolution layer and a multi-stage attention decoder to generate an enhanced mask image, and outputting a target segmentation result. According to the invention, the training overhead is reduced through the frozen image encoder and the prompt encoder, and the capability of capturing boundaries and details is enhanced by using the extension module and the attention decoder, so that the definition and accuracy of a segmentation result are improved.

The embodiment of the invention provides a system and method for detecting the angle of a wafer positioning groove, and the system comprises a wafer box, the side surface of which is provided with a side surface opening used for the incoming and outgoing of a wafer; the wafer slot is positioned in the wafer box and is used for accommodating a wafer; the plurality of infrared scanning devices are coupled to the inner wall of the wafer box so as to scan and transmit edge surface information of the wafer; and the processing module is used for generating a wafer edge image based on the edge surface information, responding to a wafer positioning groove contained in the wafer edge image, and determining the angle of the wafer positioning groove. By adopting the technical scheme, the problems of time waste and low accuracy of obtaining the angle of the positioning groove before the wafer enters the machine table can be solved.

The invention provides an ear-nose-throat department intelligent diagnosis and monitoring system based on multi-modal data fusion, and relates to the technical field of multi-modal data fusion. Multi-modal monitoring data is acquired, and an endoscope monitoring image of a patient is extracted; performing edge monitoring on the endoscope monitoring image to obtain an endoscope monitoring edge image, generating a secretion disturbance mask according to the endoscope monitoring edge image, and determining an endoscope monitoring restoration image according to the secretion disturbance mask and the endoscope monitoring image; determining a pixel decision window of each pixel point in the endoscope monitoring restored image, and performing information decision based on the corresponding pixel decision window to obtain an endoscope monitoring decision image; and extracting monitoring text data, and performing feature fusion on the monitoring text data and the endoscope monitoring decision image to generate a fusion association map. According to the method, the image quality of the endoscope monitoring image can be improved, and the correlation map of the patient is generated in combination with the monitoring text, so that knowledge fusion in ear-nose-throat monitoring is realized.

The invention relates to the technical field of image data processing, in particular to an endoscope image intelligent optimization method and system. The method comprises the following steps: acquiring a grayscale image of an endoscope image of a stomach, acquiring an edge image of the grayscale image, and performing region growth on pixel points with gradient values greater than a preset gradient in the edge image to obtain a plurality of first connected domains; according to the area of the minimum enclosing rectangle of the first connected domain and the number of edge pixel points, determining a suspected lesion area in the grayscale image, and taking the minimum grayscale value in the suspected lesion area as an initial segmentation threshold value; and gradually increasing the segmentation threshold value from the initial segmentation threshold value, segmenting the suspected lesion area to obtain a plurality of binary images, and determining a target lesion area according to the difference degree of newly added pixel points between the adjacent binary images in discreteness characteristics. By means of the technical scheme, the accurate focus area in the endoscope image of the stomach can be obtained.

The invention provides an ore image segmentation optimization method and system based on edge detection, and relates to the technical field of image processing, and the method comprises the steps: obtaining an ore particle image with to-be-detected ore; preprocessing the ore particle image; extracting an edge image of the preprocessed ore particle image through a Canny edge detection algorithm with an adaptive threshold; in combination with the ore particle image, segmenting the edge image through a pre-trained SAM model to obtain a segmentation mask marking the boundary of the edge image; inputting the ore particle image and the segmentation mask into a CRF model, and optimizing the segmentation mask by taking minimization of an energy function value in the CRF model as a target to obtain an optimized segmentation mask; carrying out area filtering based on an area threshold value on the optimized segmentation mask, and reserving a target area representing the to-be-detected ore in the ore particle image; and outputting the target region as a segmentation result of the ore particle image.

The embodiment of the invention provides an edge detection method and device based on gradient weighted fusion and an adaptive threshold, and is applied to the field of computer vision and digital image processing. The method comprises the steps of firstly preprocessing an input image, then extracting two groups of gradient magnitude diagrams and directional diagrams through an adaptive morphological operator and a traditional difference operator, and constructing a weighted fusion function according to the gradient direction consistency of each pixel point to obtain a fused gradient magnitude diagram; and adaptively determining a high threshold and a low threshold based on an information entropy maximization principle, executing an improved Canny process by combining the fused gradient magnitude diagram and the second gradient directional diagram to obtain an initial edge diagram, and outputting a final edge detection result after dynamic structure element optimization. In this way, the defects that in a traditional edge detection method, gradient information extraction is not precise, threshold selection lacks adaptability, and an edge result is fractured can be overcome, more robust and more accurate image edge detection is achieved, and the reliability of an edge detection algorithm in a complex image scene is improved.

The invention discloses an intelligent PET base cloth cutting control system, and relates to the technical field of material cutting. By means of dynamic signal collection, frequency decoupling, edge image recognition and self-adaptive control, full-process intelligent regulation and control of the PET base cloth cutting process are achieved, vibration marks are accurately restrained, the edge quality is optimized, the cutting precision and the product consistency are remarkably improved, and the method is suitable for high-end application such as optics and electricity and has wide application prospects.

The invention provides a multi-modal alignment and cross-scale structure attention-based remote sensing image building extraction method, which comprises the following steps of: performing radiation correction and geometric correction on an original hyperspectral satellite image, and performing voxelization, normalization and registration with a hyperspectral corrected image on LiDAR point cloud data to respectively obtain the hyperspectral corrected image and LiDAR corrected data; deep features of the two types of correction data are extracted through a special encoder, and after dimension unification and channel attention screening, fusion features are obtained through fusion of a weighting and gating mechanism; multi-scale features are extracted from the fusion features through multi-receptive field convolution branch, and cross-scale enhancement features are obtained by combining cross attention and geometric modeling; a prediction edge graph is generated based on cross-scale enhancement features, high-resolution guide features are combined to compensate tiny building information, and the extraction precision is improved through edge loss optimization; and carrying out denoising, edge repairing and adhesion separation on the optimized result to obtain a final building extraction result.