CN111227444A - 3D sole glue spraying path planning method based on k nearest neighbor - Google Patents
3D sole glue spraying path planning method based on k nearest neighbor Download PDFInfo
- Publication number
- CN111227444A CN111227444A CN202010053936.6A CN202010053936A CN111227444A CN 111227444 A CN111227444 A CN 111227444A CN 202010053936 A CN202010053936 A CN 202010053936A CN 111227444 A CN111227444 A CN 111227444A
- Authority
- CN
- China
- Prior art keywords
- point
- sole
- cloud data
- glue spraying
- points
- 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
Images
Classifications
-
- A—HUMAN NECESSITIES
- A43—FOOTWEAR
- A43D—MACHINES, TOOLS, EQUIPMENT OR METHODS FOR MANUFACTURING OR REPAIRING FOOTWEAR
- A43D25/00—Devices for gluing shoe parts
- A43D25/18—Devices for applying adhesives to shoe parts
-
- A—HUMAN NECESSITIES
- A43—FOOTWEAR
- A43D—MACHINES, TOOLS, EQUIPMENT OR METHODS FOR MANUFACTURING OR REPAIRING FOOTWEAR
- A43D2200/00—Machines or methods characterised by special features
- A43D2200/60—Computer aided manufacture of footwear, e.g. CAD or CAM
Landscapes
- Application Of Or Painting With Fluid Materials (AREA)
Abstract
The invention relates to a 3D sole glue spraying path planning method based on k nearest neighbor, which comprises the following steps: step 1, scanning a sole through a laser to obtain original sole point cloud data; step 2, filtering the original sole point cloud data to obtain processed sole point cloud data; step 3, extracting the outer contour of the sole according to the processed sole cloud data; and 4, extracting the inner contour of the sole according to the outer contour of the sole, and processing the inner contour of the sole to form a glue spraying path point set. According to the invention, based on point cloud data, a height threshold value and a neighborhood filtering algorithm based on kNN are integrated, noise points and abnormal points are filtered, the problem that noise clusters still exist after filtering by a traditional method is avoided, the filtering efficiency is effectively improved, and the accuracy of a glue spraying path is improved.
Description
Technical Field
The invention relates to the technical field of automatic glue spraying, in particular to a 3D sole glue spraying path planning method based on k nearest neighbor.
Background
Shoe making is a typical labor-intensive industry, most of the processes of shoe making at present adopt manual or semi-automatic operation, and the production efficiency is very low. In addition, the working environment of workers is quite severe, and particularly in the glue spraying process, the toxic gas volatilized by the adhesive seriously threatens the health of the workers and restricts the healthy development of the shoe manufacturing industry. Therefore, the automatic glue spraying has important significance.
The key of automatic glue spraying is a planning algorithm of a glue spraying path. The current path planning algorithms mainly include several types: first, based on a CAD model; secondly, image-based; and thirdly, based on laser point cloud.
The CAD model is mainly based on a sole CAD model file for path planning, and because the sole has certain expansion and deformation, the actually produced sole has certain difference with the CAD model. Therefore, the method is effective only for a small part of shoe types, and is difficult to be applied to actual production.
The vision-based method mainly extracts paths through a vision edge detection algorithm. The vision-based method can only extract two-dimensional information, and the extracted path lacks height information. In addition, the contour extraction accuracy is not particularly high due to a pixel error of edge extraction, a calibration error, and the like. This limits the application of the method.
Based on the laser point cloud method, high-precision point cloud information including plane information and height information can be extracted. Meanwhile, the laser scanning-based method can generate a corresponding outline according to the actual sole, and effectively solves the problem of shape extraction of the expansion deformation of the sole. However, the glue spraying precision of the current laser point cloud based method still needs to be improved.
Disclosure of Invention
In view of the above, the present invention provides a method for planning a glue spraying path of a 3D shoe sole based on k nearest neighbor, which improves the precision of glue spraying by improving the planning precision of the glue spraying path.
In order to achieve the purpose, the invention adopts the technical scheme that:
A3D sole glue spraying path planning method based on k nearest neighbor comprises the following steps:
step 1, scanning a sole through a laser to obtain original sole point cloud data;
step 2, filtering the original sole point cloud data to obtain processed sole point cloud data;
firstly, filtering the original sole point cloud data through a height threshold value: the point with the height larger than the height threshold value is a ground point, the point with the height smaller than the height threshold value is a sole point, and all the sole points are used as the primarily filtered sole point cloud data;
then, filtering the primarily filtered sole point cloud data by adopting a neighborhood filtering algorithm based on kNN to obtain processed sole point cloud data;
step 3, extracting the outer contour of the sole according to the processed sole cloud data;
and 4, extracting the inner contour of the sole according to the outer contour of the sole, and processing the inner contour of the sole to form a glue spraying path point set.
In the step 2, the primarily filtered shoe sole point cloud data is filtered by adopting a neighborhood filtering algorithm based on kNN, which specifically comprises the following steps:
constructing KDTree aiming at the primarily filtered sole point cloud data;
extracting k' nearest neighbor points of each point in the shoe sole point cloud data after primary filtering on the basis of a KDTree structure;
calculating the distance between each point and k nearest neighbor points thereof;
if the distance between each point and the kth nearest neighbor point is greater than a set threshold value, the point is judged as an abnormal point or a noise point, otherwise, the point is a sole point;
all sole points constitute the processed sole point cloud data.
The laser is a line laser; in the step 3, the step of extracting the outer contour is specifically as follows:
dividing the processed sole point cloud data into a plurality of different scanning lines;
taking the middle point of each scanning line;
dividing the scanning line into two sections: from the leftmost point to the middle point, and from the rightmost point to the middle point;
for the segment from the leftmost point to the middle point, traversing from left to right and extracting the first maximum value point A; for the segment from the rightmost edge to the most middle point, traversing from right to left and extracting the first maximum value point B;
a and B are shoe edge points, and the point between A and B is a sole point;
points a and B of all scan lines constitute the outer contour of the sole.
In the step 4, the inner outline of the sole is extracted as follows:
calculating the two-dimensional normal vector direction of the outer contour curve by taking the outer contour of the sole as a reference, then deviating a distance d along the normal direction, and downwards deviating a distance s along the height direction;
wherein, the calculation of the two-dimensional normal vector is as follows:
let the coordinate of the point p be x ∈ R3The k neighborhood point sets Q are { Q1,...,qk}，x∈R3Corresponding coordinate is { y1,...,yk}；
First, a vector y of a point set Q with respect to a point p is obtained1-x,...,yk-x}∈R3×k；
Let n be an element of R3For the normal vector estimation of point p, then n and { y1-x,...,ykThe dot product of-x should be as close to zero as possible, i.e. the minimization function
Obtaining the partial derivatives of each component
In the step 4, the operation of processing the inner contour of the sole to form the glue spraying path point set is as follows:
calculating the total length n of the sole and extreme points at the toe cap and the tail of the shoe, and then respectively intercepting inner contour point sets at the toe cap and the tail of the shoe according to the distance d equal to n/12, so that the inner contour is divided into four groups of point sets; the point sets at the toe and the heel of the shoe are sampled at a high frequency to be sparse, the other two groups of point sets are down-sampled at a low frequency to be sparse, and the four groups of point sets are combined to form a path point set for controlling the mechanical arm to spray glue.
The method for converting the concentrated points of the inner contour points into the glue spraying path is as follows:
each point in the inner contour point set is represented by a 6-dimensional vector (x, y, z, rx, ry, rz), wherein (x, y, z) represents the position information of the point, and (rx, ry, rz) represents the normal vector of the point;
calculating an included angle theta between the vector v1(rx, ry) and the vector v2(1,0) as an attitude parameter u of the mechanical arm, namely: u ═ acos (v1 · v2/| v1| | | v2|), and when ry > -0, u > -0; when ry <0, u < 0;
setting two other attitude parameters v of the mechanical arm to be 0 and w to be 0;
then the robot arm 6-dimensional control vector for that point is (x, y, z, u, v, w).
Compared with the prior art, the invention has the following beneficial effects:
1. based on point cloud data, a height threshold value and a neighborhood filtering algorithm based on kNN are integrated, noise points and abnormal points are filtered, the problem that noise clusters still exist after filtering in a traditional method is solved, filtering efficiency is effectively improved, and therefore accuracy of a glue spraying path is improved.
2. Aiming at the distribution characteristics of scanning lines on the edge points of the shoes, a sole edge extraction algorithm with maximum double edges is provided, and the outline of the sole edge is effectively extracted;
3. a method for calculating a normal vector of an outer contour based on kNN is provided, and an inner contour is formed by offsetting an outer contour through the normal vector. Finally, the inner contour is further smoothed using a mean smoothing algorithm.
4. A path point set calculation method for controlling glue spraying of the mechanical arm is provided, so that glue spraying of the mechanical arm is more efficient and stable.
Drawings
FIG. 1 is a flow chart of a 3D shoe sole glue spraying path planning method of the present invention;
FIG. 2 is a schematic view of the raw sole point cloud data of the present invention;
FIG. 3 is a schematic representation of the shoe sole point cloud data after initial filtering in accordance with the present invention;
FIG. 4 is a schematic view of the processed sole point cloud data of the present invention;
FIG. 5 is a scan line segmentation of the sole point cloud data of the present invention;
FIG. 6 is a one-dimensional signal distribution diagram of scan lines according to the present invention;
FIG. 7 is a diagram of outer profile extraction and normal vector estimation of a sole according to the present invention;
FIG. 8 is a schematic diagram of an inner contour extracted based on normal vector offset according to the present invention;
FIG. 9 is a schematic of the inner contour of the present invention using mean smoothing;
FIG. 10 is a schematic diagram of a set of path points for controlling the robot arm to spray glue according to the present invention.
Detailed Description
As shown in fig. 1, the invention discloses a 3D shoe sole glue spraying path planning method based on k nearest neighbor, which comprises the following steps:
step 1, scanning a sole through a laser to obtain original sole point cloud data;
step 2, filtering the original sole point cloud data to obtain processed sole point cloud data;
firstly, filtering the original sole point cloud data through a height threshold value: the point with the height larger than the height threshold value is a ground point, the point with the height smaller than the height threshold value is a sole point, and all the sole points are used as the primarily filtered sole point cloud data;
then, filtering the primarily filtered sole point cloud data by adopting a neighborhood filtering algorithm based on kNN to obtain processed sole point cloud data;
step 3, extracting the outer contour of the sole according to the processed sole cloud data;
and 4, extracting the inner contour of the sole according to the outer contour of the sole, and processing the inner contour of the sole to form a glue spraying path point set.
As shown in fig. 2 to 4, the original sole point cloud data obtained by scanning with the line laser scanner includes a sole point cloud, a ground point, a noise point, and an anomaly point. Because the bottom surface point and the sole point cloud have obvious height difference, a large number of ground points can be directly filtered out through a height threshold value. Not all ground points are filtered out and the remaining ground points form a distribution of small clusters at large distances.
It is observed that the variation of the distance from the first k (k is large enough) neighborhood points is gentle for the points on the sole, and abrupt changes exist for the distances from the noise points, the outlier and the isolated ground point to the first k (k is large enough) neighborhood points. According to the distribution characteristics and in combination with the scanning distance of the laser point cloud, a neighborhood filtering algorithm based on kNN is adopted to further filter ground points, noise points and abnormal points.
The method for filtering the primarily filtered sole point cloud data by adopting the neighborhood filtering algorithm based on kNN specifically comprises the following steps:
constructing KDTree aiming at the primarily filtered sole point cloud data;
extracting k' nearest neighbor points of each point in the shoe sole point cloud data after primary filtering on the basis of a KDTree structure;
calculating the distance between each point and k nearest neighbor points thereof;
if the distance between each point and the kth nearest neighbor point is greater than a set threshold value, the point is judged as an abnormal point or a noise point, otherwise, the point is a sole point;
all sole points constitute the processed sole point cloud data.
As shown in fig. 5 and 6, the line laser used in the present invention is scanned according to lines, and the whole point cloud can be divided into several different scanning lines. Each scanning line has certain distribution, and the observation and data analysis show that the highest points on the left and right sides of the scanning line appear on the edge points of the shoes. According to the distribution characteristic, the invention adopts the bilateral maximum sole edge extraction algorithm to extract the outer contour of the sole, and the method specifically comprises the following steps:
extracting a middle point of each scanning line;
dividing the scanning line into two sections: the leftmost point to the middle point and the rightmost point to the most middle point;
for the segment from the leftmost point to the middle point, traversing from left to right and extracting the first maximum value point A; for the segment from the rightmost edge to the most middle point, traversing from right to left and extracting the first maximum value point B;
a and B are shoe edge points, and the point between A and B is a sole point;
points a and B of all scan lines constitute the outer contour of the sole.
After the outer contour line is extracted, a motion trail path of the mechanical arm, namely the inner contour of the sole, needs to be generated. As shown in fig. 7 to 9, the present invention calculates the two-dimensional normal vector direction of the outer contour curve based on the outer contour of the sole, and then shifts d distance along the normal direction and shifts s distance down along the height direction. The key here is the estimation of the normal vector.
Let the coordinate of the point p be x ∈ R3The k neighborhood point sets Q are { Q1,...,qk}，x∈R3Corresponding coordinate is { y1,...,yk}。
First, a vector y of a point set Q with respect to a point p is obtained1-x,...,yk-x}∈R3×k. Let n be an element of R3For the normal vector estimation of point p, then n and { y1-x,...,ykThe dot product of-x should be as close to zero as possible, i.e. the minimization function
This is a least squares problem, obtained by separately deriving the partial derivatives for each component
The inner contour obtained by normal vector offset has certain curve fluctuation. This is further filtered here using the kNN average filtering algorithm: first, let the coordinates of point p be x ∈ R3The k neighborhood point sets Q are { Q1,...,qk}，x∈R3Corresponding coordinate is { y1,...,yk}. However, the device is not suitable for use in a kitchenAfter that, use
X is updated. This realizes smoothing of the inner contour.
If directly spout gluey control path as the arm after obtaining the interior profile track of sole, the smoothness of its orbit motion is relatively poor, and the velocity of motion is lower simultaneously, consequently further handles to the interior profile point: the total length n of the sole and the extreme points at the toe and the tail of the shoe are calculated, and then inner contour point sets (in the length direction of the shoe) are respectively cut at the toe and the tail of the shoe by the distance d equal to n/12, so that the inner contours are divided into four sets of point sets. The point sets at the toe and the heel of the shoe are downsampled at a high frequency to be sparse, the other two groups of point sets are downsampled at a low frequency to be sparse, and the four groups of point sets are combined to form a path point set for controlling the mechanical arm to spray glue.
Each point in the inner contour point set is represented by a 6-dimensional vector (x, y, z, rx, ry, rz), where (x, y, z) represents the location information of the point and (rx, ry, rz) represents the normal vector of the point. Calculating an included angle theta between the vector v1(rx, ry) and the vector v2(1,0) as an attitude parameter u of the mechanical arm, namely: u ═ acos (v1 · v2/| v1| | | v2|), and when ry > -0, u > -0; when ry <0, u < 0. And if the other two attitude parameters v of the robot arm are 0 and w is 0, the robot arm 6-dimensional control vector at the point is (x, y, z, u, v, w).
As shown in fig. 10, the set of inner contour points is processed by the above calculation to form a set of path points for controlling the mechanical arm to spray glue.
In summary, compared with the prior art, the invention has the following beneficial effects:
1. based on point cloud data, a height threshold value and a neighborhood filtering algorithm based on kNN are integrated, noise points and abnormal points are filtered, the problem that noise clusters still exist after filtering in a traditional method is solved, filtering efficiency is effectively improved, and therefore accuracy of a glue spraying path is improved.
2. Aiming at the distribution characteristics of scanning lines on the edge points of the shoes, a sole edge extraction algorithm with maximum double edges is provided, and the outline of the sole edge is effectively extracted;
3. a method for calculating a normal vector of an outer contour based on kNN is provided, and an inner contour is formed by offsetting an outer contour through the normal vector. Finally, the inner contour is further smoothed using a mean smoothing algorithm.
4. A path point set calculation method for controlling glue spraying of the mechanical arm is provided, so that glue spraying of the mechanical arm is more efficient and stable.
The above description is only exemplary of the present invention and is not intended to limit the technical scope of the present invention, so that any minor modifications, equivalent changes and modifications made to the above exemplary embodiments according to the technical spirit of the present invention are within the technical scope of the present invention.
Claims (6)
1. A3D sole glue spraying path planning method based on k nearest neighbor is characterized in that: the method comprises the following steps:
step 1, scanning a sole through a laser to obtain original sole point cloud data;
step 2, filtering the original sole point cloud data to obtain processed sole point cloud data;
firstly, filtering the original sole point cloud data through a height threshold value: the point with the height larger than the height threshold value is a ground point, the point with the height smaller than the height threshold value is a sole point, and all the sole points are used as the primarily filtered sole point cloud data;
then, filtering the primarily filtered sole point cloud data by adopting a neighborhood filtering algorithm based on kNN to obtain processed sole point cloud data;
step 3, extracting the outer contour of the sole according to the processed sole cloud data;
and 4, extracting the inner contour of the sole according to the outer contour of the sole, and processing the inner contour of the sole to form a glue spraying path point set.
2. The k-nearest neighbor based 3D sole glue spraying path planning method according to claim 1, characterized in that: in the step 2, the primarily filtered shoe sole point cloud data is filtered by adopting a neighborhood filtering algorithm based on kNN, which specifically comprises the following steps:
constructing KDTree aiming at the primarily filtered sole point cloud data;
extracting k' nearest neighbor points of each point in the shoe sole point cloud data after primary filtering on the basis of a KDTree structure;
calculating the distance between each point and k nearest neighbor points thereof;
if the distance between each point and the kth nearest neighbor point is greater than a set threshold value, the point is judged as an abnormal point or a noise point, otherwise, the point is a sole point;
all sole points constitute the processed sole point cloud data.
3. The k-nearest neighbor based 3D sole glue spraying path planning method according to claim 1, characterized in that: the laser is a line laser; in the step 3, the step of extracting the outer contour is specifically as follows:
dividing the processed sole point cloud data into a plurality of different scanning lines;
taking the middle point of each scanning line;
dividing the scanning line into two sections: from the leftmost point to the middle point, and from the rightmost point to the middle point;
for the segment from the leftmost point to the middle point, traversing from left to right and extracting the first maximum value point A; for the segment from the rightmost edge to the most middle point, traversing from right to left and extracting the first maximum value point B;
a and B are shoe edge points, and the point between A and B is a sole point;
points a and B of all scan lines constitute the outer contour of the sole.
4. The k-nearest neighbor based 3D sole glue spraying path planning method according to claim 1, characterized in that: in the step 4, the inner outline of the sole is extracted as follows:
calculating the two-dimensional normal vector direction of the outer contour curve by taking the outer contour of the sole as a reference, then deviating a distance d along the normal direction, and downwards deviating a distance s along the height direction;
wherein, the calculation of the two-dimensional normal vector is as follows:
let the coordinate of the point p be x ∈ R3The k neighborhood point sets Q are { Q1,...,qk}，x∈R3Corresponding coordinate is { y1,...,yk}；
First, a vector y of a point set Q with respect to a point p is obtained1-x,...,yk-x}∈R3×k；
Let n be an element of R3For the normal vector estimation of point p, then n and { y1-x,...,ykThe dot product of-x should be as close to zero as possible, i.e. the minimization function
Obtaining the partial derivatives of each component
5. The k-nearest neighbor based 3D sole glue spraying path planning method according to claim 1, characterized in that: in the step 4, the operation of processing the inner contour of the sole to form the glue spraying path point set is as follows:
calculating the total length n of the sole and extreme points at the toe cap and the tail of the shoe, and then respectively intercepting inner contour point sets at the toe cap and the tail of the shoe according to the distance d equal to n/12, so that the inner contour is divided into four groups of point sets; the point sets at the toe and the heel of the shoe are sampled at a high frequency to be sparse, the other two groups of point sets are down-sampled at a low frequency to be sparse, and the four groups of point sets are combined to form a path point set for controlling the mechanical arm to spray glue.
6. The k-nearest neighbor based 3D shoe sole glue spraying path planning method according to claim 5, characterized in that: the method for converting the concentrated points of the inner contour points into the glue spraying path is as follows:
each point in the inner contour point set is represented by a 6-dimensional vector (x, y, z, rx, ry, rz), wherein (x, y, z) represents the position information of the point, and (rx, ry, rz) represents the normal vector of the point;
calculating an included angle theta between the vector v1(rx, ry) and the vector v2(1,0) as an attitude parameter u of the mechanical arm, namely: u ═ acos (v1 · v2/| v1| | | v2|), and when ry > -0, u > -0; when ry <0, u < 0;
setting two other attitude parameters v of the mechanical arm to be 0 and w to be 0;
then the robot arm 6-dimensional control vector for that point is (x, y, z, u, v, w).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010053936.6A CN111227444A (en) | 2020-01-17 | 2020-01-17 | 3D sole glue spraying path planning method based on k nearest neighbor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010053936.6A CN111227444A (en) | 2020-01-17 | 2020-01-17 | 3D sole glue spraying path planning method based on k nearest neighbor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111227444A true CN111227444A (en) | 2020-06-05 |
Family
ID=70877936
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010053936.6A Pending CN111227444A (en) | 2020-01-17 | 2020-01-17 | 3D sole glue spraying path planning method based on k nearest neighbor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111227444A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112405123A (en) * | 2020-11-19 | 2021-02-26 | 泉州华中科技大学智能制造研究院 | Shoe sole roughing track planning method and device based on clustering algorithm |
| CN112465767A (en) * | 2020-11-25 | 2021-03-09 | 南京熊猫电子股份有限公司 | Industrial robot sole gluing track extraction method |
| CN112720477A (en) * | 2020-12-22 | 2021-04-30 | 泉州装备制造研究所 | Object optimal grabbing and identifying method based on local point cloud model |
| CN114176290A (en) * | 2020-09-14 | 2022-03-15 | 广东天机工业智能系统有限公司 | Template-free full-automatic sole glue spraying method and device and storage medium |
| CN114504170A (en) * | 2022-03-07 | 2022-05-17 | 知守科技(杭州)有限公司 | Method and system for spraying glue on soles of flaky soles 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 (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143194A (en) * | 2014-08-20 | 2014-11-12 | 清华大学 | Point cloud partition method and device |
| CN104766325A (en) * | 2015-04-09 | 2015-07-08 | 泉州装备制造研究所 | Calculation method for vamp glue spray trajectory |
| CN106651863A (en) * | 2016-11-30 | 2017-05-10 | 厦门大学 | Point cloud data based automatic tree cutting method |
| CN107808415A (en) * | 2017-11-17 | 2018-03-16 | 中国科学院合肥物质科学研究院 | Sole edge track and gluing pose extracting method based on machine vision |
| CN109754406A (en) * | 2019-03-15 | 2019-05-14 | 苏州杰锐思自动化设备有限公司 | Lithium battery pole slice burr detection device and method based on two-dimensional silhouette instrument |
| CN110599506A (en) * | 2019-10-16 | 2019-12-20 | 湖南大学 | Point cloud segmentation method for three-dimensional measurement of complex special-shaped curved surface robot |
-
2020
- 2020-01-17 CN CN202010053936.6A patent/CN111227444A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143194A (en) * | 2014-08-20 | 2014-11-12 | 清华大学 | Point cloud partition method and device |
| CN104766325A (en) * | 2015-04-09 | 2015-07-08 | 泉州装备制造研究所 | Calculation method for vamp glue spray trajectory |
| CN106651863A (en) * | 2016-11-30 | 2017-05-10 | 厦门大学 | Point cloud data based automatic tree cutting method |
| CN107808415A (en) * | 2017-11-17 | 2018-03-16 | 中国科学院合肥物质科学研究院 | Sole edge track and gluing pose extracting method based on machine vision |
| CN109754406A (en) * | 2019-03-15 | 2019-05-14 | 苏州杰锐思自动化设备有限公司 | Lithium battery pole slice burr detection device and method based on two-dimensional silhouette instrument |
| CN110599506A (en) * | 2019-10-16 | 2019-12-20 | 湖南大学 | Point cloud segmentation method for three-dimensional measurement of complex special-shaped curved surface robot |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114176290A (en) * | 2020-09-14 | 2022-03-15 | 广东天机工业智能系统有限公司 | Template-free full-automatic sole glue spraying method and device and storage medium |
| CN114176290B (en) * | 2020-09-14 | 2023-08-18 | 广东天机工业智能系统有限公司 | Template-free full-automatic sole glue spraying method, device and storage medium |
| CN112405123A (en) * | 2020-11-19 | 2021-02-26 | 泉州华中科技大学智能制造研究院 | Shoe sole roughing track planning method and device based on clustering algorithm |
| WO2022105078A1 (en) * | 2020-11-19 | 2022-05-27 | 泉州华中科技大学智能制造研究院 | Shoe sole roughing trajectory planning method and apparatus based on clustering algorithm |
| CN112465767A (en) * | 2020-11-25 | 2021-03-09 | 南京熊猫电子股份有限公司 | Industrial robot sole gluing track extraction method |
| CN112720477A (en) * | 2020-12-22 | 2021-04-30 | 泉州装备制造研究所 | Object optimal grabbing and identifying method based on local point cloud model |
| CN112720477B (en) * | 2020-12-22 | 2024-01-30 | 泉州装备制造研究所 | Object optimal grabbing and identifying method based on local point cloud model |
| CN114504170A (en) * | 2022-03-07 | 2022-05-17 | 知守科技(杭州)有限公司 | Method and system for spraying glue on soles of flaky soles and storage medium |
| CN114504170B (en) * | 2022-03-07 | 2023-06-13 | 知守科技(杭州)有限公司 | Method, system and storage medium for spraying glue to sole of sole type |
| 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 |
|---|---|---|
| CN111227444A (en) | 3D sole glue spraying path planning method based on k nearest neighbor | |
| CN110223345B (en) | Point cloud-based distribution line operation object pose estimation method | |
| CN110232389B (en) | Stereoscopic vision navigation method based on invariance of green crop feature extraction | |
| CN111724433B (en) | Crop phenotype parameter extraction method and system based on multi-view vision | |
| CN106600639B (en) | The ICP pose location technology of genetic algorithm combining adaptive threshold value constraint | |
| CN107590825B (en) | Point cloud hole repairing method based on SFM | |
| CN112405123B (en) | Shoe sole roughing track planning method and device based on clustering algorithm | |
| CN109345554A (en) | A kind of adhesion mushroom vision in-situ measuring method based on RGB-D camera | |
| CN112348864B (en) | Three-dimensional point cloud automatic registration method for laser contour features of fusion line | |
| CN108597009B (en) | Method for detecting three-dimensional target based on direction angle information | |
| CN115147437B (en) | Intelligent robot guiding machining method and system | |
| CN111539070B (en) | Wing body butt joint gap distribution control method based on measured data | |
| CN109377521B (en) | Point cloud registration method for data acquisition midpoint of ground laser scanner to optimal plane | |
| CN111311618A (en) | Circular arc workpiece matching and positioning method based on high-precision geometric primitive extraction | |
| CN107607107A (en) | A kind of Slam method and apparatus based on prior information | |
| CN102129716A (en) | Method for fitting curved surface of water-fire bending plate | |
| CN112263052B (en) | Method and system for automatically mapping vamp glue spraying path based on visual data | |
| CN114972377A (en) | 3D point cloud segmentation method and device based on moving least square method and hyper-voxels | |
| CN116309847A (en) | Stacked workpiece pose estimation method based on combination of two-dimensional image and three-dimensional point cloud | |
| CN112465767A (en) | Industrial robot sole gluing track extraction method | |
| CN108765478A (en) | It is a kind of to build the density clustering algorithm that separating monomer is built in point cloud | |
| CN111820545A (en) | Method for automatically generating sole glue spraying track by combining offline and online scanning | |
| CN112257722A (en) | Point cloud fitting method based on robust nonlinear Gaussian-Hummer model | |
| CN116012600A (en) | Method for extracting point cloud local curved surface features based on morphology | |
| CN107037779A (en) | Free form surface NC process tool track optimizing methods under non-homogeneous tolerance |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |