CN110223350A - A kind of building blocks automatic sorting method and system based on binocular vision - Google Patents
A kind of building blocks automatic sorting method and system based on binocular vision Download PDFInfo
- Publication number
- CN110223350A CN110223350A CN201910432830.4A CN201910432830A CN110223350A CN 110223350 A CN110223350 A CN 110223350A CN 201910432830 A CN201910432830 A CN 201910432830A CN 110223350 A CN110223350 A CN 110223350A
- Authority
- CN
- China
- Prior art keywords
- building blocks
- sorting
- color
- image
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000006243 chemical reaction Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 7
- 239000002023 wood Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 230000011218 segmentation Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10024—Color image
-
- 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
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of building blocks automatic sorting method and system based on binocular vision, wherein this method comprises: being demarcated to camera；The building blocks on line conveyor are acquired by calibrated camera, generate building blocks figure；The building blocks figure is pre-processed, pretreated building blocks figure is obtained；Image conversion is carried out to the pretreated building blocks figure, determines the color of building blocks；Image after determining building blocks color is handled, spatial positional information locating for the building blocks is obtained；The picture of camera acquisition is handled, the building blocks information as sorting target is obtained；The spatial positional information and the building blocks information as sorting target are sent to robot and carry out building blocks sorting.In embodiments of the present invention, building blocks spatial position is identified using the method for binocular vision and automatically grab building blocks, realize the identification of building blocks in industrial building blocks production and automatically grabbed, to solve the problems, such as that low efficiency, accuracy rate are low in building blocks sorting.
Description
Technical field
The present invention relates to industrial automation identification and technical field of machine vision more particularly to a kind of based on binocular vision
Building blocks automatic sorting method and system.
Background technique
In industrial automation identification technology development process, workpiece sorting is a cumbersome job, initial sorting side
Method is manual sorting, and the speed and accuracy of sorting both depend on proficiency of workers, tired degree and working attitude.Together
When, the sorting of certain industries has certain risk or has strict demand to the sanitary conditions of sorting environment.Therefore, it realizes
The sorting automation of workpiece has great importance.The accessory that type, shape, the color of building blocks are various and numerous also gives building blocks
Sorting bring a great deal of trouble trouble.
Can the key that realize workpiece sorting automation be the specific location that accurately identify to grabbing workpiece, and quickly quasi-
Really grab and place workpiece.In terms of non-cpntact measurement, mainly there are laser depth measurement, radar surveying etc..Laser measurement is
Object is measured by high-frequency laser pluses, such mode is expensive, is not suitable for the three-dimensional localization to workpiece；Radar
Ranging is then to analyze the identification that the reflected signal of target workpiece carries out distance by issuing radar signal, and the method is held
Vulnerable to influence of noise, on the more workpiece sorting production line of noise and it is not suitable for.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, and the present invention provides a kind of building blocks based on binocular vision
Automatic sorting method and system in the production of industrial building blocks, it can be achieved that the identification of building blocks and automatically grab, to solve building blocks sorting
The low problem of middle low efficiency, accuracy rate.
To solve the above-mentioned problems, the invention proposes a kind of building blocks automatic sorting method based on binocular vision, it is described
Method includes:
Camera is demarcated；
The building blocks on line conveyor are acquired by calibrated camera, generate building blocks figure；
The building blocks figure is pre-processed, pretreated building blocks figure is obtained；
Image conversion is carried out to the pretreated building blocks figure, determines the color of building blocks；
Image after determining building blocks color is handled, spatial positional information locating for the building blocks is obtained；
The picture of camera acquisition is handled, the building blocks information as sorting target is obtained；
The spatial positional information and the building blocks information as sorting target are sent to robot and carry out building blocks sorting.
Preferably, described the step of is carried out by image conversion, determines the color of building blocks for the pretreated building blocks figure, packet
It includes:
HSV image is converted by RGB image to the pretreated building blocks figure；
The regularity of distribution according to building blocks in HSV space distinguishes the color of the building blocks in building blocks figure, determines building blocks
Color.
Preferably, the image after described pair of determining building blocks color is handled, and obtains space bit confidence locating for the building blocks
The step of breath, comprising:
Corresponding world coordinate system is calculated with the relationship of world coordinate system according to image coordinate system, obtains the building blocks institute
The spatial positional information at place.
Preferably, the picture to camera acquisition is handled, and obtains the building blocks information as sorting target
Step, comprising:
Simultaneously gray proces are corrected to the picture of camera acquisition, obtain gray scale picture；
The gray scale picture is handled, the building blocks of overlapping building blocks the top is chosen as sorting target, obtains conduct
Sort the building blocks information of target.
Preferably, the described the step of building blocks figure is pre-processed, obtains pretreated building blocks figure, comprising:
The building blocks figure is pre-processed using median filter method, the building blocks figure after being filtered.
Correspondingly, the present invention also provides a kind of building blocks Automated Sorting System based on binocular vision, the system comprises:
Camera calibration module, for being demarcated to camera；
Image generation module generates building blocks figure for acquiring the building blocks on line conveyor by calibrated camera；
Preprocessing module obtains pretreated building blocks figure for pre-processing to the building blocks figure；
Color determination module determines the color of building blocks for carrying out image conversion to the pretreated building blocks figure；
Spatial position obtains module, for handling the image after determining building blocks color, obtains locating for the building blocks
Spatial positional information；
Information determination module is sorted, the picture for acquiring to the camera is handled, and is obtained as sorting target
Building blocks information；
Sending module, for by the spatial positional information and as sorting target building blocks information be sent to robot into
The sorting of row building blocks.
Preferably, the color determination module includes:
Conversion unit, for being converted into HSV image by RGB image to the pretreated building blocks figure；
Discrimination unit carries out area to the color of the building blocks in building blocks figure for the regularity of distribution according to building blocks in HSV space
Point, determine the color of building blocks.
Preferably, the spatial position obtains module and is also used to be calculated according to the relationship of image coordinate system and world coordinate system
Corresponding world coordinate system out obtains spatial positional information locating for the building blocks.
Preferably, the sorting information determination module includes:
Gray scale processing unit, the picture for acquiring to the camera is corrected and gray proces, obtains gray scale picture；
Object selection unit chooses the building blocks conduct of overlapping building blocks the top for handling the gray scale picture
Target is sorted, the building blocks information as sorting target is obtained.
Preferably, the preprocessing module is also used for median filter method and pre-processes to the building blocks figure, obtains
Building blocks figure after must being filtered.
In embodiments of the present invention, building blocks spatial position is identified using the method for binocular vision and automatically grab building blocks,
It realizes the identification of building blocks in industrial building blocks production and automatically grabs, to solve that low efficiency in building blocks sorting, accuracy rate is low asks
Topic, and can continuously sort and not influenced by work human efficiency；Meanwhile it being combined using binocular vision and mechanical arm
Mode, stability is high, at low cost, easy for installation.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the flow diagram of the building blocks automatic sorting method based on binocular vision of the embodiment of the present invention；
Fig. 2 is the flow diagram of the camera calibration of the embodiment of the present invention；
Fig. 3 is HSV model schematic in the embodiment of the present invention；
Fig. 4 is the structure composition schematic diagram of the building blocks Automated Sorting System based on binocular vision of the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is the flow diagram of the building blocks automatic sorting method based on binocular vision of the embodiment of the present invention, such as Fig. 1 institute
Show, this method comprises:
S1 demarcates camera；
S2 acquires the building blocks on line conveyor by calibrated camera, generates building blocks figure；
S3 pre-processes building blocks figure, obtains pretreated building blocks figure；
S4 carries out image conversion to pretreated building blocks figure, determines the color of building blocks；
S5 handles the image after determining building blocks color, obtains spatial positional information locating for the building blocks；
S6 handles the picture of camera acquisition, obtains the building blocks information as sorting target；
Spatial positional information and the building blocks information as sorting target are sent to robot and carry out building blocks sorting by S7.
In embodiments of the present invention, left and right camera is demarcated first, in Binocular Stereo Vision System, camera
Calibration is primarily to solve the geometric parameter of camera, the inner parameter including camera model and the sky relative to target workpiece
Between position external parameter.Three-dimensional information of the object in world coordinate system can be obtained by camera calibration.The present invention utilizes two dimension
Scaling board carries out not having to angle and direction shooting, then carries out knowledge method for distinguishing to calibration.Calculated linear optimization
Solution is carried out non-linear solution again by maximum likelihood method and obtains the parameter of camera.The flow chart of camera calibration is as shown in Figure 2: left,
Right camera obtains picture respectively, completes the extraction of center picture point, respectively completes calibration, final to carry out double camera calibration.
In S3, it is preferable that pre-processed using median filter method to building blocks figure, the building blocks after being filtered
Figure.
In specific implementation, to camera acquisition building blocks figure pre-process, can be used mean filter, gaussian filtering and in
The methods of value filtering is pre-processed, and by comparison treated image, the processing result of median filter method is preferable, therefore,
The present embodiment pre-processes building blocks image using median filtering.
S4 further comprises:
HSV image is converted by RGB image to pretreated building blocks figure；
The regularity of distribution according to building blocks in HSV space distinguishes the color of the building blocks in building blocks figure, determines building blocks
Color.
In specific implementation, building blocks figure is converted into HSV image by RGB image, RGB (red, green, blue) is according to eye recognition
The space that defines of color, can indicate most of color.But generally do not use rgb space because the component of rgb space with it is bright
Spend closely related, as long as that is, brightness changes, 3 components all can correspondingly change therewith.HSV (hue, saturation, intensity) basis
What the intuitive nature of color proposed, this space can react eyes for the sensing capability of color very well.Its model such as Fig. 3 institute
Show.HSV model corresponds to a conical subset in cylindrical-coordinate system, and the top surface of circular cone corresponds to V=1.It includes RGB mould
R=1 in type, G=1, tri- faces B=1, representative color are brighter.Color H around the rotation angle of V axis by giving.Red is corresponding
In 0 ° of angle, green corresponds to 120 ° of angle, and blue corresponds to 240 ° of angle.In hsv color model, each color and it
Complementary color differ 180 °.Saturation degree S value is from 0 to 1, so the radius of circular cone top surface is 1.
HSV space is converted to from rgb space.Its conversion formula is as follows:
R'=R/255；G'=G/255；B'=B/255；
Cmax=max (R', G', B')；
Cmin=min (R', G', B')；
Δ=Cmax-Cmin；
V=Cmax
The value of color image RGB is Unit8 type originally, and the range of value is 0-255, for convenience of calculating, is converted into using RGB
Double type, the range of value are 0-1, use R ', G ', B respectively ' it indicates, Cmax in formula, Cmin are respectively represented in (R ', G ', B ')
Maximum value and minimum value after converting using rgb space, can carry out Threshold segmentation in information of the HSV space to H, S, V of image,
So that it is determined that the different colours of building blocks.In specific implementation, according to building blocks HSV space the regularity of distribution, it is right in conjunction with Otsu algorithm
The color of building blocks distinguishes in picture.The threshold value of various colors building blocks is as follows:
White: V > 0.88；S≤0.1；
Black: V≤0.18；
It is red: 9 π/5 < H≤2 π；V>0.18；S>0.17；
Green: 2 π/5 < H≤4 π/5；V>0.18；S>0.17；
Yellow: 3 π/10 < H≤2 π/5；V>0.18；S>0.17；
Blue: 10 π/9 < H≤4 π/3；V>0.18；S>0.17；
Wherein: H ∈ [0,2 π], V ∈ [0,1], S ∈ [0,1].
In S5, corresponding world coordinates is calculated with the relationship of world coordinate system according further to image coordinate system
System, obtains spatial positional information locating for the building blocks.
By calculating the image analysis image coordinate system of acquisition, to calculate corresponding world coordinate system:
Wherein, (ul,vl),(ur,vr) it is coordinate value of the spatial point on the camera image of left and right；Ml,MrFor left and right camera
Projection matrix, XW,YW,ZWFor the three-dimensional coordinate of spatial point to be asked, mlAnd mrRespectively MlAnd MrElement.To two formula simultaneous above
Eliminate Zl,ZrIt can obtain:
Order matrix A is equal to:
Order matrix b is equal to:
Therefore:
AP=b
P=[XW YW ZW]T
The projection matrix of camera is it is known that if obtain (u after calibrationl,vl),(ur,vr) then according to least square method, P point can be obtained
Coordinate:
P=(AA)-1ATb
Further, S6 includes:
Simultaneously gray proces are corrected to the picture of camera acquisition, obtain gray scale picture；
Gray scale picture is handled, the building blocks of overlapping building blocks the top is chosen as sorting target, obtains as sorting
The building blocks information of target.
After the real space location information for obtaining building blocks through the above way, it is thus necessary to determine that the sorting sequence of building blocks, in product
Before wood sorting process, it should first be determined which building blocks is building blocks to be sorted.By being re-shoot after sorting every time
Image, to determine new building blocks to be sorted.It recycles according to this, completes sorting one by one.The present invention passes through the picture that two cameras obtain,
After picture corrects, it is reconverted into gray scale picture, gray scale picture is handled respectively, chooses the product of overlapping building blocks the top
Carpentery workshop is sorting target.Its process is as follows:
(1) based on picture gray value, its gray value is extended into 0~255 range；
(2) target area is split by the method that region increases, the region collection by gray value mean square deviation less than 5
Combination and segmentation comes out；
(3) mean value of the gray value in picture is calculated, and Threshold segmentation is carried out to image according to the size of mean value；
(4) screening that area is carried out to the region after Threshold segmentation, removes zone errors；
(5) maximum gradation value in the region that calculating sifting goes out.It is split using this gray value as threshold value, obtains maximum ash
The region of angle value.Building blocks representated by this region are then building blocks to be sorted.
It in embodiments of the present invention, further include robot (mechanical arm) according to spatial positional information and work after S7
It automatically grabs building blocks to sort the building blocks information of target and is put into specified place.
In embodiments of the present invention, building blocks spatial position is identified using the method for binocular vision and automatically grab building blocks,
It realizes the identification of building blocks in industrial building blocks production and automatically grabs, to solve that low efficiency in building blocks sorting, accuracy rate is low asks
Topic, and can continuously sort and not influenced by work human efficiency；Meanwhile it being combined using binocular vision and mechanical arm
Mode, stability is high, at low cost, easy for installation.
Correspondingly, the embodiment of the present invention also provides a kind of building blocks Automated Sorting System based on binocular vision, such as Fig. 4 institute
Show, which includes:
Camera calibration module 1, for being demarcated to camera；
Image generation module 2 generates building blocks for acquiring the building blocks on line conveyor by calibrated camera
Figure；
Preprocessing module 3 obtains pretreated building blocks figure for pre-processing to building blocks figure；
Color determination module 4 determines the color of building blocks for carrying out image conversion to pretreated building blocks figure；
Spatial position obtains module 5, for handling the image after determining building blocks color, obtains locating for the building blocks
Spatial positional information；
Information determination module 6 is sorted, for handling the picture that camera acquires, obtains the building blocks as sorting target
Information；
Sending module 7, for being sent to robot progress by spatial positional information and as the building blocks information for sorting target
Building blocks sorting.
In embodiments of the present invention, left and right camera is demarcated first, in Binocular Stereo Vision System, camera
Calibration is primarily to solve the geometric parameter of camera, the inner parameter including camera model and the sky relative to target workpiece
Between position external parameter.Three-dimensional information of the object in world coordinate system can be obtained by camera calibration.The present invention utilizes two dimension
Scaling board carries out not having to angle and direction shooting, then carries out knowledge method for distinguishing to calibration.Calculated linear optimization
Solution is carried out non-linear solution again by maximum likelihood method and obtains the parameter of camera.
Preprocessing module 3 pre-processes building blocks figure using median filter method, the building blocks figure after being filtered.
Further, color determination module 4 includes:
Conversion unit, for being converted into HSV image by RGB image to pretreated building blocks figure；
Discrimination unit carries out area to the color of the building blocks in building blocks figure for the regularity of distribution according to building blocks in HSV space
Point, determine the color of building blocks.
Specific color determination process can be found in the detailed description of S4 in embodiment of the method.
Further, spatial position obtains module 5 and is also used to be calculated according to the relationship of image coordinate system and world coordinate system
Corresponding world coordinate system out obtains spatial positional information locating for the building blocks.Specific spatial position determination process can join
See the detailed description of S5 in embodiment of the method.
Further, sorting information determination module 6 includes:
Gray scale processing unit obtains gray scale picture for being corrected simultaneously gray proces to the picture that camera acquires；
Object selection unit chooses the building blocks of overlapping building blocks the top as sorting for handling gray scale picture
Target obtains the building blocks information as sorting target.
After the real space location information for obtaining building blocks through the above way, it is thus necessary to determine that the sorting sequence of building blocks, in product
Before wood sorting process, it should first be determined which building blocks is building blocks to be sorted.By being re-shoot after sorting every time
Image, to determine new building blocks to be sorted.It recycles according to this, completes sorting one by one.The present invention passes through the picture that two cameras obtain,
After picture corrects, it is reconverted into gray scale picture, gray scale picture is handled respectively, chooses the product of overlapping building blocks the top
Carpentery workshop is sorting target.Its process is as follows:
(1) based on picture gray value, its gray value is extended into 0~255 range；
(2) target area is split by the method that region increases, the region collection by gray value mean square deviation less than 5
Combination and segmentation comes out；
(3) mean value of the gray value in picture is calculated, and Threshold segmentation is carried out to image according to the size of mean value；
(4) screening that area is carried out to the region after Threshold segmentation, removes zone errors；
(5) maximum gradation value in the region that calculating sifting goes out.It is split using this gray value as threshold value, obtains maximum ash
The region of angle value.Building blocks representated by this region are then building blocks to be sorted.
Specifically, the working principle of present system related function module can be found in the phase of the realization process of embodiment of the method
Description is closed, which is not described herein again.
In present system embodiment, building blocks spatial position is identified using the method for binocular vision and automatically grabs product
Wood is realized the identification of building blocks in industrial building blocks production and is automatically grabbed, so that it is low to solve low efficiency, accuracy rate in building blocks sorting
Problem, and can continuously sort and not influenced by work human efficiency；Meanwhile using binocular vision and mechanical arm knot
The mode of conjunction, stability is high, at low cost, easy for installation.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in a computer readable storage medium, storage
Medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
In addition, be provided for the embodiments of the invention above building blocks automatic sorting method based on binocular vision and system into
It has gone and has been discussed in detail, used herein a specific example illustrates the principle and implementation of the invention, the above implementation
The explanation of example is merely used to help understand method and its core concept of the invention；Meanwhile for the general technology people of this field
Member, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion this explanation
Book content should not be construed as limiting the invention.
Claims (10)
1. a kind of building blocks automatic sorting method based on binocular vision, which is characterized in that the described method includes:
Camera is demarcated；
The building blocks on line conveyor are acquired by calibrated camera, generate building blocks figure；
The building blocks figure is pre-processed, pretreated building blocks figure is obtained；
Image conversion is carried out to the pretreated building blocks figure, determines the color of building blocks；
Image after determining building blocks color is handled, spatial positional information locating for the building blocks is obtained；
The picture of camera acquisition is handled, the building blocks information as sorting target is obtained；
The spatial positional information and the building blocks information as sorting target are sent to robot and carry out building blocks sorting.
2. the building blocks automatic sorting method based on binocular vision as described in claim 1, which is characterized in that described to described pre-
The step of treated, and building blocks figure carries out image conversion, determines the color of building blocks, comprising:
HSV image is converted by RGB image to the pretreated building blocks figure；
The regularity of distribution according to building blocks in HSV space distinguishes the color of the building blocks in building blocks figure, determines the color of building blocks.
3. the building blocks automatic sorting method based on binocular vision as claimed in claim 1 or 2, which is characterized in that described to true
The step of image after constant volume wood color is handled, obtains spatial positional information locating for the building blocks, comprising:
Corresponding world coordinate system is calculated with the relationship of world coordinate system according to image coordinate system, is obtained locating for the building blocks
Spatial positional information.
4. the building blocks automatic sorting method based on binocular vision as described in claim 1, which is characterized in that described to the phase
The step of picture of machine acquisition is handled, and the building blocks information as sorting target is obtained, comprising:
Simultaneously gray proces are corrected to the picture of camera acquisition, obtain gray scale picture；
The gray scale picture is handled, the building blocks of overlapping building blocks the top is chosen as sorting target, obtains as sorting
The building blocks information of target.
5. the building blocks automatic sorting method based on binocular vision as described in claim 1, which is characterized in that described to the product
The step of wooden figure is pre-processed, and pretreated building blocks figure is obtained, comprising:
The building blocks figure is pre-processed using median filter method, the building blocks figure after being filtered.
6. a kind of building blocks Automated Sorting System based on binocular vision, which is characterized in that the system comprises:
Camera calibration module, for being demarcated to camera；
Image generation module generates building blocks figure for acquiring the building blocks on line conveyor by calibrated camera；
Preprocessing module obtains pretreated building blocks figure for pre-processing to the building blocks figure；
Color determination module determines the color of building blocks for carrying out image conversion to the pretreated building blocks figure；
Spatial position obtains module, for handling the image after determining building blocks color, obtains space locating for the building blocks
Location information；
Information determination module is sorted, the picture for acquiring to the camera is handled, and obtains the building blocks as sorting target
Information；
Sending module, for the spatial positional information and building blocks information as sorting target to be sent to robot and accumulate
Wood sorting.
7. the building blocks Automated Sorting System based on binocular vision as claimed in claim 6, which is characterized in that the color determines
Module includes:
Conversion unit, for being converted into HSV image by RGB image to the pretreated building blocks figure；
Discrimination unit distinguishes the color of the building blocks in building blocks figure for the regularity of distribution according to building blocks in HSV space, really
The color of constant volume wood.
8. the building blocks Automated Sorting System based on binocular vision as claimed in claim 6, which is characterized in that the spatial position
It obtains module to be also used to calculate corresponding world coordinate system with the relationship of world coordinate system according to image coordinate system, be somebody's turn to do
Spatial positional information locating for building blocks.
9. the building blocks Automated Sorting System based on binocular vision as claimed in claim 6, which is characterized in that the sorting information
Determining module includes:
Gray scale processing unit, the picture for acquiring to the camera is corrected and gray proces, obtains gray scale picture；
Object selection unit chooses the building blocks of overlapping building blocks the top as sorting for handling the gray scale picture
Target obtains the building blocks information as sorting target.
10. the building blocks Automated Sorting System based on binocular vision as claimed in claim 6, which is characterized in that the pretreatment
Module is also used for median filter method and pre-processes to the building blocks figure, the building blocks figure after being filtered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910432830.4A CN110223350A (en) | 2019-05-23 | 2019-05-23 | A kind of building blocks automatic sorting method and system based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910432830.4A CN110223350A (en) | 2019-05-23 | 2019-05-23 | A kind of building blocks automatic sorting method and system based on binocular vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110223350A true CN110223350A (en) | 2019-09-10 |
Family
ID=67818193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910432830.4A Pending CN110223350A (en) | 2019-05-23 | 2019-05-23 | A kind of building blocks automatic sorting method and system based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110223350A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111266315A (en) * | 2020-02-20 | 2020-06-12 | 南京工程学院 | Ore material online sorting system and method based on visual analysis |
| CN111558549A (en) * | 2020-04-28 | 2020-08-21 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Automatic detection, identification and sorting device for intelligent building blocks |
| CN113145473A (en) * | 2021-02-20 | 2021-07-23 | 广州大学华软软件学院 | Intelligent fruit sorting system and method |
| CN113808206A (en) * | 2021-09-14 | 2021-12-17 | 广东三水合肥工业大学研究院 | Typesetting system and method based on visual tracking robot |
| CN114199124A (en) * | 2021-11-09 | 2022-03-18 | 汕头大学 | Coordinate calibration method, device, system and medium based on linear fitting |
| CN114289331A (en) * | 2021-10-20 | 2022-04-08 | 浙江菜鸟供应链管理有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN115364494A (en) * | 2022-07-26 | 2022-11-22 | 福州市鹭羽智能科技有限公司 | Automatic stacking device and method for building blocks based on patterns |
| TWI814100B (en) * | 2021-10-06 | 2023-09-01 | 國立勤益科技大學 | Delivery identification and picking system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102902271A (en) * | 2012-10-23 | 2013-01-30 | 上海大学 | Binocular vision-based robot target identifying and gripping system and method |
| WO2015024407A1 (en) * | 2013-08-19 | 2015-02-26 | 国家电网公司 | Power robot based binocular vision navigation system and method based on |
| CN204234368U (en) * | 2014-09-30 | 2015-04-01 | 汕头大学 | A kind of two-sided visual detection equipment |
| CN206505660U (en) * | 2017-02-24 | 2017-09-19 | 厦门理工学院 | A kind of building blocks color-sort training platform |
| CN107301634A (en) * | 2017-06-28 | 2017-10-27 | 湖南瑞森可机器人科技有限公司 | A kind of robot automatic sorting method and system |
| CN107767423A (en) * | 2017-10-10 | 2018-03-06 | 大连理工大学 | A kind of mechanical arm target positioning grasping means based on binocular vision |
| CN109465809A (en) * | 2018-12-17 | 2019-03-15 | 中北大学 | A kind of Intelligent garbage classification robot based on binocular stereo vision fixation and recognition |
| WO2019062291A1 (en) * | 2017-09-29 | 2019-04-04 | 歌尔股份有限公司 | Binocular vision positioning method, device, and system |
-
2019
- 2019-05-23 CN CN201910432830.4A patent/CN110223350A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102902271A (en) * | 2012-10-23 | 2013-01-30 | 上海大学 | Binocular vision-based robot target identifying and gripping system and method |
| WO2015024407A1 (en) * | 2013-08-19 | 2015-02-26 | 国家电网公司 | Power robot based binocular vision navigation system and method based on |
| CN204234368U (en) * | 2014-09-30 | 2015-04-01 | 汕头大学 | A kind of two-sided visual detection equipment |
| CN206505660U (en) * | 2017-02-24 | 2017-09-19 | 厦门理工学院 | A kind of building blocks color-sort training platform |
| CN107301634A (en) * | 2017-06-28 | 2017-10-27 | 湖南瑞森可机器人科技有限公司 | A kind of robot automatic sorting method and system |
| WO2019062291A1 (en) * | 2017-09-29 | 2019-04-04 | 歌尔股份有限公司 | Binocular vision positioning method, device, and system |
| CN107767423A (en) * | 2017-10-10 | 2018-03-06 | 大连理工大学 | A kind of mechanical arm target positioning grasping means based on binocular vision |
| CN109465809A (en) * | 2018-12-17 | 2019-03-15 | 中北大学 | A kind of Intelligent garbage classification robot based on binocular stereo vision fixation and recognition |
Non-Patent Citations (1)
| Title |
|---|
| 包能胜等: ""图像处理技术在再生塑料颗粒"", 《轻工机械》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111266315A (en) * | 2020-02-20 | 2020-06-12 | 南京工程学院 | Ore material online sorting system and method based on visual analysis |
| CN111558549A (en) * | 2020-04-28 | 2020-08-21 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Automatic detection, identification and sorting device for intelligent building blocks |
| CN111558549B (en) * | 2020-04-28 | 2022-03-29 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Automatic detection, identification and sorting device for intelligent building blocks |
| CN113145473A (en) * | 2021-02-20 | 2021-07-23 | 广州大学华软软件学院 | Intelligent fruit sorting system and method |
| CN113808206A (en) * | 2021-09-14 | 2021-12-17 | 广东三水合肥工业大学研究院 | Typesetting system and method based on visual tracking robot |
| CN113808206B (en) * | 2021-09-14 | 2024-02-02 | 广东三水合肥工业大学研究院 | Typesetting system and method based on vision tracking robot |
| TWI814100B (en) * | 2021-10-06 | 2023-09-01 | 國立勤益科技大學 | Delivery identification and picking system |
| CN114289331A (en) * | 2021-10-20 | 2022-04-08 | 浙江菜鸟供应链管理有限公司 | Data processing method and device, electronic equipment and storage medium |
| CN114199124A (en) * | 2021-11-09 | 2022-03-18 | 汕头大学 | Coordinate calibration method, device, system and medium based on linear fitting |
| CN115364494A (en) * | 2022-07-26 | 2022-11-22 | 福州市鹭羽智能科技有限公司 | Automatic stacking device and method for building blocks based on patterns |
| CN115364494B (en) * | 2022-07-26 | 2024-02-23 | 福州市鹭羽智能科技有限公司 | Automatic stacking device and method for building blocks based on patterns |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223350A (en) | A kind of building blocks automatic sorting method and system based on binocular vision | |
| CN105913415B (en) | A kind of image sub-pixel edge extracting method with extensive adaptability | |
| CN104915957B (en) | A kind of matching antidote for improving industrial robot 3D vision accuracy of identification | |
| CN104680519B (en) | Seven-piece puzzle recognition methods based on profile and color | |
| CN105528789B (en) | Robot visual orientation method and device, vision calibration method and device | |
| CN106651752A (en) | Three-dimensional point cloud data registration method and stitching method | |
| CN107392929B (en) | Intelligent target detection and size measurement method based on human eye vision model | |
| CN110910350B (en) | Nut loosening detection method for wind power tower cylinder | |
| CN104091324A (en) | Quick checkerboard image feature matching algorithm based on connected domain segmentation | |
| CN105217324A (en) | A kind of novel de-stacking method and system | |
| CN106951905A (en) | Apple identification and localization method on a kind of tree based on TOF camera | |
| CN105865329A (en) | Vision-based acquisition system for end surface center coordinates of bundles of round steel and acquisition method thereof | |
| CN110245663A (en) | One kind knowing method for distinguishing for coil of strip information | |
| CN106546263A (en) | A kind of laser leveler shoot laser line detecting method based on machine vision | |
| CN107527368A (en) | Three-dimensional attitude localization method and device based on Quick Response Code | |
| CN107403435A (en) | A kind of Color Image Edge extracting method based on RGB color | |
| CN108480223A (en) | A kind of workpiece sorting system and its control method | |
| CN113643280A (en) | Plate sorting system and method based on computer vision | |
| CN104915678A (en) | Detection method and apparatus of target object in power transmission line | |
| CN103914849A (en) | Method for detecting red date image | |
| Xia et al. | Workpieces sorting system based on industrial robot of machine vision | |
| CN113237889A (en) | Multi-scale ceramic detection method and system | |
| CN111292376B (en) | Visual target tracking method of bionic retina | |
| CN115619787A (en) | UV adhesive defect detection method, system, equipment and medium | |
| CN114581857A (en) | Intelligent crown block control method based on image analysis |
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 |
Application publication date: 20190910 |
|
| RJ01 | Rejection of invention patent application after publication |