CN105865629A - Object color recognition method for robot - Google Patents
Object color recognition method for robot Download PDFInfo
- Publication number
- CN105865629A CN105865629A CN201610178719.3A CN201610178719A CN105865629A CN 105865629 A CN105865629 A CN 105865629A CN 201610178719 A CN201610178719 A CN 201610178719A CN 105865629 A CN105865629 A CN 105865629A
- Authority
- CN
- China
- Prior art keywords
- color
- rgb
- value
- robot
- recognition methods
- 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 29
- 239000003086 colorant Substances 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000005286 illumination Methods 0.000 claims description 23
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000011161 development Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000532370 Atla Species 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/462—Computing operations in or between colour spaces; Colour management systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J2003/467—Colour computing
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention proposes an object color recognition method for a robot, and the method comprises the following steps: building an RGB color database which is used for comparing the RGB values of sample colors; collecting the image data of related samples through a camera, then calculating the RGB values of sample colors in a processing system, comparing the RGB values with the data in the built RGB color database, so as to determine the colors of a sample; making a standard colourimetric card, setting a plurality of recognizable regions with different colors and a certain size on the standard colourimetric card, carrying out the equal calibration of light intensity in a current environment, enabling a calibration result to be transmitted to the processing system, and updating the RGB color database. For the color recognition technology of the same type of images, the method improves the recognition success rate of image colors to certain extent, improves the efficiency of color recognition, and guarantees the operation efficiency of the robot after color recognition.
Description
Technical field
The present invention relates to intelligent robot colour recognition field, and particularly to a kind of object for robot
Color identification method.
Background technology
At present, when carrying out Digital Image Processing and identifying, color is often an important object of study, with
The development of robotics, the colour recognition technology of object manipulator is also in constantly development.Generally
Robot all use CMOS camera to collect rgb image data to be converted into HSI color space technology
Extract and identify color.
For prior art, extraneous interference in many ways makes visual system become in whole robot system
For the link easily made mistakes, under the situation that environmental lighting conditions is unstable the most at the scene, test result
Bigger error can be there is.Certainly take RGB to turn HSI method and extract colouring information, in different illumination conditions
Under the influence of, although there is also error, but still have one for the most most basic extracting method of success rate
Fixed raising.Although effect well many compared with initially, but not ideal enough.
Summary of the invention
The present invention proposes a kind of object color recognition methods for robot, it is possible to increase colour recognition result
Success rate.In the method, to camera collection to the RGB color data base of color data and foundation enter
Row comparison, and guarantee under unstable illumination condition by the interpolation of some external equipments, robot
Visual system the color of target can be recognized accurately.
In order to achieve the above object, the present invention proposes a kind of object color recognition methods for robot, bag
Include the following step:
Set up RGB color data base, compare for the rgb value that color sample is collected;
After utilizing camera collection to arrive about the view data of sample, in processing system, calculate color sample
Rgb value, and compare with the RGB color data base of earlier set, to determine the color of sample;
Making standard color comparison card, arrange several different colours on colorimetric card has knowing of a certain size
Other region, calibrates equally to intensity of illumination in current environment, by the result transmission after calibration to processing
System, is updated RGB color data base simultaneously.
Further, the data in described RGB color data base include three attribute, be respectively rgb value,
Color designation and HSI value.
Further, described rgb value is set as 16 system numbers, and the highest two is R value, and low two are
B value, a upper rgb value is spaced apart 0x000007 with next rgb value.
Further, described HSI value is set as X, the form of X, X, and record RGB generates after turning HSI
Value.
Further, each color described color region size on colorimetric card is set as
100mm*100mm。
Further, redness, green, blueness, yellow, magenta, cyan, white, black are amounted to
Eight kinds of color settings are the color in standard color comparison card.
Further, the described step being updated RGB color data base includes:
Step 1: using the RGB color data base of foundation as the first pattern library, and the 3rd benchmark is set
Storehouse is as backup pattern library;
Step 2: start calibration: by the data of camera collection standard color comparison card and write the second pattern library, will
The value of the first pattern library and the second pattern library is compared, and covers this value to the first pattern library;
Step 3: calibrating complete needs to carry out a new round when measuring, and sends signal and makes the 3rd pattern library rewrite first
Pattern library, and jump to step 2.
Further, the method also includes adding light sensor, in the color mistake measuring different objects continuously
Cheng Zhong, when described light sensor record intensity of illumination have stable change time, i.e. neglect the illumination of moment
Intensity saltus step, feedback is recalibrated instruction, is carried out calibration again and update RGB color data base, it is to avoid
The analytical error of color data.
Further, the method is additionally included on original base continuously record calibration when starting complete with calibration
Between the intensity of illumination of current environment carry out, except making an uproar, drawing an estimated value, preventing a certain moment light in interval
Result is impacted by the change suddenly according to intensity.
The object color recognition methods for robot that the present invention proposes, by Criterion color libraries, reaches
To the purpose identifying color of object.Simultaneously by increasing standard color comparison card, to guarantee at short time illumination condition
Avoid light source that color of object is formed the error that reflection causes color data to analyze in the environment of Wen Ding;Pass through again
Improve camera collection system and add part light aid, reaching in the environment of illumination condition changes at any time,
Ensure the accuracy of data acquisition.This invention is for same type color of image identification technology, to a certain degree
On improve the recognition success rate to color of image, and improve the efficiency of colour recognition.Ensure that machine
People completes efficiency for operation after colour recognition.
Accompanying drawing explanation
Fig. 1 show the object color recognition methods flow chart for robot of present pre-ferred embodiments.
Detailed description of the invention
Provide the detailed description of the invention of the present invention below in conjunction with accompanying drawing, but the invention is not restricted to following embodiment party
Formula.According to following explanation and claims, advantages and features of the invention will be apparent from.It should be noted that,
Accompanying drawing all uses the form simplified very much and all uses non-ratio accurately, is only used for conveniently, assists lucidly
The purpose of the embodiment of the present invention is described.
Refer to Fig. 1, Fig. 1 and show the object color identification side for robot of present pre-ferred embodiments
Method flow chart.The present invention proposes a kind of object color recognition methods for robot, comprises the following steps:
Step S100: set up RGB color data base, is carried out for the rgb value collecting color sample
Relatively;
Step S200: after utilizing camera collection to arrive about the view data of sample, calculates in processing system
Go out the rgb value of color sample, and compare, to determine sample with the RGB color data base of earlier set
The color of product;
Step S300: make standard color comparison card, arranges having of several different colours certain on colorimetric card
The recognizable region of size, calibrates equally to intensity of illumination in current environment, by the result after calibration
RGB color data base, to processing system, is updated by transmission simultaneously.
According to present pre-ferred embodiments, the data in described RGB color data base include three attribute, point
It not rgb value, color designation and HSI value.Further, the value in described RGB attribute is set as 16
System number, the highest two is R value, and low two is B value, and the rgb value that such as color is red is recorded as
0xff0000, the rgb value of colors green is recorded as 0x00ff00, and the rgb value of color blue is recorded as
0x0000ff etc., a upper rgb value is spaced apart 0x000007 with next rgb value.
Color designation and rgb value one_to_one corresponding.Described HSI value is set as X, the form of X, X, record
The value that RGB generates after turning HSI.
Owing to existing identification technology cannot avoid the illumination condition impact on sample, therefore make a standard ratio
Colour atla.Colorimetric card arranges the recognizable region with a certain size of several different colours.Its purpose
Before the experiment intensity of illumination in current environment is calibrated equally, the result after calibration is transmitted extremely
Processing system, is updated RGB color data base simultaneously, in order to prevent in experimentation by illumination
The interference of environment and cause the dislocation of data result.
Each color wherein said color region size on colorimetric card is set as 100mm*100mm.Will
Redness, green, blueness, yellow, magenta, cyan, white, black amount to eight kinds of color settings for mark
Color in quasi-colorimetric card.
The described step being updated RGB color data base includes:
Step 1: using the RGB color data base of foundation as the first pattern library, and the 3rd benchmark is set
Storehouse is as backup pattern library;
Step 2: start calibration: by the data of camera collection standard color comparison card and write the second pattern library, will
The value of the first pattern library and the second pattern library is compared, and covers this value to the first pattern library;
Step 3: calibrating complete needs to carry out a new round when measuring, and sends signal and makes the 3rd pattern library rewrite first
Pattern library, and jump to step 2.
When applying due to reality, robot needs the sample image gathered to be all common colors, therefore need not relatively
For judging accurately, in the range of being set in one when analyzing color, therefore on testing stand, add two simultaneously
Light sensor, the step of amendment database update, record calibration starts and calibration continuously on the original basis
The intensity of illumination of current environment carry out, except making an uproar, drawing an estimated value, preventing certain in complete time interval
Experimental result is impacted by the change suddenly of one moment intensity of illumination.
During the color measuring different objects continuously, have surely when described light sensor records intensity of illumination
During fixed change, i.e. neglecting the intensity of illumination saltus step of moment, feedback is recalibrated instruction, is carried out again
Calibrate and update RGB color data base, it is to avoid the analytical error of color data.
In sum, the object color recognition methods for robot that the present invention proposes, pass through Criterion
Color libraries, reaches to identify the purpose of color of object.Simultaneously by increasing standard color comparison card, to guarantee in short-term
Between illumination condition stable in the environment of avoid light source that color of object is formed the mistake that reflection causes color data to analyze
By mistake;Again by improving camera collection system and adding part light aid, reach at illumination condition with time-varying
In the environment of Dong, it is ensured that the accuracy of data acquisition.This invention for same type color of image identification technology,
Improve the recognition success rate to color of image to a certain extent, and improve the efficiency of colour recognition.
Ensure that robot completes efficiency for operation after colour recognition.
Although the present invention is disclosed above with preferred embodiment, so it is not limited to the present invention.The present invention
Art has usually intellectual, without departing from the spirit and scope of the present invention, each when making
The change planted and retouching.Therefore, protection scope of the present invention is when being as the criterion depending on those as defined in claim.
Claims (9)
1. the object color recognition methods for robot, it is characterised in that comprise the following steps:
Set up RGB color data base, compare for the rgb value that color sample is collected;
After utilizing camera collection to arrive about the view data of sample, in processing system, calculate color sample
Rgb value, and compare with the RGB color data base of earlier set, to determine the color of sample;
Making standard color comparison card, arrange several different colours on colorimetric card has knowing of a certain size
Other region, calibrates equally to intensity of illumination in current environment, by the result transmission after calibration to processing
System, is updated RGB color data base simultaneously.
Object color recognition methods for robot the most according to claim 1, it is characterised in that
Data in described RGB color data base include three attribute, are rgb value, color designation and HSI respectively
Value.
Object color recognition methods for robot the most according to claim 2, it is characterised in that
Described rgb value is set as 16 system numbers, and the highest two is R value, and low two is B value, a upper RGB
Value is spaced apart 0x000007 with next rgb value.
Object color recognition methods for robot the most according to claim 2, it is characterised in that
Described HSI value is set as X, the form of X, X, the value that record RGB generates after turning HSI.
Object color recognition methods for robot the most according to claim 1, it is characterised in that
Each color described color region size on colorimetric card is set as 100mm*100mm.
Object color recognition methods for robot the most according to claim 1, it is characterised in that
Redness, green, blueness, yellow, magenta, cyan, white, black are amounted to eight kinds of color settings and is
Color in standard color comparison card.
Object color recognition methods for robot the most according to claim 1, it is characterised in that
The described step being updated RGB color data base includes:
Step 1: using the RGB color data base of foundation as the first pattern library, and the 3rd benchmark is set
Storehouse is as backup pattern library;
Step 2: start calibration: by the data of camera collection standard color comparison card and write the second pattern library, will
The value of the first pattern library and the second pattern library is compared, and covers this value to the first pattern library;
Step 3: calibrating complete needs to carry out a new round when measuring, and sends signal and makes the 3rd pattern library rewrite first
Pattern library, and jump to step 2.
Object color recognition methods for robot the most according to claim 1, it is characterised in that
The method also includes adding light sensor, during the color measuring different objects continuously, when described light
Dependent sensor records intensity of illumination when having stable change, i.e. neglects the intensity of illumination saltus step of moment, feedback
Recalibrate instruction, carry out calibration again and update RGB color data base, it is to avoid the analysis of color data
Error.
Object color recognition methods for robot the most according to claim 8, it is characterised in that
The method is additionally included on original base record calibration continuously and works as front ring in starting the time interval complete with calibration
The intensity of illumination in border also carries out, except making an uproar, drawing an estimated value, prevents the unexpected change of a certain moment intensity of illumination
Change and result is impacted.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610178719.3A CN105865629A (en) | 2016-03-25 | 2016-03-25 | Object color recognition method for robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610178719.3A CN105865629A (en) | 2016-03-25 | 2016-03-25 | Object color recognition method for robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105865629A true CN105865629A (en) | 2016-08-17 |
Family
ID=56625968
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610178719.3A Pending CN105865629A (en) | 2016-03-25 | 2016-03-25 | Object color recognition method for robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105865629A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106447598A (en) * | 2016-11-25 | 2017-02-22 | 常州纺织服装职业技术学院 | Visual system and visual method capable of recognizing multiple colors simultaneously |
CN106683140A (en) * | 2016-12-16 | 2017-05-17 | 深圳市中达瑞和科技有限公司 | Color recognition method and system |
CN107661158A (en) * | 2017-07-27 | 2018-02-06 | 芜湖微云机器人有限公司 | A kind of method for being digitized gear division colorimetric by more mesh cameras |
CN109060132A (en) * | 2018-09-11 | 2018-12-21 | 新灵电子技术开发(深圳)有限公司 | A kind of color identification processing system |
CN109711414A (en) * | 2018-12-19 | 2019-05-03 | 国网四川省电力公司信息通信公司 | Equipment indicating lamp color identification method and system based on camera image acquisition |
CN110320158A (en) * | 2018-03-30 | 2019-10-11 | 国际商业机器公司 | Mobile chemical analysis |
CN110536724A (en) * | 2017-02-21 | 2019-12-03 | 天使游戏纸牌股份有限公司 | The piece number detection system of recreation substitutionary coinage |
CN111141386A (en) * | 2020-01-09 | 2020-05-12 | 四川长虹电器股份有限公司 | Printing ink color identification method based on near infrared spectrum |
CN113091907A (en) * | 2021-03-31 | 2021-07-09 | 上海布鲁可积木科技有限公司 | Color recognition calibration method, system and medium |
CN114073494A (en) * | 2020-08-19 | 2022-02-22 | 京东方科技集团股份有限公司 | Leukocyte detection method, system, electronic device, and computer-readable medium |
CN114840704A (en) * | 2022-04-13 | 2022-08-02 | 云南省农业科学院质量标准与检测技术研究所 | Plant color comparison method, device, equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5850472A (en) * | 1995-09-22 | 1998-12-15 | Color And Appearance Technology, Inc. | Colorimetric imaging system for measuring color and appearance |
US20040032588A1 (en) * | 2002-08-19 | 2004-02-19 | Imperial Chemical Industries Plc | Method for obtaining an approximate standard colour definition for a sample colour |
CN101149291A (en) * | 2007-11-09 | 2008-03-26 | 无锡东望科技有限公司 | Printing dye aberration on-line detection method of machine vision system |
CN105082141A (en) * | 2015-05-08 | 2015-11-25 | 上海交通大学 | Execution modules, magic cube resolving robot and use method for magic cube resolving robot |
-
2016
- 2016-03-25 CN CN201610178719.3A patent/CN105865629A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5850472A (en) * | 1995-09-22 | 1998-12-15 | Color And Appearance Technology, Inc. | Colorimetric imaging system for measuring color and appearance |
US20040032588A1 (en) * | 2002-08-19 | 2004-02-19 | Imperial Chemical Industries Plc | Method for obtaining an approximate standard colour definition for a sample colour |
CN101149291A (en) * | 2007-11-09 | 2008-03-26 | 无锡东望科技有限公司 | Printing dye aberration on-line detection method of machine vision system |
CN105082141A (en) * | 2015-05-08 | 2015-11-25 | 上海交通大学 | Execution modules, magic cube resolving robot and use method for magic cube resolving robot |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106447598A (en) * | 2016-11-25 | 2017-02-22 | 常州纺织服装职业技术学院 | Visual system and visual method capable of recognizing multiple colors simultaneously |
CN106683140A (en) * | 2016-12-16 | 2017-05-17 | 深圳市中达瑞和科技有限公司 | Color recognition method and system |
CN110536724A (en) * | 2017-02-21 | 2019-12-03 | 天使游戏纸牌股份有限公司 | The piece number detection system of recreation substitutionary coinage |
CN107661158A (en) * | 2017-07-27 | 2018-02-06 | 芜湖微云机器人有限公司 | A kind of method for being digitized gear division colorimetric by more mesh cameras |
CN107661158B (en) * | 2017-07-27 | 2020-06-26 | 江苏微云人工智能有限公司 | Method for carrying out digital dental color comparison through multi-view camera |
CN110320158A (en) * | 2018-03-30 | 2019-10-11 | 国际商业机器公司 | Mobile chemical analysis |
CN109060132A (en) * | 2018-09-11 | 2018-12-21 | 新灵电子技术开发(深圳)有限公司 | A kind of color identification processing system |
CN109711414A (en) * | 2018-12-19 | 2019-05-03 | 国网四川省电力公司信息通信公司 | Equipment indicating lamp color identification method and system based on camera image acquisition |
CN111141386A (en) * | 2020-01-09 | 2020-05-12 | 四川长虹电器股份有限公司 | Printing ink color identification method based on near infrared spectrum |
CN114073494A (en) * | 2020-08-19 | 2022-02-22 | 京东方科技集团股份有限公司 | Leukocyte detection method, system, electronic device, and computer-readable medium |
WO2022037328A1 (en) * | 2020-08-19 | 2022-02-24 | 京东方科技集团股份有限公司 | White blood cell detection method and system, electronic device, and computer readable medium |
CN113091907A (en) * | 2021-03-31 | 2021-07-09 | 上海布鲁可积木科技有限公司 | Color recognition calibration method, system and medium |
CN113091907B (en) * | 2021-03-31 | 2022-07-15 | 上海布鲁可积木科技有限公司 | Color recognition calibration method, system and medium |
CN114840704A (en) * | 2022-04-13 | 2022-08-02 | 云南省农业科学院质量标准与检测技术研究所 | Plant color comparison method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105865629A (en) | Object color recognition method for robot | |
US20230206720A1 (en) | System for counting quantity of game tokens | |
CN105808416B (en) | A kind of automated testing method and system of man-machine figure interactive interface | |
US20100074508A1 (en) | Image processing device and medium storing image processing program | |
CN104123542B (en) | A kind of devices and methods therefor of hub workpiece positioning | |
Tao et al. | Smartphone-based detection of leaf color levels in rice plants | |
CN106683140B (en) | Color identification method and system | |
WO2017067023A1 (en) | Method for detecting body fluid based on special test paper | |
US9270866B2 (en) | Apparatus and method for automated self-training of white balance by electronic cameras | |
JP2018017570A (en) | Rock mass strength determination device, rock mass strength determination method, and rock mass strength determination program | |
CN107873079B (en) | Intelligence is to Barebone and for the method for colored sensing device | |
WO2008134038A1 (en) | Method and system for optimizing an image for improved analysis of material and illumination image features | |
CN105865329A (en) | Vision-based acquisition system for end surface center coordinates of bundles of round steel and acquisition method thereof | |
CN111626304B (en) | Color feature extraction method based on machine vision and application thereof | |
CN109711414A (en) | Equipment indicating lamp color identification method and system based on camera image acquisition | |
WO2019230447A1 (en) | Image processing method, medicine sensitivity test method and image processing device | |
CN108480223A (en) | A kind of workpiece sorting system and its control method | |
CN102461191A (en) | Visual display measurment and calibration systems and associated methods | |
CN112883987A (en) | Target extraction method, system, device and medium based on remote sensing spectral characteristics | |
JPH10221036A (en) | Method and apparatus for automatically identifying kind of part | |
CN116563391B (en) | Automatic laser structure calibration method based on machine vision | |
CN106932099A (en) | A kind of multispectral Online color-difference measurement instrument and its application | |
Stanco et al. | Computer graphics solutions for pottery colors specification | |
CN114486895A (en) | Method for detecting sample substance concentration based on pushing of urine drying test strip to identification | |
CN106971391A (en) | A kind of multi-template positioning wicking detection method based on colour recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160817 |