CN107808415A - Sole edge track and gluing pose extracting method based on machine vision - Google Patents

Sole edge track and gluing pose extracting method based on machine vision Download PDF

Info

Publication number
CN107808415A
CN107808415A CN201711144047.5A CN201711144047A CN107808415A CN 107808415 A CN107808415 A CN 107808415A CN 201711144047 A CN201711144047 A CN 201711144047A CN 107808415 A CN107808415 A CN 107808415A
Authority
CN
China
Prior art keywords
point
sole
curve
gluing
sole edge
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.)
Granted
Application number
CN201711144047.5A
Other languages
Chinese (zh)
Other versions
CN107808415B (en
Inventor
吴晶华
朱柯宇
申红银
路晓波
王子健
张萍
杨书强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hefei Institutes of Physical Science of CAS
Original Assignee
Hefei Institutes of Physical Science of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hefei Institutes of Physical Science of CAS filed Critical Hefei Institutes of Physical Science of CAS
Priority to CN201711144047.5A priority Critical patent/CN107808415B/en
Publication of CN107808415A publication Critical patent/CN107808415A/en
Application granted granted Critical
Publication of CN107808415B publication Critical patent/CN107808415B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/10—Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
    • 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
    • G06T7/50—Depth or shape recovery
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computer Graphics (AREA)
  • Software Systems (AREA)
  • Image Processing (AREA)
  • Manipulator (AREA)
  • Application Of Or Painting With Fluid Materials (AREA)

Abstract

The invention discloses a kind of sole edge track based on machine vision and gluing pose extracting method, it is characterized in that obtain sole curved surface initial three-dimensional cloud data first with 3D laser sensor, denoising three dimensional point cloud is obtained by filtering process, sole curved surface scanning profile diagram is formed with denoising three dimensional point cloud；Then denoising three dimensional point cloud is subjected to dimension-reduction treatment, and is mapped as two-dimensional depth image；Data processing is carried out for two-dimensional depth image, so as to obtain sole edge geometric locus；Gluing spray gun track curve is obtained using offset algorithm and curve matching for the sole edge geometric locus again, the gluing pose for obtaining spray gun operating point is calculated according to the gluing spray gun track curve.The present invention realizes Intelligent Recognition sole profile and extracts sole edge curve, and operating position and the posture of robot coating are obtained by data processing, it is not necessary to manually participates in.

Description

Sole edge track and gluing pose extracting method based on machine vision
Technical field
The present invention relates to a kind of sole glue spraying track extraction method applied to sole processing manufacturing industry, and in particular to is based on The intelligent shoe bottom glue spraying method of machine vision technique.
Background technology
With application of the digital production technology in shoe industry, robot is progressively applied in shoes glue spraying process, mesh Preceding glue spraying track is generally obtained using the method for teaching, realizes the automation of glue spraying process to a certain extent, but it Adaptability it is not strong, be required for re-starting programming for different styles, the customization of different size shoes, programming process needs specially Industry personage artificially participates in, and the cumbersome efficiency of process is low, and precision is not easy to control, and is substantially by demonstrator's range estimation to determine.
In recent years, also occur relying on 3 Dimension Image Technique to carry out the technology to spray piece modeling, but it is not mature enough, modeled Journey relies on artificial participate in, it is necessary to be post-processed for threedimensional model, progress manual edit and optimization.The side of the shortcomings of doing so one Face can not accomplish automation, it is necessary to which the threedimensional model editor of specialty recognizes participation, and error occurs unavoidably in another aspect human-edited, Cause model not accurate enough, finally influence spraying effect.Sole edge profile acquiring technology is very crucial in intelligent shoe industry, will Determine the precision of the actual glue spraying track of generation.
The content of the invention
It is an object of the invention to provide a kind of sole edge track based on machine vision and gluing pose extracting method, Realize Intelligent Recognition sole profile and extract sole edge curve, and the operating position of robot coating is obtained by data processing And posture.
The present invention adopts the following technical scheme that to solve technical problem：
The characteristics of sole edge track of the present invention based on machine vision and gluing pose extracting method is as follows Carry out：
Step 1, using 3D laser sensor sole curved surface initial three-dimensional cloud data is obtained, it is former for the sole curved surface Beginning three dimensional point cloud uses median filter process, filters out 3D laser sensor and gathers the glitch noise to be formed, obtains denoising three Cloud data is tieed up, sole curved surface scanning profile diagram is formed with the denoising three dimensional point cloud；
Step 2, the denoising three dimensional point cloud is subjected to dimension-reduction treatment, and is mapped as two-dimensional depth image；For institute State two-dimensional depth image and carry out data processing, so as to obtain sole edge geometric locus；
Step 3, offset algorithm and curve matching acquisition gluing spray gun track are used for the sole edge geometric locus Curve, the gluing pose for obtaining spray gun operating point is calculated according to the gluing spray gun track curve.
The characteristics of sole edge track of the present invention based on machine vision and gluing pose extracting method, lies also in：The step Mapping in rapid 2 refers to：Point P (x, y, z) in sole curved surface is sequentially stored in and denoising three-dimensional in the way of a line one arranges Cloud data corresponds to the two-dimensional depth image that m × n is formed in the picture of ranks, and m is image line, and n is image column, at the data Reason is to carry out as follows：
Step 2.1, for m × n two-dimensional depth image to m rows, all traveled through from left to right, until for the first time Untill meeting formula (1), the point for meeting formula (1) for the first time is recorded in left data point set QleftIn；
Step 2.2, for m × n two-dimensional depth image to m rows, turn left and traveled through from the right side, until meeting formula for the first time (1) untill, the point for meeting formula (1) for the first time is recorded in right data point set QrightIn；
f(i,j)[2]≠0 (1)
I is the line number of image, and j is the columns of image；
F (i, j) represents the i-th row, the triple channel pixel value of jth row；
F (i, j) [u] represents the i-th row, the u passage pixel values of jth row, 0≤u≤2；
Step 2.3, by left data point set QleftIn first point be sequentially mapped to data point set Q to a last pointi In, and by right data point set QrightIn last o'clock be sequentially recorded in data point set Q to first pointiIn, then QiMiddle number The point of strong point collection is the discrete point of sole edge geometric locus, therefore obtains the discrete curve Q of sole edge geometric locusi。
The characteristics of sole edge track of the present invention based on machine vision and gluing pose extracting method, lies also in：Described It is the discrete curve Q of the sole edge geometric locus to be obtained in step 2 in step 3iAs sole edge contour curve, institute Stating sole edge contour curve is made up of equally spaced collection point, for adopting for the sole edge contour curve equal intervals Collection point takes out each 3 points group at adjacent o'clock successively using three as one group, order：It is p respectively to take three points in any 3 points groupk Point, pk+1Point and pk+2Point, with the pkPoint, pk+1Point and pk+2Point determines a spatial triangle plane Hk, determine the space triangular Shape plane HkNormal direction, and the geometric center point e of the spatial triangle planek；In three dimensions, with the geometry Heart point ekCentered on, using r as radius, excessively described normal direction makes the space circle C perpendicular with sole curved surface scanning profile diagramk, it is described Space circle CkOnly one point, which is intersected at, with sole curved surface scanning profile diagram is designated as intersection point Mk, it is bent for the sole edge profile All intersection point M are found out in all equally spaced collection points on linekPoint as on bias curve, using least square method to all Intersection point MkCarry out curve fitting, obtain actual spray gun track curve, the actual spray gun track curve meter for recycling fitting to obtain Calculate the operating position for obtaining robot coating and posture.
Compared with prior art, the present invention has the beneficial effect that：
The inventive method need not be directed to different sizes, and the sole of different styles is programmed, and spraying path is according to footwear The surface dynamic generation at bottom, even if having changed sole or having put orientation, without manual intervention；Can be with automatic identification sole Size, style, you can extracted for different sole shape march thread paths, without specialty, modeling personage enters to different soles Row three-dimensional modeling.
Brief description of the drawings
Fig. 1 is the inventive method schematic flow sheet；
Fig. 2 is that the inventive method implements system schematic；
Label in figure：1 delivery platform, 2 soles, 3 computers, 4 be 3D laser sensor, 5 Glue Spreading Robots.
Embodiment
Referring to Fig. 1 and Fig. 2, sole edge track and gluing pose extracting method in the present embodiment based on machine vision are Carry out as follows：
Step 1, using 3D laser sensor obtain sole curved surface initial three-dimensional cloud data, for sole curved surface original three Dimension cloud data uses median filter process, filters out 3D laser sensor and gathers the glitch noise to be formed, obtains denoising three-dimensional point Cloud data, sole curved surface scanning profile diagram is formed with denoising three dimensional point cloud.
Step 2, denoising three dimensional point cloud is subjected to dimension-reduction treatment, and is mapped as two-dimensional depth image；For two-dimentional deep Spend image and carry out data processing, so as to obtain sole edge geometric locus.
Mapping refers to：Point P (x, y, z) in sole curved surface is sequentially stored in and denoising three-dimensional in the way of a line one arranges Cloud data corresponds to the two-dimensional depth image that m × n is formed in the picture of ranks, and m is image line, and n is image column, and data processing is Carry out as follows：
Step 2.1, for m × n two-dimensional depth image to m rows, all traveled through from left to right, until for the first time Untill meeting formula (1), the point for meeting formula (1) for the first time is recorded in left data point set QleftIn；
Step 2.2, for m × n two-dimensional depth image to m rows, all turn left from the right side being traveled through, until for the first time Untill meeting formula (1), the point for meeting formula (1) for the first time is recorded in right data point set QrightIn；
f(i,j)[2]≠0 (1)
I is the line number of image, and j is the columns of image；
F (i, j) represents the i-th row, the triple channel pixel value of jth row；
F (i, j) [u] represents the i-th row, the u passage pixel values of jth row, 0≤u≤2；
Step 2.3, by left data point set QleftIn first point be sequentially mapped to data point set Q to a last pointi In, and by right data point set QrightIn last o'clock be sequentially recorded in data point set Q to first pointiIn, then QiMiddle number The point of strong point collection is the discrete point of sole edge geometric locus, therefore obtains the discrete curve Q of sole edge geometric locusi。
Step 3, offset algorithm and curve matching acquisition gluing spray gun track curve are used for sole edge geometric locus, The gluing pose for obtaining spray gun operating point is calculated according to gluing spray gun track curve.
Specifically with the discrete curve Q of the sole edge geometric locus obtained in step 2iIt is bent as sole edge profile Line, sole edge contour curve are made up of equally spaced collection point, the collection for sole edge contour curve equal intervals O'clock each 3 points group is taken out successively as one group at adjacent o'clock, make using three：It is p respectively to take three points in any 3 points groupkPoint, pk+1Point and pk+2Point, with pkPoint, pk+1Point and pk+2Point determines a spatial triangle plane Hk, determine spatial triangle plane Hk's Normal direction, and the geometric center point e of spatial triangle planek；In three dimensions, with geometric center point ekCentered on, using r as Radius, cross normal direction and make the space circle C perpendicular with sole curved surface scanning profile diagramk, space circle CkWith sole curved surface scanning profile Figure intersects at only one point and is designated as intersection point Mk, found out for all equally spaced collection points on sole edge contour curve all Intersection point MkPoint as on bias curve, using least square method to all intersection point MkCarry out curve fitting, obtain actual spray Rifle geometric locus, recycle the curve of fitting to calculate the operating position for obtaining robot coating and posture, control Glue Spreading Robot Gluing is carried out according to acquired operating position and posture.
Fig. 2 show the inventive method and implements system schematic, treats that the sole 2 of gluing is placed on delivery platform 1, with biography Send platform 1 to move ahead, gathered by 3D laser sensor 4 obtain sole curved surface initial three-dimensional cloud data first, and data are transmitted To computer 3, data processing is carried out by the inventive method in computer 3, finally obtains the gluing pose of spray gun operating point, by Computer 3 controls Glue Spreading Robot 5 to carry out gluing according to acquired operating position and posture.

Claims (3)

1. a kind of sole edge track and gluing pose extracting method based on machine vision, it is characterized in that entering as follows OK：
Step 1, using 3D laser sensor obtain sole curved surface initial three-dimensional cloud data, for the sole curved surface original three Dimension cloud data uses median filter process, filters out 3D laser sensor and gathers the glitch noise to be formed, obtains denoising three-dimensional point Cloud data, sole curved surface scanning profile diagram is formed with the denoising three dimensional point cloud；
Step 2, the denoising three dimensional point cloud is subjected to dimension-reduction treatment, and is mapped as two-dimensional depth image；For described two Tie up depth image and carry out data processing, so as to obtain sole edge geometric locus；
Step 3, offset algorithm and curve matching acquisition gluing spray gun track curve are used for the sole edge geometric locus, The gluing pose for obtaining spray gun operating point is calculated according to the gluing spray gun track curve.
2. sole edge track and gluing pose extracting method according to claim 1 based on machine vision, its feature It is：Mapping in the step 2 refers to：By the point P (x, y, z) in sole curved surface by a line one arrange in the way of be sequentially stored in Denoising three dimensional point cloud corresponds to the two-dimensional depth image that m × n is formed in the picture of ranks, and m is image line, and n is image column, institute It is to carry out as follows to state data processing：
Step 2.1, for m × n two-dimensional depth image to m rows, all traveled through, met until first time from left to right Untill formula (1), the point for meeting formula (1) for the first time is recorded in left data point set QleftIn；
Step 2.2, for m × n two-dimensional depth image to m rows, turn left and traveled through from the right side, until meeting formula (1) for the first time Untill, the point for meeting formula (1) for the first time is recorded in right data point set QrightIn；
f(i,j)[2]≠0 (1)
I is the line number of image, and j is the columns of image；
F (i, j) represents the i-th row, the triple channel pixel value of jth row；
F (i, j) [u] represents the i-th row, the u passage pixel values of jth row, 0≤u≤2；
Step 2.3, by left data point set QleftIn first point be sequentially mapped to data point set Q to a last pointiIn, and By right data point set QrightIn last o'clock be sequentially recorded in data point set Q to first pointiIn, then QiMiddle data point set Point be sole edge geometric locus discrete point, therefore obtain sole edge geometric locus discrete curve Qi。
3. sole edge track and gluing pose extracting method according to claim 2 based on machine vision, its feature It is：It is the discrete curve Q of the sole edge geometric locus to be obtained in step 2 in the step 3iAs sole edge wheel Wide curve, the sole edge contour curve are made up of equally spaced collection point, in the sole edge contour curve Each 3 points group is taken out at adjacent o'clock in equally spaced collection point successively using three as one group, makes：Take three in any 3 points group Point is p respectivelykPoint, pk+1Point and pk+2Point, with the pkPoint, pk+1Point and pk+2Point determines a spatial triangle plane Hk, determine institute State spatial triangle plane HkNormal direction, and the geometric center point e of the spatial triangle planek；In three dimensions, with The geometric center point ekCentered on, using r as radius, excessively described normal direction makes the sky perpendicular with sole curved surface scanning profile diagram Between circle Ck, the space circle CkOnly one point, which is intersected at, with sole curved surface scanning profile diagram is designated as intersection point Mk, for the sole All intersection point M are found out in all equally spaced collection points on edge contour curvekPoint as on bias curve, utilizes a most young waiter in a wineshop or an inn Multiplication is to all intersection point MkCarry out curve fitting, obtain actual spray gun track curve, the actual spray gun for recycling fitting to obtain Geometric locus calculates the operating position for obtaining robot coating and posture.
CN201711144047.5A 2017-11-17 2017-11-17 Sole edge track and gluing pose extraction method based on machine vision Active CN107808415B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711144047.5A CN107808415B (en) 2017-11-17 2017-11-17 Sole edge track and gluing pose extraction method based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711144047.5A CN107808415B (en) 2017-11-17 2017-11-17 Sole edge track and gluing pose extraction method based on machine vision

Publications (2)

Publication Number Publication Date
CN107808415A true CN107808415A (en) 2018-03-16
CN107808415B CN107808415B (en) 2021-01-26

Family

ID=61590394

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711144047.5A Active CN107808415B (en) 2017-11-17 2017-11-17 Sole edge track and gluing pose extraction method based on machine vision

Country Status (1)

Country Link
CN (1) CN107808415B (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108537808A (en) * 2018-04-08 2018-09-14 易思维（天津）科技有限公司 A kind of gluing online test method based on robot teaching point information
CN109459759A (en) * 2018-11-13 2019-03-12 中国科学院合肥物质科学研究院 City Terrain three-dimensional rebuilding method based on quadrotor drone laser radar system
CN109590140A (en) * 2018-12-26 2019-04-09 易视智瞳科技（深圳）有限公司 A kind of coating system and its method, automatic double surface gluer and computer readable storage medium
CN109916308A (en) * 2019-01-14 2019-06-21 佛山市南海区广工大数控装备协同创新研究院 A kind of information collecting method and its system of sole
CN110189376A (en) * 2019-05-06 2019-08-30 达闼科技（北京）有限公司 Object positioning method and positioning device for body
CN110269323A (en) * 2019-07-17 2019-09-24 东莞特雷斯智能科技有限公司 A kind of coating system for sole track identification
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
CN111035115A (en) * 2020-03-13 2020-04-21 杭州蓝芯科技有限公司 Sole gluing path planning method and device based on 3D vision
CN111055286A (en) * 2020-01-13 2020-04-24 广州启帆工业机器人有限公司 Industrial robot track generation method, system, device and storage medium
CN111227444A (en) * 2020-01-17 2020-06-05 泉州装备制造研究所 3D sole glue spraying path planning method based on k nearest neighbor
CN111820545A (en) * 2020-06-22 2020-10-27 浙江理工大学 Method for automatically generating sole glue spraying track by combining offline and online scanning
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
CN113095337A (en) * 2021-04-23 2021-07-09 知守科技(杭州)有限公司 Multicolor sole target extraction method, device and system and electronic device
CN113223030A (en) * 2021-04-20 2021-08-06 梅卡曼德（北京）机器人科技有限公司 Glass gluing method and device, electronic equipment and storage medium
CN114049366A (en) * 2021-10-28 2022-02-15 福建屹立智能化科技有限公司 Method for 3D visual extraction of gluing track of sole and storage device
CN114176290A (en) * 2020-09-14 2022-03-15 广东天机工业智能***有限公司 Template-free full-automatic sole glue spraying method and device and storage medium
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
CN114794669A (en) * 2022-03-31 2022-07-29 深圳市如本科技有限公司 Vamp gluing track generation method and system, computer equipment and storage medium
WO2022222934A1 (en) * 2021-04-20 2022-10-27 梅卡曼德（北京）机器人科技有限公司 Glass adhesive coating method, glass adhesive coating apparatus, electronic device, and storage medium
WO2022237166A1 (en) * 2021-05-11 2022-11-17 梅卡曼德（北京）机器人科技有限公司 Trajectory generation method and apparatus, electronic device, storage medium, and 3d camera
CN115969144A (en) * 2023-01-09 2023-04-18 东莞市智睿智能科技有限公司 Sole glue spraying track generation method, system, equipment and storage medium
CN117392163A (en) * 2023-12-11 2024-01-12 泉州华中科技大学智能制造研究院 3D vision-based method for extracting track of collar sticker of shoe

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104463851A (en) * 2014-11-19 2015-03-25 哈尔滨工业大学深圳研究生院 Automatic shoe sole edge line tracking method based on robot
CN106123773A (en) * 2016-06-14 2016-11-16 中国科学院合肥物质科学研究院 A kind of industrial robot sole gluing track positioner and localization method thereof
CN107230246A (en) * 2016-12-29 2017-10-03 上海大学 A kind of 3-D scanning cloud data sliced sheet processing method of sole profile

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104463851A (en) * 2014-11-19 2015-03-25 哈尔滨工业大学深圳研究生院 Automatic shoe sole edge line tracking method based on robot
CN106123773A (en) * 2016-06-14 2016-11-16 中国科学院合肥物质科学研究院 A kind of industrial robot sole gluing track positioner and localization method thereof
CN107230246A (en) * 2016-12-29 2017-10-03 上海大学 A kind of 3-D scanning cloud data sliced sheet processing method of sole profile

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
汪安国: "基于结构光的鞋底信息提取与机器人喷胶轨迹", 《浙江理工大学硕士学位论文》 *

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108537808A (en) * 2018-04-08 2018-09-14 易思维（天津）科技有限公司 A kind of gluing online test method based on robot teaching point information
CN108537808B (en) * 2018-04-08 2019-02-22 易思维（天津）科技有限公司 A kind of gluing online test method based on robot teaching point information
CN109459759A (en) * 2018-11-13 2019-03-12 中国科学院合肥物质科学研究院 City Terrain three-dimensional rebuilding method based on quadrotor drone laser radar system
CN109459759B (en) * 2018-11-13 2020-06-30 中国科学院合肥物质科学研究院 Urban terrain three-dimensional reconstruction method based on quad-rotor unmanned aerial vehicle laser radar system
CN109590140A (en) * 2018-12-26 2019-04-09 易视智瞳科技（深圳）有限公司 A kind of coating system and its method, automatic double surface gluer and computer readable storage medium
CN109916308A (en) * 2019-01-14 2019-06-21 佛山市南海区广工大数控装备协同创新研究院 A kind of information collecting method and its system of sole
CN110189376A (en) * 2019-05-06 2019-08-30 达闼科技（北京）有限公司 Object positioning method and positioning device for body
CN110269323A (en) * 2019-07-17 2019-09-24 东莞特雷斯智能科技有限公司 A kind of coating system for sole track identification
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
CN111055286A (en) * 2020-01-13 2020-04-24 广州启帆工业机器人有限公司 Industrial robot track generation method, system, device and storage medium
CN111227444A (en) * 2020-01-17 2020-06-05 泉州装备制造研究所 3D sole glue spraying path planning method based on k nearest neighbor
CN111035115A (en) * 2020-03-13 2020-04-21 杭州蓝芯科技有限公司 Sole gluing path planning method and device based on 3D vision
CN111820545A (en) * 2020-06-22 2020-10-27 浙江理工大学 Method for automatically generating sole glue spraying track by combining offline and online scanning
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
CN114176290A (en) * 2020-09-14 2022-03-15 广东天机工业智能***有限公司 Template-free full-automatic sole glue spraying method and device and storage medium
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
CN113223030A (en) * 2021-04-20 2021-08-06 梅卡曼德（北京）机器人科技有限公司 Glass gluing method and device, electronic equipment and storage medium
WO2022222934A1 (en) * 2021-04-20 2022-10-27 梅卡曼德（北京）机器人科技有限公司 Glass adhesive coating method, glass adhesive coating apparatus, electronic device, and storage medium
CN113095337A (en) * 2021-04-23 2021-07-09 知守科技(杭州)有限公司 Multicolor sole target extraction method, device and system and electronic device
WO2022237166A1 (en) * 2021-05-11 2022-11-17 梅卡曼德（北京）机器人科技有限公司 Trajectory generation method and apparatus, electronic device, storage medium, and 3d camera
CN114049366A (en) * 2021-10-28 2022-02-15 福建屹立智能化科技有限公司 Method for 3D visual extraction of gluing track of sole and storage device
CN114794669A (en) * 2022-03-31 2022-07-29 深圳市如本科技有限公司 Vamp gluing track generation method and system, computer equipment and storage medium
CN115969144A (en) * 2023-01-09 2023-04-18 东莞市智睿智能科技有限公司 Sole glue spraying track generation method, system, equipment and storage medium
CN117392163A (en) * 2023-12-11 2024-01-12 泉州华中科技大学智能制造研究院 3D vision-based method for extracting track of collar sticker of shoe
CN117392163B (en) * 2023-12-11 2024-04-12 泉州华中科技大学智能制造研究院 3D vision-based method for extracting track of collar sticker of shoe

Also Published As

Publication number Publication date
CN107808415B (en) 2021-01-26

Similar Documents

Publication Publication Date Title
CN107808415A (en) Sole edge track and gluing pose extracting method based on machine vision
CN102880866B (en) Method for extracting face features
US7912583B2 (en) Environment map building method, environment map building apparatus and mobile robot apparatus
US9373190B2 (en) High-quality stereo reconstruction featuring depth map alignment and outlier identification
CN103733226B (en) Quickly there is the tracking of joint motions
CN107590831B (en) Stereo matching method based on deep learning
CN110717984A (en) Automatic sole gluing method and system based on three-dimensional reconstruction and storage medium
CN112465767A (en) Industrial robot sole gluing track extraction method
CN110876512B (en) Control method of high-precision automatic gluing system for soles
CN104463851A (en) Automatic shoe sole edge line tracking method based on robot
CN101894377B (en) Tracking method of three-dimensional mark point sequence and system thereof
CN105574933B (en) The comprehensive profile accurate Drawing method of object
CN108305283A (en) Human bodys' response method and device based on depth camera and basic form
CN112435239A (en) Scindapsus aureus leaf shape parameter estimation method based on MRE-PointNet and self-encoder model
CN106570877B (en) Based on coal-winning machine virtual prototype the coal-winning machine pose alignment system and method registering with true picture
CN103942829A (en) Single-image human body three-dimensional posture reconstruction method
CN110731581A (en) method for spraying glue by collecting 3D shape of sole
CN105608737A (en) Human foot three-dimensional reconstruction method based on machine learning
CN111227444A (en) 3D sole glue spraying path planning method based on k nearest neighbor
CN111820545A (en) Method for automatically generating sole glue spraying track by combining offline and online scanning
CN109859099A (en) The quick minimizing technology of potting corn weeds based on SFM point cloud depth degree
CN107093182B (en) A kind of human height's estimation method based on feature corners
CN103914873B (en) A kind of sculpture threedimensional model driven according to human action generates method
CN114504170A (en) Method and system for spraying glue on soles of flaky soles and storage medium
CN111546337A (en) Industrial robot full-coverage path generation method and system based on free-form 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