CN113487640A - Point cloud projection-based algorithm for extracting three-dimensional glue spraying track of shoe mold through variable intercept contour deviation - Google Patents
Point cloud projection-based algorithm for extracting three-dimensional glue spraying track of shoe mold through variable intercept contour deviation Download PDFInfo
- Publication number
- CN113487640A CN113487640A CN202110858575.7A CN202110858575A CN113487640A CN 113487640 A CN113487640 A CN 113487640A CN 202110858575 A CN202110858575 A CN 202110858575A CN 113487640 A CN113487640 A CN 113487640A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- shoe mold
- point
- algorithm
- contour
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003292 glue Substances 0.000 title claims abstract description 47
- 238000005507 spraying Methods 0.000 title claims abstract description 47
- 238000001914 filtration Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000009467 reduction Effects 0.000 claims abstract description 4
- 230000005484 gravity Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 238000013519 translation Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 9
- 230000006872 improvement Effects 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000007246 mechanism Effects 0.000 abstract description 4
- 230000008859 change Effects 0.000 abstract description 2
- 239000007921 spray Substances 0.000 abstract 1
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Footwear And Its Accessory, Manufacturing Method And Apparatuses (AREA)
Abstract
The invention adopts the algorithm of extracting the three-dimensional glue spraying track of the shoe mold based on point cloud projection variable intercept contour deviation, and solves the limitation that the modes of manual glue spraying, control of an execution mechanism for processing in a teaching and off-line programming mode and the like in the shoe mold glue spraying process in the shoe manufacturing industry cannot adapt to the change of the processing working condition in time. According to the invention, the point cloud characteristics obtained by linear structured light scanning of the shoe mold are utilized, the point cloud is preprocessed by using direct connection, statistics and grid filtering, the point cloud outline of the plane shoe mold is obtained by data dimension reduction, the accurate shoe mold glue spraying track is obtained by using a variable intercept outline offset algorithm and B spline fitting, the intelligent processing of the shoe mold can be effectively carried out by a three-dimensional guiding processing technology, and the method is a great improvement on the shoe mold glue spraying process. The variable intercept contour offset algorithm is not only suitable for shoe mold spray, but also suitable for acquiring other complex curved surface three-dimensional tracks.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to an algorithm for extracting a three-dimensional glue spraying track of a shoe mold based on point cloud projection variable intercept contour deviation.
Background
In recent years, the shoe making industry in China is rapidly developed and becomes the biggest shoe manufacturing base and export base in the world. But nowadays, the shoe making industry in China still depends on a large amount of cheap labor force to maintain production, the production industry is large and weak, automation and intellectualization are lacked, enterprises urgently need to change the existing mode in fierce market competition at home and abroad, and the enterprises strive to adopt machinery to replace manual simple and repeated labor to realize the intellectualization of shoe production. With the rapid development of science and technology in China in recent years, the technologies of machine vision, three-dimensional reconstruction, deep learning, intelligent production equipment and the like are mature day by day, so that the shoe making industry can advance to the field of intelligent manufacturing, and the problem of uneven glue spraying and spraying process quality of a shoe mold in the manual production process and the harm of adhesive to a human body in the glue spraying process can be effectively solved by adopting automatic machine production to replace manual work. The machine replaces the manual work and can also control glued membrane thickness and spraying area effectively, can guarantee the homogeneity of the homogeneity and the uniformity of thickness of glued membrane, improves sticky quality to and the aesthetic property of shoe mold. In addition, because the traditional teaching and off-line programming mode controls the execution mechanism to process and other modes, once the working environment or the target product workpiece changes, the robot cannot adapt to the changes in time, and the operation such as glue spraying can fail; therefore, in many industrial production environments such as shoe mold glue spraying, an industrial robot is required to have eyes similar to a human, and to perform higher-level intelligent functions such as recognition, analysis, processing and the like in the working process. At present, a guide processing technology taking machine vision as a core is gradually becoming a core technology of modern intelligent manufacturing; therefore, the invention provides a brand-new algorithm for extracting the shoe mold three-dimensional glue spraying track based on point cloud projection variable intercept contour deviation on the basis of a traditional teaching and off-line programming mode control actuating mechanism for processing, and the shoe mold glue spraying track is obtained in real time through the algorithm for guiding and processing the robot.
Disclosure of Invention
The invention provides an algorithm for extracting a three-dimensional glue spraying track of a shoe mold based on point cloud projection variable intercept contour deviation; the three-dimensional track extraction algorithm is not only suitable for obtaining the glue spraying track of the shoe mold, but also suitable for extracting the tracks of other complex curved surface products.
The invention provides an algorithm for extracting a three-dimensional glue spraying track of a shoe mold based on point cloud projection variable intercept contour deviation, which comprises the following steps of:
s1, shoe mold point cloud preprocessing, namely, acquiring shoe mold point cloud data by using line structured light and carrying out a series of point cloud preprocessing operations in a reverse direction;
s2, performing dimensionality reduction processing on shoe mold point cloud data, projecting the preprocessed point cloud onto an XOY plane, obtaining the main direction of the point cloud by using a PCA algorithm, and establishing a coordinate system;
s3, extracting the outline by a convex hull algorithm, and applying the convex hull algorithm to the extraction of the point cloud edge outline of the projection shoe mold;
s4, projection contour variable intercept offset, obtaining an offset point by a two-dimensional point cloud gravity center C and a midpoint P, and carrying out point cloud offset according to different offset areas of the shoe mold to obtain a point cloud contour of the shoe mold sprayed with glue;
s5, fitting the offset contour by a B spline curve, solving the problems of local overlapping and local sparsity of contour points obtained by a variable intercept offset algorithm, and obtaining the glue spraying track of the shoe mold by fitting the B spline curve.
In a further improvement, the step S1 specifically includes:
the pretreatment of the shoe mold point cloud comprises height direction direct filtering treatment, statistical filtering and outlier removing treatment and voxel grid filtering simplified point cloud treatment;
the height direction direct filtering processing is an algorithm for removing plane support by using a height direction direct filtering method, by taking the thought of foreground and background separation in image processing as reference, shoe mold point cloud data of a target is segmented in a point cloud height direction histogram according to the selection of a threshold value, and background and partial interference point clouds are removed;
the statistical filtering for removing outliers is realized by judging the distances between statistical points and all adjacent points thereof through a statistical filtering algorithm, if the obtained statistical average distance exceeds a standard range, the outliers are determined, and if a space point p and n adjacent points in the field thereof are assumed, the outlier determination formula is as follows:
the voxel grid filtering simplified point cloud utilizes a point cloud simplification algorithm, the point cloud simplification algorithm can simplify the number of point clouds on the premise of ensuring point cloud characteristic information, the voxel grid filtering is to divide a minimum cube grid in a constructed point cloud three-dimensional voxel grid, and other points are replaced by the closest point of the gravity center of the minimum cube grid, so that point cloud simplification is realized.
In a further improvement, the step S2 specifically further includes:
the point cloud data is essentially a set of three-dimensional spatial points, the points are represented as P (x0, y0, z0), and the preprocessed point cloud is projected onto an XOY plane to obtain a plane point cloud; and obtaining the main direction of the projected plane point cloud by using a PCA algorithm and establishing a coordinate system.
In a further improvement, the step S3 specifically includes:
the convex hull algorithm is applied to the extraction of the projection shoe mold point cloud edge contour, namely, the minimum point of a y coordinate in the plane point cloud is set as p1, if a plurality of minimum points of the y coordinate exist, the minimum point of an x coordinate is set as p1, coordinates of other points in the point set are transformed, so that p1 becomes the coordinate origin of the plane point cloud, the origin is connected with other points by line segments, an included angle between the line segments and the horizontal coordinate is calculated, an included angle sequence is obtained, dictionary type classification sorting is carried out according to the size of the included angle and the distance from the included angle to p1, the sequence p1 to pn is obtained, then, the sequence is scanned once, the internal points are eliminated, and the rest are the boundary points of the plane point cloud.
In a further improvement, the step S4 specifically includes:
the ideal shoe mold glue spraying track is that the edge contour line is on the curved surface of the shoe moldThe three-dimensional offset curve is a two-dimensional offset curve of the edge contour of the plane point cloud after the curve is projected to the plane, the center of gravity of the point cloud after the shoe mold plane projection in the step S2 is set as C (xc, yc), the contour point cloud set obtained by the plane point cloud convex hull algorithm in the step S3 is set as D, and if the center point P0(x0, y0) of the two-dimensional point cloud contour corresponds to the offset point Fq (xq, yq) to be solved, the offset point Fq (xq, yq) is obtained, the offset curve is obtained by the step S3, and the offset curve is obtained by the step S0Offset distance d (u); assuming that the nearest neighbor point is P1(x1, y1) searched in the point cloud set D by taking P0 as a center, the method is used for solving the problem that the nearest neighbor point is P1(x1, y1)The straight lineNormal vector of (1)ByAndthe offset point Fq (xq, yq) can be solved by two constraints;
the upper form synthesizes a straight lineThe two cases of normal vector of (2) are horizontal direction translation and vertical direction translation, and because of the arithmetic square root operation, each calculation obtains two deviation points Fq1(xq1, yq1) and Fq2(xq2, yq 2); in practice, to obtain a point shifted from the edge contour point to the point cloud inner side, it can be considered that Fq closest to the center of gravity C (xc, yc) is the target point, and thereforeAndmiddle and smaller FqThe result is obtained; the thicknesses of all parts of the edge of the shoe mold are different, so that offset values are different, different values are offset at different nodes along the main characteristic X-axis direction on the basis of a point cloud main direction coordinate system obtained by the PCA algorithm of the step S2, four offset areas are set by taking 30%, 65% and 80% positions from the heel to the top of the shoe as boundary points, and the offset distances are 2cm, 3.8cm, 2cm and 1cm in sequence.
In a further improvement, the step S5 specifically includes:
the contour points obtained by the variable intercept offset algorithm of the step S4 have the problems of local overlap and local sparsity, and the track of the shoe mold three-dimensional glue spraying can be obtained by finding the corresponding points in the three-dimensional point cloud by the B spline track points on the XOY plane, namely finding the corresponding Z coordinates according to the XY coordinates of the plane points.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention adopts the algorithm for extracting the three-dimensional glue spraying track of the shoe mold based on point cloud projection variable intercept contour deviation, solves the problem of failure of operations such as glue spraying and the like caused by the fact that the traditional teaching and offline programming mode controls the execution mechanism to process and the like in the glue spraying process of the shoe mold can not adapt to different processing working conditions and the shoe mold in time, and can effectively improve the glue spraying process of the shoe mold by utilizing the point cloud-based three-dimensional vision guiding technology of the shoe mold glue spraying;
2. the invention has the creativity that the invention can effectively obtain the glue spraying track similar to the shoe mold and the track of other complex curved surfaces by the variable intercept contour offset algorithm, thereby carrying out three-dimensional guide processing, such as tasks of automatic glue spraying, rust removal, cutting and the like. Greatly improves the technological level and the processing efficiency of glue spraying of the shoe mold, and greatly improves the production quality, the appearance and other aspects of the shoe mold.
Drawings
The drawings are for illustrative purposes only and are not to be construed as limiting the patent; for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
Fig. 1 is a schematic overall flow chart of an embodiment of the present invention.
Detailed Description
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted" and "connected" are to be interpreted broadly, e.g., as being either fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, so to speak, as communicating between the two elements. The specific meaning of the above terms in the present invention can be understood in specific cases to those skilled in the art. The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
The point cloud data of the shoe mold obtained by linear structured light scanning is utilized, the glue spraying track of the shoe mold is positioned on the curved surface of the inner side wall, the point cloud curvatures and the densities of the curved surfaces of the side walls at different positions are different, and the three-dimensional glue spraying track cannot be obtained by directly adopting a feature extraction method. Therefore, the present invention will be implemented with the following steps.
Referring to fig. 1, an algorithm for extracting a three-dimensional glue spraying track of a shoe mold based on point cloud projection variable intercept contour deviation comprises the following steps:
s1, shoe mold point cloud pretreatment: 1) height direction straight-through filtering treatment: the algorithm for removing the plane support by using the height direction straight-through filtering method is simple and has higher speed; by taking the idea of foreground and background separation in image processing as a reference, shoe mold point cloud data of a target is segmented in the point cloud height direction histogram according to the selection of a threshold value, and most of background and some interference point clouds are removed. 2) Removing outliers by statistical filtering: the residual interference point clouds are mainly some outliers after the straight-through filtering processing in the height direction, the statistical filtering algorithm is realized by judging the distance between a statistical point and all the adjacent points, and if the obtained statistical average distance exceeds a standard range, the outliers are obtained. Assuming a space point p and n adjacent points in the field, the outlier determination formula is as follows:
3) voxel grid filtering simplifying point cloud: the point cloud simplification algorithm can simplify the number of point clouds on the premise of ensuring point cloud characteristic information, so that subsequent point cloud processing is more efficient; and the voxel grid filtering is to divide a minimum cube grid in the constructed point cloud three-dimensional voxel grid and replace other points by the closest point of the gravity center of the minimum cube grid so as to realize the simplification of the point cloud.
S2: and (3) performing shoe mold point cloud data dimensionality reduction treatment: the point cloud data is essentially a set of three-dimensional spatial points, the points are represented as P (x0, y0, z0), and the preprocessed point cloud is projected onto an XOY plane to obtain a plane point cloud; and obtaining the main direction of the projected plane point cloud by using a PCA algorithm and establishing a coordinate system.
S3: extracting the contour by a convex hull algorithm: the convex hull algorithm is applied to the extraction of the projection shoe mold point cloud edge contour, namely, the minimum point of a y coordinate in the plane point cloud is set as p1, if a plurality of minimum points of the y coordinate exist, the minimum point of an x coordinate is set as p1, coordinates of other points in the point set are transformed, so that p1 becomes the coordinate origin of the plane point cloud, the origin is connected with other points by line segments, an included angle between the line segments and the horizontal coordinate is calculated, an included angle sequence is obtained, dictionary type classification sorting is carried out according to the size of the included angle and the distance from the included angle to p1, the sequence p1 to pn is obtained, then, the sequence is scanned once, the internal points are eliminated, and the rest are the boundary points of the plane point cloud.
S4 projection profile variable intercept offset:
the ideal shoe mould glue spraying track is a three-dimensional offset curve of the edge contour line on the shoe mould curved surface, and the curve is a two-dimensional offset curve of the plane point cloud edge contour after being projected to the plane. Setting the point after the planar projection of the shoe mold in the step S2The cloud center of gravity is C (xc, yc), the contour point cloud set obtained by the planar point cloud convex hull algorithm in the step S3 is D, and if the two-dimensional point cloud contour midpoint P0(x0, y0) corresponds to the offset point Fq (xq, yq) to be solved, the cloud center of gravity is C (xc, yc), and the contour point cloud set is DThe offset distance is d (u). Assuming that the nearest neighbor point is P1(x1, y1) searched in the point cloud set D by taking P0 as a center, the method is used for solving the problem that the nearest neighbor point is P1(x1, y1)The straight lineNormal vector of (1)ByAndtwo constraints can solve for the offset point Fq (xq, yq).
The upper form synthesizes a straight lineTwo cases of normal vector of (2) are not existed, actually horizontal direction translation and vertical direction translation, because of the arithmetic square root operation, each calculation will obtain two deviation points Fq1(xq1, yq1) and Fq2(xq2, yq 2); in practice, to obtain a point shifted from the edge contour point to the point cloud inner side, it can be considered that Fq closest to the center of gravity C (xc, yc) is the target point, and thereforeAndmiddle and smaller FqThe result is obtained. The thicknesses of all parts of the edges of the shoe mold are different, so that offset values are different, different values are offset at different nodes along the main characteristic X-axis direction on the basis of a point cloud main direction coordinate system obtained by the PCA algorithm of the step S2, four offset areas are set by taking 30%, 65% and 80% positions from the heel to the top of the shoe as boundary points, and good offset effects can be obtained by sequentially offsetting the distances of 2cm, 3.8cm, 2cm and 1 cm.
S5: b-spline curve fitting offset profile: the contour points obtained by the variable intercept offset algorithm of step S4 have the problems of local overlap and local sparseness, and obviously, these contour points cannot be used as the glue spraying trajectory of the robot. Therefore, the contour point cloud obtained by fitting and shifting the B-spline curve is adopted to represent the glue spraying track of the target plane.
S6: acquiring a three-dimensional glue spraying track: finding the corresponding point in the three-dimensional point cloud by the B spline track point on the XOY plane, namely finding the corresponding Z coordinate according to the XY coordinate of the plane point, and obtaining the three-dimensional glue spraying track of the shoe mold.
In the drawings, the positional relationship is described for illustrative purposes only and is not to be construed as limiting the present patent; it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (6)
1. An algorithm for extracting a three-dimensional glue spraying track of a shoe mold based on point cloud projection variable intercept contour deviation is characterized by comprising the following steps:
s1, shoe mold point cloud preprocessing, namely, acquiring shoe mold point cloud data by using line structured light and carrying out a series of point cloud preprocessing operations in a reverse direction;
s2, performing dimensionality reduction processing on shoe mold point cloud data, projecting the preprocessed point cloud onto an XOY plane, obtaining the main direction of the point cloud by using a PCA algorithm, and establishing a coordinate system;
s3, extracting the outline by a convex hull algorithm, and applying the convex hull algorithm to the extraction of the point cloud edge outline of the projection shoe mold;
s4, projection contour variable intercept offset, obtaining an offset point by a two-dimensional point cloud gravity center C and a midpoint P, and carrying out point cloud offset according to different offset areas of the shoe mold to obtain a point cloud contour of the shoe mold sprayed with glue;
s5, fitting the offset contour by a B spline curve, solving the problems of local overlapping and local sparsity of contour points obtained by a variable intercept offset algorithm, and obtaining the glue spraying track of the shoe mold by fitting the B spline curve.
2. The algorithm for extracting the three-dimensional glue spraying track of the shoe mold based on the point cloud projection variable intercept contour deviation as claimed in claim 1, wherein the step S1 specifically comprises:
the pretreatment of the shoe mold point cloud comprises height direction direct filtering treatment, statistical filtering and outlier removing treatment and voxel grid filtering simplified point cloud treatment;
the height direction direct filtering processing is an algorithm for removing plane support by using a height direction direct filtering method, by taking the thought of foreground and background separation in image processing as reference, shoe mold point cloud data of a target is segmented in a point cloud height direction histogram according to the selection of a threshold value, and background and partial interference point clouds are removed;
the statistical filtering for removing outliers is realized by judging the distances between statistical points and all adjacent points thereof through a statistical filtering algorithm, if the obtained statistical average distance exceeds a standard range, the outliers are determined, and if a space point p and n adjacent points in the field thereof are assumed, the outlier determination formula is as follows:
the voxel grid filtering simplified point cloud utilizes a point cloud simplification algorithm, the point cloud simplification algorithm can simplify the number of point clouds on the premise of ensuring point cloud characteristic information, the voxel grid filtering is to divide a minimum cube grid in a constructed point cloud three-dimensional voxel grid, and other points are replaced by the closest point of the gravity center of the minimum cube grid, so that point cloud simplification is realized.
3. The algorithm for extracting the shoe mold three-dimensional glue spraying track based on point cloud projection variable intercept contour deviation according to claim 2, wherein the step S2 specifically further comprises:
the point cloud data is essentially a set of three-dimensional spatial points, the points are represented as P (x0, y0, z0), and the preprocessed point cloud is projected onto an XOY plane to obtain a plane point cloud; and obtaining the main direction of the projected plane point cloud by using a PCA algorithm and establishing a coordinate system.
4. The algorithm for extracting the shoe mold three-dimensional glue spraying track based on the point cloud projection variable intercept contour deviation as claimed in claim 3, wherein the step S3 specifically comprises:
the convex hull algorithm is applied to the extraction of the projection shoe mold point cloud edge contour, namely, the minimum point of a y coordinate in the plane point cloud is set as p1, if a plurality of minimum points of the y coordinate exist, the minimum point of an x coordinate is set as p1, coordinates of other points in the point set are transformed, so that p1 becomes the coordinate origin of the plane point cloud, the origin is connected with other points by line segments, an included angle between the line segments and the horizontal coordinate is calculated, an included angle sequence is obtained, dictionary type classification sorting is carried out according to the size of the included angle and the distance from the included angle to p1, the sequence p1 to pn is obtained, then, the sequence is scanned once, the internal points are eliminated, and the rest are the boundary points of the plane point cloud.
5. The algorithm for extracting the shoe mold three-dimensional glue spraying track based on the point cloud projection variable intercept contour deviation as claimed in claim 4, wherein the step S4 specifically comprises:
the ideal shoe mould glue spraying track is a three-dimensional offset curve of the edge contour line on the curved surface of the shoe mouldProjecting the two-dimensional offset curve to a plane and then being a plane point cloud edge contour, setting the point cloud gravity center point after the shoe mold plane projection in the step S2 as C (xc, yc), setting the contour point cloud set obtained by the plane point cloud convex hull algorithm in the step S3 as D, and if the two-dimensional point cloud contour center point P0(x0, y0) corresponds to the deviation point Fq (xq, yq) to be solved, then obtaining the two-dimensional offset curve of the point cloud edge contour in the step S3 as DOffset distance d (u); assuming that the nearest neighbor point is P1(x1, y1) searched in the point cloud set D by taking P0 as a center, the method is used for solving the problem that the nearest neighbor point is P1(x1, y1)The straight lineNormal vector of (1)ByAndthe offset point Fq (xq, yq) can be solved by two constraints;
the upper form synthesizes a straight lineThe two cases of normal vector of (2) are horizontal direction translation and vertical direction translation, and because of the arithmetic square root operation, each calculation obtains two deviation points Fq1(xq1, yq1) and Fq2(xq2, yq 2); in practice, to obtain a point shifted from the edge contour point to the point cloud inner side, it can be considered that Fq closest to the center of gravity C (xc, yc) is the target point, and thereforeAndmiddle and smaller FqThe result is obtained; the thicknesses of all parts of the edge of the shoe mold are different, so that offset values are different, different values are offset at different nodes along the main characteristic X-axis direction on the basis of a point cloud main direction coordinate system obtained by the PCA algorithm of the step S2, four offset areas are set by taking 30%, 65% and 80% positions from the heel to the top of the shoe as boundary points, and the offset distances are 2cm, 3.8cm, 2cm and 1cm in sequence.
6. The algorithm for extracting the shoe mold three-dimensional glue spraying track based on the point cloud projection variable intercept contour deviation as claimed in claim 5, wherein the step S5 specifically comprises:
the contour points obtained by the variable intercept offset algorithm of the step S4 have the problems of local overlap and local sparsity, and the track of the shoe mold three-dimensional glue spraying can be obtained by finding the corresponding points in the three-dimensional point cloud by the B spline track points on the XOY plane, namely finding the corresponding Z coordinates according to the XY coordinates of the plane points.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110858575.7A CN113487640A (en) | 2021-07-28 | 2021-07-28 | Point cloud projection-based algorithm for extracting three-dimensional glue spraying track of shoe mold through variable intercept contour deviation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110858575.7A CN113487640A (en) | 2021-07-28 | 2021-07-28 | Point cloud projection-based algorithm for extracting three-dimensional glue spraying track of shoe mold through variable intercept contour deviation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113487640A true CN113487640A (en) | 2021-10-08 |
Family
ID=77943258
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110858575.7A Pending CN113487640A (en) | 2021-07-28 | 2021-07-28 | Point cloud projection-based algorithm for extracting three-dimensional glue spraying track of shoe mold through variable intercept contour deviation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113487640A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114862884A (en) * | 2022-05-13 | 2022-08-05 | 苏州大学 | Three-dimensional contour information extraction method and device, electronic equipment and storage medium |
WO2024087121A1 (en) * | 2022-10-27 | 2024-05-02 | Abb Schweiz Ag | Method, electronic device and computer program product for generating a path |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107830812A (en) * | 2017-09-14 | 2018-03-23 | 同济大学 | A kind of laser reflection piece implementation method suitable for being positioned in tunnel with deformation analysis |
CN109977352A (en) * | 2019-03-21 | 2019-07-05 | 哈尔滨工业大学 | Large high-speed revolution equipment single-stage components bounce data processing method based on the processing of incoordinate interval filtering validity |
CN112862704A (en) * | 2021-01-22 | 2021-05-28 | 北京科技大学 | Glue spraying and glue spraying quality detection system based on 3D vision |
-
2021
- 2021-07-28 CN CN202110858575.7A patent/CN113487640A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107830812A (en) * | 2017-09-14 | 2018-03-23 | 同济大学 | A kind of laser reflection piece implementation method suitable for being positioned in tunnel with deformation analysis |
CN109977352A (en) * | 2019-03-21 | 2019-07-05 | 哈尔滨工业大学 | Large high-speed revolution equipment single-stage components bounce data processing method based on the processing of incoordinate interval filtering validity |
CN112862704A (en) * | 2021-01-22 | 2021-05-28 | 北京科技大学 | Glue spraying and glue spraying quality detection system based on 3D vision |
Non-Patent Citations (1)
Title |
---|
周阳: "基于点云的鞋模喷胶三维视觉引导关键技术研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》, no. 12, pages 3 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114862884A (en) * | 2022-05-13 | 2022-08-05 | 苏州大学 | Three-dimensional contour information extraction method and device, electronic equipment and storage medium |
CN114862884B (en) * | 2022-05-13 | 2024-02-27 | 苏州大学 | Three-dimensional contour information extraction method and device, electronic equipment and storage medium |
WO2024087121A1 (en) * | 2022-10-27 | 2024-05-02 | Abb Schweiz Ag | Method, electronic device and computer program product for generating a path |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113487640A (en) | Point cloud projection-based algorithm for extracting three-dimensional glue spraying track of shoe mold through variable intercept contour deviation | |
CN111035115B (en) | Sole gluing path planning method and device based on 3D vision | |
CN112348864B (en) | Three-dimensional point cloud automatic registration method for laser contour features of fusion line | |
CN107856309A (en) | A kind of increasing material manufacturing is with remanufacturing fast path planing method | |
CN110223345A (en) | Distribution line manipulating object position and orientation estimation method based on cloud | |
CN107598775A (en) | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished | |
CN112405123A (en) | Shoe sole roughing track planning method and device based on clustering algorithm | |
CN111227444A (en) | 3D sole glue spraying path planning method based on k nearest neighbor | |
CN110348086A (en) | A kind of rose cutter vertical milling surface roughness fast modeling method | |
CN112465767A (en) | Industrial robot sole gluing track extraction method | |
Filaretov et al. | The automatization method of processing of flexible parts without their rigid fixation | |
CN114902872A (en) | Visual guidance method for picking fruits by robot | |
CN103480534A (en) | Robot spray workpiece surface modeling method | |
CN114618704B (en) | 3D vision guiding robot programming-free spraying method and system | |
CN110288706B (en) | Fitting method of small-curvature irregular point cloud curved surface | |
CN117853742A (en) | Welding seam groove feature extraction method based on structured light and welding robot | |
CN108304686A (en) | A kind of adaptive dynamic evolution computational methods of roughing process | |
CN108177028B (en) | Ceramic grinding process | |
CN107301310B (en) | Method for constructing three-dimensional process template of mechanical part | |
CN113554713A (en) | Hole-making visual positioning and detecting method for airplane skin mobile robot | |
CN108629315A (en) | A kind of more plane recognition methods for three-dimensional point cloud | |
CN102938005A (en) | Middle entity generating method of cutting and machining working procedure | |
CN107065767B (en) | Method for generating 3D contour chamfering processing path | |
CN111805556B (en) | Casting burr cleaning system and method | |
CN114119773A (en) | Camera automatic focusing method for intelligent grabbing detection of industrial robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |