CN111035115B - Sole gluing path planning method and device based on 3D vision - Google Patents
Sole gluing path planning method and device based on 3D vision Download PDFInfo
- Publication number
- CN111035115B CN111035115B CN202010173127.9A CN202010173127A CN111035115B CN 111035115 B CN111035115 B CN 111035115B CN 202010173127 A CN202010173127 A CN 202010173127A CN 111035115 B CN111035115 B CN 111035115B
- Authority
- CN
- China
- Prior art keywords
- sole
- point
- gluing
- points
- 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.)
- Active
Links
- 238000004026 adhesive bonding Methods 0.000 title claims abstract description 151
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000009499 grossing Methods 0.000 claims abstract description 27
- 238000013507 mapping Methods 0.000 claims abstract description 17
- 239000006185 dispersion Substances 0.000 claims abstract description 11
- 238000005520 cutting process Methods 0.000 claims description 41
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 4
- 238000007670 refining Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000010073 coating (rubber) Methods 0.000 claims 1
- 230000002093 peripheral effect Effects 0.000 claims 1
- 230000008569 process Effects 0.000 description 15
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000003292 glue Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a device for planning a sole gluing path based on 3D vision, which comprises the following steps: acquiring sole point cloud data through a 3D camera; calculating normal vector characteristics of each point in the sole point cloud data, and extracting point cloud data meeting the preset normal vector characteristics according to a Gaussian ball mapping principle to serve as local interior points of the sole gluing contour; acquiring a sole gluing contour curve discrete point set according to the sole gluing contour local inner points; thinning and smoothing the discrete point set of the sole gluing contour curve; numbering the discrete point sets of the sole gluing contour curve after thinning and smoothing according to the principle of proximity; after numbering, performing curve fitting on the discrete point set of the sole gluing contour curve, and performing self-adaptive dispersion to obtain contour discrete points; and calculating a gluing path according to the discrete points of the contour. The Gaussian ball mapping principle provided by the invention can be used for solving the local inner point of the sole gluing contour line, reducing useless data, quickly and accurately positioning the area of the sole gluing contour line, improving the algorithm speed and ensuring the precision.
Description
Technical Field
The invention relates to the technical field of sole gluing, in particular to a 3D vision-based sole gluing path planning method and device.
Background
At the present stage, the market of the shoe making industry is huge, and the shoe making industry is changing into the quality type and the benefit type. The sole gluing process is a time-consuming key process in the shoe making process, and the process has a series of problems of low production efficiency, poor gluing quality, harsh working environment and the like, so that the production cost is indirectly increased. Therefore, the realization of the automation of the gluing process is a real and necessary requirement of the shoe industry. At present, most gluing processes are finished by using a shoe machine with a specific shape; or generating a specific sole gluing track by manual 'teaching', storing the specific sole gluing track in a memory, and then taking out data from the memory and executing; or modeling the gluing piece, spraying by using a CAD model and other methods, the process is complicated, the operation is complex, the track extraction is long-time-consuming, even professional intervention is needed, and the method is not suitable for gluing soles with various specifications.
The invention discloses a method for acquiring sole point cloud data by using a 3D laser sensor, performing dimensionality reduction mapping on the sole point cloud data to obtain a two-dimensional depth image, processing the two-dimensional depth image to obtain a sole edge track curve, and fitting a bias algorithm and a curve to obtain a gluing spray gun track curve. When the heel or the periphery of the shoe is extended greatly, the extraction of the edge track of the sole is influenced greatly, and the universality is poor; meanwhile, the 3D laser sensor acquires sole information in a scanning mode, and compared with the point cloud obtained by 3D vision, the point cloud has the disadvantages of no order, sparsity, limited information amount, low acquisition speed and the like, and the automatic gluing efficiency is greatly influenced.
The invention provides a method for acquiring sole information by using a three-dimensional laser sensor, creating a sole space model according to sole point cloud, extracting a sole outline according to the space model, and further extracting a gluing outline to generate a gluing track, and belongs to the patent application with the patent publication number of CN 201910376398.1. The method has the defects of complicated process, high time consumption in the establishment of the sole point cloud space model, direct influence on the quality of a gluing track caused by the quality of the space model and poor stability.
Disclosure of Invention
The invention aims to provide a method and a device for planning a sole gluing path based on 3D vision, which are used for solving the problems of low efficiency, poor adaptability, low automation integration performance and the like in the related technology.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
in a first aspect, according to an embodiment of the present invention, there is provided a 3D vision-based sole gluing path planning method, including:
acquiring sole point cloud data through a 3D camera;
calculating normal vector characteristics of each point in the sole point cloud data, and extracting point cloud data meeting the preset normal vector characteristics according to a Gaussian ball mapping principle to serve as local interior points of the sole gluing contour;
acquiring a sole gluing contour curve discrete point set according to the sole gluing contour local inner points;
thinning and smoothing the discrete point set of the sole gluing contour curve;
numbering the discrete point sets of the sole gluing contour curve after thinning and smoothing according to the principle of proximity;
after numbering, performing curve fitting on the discrete point set of the sole gluing contour curve, and performing self-adaptive dispersion to obtain contour discrete points;
and calculating a gluing path according to the discrete points of the contour.
Further, when the 3D camera is used for acquiring sole point cloud data, the sole sample placing mode is a mode compatible with disordered orientation according to the principle that the 3D camera is basically perpendicular to the bottom surface of the sole, and the 3D camera is a coded structured light 3D camera.
Further, sole point cloud data is acquired through a 3D camera, and the method comprises the following steps:
performing Z-direction, X-direction and Y-direction direct filtering according to the relative position of the camera and the sole, and reducing the point cloud data to the sole and the preset range around the sole;
and fitting the plane of the sole by utilizing sampling consistency, and removing the point cloud data of the overlook of the single sole sample.
Further, calculating the normal vector characteristics of each point in the sole point cloud data through a kdtree searching method.
Further, according to the local inner point of the sole gluing contour, a discrete point set of a sole gluing contour curve is obtained, and the method comprises the following steps:
calculating the mass center of the point cloud in the sole gluing contour local by using geometry, moving the mass center for a preset distance along the positive direction of the Z axis to obtain a fixed point, and simultaneously calculating the maximum value and the minimum value of the point cloud in the sole gluing contour local in the directions of the x axis and the y axis and the respective difference of the maximum value and the minimum value;
selecting the larger difference of the maximum values of the x axis and the y axis as a cutting direction, taking the local inner points of the minimum value and the maximum value of the x axis or the y axis of the cutting direction as the beginning and the end of cutting, taking a plane parallel to the z as a cutting plane, carrying out equidistant cutting on the local inner point cloud of the sole gluing contour, and reserving point data within a certain distance from the cutting plane and marking as a cutting point cloud block;
traversing the cutting point cloud blocks, mapping the cloud blocks into the plane of the cutting surface where the fixed point is located, traversing the points in the cutting point cloud blocks, respectively calculating the curvatures of the connecting lines of the points and the fixed point, extracting two point data with the maximum curvature, and forming a sole gluing contour curve discrete point set by all the extracted points.
And further, refining and smoothing the discrete point set of the sole gluing profile curve by adopting a moving least square method.
Further, numbering the discrete point sets of the sole gluing contour curve after thinning and smoothing according to the principle of proximity, comprising:
calculating the most value of the sole gluing contour curve discrete point set subjected to thinning and smoothing in the x or y axis, connecting the two points to which the most value of the x or y axis belongs in the sole gluing contour curve discrete point set to form a straight line, dividing the sole gluing contour curve discrete point set subjected to thinning and smoothing into two parts taking the straight line as a boundary, respectively traversing the two part point sets by taking the point to which the minimum value and the maximum value of the x or y axis belong as target points, selecting one target point, sequentially sorting according to the distance between the two points to obtain two part sorting point sets, and connecting the two part sorting point sets end to end together with the two target points for numbering.
Further, performing curve fitting on the discrete point set of the sole gluing contour curve, and performing self-adaptive dispersion to obtain the discrete points of the contour, including:
the three-dimensional curve fitting method adopts Nurbs curve fitting to remove discrete points dissociating outside the curve and obtain contour discrete points.
Further, according to the contour discrete points, calculating a gluing path, comprising:
moving the profile discrete points in the respective normal vector directions by a preset distance to obtain the position of a gluing gun mouth;
and according to the calibration relation between the camera and the manipulator, carrying out coordinate transformation on the path point of the gluing gun port to generate a path point, and forming a gluing path.
In a second aspect, according to an embodiment of the present invention, there is also provided a 3D vision-based sole gluing path planning apparatus, including:
the data acquisition module is used for acquiring sole point cloud data through the 3D camera;
the inner point calculation module is used for calculating the normal vector characteristics of each point in the sole point cloud data, extracting the point cloud data meeting the preset normal vector characteristics according to the Gaussian sphere mapping principle and using the point cloud data as the inner points of the sole gluing contour;
the discrete point set calculation module is used for acquiring a discrete point set of a sole gluing contour curve according to the local inner points of the sole gluing contour;
the thinning and smoothing module is used for thinning and smoothing the discrete point set of the sole gluing profile curve;
the numbering module is used for numbering the dispersed point sets of the sole gluing contour curve after the thinning and smoothing treatment according to the principle (sequence) of the vicinity;
the outline discrete point acquisition module is used for carrying out curve fitting on a sole gluing outline curve discrete point set after numbering, and carrying out self-adaptive dispersion to obtain outline discrete points;
and the path calculation module is used for calculating the gluing path according to the contour discrete points.
According to the embodiment of the invention, the inner point of the sole gluing contour line is calculated according to the Gaussian ball mapping principle, so that useless data can be reduced, the area of the sole gluing contour line can be quickly and accurately positioned, the algorithm speed is increased, and the accuracy is guaranteed. The 3D camera used by the invention belongs to pure vision, has small response time compared with a three-dimensional laser sensor under the condition of equal precision, quickly acquires sole information, is beneficial to reducing the time consumption of an automatic gluing process, and can improve the efficiency. The shoe sole information acquisition and the automatic generation of the gluing track have good universality, can be suitable for gluing shoes of different styles, optimizes the shoe making process flow and improves the quality level of products.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flow chart of a 3D vision-based shoe sole gluing path planning method according to an embodiment of the present invention;
FIG. 2 is a set of points of a sole glue line profile according to an embodiment of the invention;
FIG. 3 is a line drawing of a sole glue application profile according to an embodiment of the invention;
fig. 4 is a schematic structural diagram of a 3D vision-based sole gluing path planning device according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In accordance with an embodiment of the present invention, there is provided a 3D vision-based sole gluing path planning method, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a 3D vision-based sole gluing path planning method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S101, acquiring sole point cloud data, such as a ground wire discrete point set, through a 3D camera;
step S102, calculating normal vector characteristics of each point in the sole point cloud data, extracting point cloud data meeting the preset normal vector characteristics according to a Gaussian sphere mapping principle, and using the point cloud data as a sole gluing contour local inner point;
step S103, acquiring a sole gluing contour curve discrete point set according to the sole gluing contour local inner points;
step S104, thinning and smoothing the discrete point set of the sole gluing contour curve;
s105, numbering the discrete point sets of the sole gluing contour curve subjected to thinning and smoothing according to the principle of closeness;
s106, after numbering, performing curve fitting on the discrete point set of the sole gluing contour curve, and performing self-adaptive dispersion to obtain contour discrete points;
and step S107, calculating a gluing path according to the discrete points of the contour.
According to the embodiment of the invention, the inner point of the sole gluing contour line is obtained by the Gaussian ball mapping principle, so that useless data can be reduced, the area of the sole gluing contour line can be quickly and accurately positioned, the algorithm speed is increased, and the accuracy is guaranteed. The 3D camera used by the invention belongs to pure vision, has small response time compared with a three-dimensional laser sensor under the condition of equal precision, quickly acquires sole information, is beneficial to reducing the time consumption of an automatic gluing process, and can improve the efficiency. The shoe sole information acquisition and the automatic generation of the gluing track have good universality, can be suitable for gluing shoes of different styles, optimizes the shoe making process flow and improves the quality level of products.
Each step of the above embodiment will be described in detail below with reference to a sole model, referred to as a sole M.
Step S101, obtaining sole point cloud data through a 3D camera, specifically as follows:
when sole point cloud data are acquired through the 3D camera, the sole sample placing mode is a mode compatible with disordered orientation according to the principle that the 3D camera is basically perpendicular to the bottom surface of the sole, and the 3D camera adopts a coded structured light 3D camera.
In this embodiment, the camera is positioned at a meter above the operation platform with the field of view facing vertically downward, and the sole M is horizontally placed on the work platform along the x-axis of the camera with the bottom surface facing downward and positioned at the center of the field of view of the camera.
And (3) acquiring the original point cloud of the sole M by using a sensor, and carrying out a series of filtering treatment to obtain the point cloud of the sole M. The sensor for collecting the sole M point cloud data adopts a coded structured light 3D camera, and compared with a three-dimensional laser sensor, the sensor has the advantages of high point cloud collecting speed and high imaging speed; and secondly, the acquired data is data in the whole visual field range of the camera, the data volume is large, in order to improve the algorithm speed, the original point cloud data is sampled down, the square area where the sole M is located is divided according to the relative position of the camera and the sole, the Z-direction, the X-direction and the Y-direction direct filtering are carried out, meanwhile, the sampling consistency algorithm is utilized to fit an operation platform and remove all noise points, and the single sole M point cloud is obtained.
Step S102, calculating normal vector characteristics of each point in the sole point cloud data, extracting point cloud data meeting the preset normal vector characteristics according to a Gaussian sphere mapping principle, and using the point cloud data as a sole gluing contour local inner point, wherein the method specifically comprises the following steps:
in this embodiment, the local inner point is a sole gluing contour line and a point cloud set in a certain range near the sole gluing contour line, the sole gluing contour line is an intersection line of the bottom surface of the upper and the side surface of the upper, and points on the bottom surface of the upper and the side surface have obvious mutation on the normal vector characteristic. Therefore, the sole M point cloud obtained in the step S101 is searched and calculated according to the radius b millimeter through the kdtree, the normal vector characteristics of each point are calculated, point cloud data meeting the obvious mutation area of the normal vector characteristics are extracted according to the Gaussian sphere mapping principle, and the point set is the local inner point of the sole M gluing contour. The sole gluing contour line area can be rapidly and accurately positioned, and the interference of the point cloud of the outer boundary part of the sole is reduced.
Step S103, obtaining a sole gluing contour curve discrete point set according to the sole gluing contour local inner point, which comprises the following specific steps:
in this embodiment, the centroid (x, y, Z) of the inner point of the sole gluing contour in the step S102 is calculated first in geometry, the centroid moves by a distance c in the positive direction of the Z axis to obtain a fixed point P (x, y, Z + c), and the maximum point and the minimum point of the point cloud x (y) and the difference value thereof are calculated; selecting the largest difference between the maximum values of x and y as a cutting direction, taking the minimum point and the maximum point of x or y as the beginning and the end of cutting, taking a plane perpendicular to x (y) as a cutting plane, recording the minimum point of x as T1 and the maximum point as T2 according to the placement form of the sole M in the step S101, carrying out d-millimeter equidistant cutting on the inner points of the gluing profile of the sole M from T1 to T2, and reserving point data e millimeters from the cutting plane to be recorded as a cloud block of cutting points (an arc discrete point set); traversing the cutting point cloud blocks, mapping the cloud blocks into the plane of the cutting surface where the P point is located, traversing the points in the cutting point cloud blocks, respectively calculating the curvature of a connecting line with the P point, extracting two points of data (tangent points) with the maximum curvature, and forming a discrete point set of the sole M contour curve by all the extracted points, as shown in figure 2.
Step S104, thinning and smoothing the discrete point set of the sole gluing contour curve, which is concretely as follows:
in the embodiment, the method for refining and smoothing the discrete point set of the M-profile curve of the sole adopts a moving least square method, and selects a proper order basis function and a proper weight function to achieve the precision and smoothness required by use.
Step S105, numbering the discrete point sets of the sole gluing contour curve after thinning and smoothing according to the principle of closeness, and specifically comprising the following steps:
in this embodiment, step S104 refines the smooth point cloud x by a minimum point T3 and a maximum point T4, connects two points T3 and T4 to form a straight line T3T4, divides the refined smooth point cloud into two parts a and B bounded by the straight line T3T4, selects a T3 target point, traverses the point sets a and B respectively, sorts the two point sets in sequence according to the distance between the two points to obtain a 'sorted point set (from small to large) and a' sorted point set (from large to small), and numbers a ', T4, B', and T3 by ending connection.
Step S106, after numbering, carrying out curve fitting on the discrete point set of the sole gluing contour curve, and carrying out self-adaptive dispersion to obtain contour discrete points, wherein the method specifically comprises the following steps:
in the embodiment, the three-dimensional curve fitting method adopts the Nurbs curve fitting, and in order that the manipulator runs stably, the Nurbs curve is subjected to self-adaptive dispersion according to the length and the chord height threshold value to obtain a group of sole M gluing track points.
Step S107, calculating a gluing path according to the contour discrete points, which is as follows:
in this embodiment, the gluing path does not coincide with the sole gluing contour, but the contour discrete points obtained in step S106 need to be moved by a certain distance (2-5 mm) in the respective normal vector directions to obtain the position of the gluing muzzle; and (3) according to the calibration relation between the camera and the manipulator, carrying out coordinate transformation on the path point of the gluing muzzle to generate a path point, forming a gluing path, as shown in fig. 3, and then sending the generated path point to a motion program of the manipulator, so that the manipulator moves to a corresponding position according to the received path in sequence to complete the gluing process flow.
Fig. 4 is a schematic structural diagram of a 3D vision-based sole gluing path planning device according to an embodiment of the present invention, which can execute any 3D vision-based sole gluing path planning method according to any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. As shown in fig. 4, the apparatus includes:
a data acquisition module 91 for acquiring the sole point cloud data by a 3D camera;
an interior point calculation module 92, configured to calculate normal vector features of each point in the sole point cloud data, extract point cloud data satisfying predetermined normal vector features according to a gaussian sphere mapping principle, and use the point cloud data as a sole gluing contour local interior point;
a discrete point set calculation module 93, configured to obtain a discrete point set of a sole gluing contour curve according to the sole gluing contour local inner point;
a thinning and smoothing module 94, configured to thin and smooth the discrete point set of the sole gluing profile curve;
a numbering module 95, which is used for numbering the discrete point sets of the sole gluing contour curve after the thinning and smoothing treatment according to the principle (sequence) of the vicinity;
the outline discrete point acquisition module 96 is used for carrying out curve fitting on the sole gluing outline curve discrete point set after numbering, and carrying out self-adaptive dispersion to obtain outline discrete points;
and a path calculation module 97, configured to calculate a gluing path according to the contour discrete points.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (9)
1. A3D vision-based sole gluing path planning method is characterized by comprising the following steps:
acquiring sole point cloud data through a 3D camera, wherein the 3D camera adopts a coded structured light 3D camera;
calculating normal vector characteristics of each point in the sole point cloud data, and extracting point cloud data meeting the preset normal vector characteristics in a three-dimensional space according to a Gaussian ball mapping principle to serve as local inner points of the sole gluing contour;
according to the local inner points of the sole gluing contour, a discrete point set of a sole gluing contour curve is obtained by using geometry, and the method specifically comprises the following steps: calculating the mass center of the point cloud in the sole gluing contour local by using geometry, moving the mass center for a preset distance along the positive direction of a z axis to obtain a fixed point, and simultaneously calculating the maximum value and the minimum value of the point cloud in the sole gluing contour local in the directions of the x axis and the y axis and the respective difference of the maximum value and the minimum value; selecting the larger difference of the maximum values of the x axis and the y axis as a cutting direction, taking the local inner points of the minimum value and the maximum value of the x axis or the y axis of the cutting direction as the beginning and the end of cutting, taking a plane parallel to the z axis as a cutting plane, carrying out equidistant cutting on the local inner point cloud of the sole gluing contour, and reserving point data within a certain distance from the cutting plane and marking as a cutting point cloud block; traversing the cutting point cloud blocks, mapping the cutting point cloud blocks into a plane of a cutting surface where the fixed point is located, traversing points in the cutting point cloud blocks, respectively calculating curvatures of connecting lines with the fixed point, extracting two point data with the maximum curvatures, and forming a sole gluing contour curve discrete point set by all the extracted points;
carrying out three-dimensional thinning and smoothing on the discrete point set of the sole gluing contour curve;
numbering the discrete point sets of the sole gluing contour curve subjected to thinning and smoothing according to the distance between two points according to the principle of proximity;
after numbering, carrying out three-dimensional curve fitting on the discrete point set of the sole gluing contour curve, and carrying out self-adaptive dispersion to obtain contour discrete points;
and calculating a gluing path according to the discrete points of the contour.
2. The 3D vision-based sole gluing path planning method according to claim 1, wherein when the 3D camera is used for obtaining the sole point cloud data, the sole sample placement mode is compatible with a disordered orientation mode according to the principle that the 3D camera is basically vertical to the sole bottom surface.
3. The 3D vision-based sole gluing path planning method according to claim 1, wherein the obtaining of sole point cloud data through a 3D camera comprises:
performing Z-direction, X-direction and Y-direction straight-through filtering according to the relative position of the 3D camera and the sole, and reducing the point cloud data to the sole and the peripheral preset range thereof;
and fitting the sole plane by utilizing sampling consistency, and removing noise points to obtain point cloud data of single sole sample overlook.
4. The 3D vision-based sole gluing path planning method according to claim 1, wherein normal vector features of each point in the sole point cloud data are calculated through a kdtree search method.
5. The method for planning the sole gluing path based on the 3D vision as claimed in claim 1, wherein the three-dimensional refining and smoothing are carried out on the discrete point set of the sole gluing profile curve by adopting a moving least square method.
6. The method for planning the sole gluing path based on the 3D vision according to the claim 1, wherein the discrete point sets of the sole gluing contour curve after the thinning and smoothing are numbered according to the distance between two points and the principle of proximity, and the method comprises the following steps:
calculating the most value of the sole gluing contour curve discrete point set subjected to thinning and smoothing in the x or y axis, connecting the two points to which the most value of the x or y axis belongs in the sole gluing contour curve discrete point set to form a straight line, dividing the sole gluing contour curve discrete point set subjected to thinning and smoothing into two parts taking the straight line as a boundary, respectively traversing the two part point sets by taking the point to which the minimum value and the maximum value of the x or y axis belong as target points, selecting one target point, sequentially sorting according to the distance between the two points to obtain two part sorting point sets, and connecting the two part sorting point sets end to end together with the two target points for numbering.
7. The method for planning the sole gluing path based on the 3D vision according to claim 1, wherein the three-dimensional curve fitting is performed on a discrete point set of a sole gluing profile curve, and the self-adaptive dispersion is performed to obtain discrete points of the profile, and the method comprises the following steps:
the three-dimensional curve fitting method adopts Nurbs curve fitting to remove discrete points dissociating outside the curve and obtain contour discrete points.
8. The 3D vision-based sole gluing path planning method according to claim 1, wherein calculating a gluing path according to contour discrete points comprises:
moving the profile discrete points in the respective normal vector directions by a preset distance to obtain the position of a gluing gun mouth;
and according to the calibration relation between the 3D camera and the manipulator, carrying out coordinate transformation on the path point of the gluing muzzle to generate a path point, and forming a gluing path.
9. The utility model provides a sole rubber coating route planning device based on 3D vision which characterized in that includes:
the data acquisition module is used for acquiring sole point cloud data through a 3D camera, wherein the 3D camera adopts a coded structured light 3D camera;
the inner point calculation module is used for calculating the normal vector characteristics of each point in the sole point cloud data, extracting the point cloud data meeting the preset normal vector characteristics in a three-dimensional space according to a Gaussian ball mapping principle, and using the point cloud data as the inner points of the sole gluing contour;
the discrete point set calculation module is used for obtaining a discrete point set of a sole gluing contour curve by using geometry according to the local inner points of the sole gluing contour, and specifically comprises the following steps: calculating the mass center of the point cloud in the sole gluing contour local by using geometry, moving the mass center for a preset distance along the positive direction of a z axis to obtain a fixed point, and simultaneously calculating the maximum value and the minimum value of the point cloud in the sole gluing contour local in the directions of the x axis and the y axis and the respective difference of the maximum value and the minimum value; selecting the larger difference of the maximum values of the x axis and the y axis as a cutting direction, taking the local inner points of the minimum value and the maximum value of the x axis or the y axis of the cutting direction as the beginning and the end of cutting, taking a plane parallel to the z axis as a cutting plane, carrying out equidistant cutting on the local inner point cloud of the sole gluing contour, and reserving point data within a certain distance from the cutting plane and marking as a cutting point cloud block; traversing the cutting point cloud blocks, mapping the cutting point cloud blocks into a plane of a cutting surface where the fixed point is located, traversing points in the cutting point cloud blocks, respectively calculating curvatures of connecting lines with the fixed point, extracting two point data with the maximum curvatures, and forming a sole gluing contour curve discrete point set by all the extracted points;
the thinning and smoothing module is used for carrying out three-dimensional thinning and smoothing on the discrete point set of the sole gluing profile curve;
the numbering module is used for numbering the discrete point set of the sole gluing contour curve subjected to thinning and smoothing according to the principle of proximity according to the distance between two points;
the outline discrete point acquisition module is used for performing three-dimensional curve fitting on the sole gluing outline curve discrete point set after numbering, and performing self-adaptive dispersion to obtain outline discrete points;
and the path calculation module is used for calculating the gluing path according to the contour discrete points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010173127.9A CN111035115B (en) | 2020-03-13 | 2020-03-13 | Sole gluing path planning method and device based on 3D vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010173127.9A CN111035115B (en) | 2020-03-13 | 2020-03-13 | Sole gluing path planning method and device based on 3D vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111035115A CN111035115A (en) | 2020-04-21 |
| CN111035115B true CN111035115B (en) | 2020-06-30 |
Family
ID=70230789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010173127.9A Active CN111035115B (en) | 2020-03-13 | 2020-03-13 | Sole gluing path planning method and device based on 3D vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111035115B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111702772B (en) * | 2020-06-04 | 2022-07-12 | 浙江和生荣智能科技有限公司 | Automatic upper surface guiding and gluing method and system |
| CN114176290B (en) * | 2020-09-14 | 2023-08-18 | 广东天机工业智能***有限公司 | Template-free full-automatic sole glue spraying method, device and storage medium |
| CN112464812B (en) * | 2020-11-27 | 2023-11-24 | 西北工业大学 | Vehicle-based concave obstacle detection method |
| CN112634203B (en) * | 2020-12-02 | 2024-05-31 | 富联精密电子(郑州)有限公司 | Image detection method, electronic device, and computer-readable storage medium |
| CN113219903B (en) * | 2021-05-07 | 2022-08-19 | 东北大学 | Billet optimal shearing control method and device based on depth vision |
| CN113643282A (en) * | 2021-08-31 | 2021-11-12 | 歌尔光学科技有限公司 | Workpiece gluing track generation method and device, electronic equipment and storage medium |
| CN113696181B (en) * | 2021-08-31 | 2023-02-17 | 上海景吾智能科技有限公司 | Robot cleaning route planning method and system suitable for irregular plane |
| CN113907490B (en) * | 2021-10-28 | 2022-07-08 | 福建屹立智能化科技有限公司 | Dynamic following glue spraying method and system |
| CN114747840B (en) * | 2022-05-07 | 2023-10-20 | 东华大学 | Method for adjusting sole gluing posture, storage device and sole gluing robot |
| WO2024087121A1 (en) * | 2022-10-27 | 2024-05-02 | Abb Schweiz Ag | Method, electronic device and computer program product for generating a path |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303229A (en) * | 2007-05-09 | 2008-11-12 | 哈尔滨理工大学 | Structure light 3D measuring technology based on edge gray code and line movement |
| CN110838115A (en) * | 2019-11-12 | 2020-02-25 | 武汉大学 | Ancient cultural relic three-dimensional model change detection method by contour line extraction and four-dimensional surface fitting |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104463851B (en) * | 2014-11-19 | 2018-05-22 | 哈尔滨工业大学深圳研究生院 | A kind of sole edge line automatic tracking method based on robot |
| CN105894120B (en) * | 2016-04-08 | 2021-09-24 | 泉州装备制造研究所 | Sole glue spraying path planning method based on attitude control |
| CN107230246B (en) * | 2016-12-29 | 2020-04-03 | 上海大学 | Three-dimensional scanning point cloud data slicing processing method for sole profile |
| CN107808415B (en) * | 2017-11-17 | 2021-01-26 | 中国科学院合肥物质科学研究院 | Sole edge track and gluing pose extraction method based on machine vision |
| CN110226806B (en) * | 2019-05-07 | 2022-04-01 | 深圳市皕像科技有限公司 | Sole gluing track generation method and device |
| CN110717984A (en) * | 2019-09-10 | 2020-01-21 | 佛山缔乐视觉科技有限公司 | Automatic sole gluing method and system based on three-dimensional reconstruction and storage medium |
-
2020
- 2020-03-13 CN CN202010173127.9A patent/CN111035115B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303229A (en) * | 2007-05-09 | 2008-11-12 | 哈尔滨理工大学 | Structure light 3D measuring technology based on edge gray code and line movement |
| CN110838115A (en) * | 2019-11-12 | 2020-02-25 | 武汉大学 | Ancient cultural relic three-dimensional model change detection method by contour line extraction and four-dimensional surface fitting |
Non-Patent Citations (2)
| Title |
|---|
| "基于三维点云的喷涂机器人路径规划方法研究";童宁;《中国优秀硕士学位论文全文数据库 信息科技辑》;20200229;第4.4.3节 * |
| "面向在线检测***的IGES复杂曲面接口技术研究";张小辉;《中国优秀硕士学位论文全文数据库 信息科技辑》;20130228;第3章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111035115A (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111035115B (en) | Sole gluing path planning method and device based on 3D vision | |
| CN109541997B (en) | Spraying robot rapid intelligent programming method for plane/approximate plane workpiece | |
| CN111299815B (en) | Visual detection and laser cutting trajectory planning method for low-gray rubber pad | |
| CN112348864B (en) | Three-dimensional point cloud automatic registration method for laser contour features of fusion line | |
| CN105046694B (en) | A kind of point cloud rapid registering method based on surface fitting coefficient characteristics | |
| CN111696210A (en) | Point cloud reconstruction method and system based on three-dimensional point cloud data characteristic lightweight | |
| CN108089544B (en) | Trajectory generation method and control system for sole glue spraying robot | |
| CN111077844B (en) | Part accurate machining method based on measured data feature guidance | |
| CN108303037A (en) | A kind of detection method and device of the workpiece surface shape difference based on cloud analysis | |
| CN103310481B (en) | A kind of point cloud compressing method based on fuzzy entropy iteration | |
| CN111702772B (en) | Automatic upper surface guiding and gluing method and system | |
| CN113628263A (en) | Point cloud registration method based on local curvature and neighbor characteristics thereof | |
| CN107598775A (en) | It is a kind of by laser detect the method that simultaneously multi-axis robot is polished | |
| CN115205690B (en) | Method and device for extracting street tree in monomer mode based on MLS point cloud data | |
| CN103049622A (en) | Reverse engineering processing system and method based on space code projection | |
| CN112508895B (en) | Propeller blade quality assessment method based on curved surface registration | |
| CN114972377A (en) | 3D point cloud segmentation method and device based on moving least square method and hyper-voxels | |
| CN110349159B (en) | Three-dimensional shape segmentation method and system based on weight energy adaptive distribution | |
| CN114926699A (en) | Indoor three-dimensional point cloud semantic classification method, device, medium and terminal | |
| CN111179321A (en) | Point cloud registration method based on template matching | |
| CN109102538B (en) | Method for extracting land characteristic points and land characteristic lines by using contour line data and weather map analysis method | |
| CN116452583B (en) | Point cloud defect detection method, device and system and storage medium | |
| CN107490346A (en) | A kind of RFID multi-tags Network Three-dimensional measurement modeling method of view-based access control model | |
| CN111340834B (en) | Lining plate assembly system and method based on laser radar and binocular camera data fusion | |
| CN110288706B (en) | Fitting method of small-curvature irregular point cloud curved surface |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200421 Assignee: Hangzhou Jintou Finance Leasing Co.,Ltd. Assignor: HANGZHOU LANXIN TECHNOLOGY CO.,LTD. Contract record no.: X2023980031743 Denomination of invention: A method and device for shoe sole gluing path planning based on 3D vision Granted publication date: 20200630 License type: Exclusive License Record date: 20230202 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method and device for shoe sole gluing path planning based on 3D vision Effective date of registration: 20230207 Granted publication date: 20200630 Pledgee: Hangzhou Jintou Finance Leasing Co.,Ltd. Pledgor: HANGZHOU LANXIN TECHNOLOGY CO.,LTD. Registration number: Y2023110000056 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: Hangzhou Jintou Finance Leasing Co.,Ltd. Assignor: HANGZHOU LANXIN TECHNOLOGY CO.,LTD. Contract record no.: X2023980031743 Date of cancellation: 20240402 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Granted publication date: 20200630 Pledgee: Hangzhou Jintou Finance Leasing Co.,Ltd. Pledgor: HANGZHOU LANXIN TECHNOLOGY CO.,LTD. Registration number: Y2023110000056 |