CN108198186A - It is a kind of that the method and system for realizing spray painting are tracked in wu-zhi-shan pig view-based access control model - Google Patents
It is a kind of that the method and system for realizing spray painting are tracked in wu-zhi-shan pig view-based access control model Download PDFInfo
- Publication number
- CN108198186A CN108198186A CN201711444368.7A CN201711444368A CN108198186A CN 108198186 A CN108198186 A CN 108198186A CN 201711444368 A CN201711444368 A CN 201711444368A CN 108198186 A CN108198186 A CN 108198186A
- Authority
- CN
- China
- Prior art keywords
- image
- zhi
- value
- target
- spray painting
- 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 77
- 238000007592 spray painting technique Methods 0.000 title claims abstract description 34
- 230000008569 process Effects 0.000 claims abstract description 42
- 238000003709 image segmentation Methods 0.000 claims abstract description 17
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 239000003973 paint Substances 0.000 claims abstract description 8
- 230000005540 biological transmission Effects 0.000 claims description 20
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000009825 accumulation Methods 0.000 claims description 16
- 230000011218 segmentation Effects 0.000 claims description 15
- 238000012804 iterative process Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 238000011049 filling Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000000694 effects Effects 0.000 abstract description 5
- 238000010422 painting Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 21
- 238000010586 diagram Methods 0.000 description 11
- 230000033001 locomotion Effects 0.000 description 8
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 4
- 230000008878 coupling Effects 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000036961 partial effect Effects 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000012447 hatching Effects 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 230000013011 mating Effects 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000000377 silicon dioxide Substances 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 241000282887 Suidae Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000011664 nicotinic acid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000001259 photo etching Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000013336 robust study Methods 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/149—Segmentation; Edge detection involving deformable models, e.g. active contour models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method and system for being tracked in wu-zhi-shan pig view-based access control model and realizing and painting, method includes:Image Acquisition is carried out to spray painting object based on the vision system on the wu-zhi-shan pig ontology;Image after acquisition is filtered;Image segmentation is carried out to the image after filtering process according to parameter preset;The biometric data of target object is obtained based on target database;Feature based identification data complete the positioning to target object;Positioning generation working distal tip control instruction based on target object;Spray painting to the object that paints is completed based on the working distal tip control instruction.Through the embodiment of the present invention, the target template to be matched by the foundation of targetedly target, realizes corresponding search process, reaches the vision tracking effect to target ontology, so as to fulfill application process of the wu-zhi-shan pig in terms of lacquering technologies.
Description
Technical field
The present invention relates to robotic technology fields, and in particular to a kind of tracked in wu-zhi-shan pig view-based access control model realizes spray painting
Method and system.
Background technology
With the continuous development of robot technology, more and more robots start to substitute the various tasks of mankind's execution.Machine
Device people is to automatically control being commonly called as machine (Robot), automatically controls machine and includes all simulation human behaviors or thought and simulation
The machinery (such as robot dog, Doraemon etc.) of other biological.There are many classification and dispute to the definition of robot in the narrow sense, have
A little computer programs or even also referred to as robot.In contemporary industry, robot refers to the man-made machine dress that can perform task automatically
It puts, to replace or assist human work.Highly emulated robot in ideal is advanced integral traffic control opinion, mechano-electronic, calculating
Machine and artificial intelligence, materialogy and bionic product, scientific circles research and develop to this direction at present, but robot is remote
Process control is still not perfect, and the application of big data is universal not yet, and the data acquisition of robot is also in off-line state, robot depth
Degree study also comes from the storage of native data.
Target following is one of underlying issue important in computer vision research field, in monitoring, estimation, man-machine
Interaction etc. has very extensive application.The many track algorithms occurred in recent years can be preferable under certain scene
Track target object, such as particle filter, Boosting algorithms, L1 track algorithms.But since video is a complex scene
Under sequential image sequence, complex scene includes illumination variation, blocks, acts that deformation, background be mixed and disorderly, target scale variation
Deng therefore, one adaptive objective expression model of structure is grinding for current tracking field to obtain the track algorithm of robust
Study carefully hot spot and difficulties.How preferably to realize the visual tracking method in robot technology, need for Image Acquisition
Image is handled and is established suitable object module to complete accordingly to search for and complete spray painting action.
Invention content
The present invention provides a kind of method and system for being tracked in wu-zhi-shan pig view-based access control model and realizing and painting, by being directed to
Property the target template that matches of target foundation, realize corresponding search process, reach the vision tracking effect to target ontology, from
And realize application process of the wu-zhi-shan pig in terms of lacquering technologies.
The present invention provides a kind of method for being tracked in wu-zhi-shan pig view-based access control model and realizing spray painting, the wu-zhi-shan pigs
Including rotating base module, the first arm, the second arm, first connecting rod, second connecting rod, the first arm drive component, first connecting rod driving
Component, working distal tip, revolution driving component, revolution transmission component, rotation drive component and rotation transmission component, the method packet
It includes:
Image Acquisition is carried out to spray painting object based on the vision system on the wu-zhi-shan pig ontology;
Image after acquisition is filtered;
Image segmentation is carried out to the image after filtering process according to parameter preset;
The biometric data of target object is obtained based on target database;
Feature based identification data complete the positioning to target object;
Positioning generation working distal tip control instruction based on target object;
Spray painting to the object that paints is completed based on the working distal tip control instruction.
It is described to be included according to parameter progress image segmentation preset in vision system:
Create grey level histogram;
Confirm segmentation threshold;
Gray value and threshold value are compared;
Binary conversion treatment is carried out to grey level histogram;
Retrieval profile is carried out to grey level histogram;
Profile is surrounded in filling.
The establishment grey level histogram includes:
Calculate the accumulation histogram of original image;
The accumulation histogram of computational rules histogram;
Calculate the absolute value of the difference of two accumulation histograms;
The mapping of gray level is established according to accumulation histogram difference.
It is described that grey level histogram progress binary conversion treatment is included:
Process of convolution is carried out to grey level histogram using Gaussian function, obtains smooth template;
Pixel value in grey level histogram and smooth template are subtracted each other into acquisition difference value;
Process is iterated to the difference value of acquisition using threshold binarization algorithm and obtains maximum between-cluster variance value;
Background parts in grey level histogram are split by processing based on maximum between-cluster variance value.
The process that is iterated using threshold binarization algorithm to the difference value of acquisition obtains maximum between-cluster variance value packet
It includes:
Successively decreased since threshold value initial value zero based on pre-set iterations and be iterated process;
In iterative process each time, binary conversion treatment is carried out, and obtain the difference value based on threshold value and difference value
Binary value after corresponding original pixel value and binary conversion treatment;
Inter-class variance value is calculated, and form an inter-class variance in an iterative process based on original pixel value and binary value
Value set;
After iterative process terminates, traversal method is taken to obtain the maximum between-cluster variance value in inter-class variance value set.
The completion includes the positioning of target object:
Feature based identifies data creation target tracking model;
The object module to match is found in image based on Targets model after singulation;
The object module edge corresponding to image after extraction segmentation;
Target object in object module corresponding to search;
Judge whether to find target object based on target tracking model;
Calculate the target location corresponding to target object.
Correspondingly, the present invention also provides a kind of system for being tracked in wu-zhi-shan pig view-based access control model and realizing spray painting, it is described
Wu-zhi-shan pig includes rotating base module, the first arm, the second arm, first connecting rod, second connecting rod, the first arm drive component, the
One connecting rod drive component, working distal tip, revolution driving component, revolution transmission component, rotation drive component and rotation transmission component,
The system comprises:
Image capture module, for carrying out image to spray painting object based on the vision system on the wu-zhi-shan pig ontology
Acquisition;
Image filtering module, for being filtered to the image after acquisition;
Image segmentation module, for carrying out image segmentation to the image after filtering process according to parameter preset;
Characteristic module, for obtaining the biometric data of target object based on target database;
Feature recognition module completes the positioning to target object for feature based identification data;
Control process module generates working distal tip control instruction, and based on the work for the positioning based on target object
Make spray painting of the end-of-pipe control instruction completion to the object that paints.
Described image segmentation module is used to create grey level histogram;Confirm segmentation threshold;Gray value and threshold value are compared
Compared with;Binary conversion treatment is carried out to grey level histogram;Retrieval profile is carried out to grey level histogram;Profile is surrounded in filling.
The feature recognition module identifies data creation target tracking model for feature based;Based on Targets model
The object module to match is found in image after singulation;The object module edge corresponding to image after extraction segmentation;It searches
Target object in object module corresponding to rope;Judge whether to find target object based on target tracking model;Calculate object
Target location corresponding to body.
In the present invention, the image of acquisition is filtered, and realizes the establishment of the grey level histogram of acquisition image
Process carries out grey level histogram binary conversion treatment, and extraction more meets the overall profile of object module, is reached for succeeding target search
To the dimension template to match.By, using threshold binarization algorithm, being avoided that grey level histogram since image obscures or multiple
Binary image segmentation failure, realization accurately come target and background partial segmentation caused by miscellaneous image background information,
So as to be conducive to the later stage to the quick positioning of target part and by template matches mechanism can Rapid matching go out corresponding mesh
Object is marked, the Image Acquisition to the object that paints can be completed based on wu-zhi-shan pig, and completes corresponding spray painting control process mistake
Journey realizes robot construction automation.
Description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, to embodiment or will show below
There is attached drawing needed in technology 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 shows the three dimensional structure diagram of wu-zhi-shan pig of the embodiment of the present invention;
Fig. 2 shows the front views of wu-zhi-shan pig of the embodiment of the present invention;
Fig. 3 shows the Section A-A schematic diagram of the embodiment of the present invention;
Fig. 4 shows the section B-B schematic diagram of the embodiment of the present invention;
Fig. 5 shows the vertical view of wu-zhi-shan pig of the embodiment of the present invention;
Fig. 6 is the method flow diagram that realization spray painting is tracked in wu-zhi-shan pig view-based access control model in the embodiment of the present invention;
Fig. 7 is to carry out image partition method flow chart according to parameter preset in vision system in the embodiment of the present invention;
Fig. 8 is the establishment grey level histogram method flow diagram in the embodiment of the present invention;
Fig. 9 is to carry out binary processing method flow chart to grey level histogram in the embodiment of the present invention;
Figure 10 is being iterated process to the difference value of acquisition using threshold binarization algorithm and obtain in the embodiment of the present invention
Obtain maximum between-cluster variance value method flow diagram;
Figure 11 is localization method flow chart of the completion in the embodiment of the present invention to target object;
Figure 12 is the system for tracking realization spray painting in wu-zhi-shan pig view-based access control model in the embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 shows the three dimensional structure diagram of wu-zhi-shan pig of the embodiment of the present invention, and Fig. 2 shows the embodiment of the present invention
The front view of wu-zhi-shan pig, Fig. 5 show the vertical view of wu-zhi-shan pig of the embodiment of the present invention.
Wu-zhi-shan pig provided in an embodiment of the present invention, including rotating base module 901, the first arm 102, the second arm 103,
First connecting rod 105, second connecting rod 104, the first arm drive component 107,106 drive component of first connecting rod, revolution driving component
801st, transmission component, rotation drive component 802 and rotation transmission component are turned round.
The rotating base module includes rotating base motor 206, retarder 207, shaft coupling 208, platform 101;
The shell 201 of the rotating base motor is fixed on a rotating base electric machine support, and shaft is arranged simultaneously along z forward directions
It is connect with the input terminal of the retarder 207;
The output terminal of the retarder 207 is connect with the input terminal of shaft coupling 208, the output terminal of the shaft coupling 208 with
The platform 101 connects;
Rotating base motor 206 drives platform 101 to rotate through retarder 207, shaft coupling 208.
Hereinafter, first the component above platform is introduced, then rotating base module is introduced.
Firstly the need of explanation, in order to mitigate the weight of the first arm 102 and the second arm 103, the of the embodiment of the present invention
The structure of one arm 102 be open column shape structure, specially rectangular open column shape structure;Second arm 103 passes through two piece of second arm lid
Plate forms, and is connected and fixed by more than one second arm fixing piece between two piece of second arm cover board;It, can in specific implementation
It is set as various forms of arm configurations.
The platform 101 is parallel with x/y plane, and in specific implementation, 101 top surface of platform is a plane, the plane and x/y plane
Parallel, shape is not unique.
In the platform x forward, y is provided with to connect with the second base shaft to the first opposite base shaft connector 109
Part 111;
Fig. 3 shows the sectional view of Section A-A, succinct for view, only shows there is the part of cutting plane;Bearing
Hatching is not shown due to complex in figure;In order to reduce friction, bearing is based between the opposite each parts slided
It connects with bearing holder (housing, cover), since the connection mode is relatively conventional in industry, is not discussed in detail.It is connected in the first base shaft
Between 109 and second base shaft connector of part, 111 opposite face, cylindrical 812 beginning of the first base shaft is slidably mounted on institute
It states on the first base shaft connector 109;One the second cylindrical base shaft beginning 815 is slidably mounted on the second base shaft and connects
On fitting;The first base shaft axis 812 and 815 axis collinear of the second base shaft are simultaneously parallel with y-axis.
First arm, 102 beginning is slide hinged in the first base shaft 812 and/or the second base shaft 815, this hair
First arm 102 of bright embodiment is open column shape structure, across slide hinged in the first base shaft 812 and the second base shaft 815
On;First arm, 102 end is hinged with 103 beginning of the second arm;It is cut with scissors with the working distal tip the second arm end 103
It connects.
105 beginning of first connecting rod is slide hinged in the first base shaft 812 and/or the second base shaft 815, end
End is hinged with 104 beginning of second connecting rod;104 end of second connecting rod is articulated with 103 middle part of the second arm or end
On;First arm 102, the second arm 103, first connecting rod 105 and second connecting rod 104 form a four-bar mechanism;
The first arm drive component 107 is installed on the platform 101, for driving first arm 102 around described
First base shaft 812 and/or the second base shaft 815 rotate;The first connecting rod drive component 106 is installed on the platform 101
On, for the first connecting rod 105 to be driven to be rotated around the first base shaft 812.
It should be noted that the first arm drive component and the second arm drive component can control and keep the first arm, second
The position of the four-bar mechanism structure of arm, first connecting rod and second connecting rod composition;The position of working distal tip passes through revolution driving group
Part 801, revolution transmission component, rotation drive component 802 and rotation transmission component are controlled.
Wherein, the first base shaft 812 is driven by revolution driving component 801.Revolution driving component 801 includes revolution driving electricity
Machine 810, revolution driving retarder 811 and mating bearing and bearing holder (housing, cover).First base shaft, 812 beginning is slidably mounted on first
On base shaft connector 109, end is fixed with the first revolution belt wheel 813;Revolution driving retarder 811 is fixed on the first base shaft
On 812;Revolution driving motor 810 is connect through revolution driving retarder 811 with the first base shaft connector 109;Revolution driving electricity
Machine 810 is rotated through revolution driving retarder 811, the first base shaft 812 driving the first revolution belt wheel 813.
Second base shaft 815 is driven by rotation drive component 801.Rotation drive component 802 includes rotation driving motor
817th, rotation driving retarder 816 and mating bearing and bearing holder (housing, cover).Second base shaft, 815 beginning is slidably mounted on the second base
On shaft connector 111, end is fixed with the first revolution belt wheel 814;Rotation driving retarder 816 is fixed on the second base shaft company
On fitting 111;Rotation driving motor 817 is connect through rotation driving retarder 816 with the second base shaft 815;Rotation driving motor
817 drive the first rotation belt wheel 814 to rotate through rotation driving retarder 815, the second base shaft 815.
Fig. 4 shows the cross-sectional view of section B-B, succinct for view, only shows there is the portion of cutting plane
Point;The hatching of bearing is not shown due to complex in figure;In order to reduce friction, the opposite each parts slided it
Between connected based on bearing with bearing holder (housing, cover), since the connection mode is relatively conventional in industry, be not discussed in detail.First arm 104
End and 103 beginning of the second arm are hinged, specifically, second joint shaft 834 is along y to through the y forward directions face of the first arm 104 and y
Negative sense face.The second revolution sleeve 833, second is slidably fitted in second joint shaft 834 from rotaring sleeve 832, wherein, second time
Rotaring sleeve 833 is slidably mounted on the first arm 104y negative senses face, is fixedly connected with second respectively the first arm 104 is inside and outside
It turns round belt wheel one 836 and second and turns round belt wheel 2 835;Second is slidably mounted on from rotaring sleeve 832 on the first arm 104y forward directions face,
It is fixedly connected with the second rotation belt wheel 1 and the second rotation belt wheel 2 838 respectively the first arm 104 is inside and outside.Second
Two piece of second arm cover board 137 of arm is slidably mounted on the second revolution sleeve 833, second from rotaring sleeve 832 respectively.
Fig. 5 shows the vertical view of the embodiment of the present invention, wherein, it is unrelated with working distal tip rotary motion and spinning motion
Component not shows that partial enlarged view is the sectional view of the second arm end.It is provided on second arm, 103 end along y to perforative
Third joint shaft 842;Third joint shaft 842y forward ends are fixedly connected with third rotation belt wheel 840, and y negative ends slide peace
Sleeve 843 is turned round equipped with third, third revolution sleeve 843 is slidably mounted on the second arm 103y negative senses face, wherein, third revolution
Sleeve 843 is fixedly connected with third revolution belt wheel 847 in y negative senses.
The working distal tip of the embodiment of the present invention includes rounded end 844 and the rotation end being slidably mounted on rounded end 844
845;Rounded end 844 is slidably mounted in third joint shaft 842, and y negative ends connect fixation with third revolution sleeve 843, from
It is vertical with the axis of third joint shaft 842 to turn 845 axis of end.
First bevel gear 841 is also fixedly connected in third joint shaft 842, the second cone tooth is fixedly connected on rotation end
Wheel 846;First bevel gear 841 and second bevel gear 842 engage, and axis is vertical between each other.
With reference to the modular construction explanation being located above to the wu-zhi-shan pig of the embodiment of the present invention above platform, below to this
The rotary motion and spinning motion of the working distal tip of inventive embodiments are summarized.
It turns round transmission component and includes the first revolution belt wheel, the second revolution revolution of belt wheel one, second belt wheel two, third rotating belt
Wheel and revolution belt one, revolution belt two for transmission.The first base of revolution driving Component driver shaft rotates, and drives first time
Turn belt wheel rotation;First revolution belt wheel is based on revolution belt one and the second revolution belt wheel one is driven to rotate;Second revolution one He of belt wheel
Second revolution belt wheel diyl is fixed and is synchronized with the movement in the second revolution sleeve connection;Second revolution belt wheel diyl is in revolution belt two
Drive third revolution belt wheel movement;Third is turned round belt wheel and is fixed, and rotate synchronously based on third revolution sleeve connection with rounded end.
Rotation transmission component includes the first rotation belt wheel, the second rotation belt wheel one, the second rotation belt wheel two, third rotation band
Wheel, first bevel gear, second bevel gear and rotation belt one, rotation belt two for transmission;Rotation drive component driving the
Diyl shaft rotates, and drives the rotation of the first rotation belt wheel;First rotation belt wheel is based on rotation belt one and drives the second rotation belt wheel
One rotation;Second rotation belt wheel one and the second rotation belt wheel two are fixed and are synchronized with the movement based on the second rotation sleeve connection;Second
Rotation belt wheel two is based on rotation belt two and drives the movement of third rotation belt wheel;Third rotation belt wheel is based on third with first bevel gear
Joint shaft connection is fixed, and rotate synchronously;Second bevel gear is orthogonal with first bevel gear to be engaged and is driven by first bevel gear
It is dynamic to realize rotation;The turning end being connect with second bevel gear is on rounded end around own axes rotation.
Correspondingly, Fig. 6 shows the side that realization spray painting is tracked in wu-zhi-shan pig view-based access control model in the embodiment of the present invention
Method flow chart, includes the following steps:
S601, Image Acquisition is carried out to spray painting object based on the vision system on wu-zhi-shan pig ontology;
The vision system can be generally fixed on the mechanical arm of wu-zhi-shan pig or working distal tip etc..Image Acquisition
Technology can be based on CCD technologies and realize, CCD (Charge Coupled Device) i.e. charge misfortune clutch parts are based on metal one
The electrooptical device of oxide semiconductor technology is made of i.e. many photosensitive pixels on the surface of p-type (or N-type) silicon substrate
The silica that a layer thickness about 0. cuts m, which is formed, with method for oxidation layer of metal film is deposited on silica again, and use photoetching
Method gate-shaped electrode is made.The groundwork step of CCD is:Incident photon is transformed into charge, these electric charge transfers are arrived
On output amplifier, and charge is transformed into voltage or current signal, enable these voltages or electric current by sensor outside circuit
It perceives.After grid applies positive bias, hole is ostracised, and generates depletion region, and bias continues to increase, and depletion region will be further to half
Extend in conductor, semiconductor electronic is attracted to surface, forms one layer very thin but that concentration of electric charges is very high inversion layer.It is electric in CCD
Lotus is from a position transfer to another position, in start time, has some charge storages in first electrode of the bias for 10V
Under potential well in, on other electrodes added with more than door screen value low voltage.After certain moment, the voltage hair on each electrode
Changing, charge packet move right.The voltage changed according to certain rules is added to each electrodes of CCD (such as external clock voltage)
On, the charge packet under electrode is just transferred to output terminal in certain direction along semiconductor surface, realizes the self-scanning of image, thus will
The optical imagery being radiated on CCD is converted into electric signal image, directly displays image overall picture.
S602, the image after acquisition is filtered;
Image filtering inhibits the noise of target image under conditions of image detail feature is retained as possible, is
Indispensable operation in image preprocessing, treatment effect quality will directly influence subsequent image processing and analysis have
Effect property and reliability.Not perfect due to imaging system, transmission medium and recording equipment etc., digital picture is in its formation, transmission
It is often polluted in recording process by a variety of noises.In addition, certain links in image procossing work as the picture object of input simultaneously
Not as good as can also introduce noise in result images during anticipation.These noises often show as one and cause stronger visual effect on the image
Isolated pixel point or block of pixels.Generally, noise signal it is uncorrelated to the object to be studied it occur with useless message form,
Upset the observable information of image.For data image signal, psophometer is either large or small extreme value, these extreme values pass through plus-minus
It acts on the true gray value of image pixel, bright, dim spot interference is caused to image, picture quality is greatly reduced, influences figure
As the progress of the subsequent work such as recovery, segmentation, feature extraction, image identification.Construct a kind of effective wave filter for inhibiting noise
It must take into consideration two basic problems:The noise in target and background can effectively be removed;Meanwhile image object can be protected well
Shape, size and specific geometry and topological features.
S603, image segmentation is carried out to the image after filtering process according to parameter preset;
Specifically, Fig. 7 is shown in the embodiment of the present invention carries out image segmentation according to parameter preset in vision system
Method flow diagram includes the following steps:
S701:Create grey level histogram;
Specifically, Fig. 8 shows the establishment grey level histogram method flow diagram in the embodiment of the present invention, including walking as follows
Suddenly:
S801, the accumulation histogram for calculating original image;
The accumulation histogram of S802, computational rules histogram;
S803, calculate two accumulation histograms difference absolute value;
S804, the mapping that gray level is established according to accumulation histogram difference.
S702, confirm segmentation threshold;
S703, gray value and threshold value are compared;
S704, binary conversion treatment is carried out to grey level histogram;
Specifically, Fig. 9 is shown in the embodiment of the present invention carries out binary processing method flow chart to grey level histogram,
Include the following steps:
S901, process of convolution is carried out to grey level histogram using Gaussian function, obtains smooth template;
S902, the pixel value in grey level histogram and smooth template are subtracted each other into acquisition difference value;
S903, process acquisition maximum between-cluster variance value is iterated to the difference value of acquisition using threshold binarization algorithm;
The difference value of acquisition is carried out using threshold binarization algorithm specifically, Figure 10 is shown in the embodiment of the present invention
Iterative process obtains maximum between-cluster variance value method flow diagram, specifically comprises the following steps:
S1001, being successively decreased since threshold value initial value zero based on pre-set iterations is iterated process;
S1002, in iterative process each time, binary conversion treatment is carried out based on threshold value and difference value, and described in obtaining
The binary value after original pixel value and binary conversion treatment corresponding to difference value;
S1003, inter-class variance value is calculated based on original pixel value and binary value, and forms a class in an iterative process
Between variance value set;
S1004, after iterative process terminates, take traversal method obtain inter-class variance value set in maximum kind between side
Difference.
S904, the background parts in grey level histogram are split by processing based on maximum between-cluster variance value
S705, retrieval profile is carried out to grey level histogram;
Profile is surrounded in S706, filling.
S604, the biometric data that target object is obtained based on target database;
S605, feature based identification data complete the positioning to target object;
Specifically, Figure 11 shows localization method flow chart of the completion in the embodiment of the present invention to target object, including
Following steps:
S1101, feature based identification data creation target tracking model;
S1102, based on finding the object module that matches in Targets model image after singulation;
The object module edge corresponding to image after S1103, extraction segmentation;
Target object in object module corresponding to S1104, search;
S1105, judge whether to find target object based on target tracking model, be returned to if target object is not found
It is continued search in S1104, S1106 is entered if target object is found;
Target location corresponding to S1106, calculating target object.
S606, the positioning generation working distal tip control instruction based on target object;
S607, the spray painting to the object that paints is completed based on the working distal tip control instruction.
Specifically, Figure 12 show in the embodiment of the present invention wu-zhi-shan pig view-based access control model track realize spray painting be
It unites structure diagram, which includes rotating base module, the first arm, the second arm, first connecting rod, second connecting rod, the
One arm drive component, first connecting rod drive component, working distal tip, revolution driving component, revolution transmission component, rotation drive component
With rotation transmission component, the system comprises:
Image capture module, for carrying out image to spray painting object based on the vision system on the wu-zhi-shan pig ontology
Acquisition;
Image filtering module, for being filtered to the image after acquisition;
Image segmentation module, for carrying out image segmentation to the image after filtering process according to parameter preset;
Characteristic module, for obtaining the biometric data of target object based on target database;
Feature recognition module completes the positioning to target object for feature based identification data;
Control process module generates working distal tip control instruction, and based on the work for the positioning based on target object
Make spray painting of the end-of-pipe control instruction completion to the object that paints.
It should be noted that the system is fixed generally as a system module on wu-zhi-shan pig, such as vision system
It acts in the working distal tip or working arm of wu-zhi-shan pig, entire control process module can be in wu-zhi-shan pig ontology
On the controller in portion, receive vision system institute feedack and complete information parsing and controlled process, entire processing is all based on
Wu-zhi-shan pig integrally completes corresponding actions, and whole system is all a part for wu-zhi-shan pig, as circuit, software etc.
Realization process is that respective function is realized in a circuit module or the software module corresponding position on wu-zhi-shan pig ontology
And effect.
In specific implementation process, which is used to create grey level histogram;Confirm segmentation threshold;By gray value
It is compared with threshold value;Binary conversion treatment is carried out to grey level histogram;Retrieval profile is carried out to grey level histogram;Wheel is surrounded in filling
It is wide.
In specific implementation process, which includes:Calculate the accumulation histogram of original image;Computational rules are straight
The accumulation histogram of square figure;Calculate the absolute value of the difference of two accumulation histograms;Gray level is established according to accumulation histogram difference
Mapping.
In specific implementation process, binary conversion treatment is carried out to grey level histogram and is included:Using Gaussian function to intensity histogram
Figure carries out process of convolution, obtains smooth template;Pixel value in grey level histogram and smooth template are subtracted each other into acquisition difference value;It adopts
Process is iterated to the difference value of acquisition with threshold binarization algorithm and obtains maximum between-cluster variance value;Based on maximum between-cluster variance
Background parts in grey level histogram are split processing by value.
In specific implementation process, this is iterated the difference value of acquisition process using threshold binarization algorithm and obtains maximum
Inter-class variance value includes:Successively decreased since threshold value initial value zero based on pre-set iterations and be iterated process;
In iterative process each time, binary conversion treatment is carried out, and obtain the original corresponding to the difference value based on threshold value and difference value
Binary value after pixel value and binary conversion treatment;Inter-class variance value is calculated, and repeatedly based on original pixel value and binary value
An inter-class variance value set is formed during generation;After iterative process terminates, traversal method is taken to obtain inter-class variance value
Maximum between-cluster variance value in set.
In specific implementation process, this feature identification module identifies data creation target tracking model for feature based;Base
The object module to match is found in the image of Targets model after singulation;The mesh corresponding to image after extraction segmentation
Mark module edge;Target object in object module corresponding to search;Judge whether to find object based on target tracking model
Body;Calculate the target location corresponding to target object.
To sum up, the image of acquisition is filtered, and realizes the establishment process of the grey level histogram of acquisition image, it is right
Grey level histogram carries out binary conversion treatment, and extraction more meets the overall profile of object module, reaches phase for succeeding target search
The dimension template matched.By, using threshold binarization algorithm, being avoided that grey level histogram since image obscures or complicated figure
The binary image segmentation failure as caused by background information, realization accurately comes target and background partial segmentation, so as to have
Conducive to the later stage to the quick positioning of target part and by template matches mechanism can Rapid matching go out corresponding object
Body.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can be stored in computer readable storage medium, and storage is situated between
Matter can include:Read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access
Memory), disk or CD etc..
Visual tracking method and system in the robot provided above the embodiment of the present invention are described in detail,
Specific case used herein is expounded the principle of the present invention and embodiment, and the explanation of above example is only used
In facilitating the understanding of the method and its core concept of the invention;Meanwhile for those of ordinary skill in the art, according to the present invention
Thought, there will be changes in specific embodiments and applications, in conclusion the content of the present specification should not be construed as
Limitation of the present invention.
Claims (9)
1. a kind of track the method for realizing spray painting in wu-zhi-shan pig view-based access control model, which is characterized in that the wu-zhi-shan pig packet
Include rotating base module, the first arm, the second arm, first connecting rod, second connecting rod, the first arm drive component, first connecting rod driving group
Part, working distal tip, revolution driving component, revolution transmission component, rotation drive component and rotation transmission component, the method packet
It includes:
Image Acquisition is carried out to spray painting object based on the vision system on the wu-zhi-shan pig ontology;
Image after acquisition is filtered;
Image segmentation is carried out to the image after filtering process according to parameter preset;
The biometric data of target object is obtained based on target database;
Feature based identification data complete the positioning to target object;
Positioning generation working distal tip control instruction based on target object;
Spray painting to the object that paints is completed based on the working distal tip control instruction.
2. the method for realizing spray painting is tracked in wu-zhi-shan pig view-based access control model as described in claim 1, which is characterized in that described
Image segmentation is carried out according to parameter preset in vision system to include:
Create grey level histogram;
Confirm segmentation threshold;
Gray value and threshold value are compared;
Binary conversion treatment is carried out to grey level histogram;
Retrieval profile is carried out to grey level histogram;
Profile is surrounded in filling.
3. the method for realizing spray painting is tracked in wu-zhi-shan pig view-based access control model as claimed in claim 2, which is characterized in that described
Grey level histogram is created to include:
Calculate the accumulation histogram of original image;
The accumulation histogram of computational rules histogram;
Calculate the absolute value of the difference of two accumulation histograms;
The mapping of gray level is established according to accumulation histogram difference.
4. the method for realizing spray painting is tracked in wu-zhi-shan pig view-based access control model as claimed in claim 3, which is characterized in that described
Binary conversion treatment is carried out to grey level histogram to include:
Process of convolution is carried out to grey level histogram using Gaussian function, obtains smooth template;
Pixel value in grey level histogram and smooth template are subtracted each other into acquisition difference value;
Process is iterated to the difference value of acquisition using threshold binarization algorithm and obtains maximum between-cluster variance value;
Background parts in grey level histogram are split by processing based on maximum between-cluster variance value.
5. the method for realizing spray painting is tracked in wu-zhi-shan pig view-based access control model as claimed in claim 4, which is characterized in that described
Process acquisition maximum between-cluster variance value is iterated to the difference value of acquisition using threshold binarization algorithm to include:
Successively decreased since threshold value initial value zero based on pre-set iterations and be iterated process;
In iterative process each time, binary conversion treatment is carried out based on threshold value and difference value, and it is right to obtain the difference value institute
Binary value after the original pixel value and binary conversion treatment answered;
Inter-class variance value is calculated, and form an inter-class variance value collection in an iterative process based on original pixel value and binary value
It closes;
After iterative process terminates, traversal method is taken to obtain the maximum between-cluster variance value in inter-class variance value set.
6. the method for realizing spray painting, feature are tracked in wu-zhi-shan pig view-based access control model as described in any one of claim 1 to 5
It is, the completion includes the positioning of target object:
Feature based identifies data creation target tracking model;
The object module to match is found in image based on Targets model after singulation;
The object module edge corresponding to image after extraction segmentation;
Target object in object module corresponding to search;
Judge whether to find target object based on target tracking model;
Calculate the target location corresponding to target object.
7. a kind of track the system for realizing spray painting in wu-zhi-shan pig view-based access control model, which is characterized in that the wu-zhi-shan pig packet
Include rotating base module, the first arm, the second arm, first connecting rod, second connecting rod, the first arm drive component, first connecting rod driving group
Part, working distal tip, revolution driving component, revolution transmission component, rotation drive component and rotation transmission component, the system packet
It includes:
Image capture module is adopted for carrying out image to spray painting object based on the vision system on the wu-zhi-shan pig ontology
Collection;
Image filtering module, for being filtered to the image after acquisition;
Image segmentation module, for carrying out image segmentation to the image after filtering process according to parameter preset;
Characteristic module, for obtaining the biometric data of target object based on target database;
Feature recognition module completes the positioning to target object for feature based identification data;
Control process module generates working distal tip control instruction, and based on work end for the positioning based on target object
Control instruction is held to complete the spray painting to the object that paints.
8. the system for realizing spray painting is tracked in wu-zhi-shan pig view-based access control model as claimed in claim 7, which is characterized in that described
Image segmentation module is used to create grey level histogram;Confirm segmentation threshold;Gray value and threshold value are compared;To intensity histogram
Figure carries out binary conversion treatment;Retrieval profile is carried out to grey level histogram;Profile is surrounded in filling.
9. the system for realizing spray painting is tracked in wu-zhi-shan pig view-based access control model as claimed in claim 8, which is characterized in that described
Feature recognition module identifies data creation target tracking model for feature based;Figure based on Targets model after singulation
The object module to match is found as in;The object module edge corresponding to image after extraction segmentation;Target corresponding to search
Mould target object in the block;Judge whether to find target object based on target tracking model;Calculate the mesh corresponding to target object
Cursor position.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711444368.7A CN108198186A (en) | 2017-12-27 | 2017-12-27 | It is a kind of that the method and system for realizing spray painting are tracked in wu-zhi-shan pig view-based access control model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711444368.7A CN108198186A (en) | 2017-12-27 | 2017-12-27 | It is a kind of that the method and system for realizing spray painting are tracked in wu-zhi-shan pig view-based access control model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108198186A true CN108198186A (en) | 2018-06-22 |
Family
ID=62584544
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711444368.7A Pending CN108198186A (en) | 2017-12-27 | 2017-12-27 | It is a kind of that the method and system for realizing spray painting are tracked in wu-zhi-shan pig view-based access control model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108198186A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111013883A (en) * | 2019-11-25 | 2020-04-17 | 浙江明泉工业涂装有限公司 | Robot control method for intelligent spraying of multiple vehicle types |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339462A (en) * | 2010-07-23 | 2012-02-01 | 北京东方泰坦科技股份有限公司 | Intelligent investment project searching technology based on remote-sensing image variation detection algorithm |
CN106558070A (en) * | 2016-11-11 | 2017-04-05 | 华南智能机器人创新研究院 | A kind of method and system of the visual tracking under the robot based on Delta |
-
2017
- 2017-12-27 CN CN201711444368.7A patent/CN108198186A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339462A (en) * | 2010-07-23 | 2012-02-01 | 北京东方泰坦科技股份有限公司 | Intelligent investment project searching technology based on remote-sensing image variation detection algorithm |
CN106558070A (en) * | 2016-11-11 | 2017-04-05 | 华南智能机器人创新研究院 | A kind of method and system of the visual tracking under the robot based on Delta |
Non-Patent Citations (3)
Title |
---|
朱亚光 等: "《中国科学技术文库 普通卷 自动化技术、计算机科学技术》", 31 January 1998 * |
李莉 等: "适于路面破损图像处理的边缘检测方法", 《同济大学学报》 * |
李阳: "基于视觉的移动机器人运动目标跟踪技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111013883A (en) * | 2019-11-25 | 2020-04-17 | 浙江明泉工业涂装有限公司 | Robot control method for intelligent spraying of multiple vehicle types |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kraft et al. | Birth of the object: Detection of objectness and extraction of object shape through object–action complexes | |
Saeedi et al. | Vision-based 3-D trajectory tracking for unknown environments | |
US11331806B2 (en) | Robot control method and apparatus and robot using the same | |
Grosso et al. | 3d object reconstruction using stereo and motion | |
CN108161938A (en) | Visual tracking method and system in a kind of robot | |
Taylor et al. | Visual perception and robotic manipulation: 3D object recognition, tracking and hand-eye coordination | |
Sun et al. | Weakly-supervised DCNN for RGB-D object recognition in real-world applications which lack large-scale annotated training data | |
Tian et al. | Research on multi-sensor fusion SLAM algorithm based on improved gmapping | |
Sinha et al. | Convolutional neural network based sensors for mobile robot relocalization | |
Lou | Crawling robot manipulator tracking based on gaussian mixture model of machine vision | |
CN108198186A (en) | It is a kind of that the method and system for realizing spray painting are tracked in wu-zhi-shan pig view-based access control model | |
Tadic | Study on automatic electric vehicle charging socket detection using ZED 2i depth sensor | |
Gao et al. | In-hand pose estimation using hand-mounted rgb cameras and visuotactile sensors | |
Zhang et al. | Dex-Net AR: Distributed deep grasp planning using a commodity cellphone and augmented reality app | |
Lin et al. | A novel robust algorithm for position and orientation detection based on cascaded deep neural network | |
CN113681560B (en) | Method for operating articulated object by mechanical arm based on vision fusion | |
Wang | A survey of visual analysis of human motion and its applications | |
Keleştemur et al. | Learning bayes filter models for tactile localization | |
Sandini et al. | Retina-like CCD sensor for active vision | |
LIU et al. | Robot intelligence for real world applications | |
Talu et al. | An implementation of a novel vision‐based robotic tracking system | |
Zhang et al. | Dynamic Semantics SLAM Based on Improved Mask R-CNN | |
Duckworth | Unsupervised Human Activity Analysis for Intelligent Mobile Robot | |
Batra et al. | Real-Time Object Detection and Localization for Vision-Based Robot Manipulator | |
Qin et al. | A review of visual SLAM with dynamic objects |
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: 20180622 |
|
RJ01 | Rejection of invention patent application after publication |