28 results about "Contour segment" patented technology

The invention belongs to the field of image processing, and provides a satellite and low-altitude unmanned aerial vehicle remote sensing data fusion method, which comprises the following steps: extracting linear ground feature contour information from a satellite remote sensing image of a target area, and dividing a linear ground feature contour into a plurality of contour segments; extracting real-time linear ground feature contour information from the unmanned aerial vehicle remote sensing image of the target area, and dividing the real-time linear ground feature contour into a plurality of contour segments with the same structural form as the satellite remote sensing image; performing corresponding matching on linear ground feature contour segments in the satellite remote sensing image and the unmanned aerial vehicle remote sensing image, and constructing a stable contour segment pair; carrying out geometric registration processing on stable regions in the satellite remote sensing image and the unmanned aerial vehicle remote sensing image; and adjusting the observation angle of the unmanned aerial vehicle image in the changed area based on the relative spatial relationship between the flight path of the unmanned aerial vehicle and the linear ground feature, and fusing the image after angle adjustment and the satellite remote sensing image.

The invention discloses a method and system for detecting the maximum crack width of a building structure based on machine vision, and relates to the technical field of image processing.The method comprises the steps that a surface image of the building structure is obtained through image acquisition equipment, a binary image corresponding to the surface image is constructed, and the crack contour of the building structure is extracted according to the binary image; the method comprises the steps that firstly, a crack contour is divided into a plurality of contour sections, crack width value calculation is conducted on each contour section, finally, the crack width values of all the contour sections are compared, the maximum crack width of the building structure crack is determined, and measurement and positioning of the maximum crack width are achieved. Systematic errors are reduced, high robustness is achieved, and the maximum crack width of the building structure can be rapidly and accurately measured.

The invention relates to a robot drawing method, device and equipment and a storage medium, and is applied to the field of robot control. Contour extraction processing and skeleton extraction processing are carried out on the original image, a contour image is generated, the contour image comprises a plurality of contour segments, and each contour segment comprises a plurality of contour points; a Douglas-Peucker algorithm is adopted to simplify the number of contour points of each contour segment in the contour image, and a contour optimization image is generated; converting the image coordinate system of the contour optimization image into an actual coordinate system of preset paper according to the size of the preset paper; according to a contour screening threshold value, screening an optimized contour section in the contour optimization image, and according to the optimized contour section, generating a contour secondary optimization image; and controlling the robot to finish drawing in the actual coordinate system according to the outline secondary optimization image and preset drawing parameters. The method has the technical effects that the drawing precision is guaranteed while the drawing efficiency of the robot is improved.

The invention provides a point cloud building contour line extraction method based on context geometric global optimization, and relates to the technical field of airborne laser radar data processing, and the method comprises the steps: obtaining airborne laser radar point cloud data; processing the point cloud data by using a progressive triangulation network encryption filtering algorithm, and separating the point cloud data into ground points and non-ground points; obtaining an initial seed point, and extracting a building point; an Alpha Shapes algorithm is adopted to process the building points to obtain building contour points; combining the contour point groups to obtain building contour line segments; constructing an undirected weight map, segmenting the undirected weight map, and distributing a direction angle for each contour line segment; and generating a final building contour line according to the adjusted contour line segment. According to the invention, the collected airborne laser radar point cloud data of the building area is processed in a data driving mode to extract the building contour line, so that subsequent various applications based on the building contour line are facilitated.

The invention relates to the technical field of medical image processing, in particular to an acupuncture guide system based on image registration. According to the method, the height parameter field of the human body surface three-dimensional model is established and the contour line density distribution is extracted, so that hierarchical division and density aggregation identification of morphological characteristics of a target area can be realized, and local geometric characteristic identification is carried out by carrying out tangential analysis on direction changes of continuous contour line segments and combining Gaussian curvature. According to the method, geometric abnormal point locations of the surface structure can be accurately calibrated, and an area with direction stability and geometric continuity can be discriminated in multi-point data in combination with a space consistency judgment mechanism in the normal direction, so that the space identification process is more robust, and the accuracy of the space identification is improved. Multi-feature re-check judgment of a fitting end point can be realized through density peak value and normal consistency dual screening, the spatial accuracy of a positioning point is guaranteed, and the consistency of structural continuity and visual guidance information can be considered through a path construction mode generated by combining an image registration result and image gradient information.

The invention relates to an optimization method (10) for adapting processing parameters (12) in a laser processing method for processing at least one workpiece (16; 16a-h) with a laser processing machine (14), comprising the method steps: f) providing (18) at least one workpiece contour (20; 20a-k) of the workpiece (16; 16a-h) to be manufactured; g) segmenting (26) the workpiece contour (20; 20a-k) by dividing the at least one workpiece contour (20; 20a-k) into contour segments (28; 28a-h); h) determining (30) at least one monitoring segment (32; 32a-e) in the workpiece contour (20; 20a-k) from the contour segments (28; 28a-h); i) determining (40) predetermined optimal processing parameters (38; 38a-d) for the monitoring segment (32; 32a-e) by comparing the monitoring segment (32; 32a-e) with stored reference segments (36; 36a-d); j) Outputting (42) the determined optimal machining parameters (38; 38a-d). The invention also relates to an optimization system (46) and a laser processing system (44).

The present disclosure provides a method for determining shared contours of adjacent objects in an image, a method for annotating contours, and an apparatus. The method for determining shared contours of adjacent objects includes obtaining position information of a first annotation point and a second annotation point in an already annotated contour, intercepting a contour segment from the already annotated contour as a shared contour with a contour to be annotated currently, so as to keep the contour annotations of adjacent objects in the image closely aligned through contour sharing.

The present invention relates to the technical field of text recognition, and in particular to a character recognition method based on character contours, comprising: S1: extracting multiple contour components of a character to be recognized and generating an overall identification code; S2: using a character recognition library and an overall identification code to recognize the character to be recognized, and judging whether the character to be recognized can be recognized; if not, turning to S3; S3: segmenting the character to be recognized, and extracting contour components of each contour segment after segmentation to generate a local identification code; S4: using a character recognition library and a local identification code to recognize the character to be recognized. The beneficial effect of the present invention is that by obtaining the contour components of the character and generating an identification code according to the shape change of the character contour, an effective representation of the character contour shape is achieved, so that a relatively accurate match can be performed according to the character recognition library, and the same recognition effect can be achieved for tilted, rotated, and stretched fonts, which is convenient for recognizing various paper documents.

The present invention belongs to the field of image processing and provides a method for fusing satellite and low-altitude unmanned aerial vehicle remote sensing data. The method comprises the following steps: extracting linear object contour information from a satellite remote sensing image of a target area and dividing the linear object contour into a plurality of contour segments; extracting real-time linear object contour information from the unmanned aerial vehicle remote sensing image of the target area and dividing the real-time linear object contour into a plurality of contour segments with the same structural form as in the satellite remote sensing image; performing corresponding matching on the linear object contour segments in the satellite remote sensing image and the unmanned aerial vehicle remote sensing image to construct a stable contour segment pair; performing geometric registration processing on the satellite remote sensing image and the stable area in the unmanned aerial vehicle remote sensing image; adjusting the observation angle of the unmanned aerial vehicle image in the changed area based on the relative spatial relationship between the unmanned aerial vehicle flight trajectory and the linear object, and fusing the image after the angle adjustment with the satellite remote sensing image.

The application provides a tumor radiotherapy multi-modal image fusion method and system, which extracts an initial target region contour of a tumor and a set of all high metabolic voxels; determines the shortest spatial distance from each voxel in the set of high metabolic voxels to all contour points on the initial target region contour, and then generates a distance statistical histogram; identifies a far-end distance point cluster that is significantly separated from a main distribution cluster, separates a corresponding spatial outlier voxel cluster from the set of high metabolic voxels; on the initial target region contour, determines continuous contour points closest to the spatial outlier voxel cluster as a to-be-corrected contour segment; determines a displacement vector of each point on the to-be-corrected contour segment to the spatial outlier voxel cluster, adjusts the spatial position of the to-be-corrected contour segment according to the displacement vector, and obtains an optimized target region contour of the tumor. The scheme of the application can avoid definition distortion of the target region contour caused by main noise interference.

The invention relates to the technical field of contour recognition, in particular to a fast contour recognition method under a complex background, and the method comprises the steps: carrying out the contour recognition training under the complex background through employing a sample image, and collecting contour attribute data, so as to determine a plurality of first clear contour segments; determining a standard contour frame based on the performance parameters of the plurality of first clear contour segments; collecting contour attribute data of the image of the target detection area, and determining a plurality of second clear contour segments so as to determine a plurality of contour matching segments; determining whether to trigger quick matching or not based on the proportion of the contour matching section; determining the adjustment amount of the contour recognition optimization parameter based on the plurality of second clear contour segments; and processing the image of the target detection area by using the adjusted contour recognition optimization parameters, and obtaining a plurality of second clear contour segments again to determine whether to trigger rapid matching. According to the invention, the efficiency and accuracy of rapid contour recognition under a complex background are improved.

The invention relates to the technical field of image processing, in particular to an aluminum alloy pipe compression molding defect classification method. The method comprises the steps of obtaining a front surface image of a to-be-detected aluminum alloy shell obtained by performing extrusion treatment on an aluminum alloy pipe, and obtaining a first outer contour of the front surface image; determining a mass center of an outer contour pixel point of the first outer contour, and respectively determining central moments of different outer contour segments of the first outer contour relative to the mass center of the first outer contour; constructing a first feature sequence according to the central moments of different outer contour segments of the first outer contour, and obtaining a second feature sequence of the standard aluminum alloy shell; performing shift matching on the first feature sequence and the second feature sequence, and determining a contour defect value according to a DTW distance of a shift matching result; and classifying shape defects according to the contour defect values. By means of the technical scheme, classification of shape defects of the aluminum alloy shell made of the aluminum alloy pipe can be achieved.

The invention discloses a two-stage multimode image matching method based on information entropy, and belongs to the field of image processing. The method comprises the following steps: filtering an image, and converting the image into a corresponding high-frequency enhanced image; contour detection is carried out on the two images, salient angular points on contours are extracted to serve as feature points, and the main direction of each feature point is determined; constructing a PIIFD descriptor for each feature point in the two images; entropy values of contour segments near the feature points are calculated and summarized, comprehensive information entropy of the feature points is obtained, and descriptors are classified based on the comprehensive information entropy; and calculating and comparing the similarity of each pair of feature points in the two images to realize feature matching, and removing abnormal matching point pairs. In practical application, the method not only can extract structural information, but also can reduce the influence of illumination variation on matching. The information entropy focuses on the texture and edge information of the region and does not depend on the pixel value, so that the matching accuracy and robustness can be kept in an environment with relatively large illumination variation.

The present application relates to the technical field of contour recognition, and particularly relates to a fast contour recognition method in a complex background, contour recognition training in the complex background is performed using sample images, contour attribute data is collected to determine a plurality of first clear contour segments; a standard contour frame is determined based on performance parameters of the plurality of first clear contour segments; contour attribute data of an image of a target detection region is collected, a plurality of second clear contour segments are determined to determine a plurality of contour matching segments; whether to trigger fast matching is determined based on a proportion of the contour matching segments; an adjustment amount of contour recognition optimization parameters is determined based on the plurality of second clear contour segments; the image of the target detection region is processed using the adjusted contour recognition optimization parameters, the plurality of second clear contour segments are reacquired to determine whether to trigger fast matching. The present application improves the efficiency and accuracy of fast contour recognition in a complex background.

Embodiments of the present application provide a bolt size measurement method and device, electronic equipment and storage medium. The method comprises calibrating a camera for shooting a bolt; acquiring an image of the bolt shot by the camera, and identifying a thread edge contour area of the bolt from the image; performing feature extraction on the thread edge contour area to obtain a thread contour of the bolt; segmenting the thread contour by using an improved adaptive DP algorithm to obtain a plurality of contour segments; fitting the contour segments by using a Hough transform to obtain a smooth thread contour; detecting an angular point of the curvature corresponding to the smooth thread contour based on an optimized FRPD algorithm; and fitting the angular point by using a least square method transformation to calculate the size of a major diameter and a minor diameter of the thread of the bolt. Based on this, the bolt size measurement method of the embodiments of the present application has high measurement accuracy, accuracy and real-time performance, and can be used for detecting the size of bolt parts in the field of mechanical equipment manufacturing.

The invention provides a graph modeling method and device, a storage medium and computer equipment, and the method comprises the steps: carrying out the feature coding of each contour segment corresponding to a contour curve in a photoetching layout through a first neural network, and obtaining a segment structure feature vector corresponding to each contour segment; obtaining each arc length position parameter corresponding to the contour section; the arc length position parameter is used for indicating the corresponding arc length percentage of each sampling point in the contour section in the contour section; generating a sampling position vector corresponding to each sampling point by using a second neural network according to the arc length position parameter; determining a target coordinate corresponding to each sampling point in the contour segment by using a third neural network according to the segment structure feature vector and each sampling position vector; and according to each target coordinate corresponding to each contour section, determining a modeled curve corresponding to the contour curve.

This invention discloses a method for extracting human contour boundaries in complex scenes based on deep learning, comprising: acquiring the original scene image; processing it using a feature extraction model to obtain a multi-scale feature map, a coarse human contour probability map, and human skeletal information; performing topological analysis based on the feature map and probability map to obtain the contour segments to which limbs belong and occlusion sequence information; performing feature re-aggregation on the concave corner regions in combination with the skeletal information to obtain the concave corner recovery contour segment; inferring the geometric information of the occlusion break endpoints based on the contour segment and obtaining the endpoint geometric constraint parameters; and finally stitching together the above parameters and occlusion sequence information to output a human contour boundary map. This invention overcomes the problems of topological confusion and local geometric blunting under severe occlusion and pose overlap, and achieves human boundary reconstruction with high fidelity.

A computing device including one or more processing devices configured to receive raster data including raster data values. The processing devices obtain classifier grid data including classification values selected from among two or more classes. The processing devices generate a contour map by, for each of the classes, generating contour segments connecting pairs of grid locations included in the raster data. Generating the contour segments includes computing respective topological cases of cells of a superimposed grid, which includes cells of the raster data that are associated with respective classification values. Generating the contour segments further includes computing respective classifier cases of the cells. The contour segments are computed based on the topological cases and classifier cases of the cells and are combined into contours. The contour map is computed as a visual representation of the contours. The processing devices output the contour map for display at a display device.

The embodiment of the invention relates to a measurement method and device and a storage medium. The method provided herein comprises: in an image having a measurement object, determining a reference start point and a reference end point for a first contour segment associated with the measurement object; determining a target path connected between the reference start point and the reference end point based on respective confidence levels of a plurality of pixels located between the reference start point and the reference end point in the image, where a confidence level of a pixel of the plurality of pixels indicates a likelihood of taking the pixel as part of the first contour segment; and determining a measurement result for the measurement object by measuring a second contour segment associated with the measurement object and a first contour segment generated based on the target path.

The invention relates to a computing device and a method for use with the computing device. A computing device includes one or more processing devices configured to receive raster data including raster data values. The processing device obtains classifier grid data including classification values selected from two or more categories. The processing device generates a contour map by generating, for each category, contour segments connecting pairs of grid positions included in the raster data. Generating the isoline segments includes calculating respective topological conditions for cells of an overlay grid including cells of raster data associated with respective classification values. Generating the isoline segments also includes calculating respective classifier conditions for the cells. The isoline segments are calculated based on topology conditions and classifier conditions of the cells, and are combined into isolines. A contour map is calculated as a visual representation of contour lines. The processing device outputs the contour map for display at the display device.

The present application relates to the field of contour recognition technology, and specifically provides a method, device, storage medium and electronic device for contour tracking. The method may include: identifying each pixel point in the image pixels to determine the pixel type and the current cluster number of each pixel point; generating a set storing all contour segments based on the pixel type and the current cluster number of each pixel point; the set storing all contour segments includes: contour segment sets of at least one object; the contour segment set of each object includes a first subset and a second subset; merging the contour segments included in each object according to the contour segment set of each object to obtain a complete contour and the final cluster number of each pixel point in the complete contour. Some embodiments of the present application can improve the accuracy and efficiency of object contour tracking.

The application relates to the technical field of wafer defect measurement, and specifically discloses a wafer edge collapse size measurement method and device, a storage medium and computer equipment, the method comprising the following steps: obtaining a wafer image to be detected, detecting an edge collapse region of the wafer image to be detected, outputting an edge collapse defect region, and detecting a wafer region of the wafer image to be detected, and outputting a wafer contour; extracting a local contour segment corresponding to the edge collapse defect region from the wafer contour; determining a reference line based on a straight line where the local contour segment is located, measuring a maximum width in the edge collapse defect region and parallel to the reference line as a defect width along the wafer edge direction, and measuring a maximum depth in the edge collapse defect region and perpendicular to the reference line as a defect depth along the wafer radial direction. The application strictly aligns the measurement reference with the physical definition of manual wafer edge measurement through the local contour segment, aligns the automatic detection result with the rechecking result of the quality inspection personnel, and avoids systematic deviation caused by inconsistent measurement directions.

This application provides a method, apparatus, storage medium, and computer device for calibrating capacitive sensor signals. The method includes acquiring a first distance between a preset calibration position and the processed area of ​​each processed contour segment, and a second distance between the position and the workpiece edge. If the first distance is greater than or equal to a preset safety distance, and the second distance is greater than or equal to the preset safety distance, a real-time calibration mark P is marked at the preset calibration position. Timing is then performed on the nth processed contour segment. It is then determined whether the nth processed contour segment is complete. If so, the timing time T is compared with a preset detection interval B. If T ≥ B, it is determined whether the (n+1)th processed contour segment has a real-time calibration mark P. If the (n+1)th processed contour segment has a real-time calibration mark P, calibration is performed at the preset calibration position of the (n+1)th processed contour segment. The capacitive sensor signal calibration method provided by this application can achieve accurate calibration of capacitive sensor signals.

This application proposes an intelligent extraction and structured transformation method for holographic features of open-pit mine slopes, belonging to the field of intelligent slope feature technology. The method includes: establishing a color-coded parameter mapping model; assigning corresponding color attributes to each layer according to the parameter mapping model to generate a parsable digital slope file; extracting the slope's geometric shape from the digital slope file and calculating the bounding box of the slope region; performing meshing processing on the bounding box of the slope region, converting the data in the meshed bounding box into fixed-size three-dimensional mesh data; identifying the external contour line of the slope using a contour extraction algorithm based on the fixed-size three-dimensional mesh data; calculating the local dip angle of each contour segment based on the coordinates of adjacent points in the discrete surface point set; and performing semantic segmentation along the external contour line of the slope based on the local dip angle of each contour segment. This method solves the problem that slope features are difficult for computers to efficiently identify and use for deep learning.

The present invention discloses a method and system for detecting the maximum crack width of a building structure based on machine vision, which relates to the field of image processing technology. The method obtains a surface image of a building structure through an image acquisition device, constructs a binary image corresponding to the surface image, and extracts the crack contour of the building structure based on the binary image. The crack contour is then divided into multiple contour segments, a crack width value is calculated for each contour segment, and finally the crack width value of each contour segment is compared to determine the maximum crack width of the crack in the building structure, thereby achieving measurement and positioning of the maximum crack width. This embodiment can make the crack measurement direction consistent with the actual physical direction, reduce systematic errors, have high robustness, and can quickly and accurately measure the maximum crack width of the building structure.

The invention discloses a point cloud space geometry restoration method and device, electronic equipment and a storage medium. The method comprises the following steps: scanning and collecting two-dimensional point cloud data and a contour set along a sample contour through a sensor; wherein the point cloud data comprises a plurality of uncalibrated initial point clouds, and the contour set comprises a plurality of contour segments; segmenting the point cloud data according to the plurality of contour segments to obtain a plurality of point cloud units; performing two-dimensional gridding and sub-pixel interpolation on the point cloud unit, and raising the dimension of the interpolated point cloud unit to a three-dimensional space; calculating a bending rule of the contour set, and performing bending transformation on the plurality of interpolated point cloud units in the three-dimensional space according to the bending rule of the contour set, so that the bending rule of the plurality of transformed point cloud units is consistent with the bending rule of the contour set; and splicing the plurality of transformed point cloud units into a complete geometric restoration point cloud. According to the method, point cloud space geometry restoration is realized on the premise that calibration cannot be implemented.

The application relates to the technical field of image processing, in particular to an aluminum alloy pipe compression molding defect classification method. The method comprises the following steps: obtaining a front surface image of an aluminum alloy shell to be detected obtained by extruding an aluminum alloy pipe, and obtaining a first outer contour of the front surface image; determining the center of mass of outer contour pixels of the first outer contour, and respectively determining the central moments of different outer contour segments of the first outer contour relative to the center of mass of the first outer contour; constructing a first feature sequence according to the central moments of the different outer contour segments of the first outer contour, and obtaining a second feature sequence of a standard aluminum alloy shell; performing shift matching on the first feature sequence and the second feature sequence, and determining an outline defect value according to a DTW distance of a shift matching result; and classifying shape defects according to the outline defect value. Through the above technical scheme, the classification of shape defects of an aluminum alloy shell manufactured from an aluminum alloy pipe can be realized.

This invention relates to a method for collaborative simplification of roads and settlements, belonging to the field of digital mapping technology. The invention first uses Delaunay triangulation to extract the contour segments of adjacent settlements and the corresponding road segments. Then, it performs node matching on the extracted settlement contour segments and their corresponding road segments. Finally, it simplifies roads using constraint points, synchronizing the node selection of roads to the corresponding settlement contours based on the node matching results, thus achieving collaborative simplification. This invention establishes node-level associations between roads and settlements in adjacent areas through node matching, synchronizing the node selection of roads to the adjacent settlement contours, thereby achieving collaborative simplification. Compared to traditional road and settlement simplification methods, this invention effectively maintains the shape similarity and topological consistency between features, significantly reducing topological and shape conflicts.