CN107392906B - Glass cleaning method based on multiple image acquisition and mechanical arm - Google Patents
Glass cleaning method based on multiple image acquisition and mechanical arm Download PDFInfo
- Publication number
- CN107392906B CN107392906B CN201710678575.2A CN201710678575A CN107392906B CN 107392906 B CN107392906 B CN 107392906B CN 201710678575 A CN201710678575 A CN 201710678575A CN 107392906 B CN107392906 B CN 107392906B
- Authority
- CN
- China
- Prior art keywords
- glass
- cleaning
- target glass
- value
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
- A47L1/00—Cleaning windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
Abstract
The invention discloses a glass cleaning method based on multiple times of image acquisition and a mechanical arm, which comprises the following steps: collecting current image R of target glass under light transmission1(ii) a To R1Carrying out gray scale processing to obtain a first image T1Counting of T1The middle gray value is greater than the first gray value A1Area sum Q of the regions of1(ii) a Shading the target glass; collecting current image R under shading of target glass2(ii) a To R2Performing gray scale processing to obtain a second image T2Counting of T2The middle gray scale value is larger than the second gray scale value A2Area sum Q of the regions of2(ii) a Will Q1And Q2And Q3And comparing the target glass with a preset area value, and cleaning the target glass through the cleaning manipulator according to a comparison result.
Description
Technical Field
The invention relates to the technical field of robots, in particular to a glass cleaning method based on multiple image acquisition and a manipulator.
Background
With the development of times, the population on the earth is increased, the urban high-rise buildings are higher, the multi-storey residential buildings where people live are gradually replaced by the high-rise residential buildings, the window glass of the high-rise residential buildings is cleaned to become a big problem troubling residents, the window is the most important light source in home life, most of the window glass is transparent and not resistant to dirt, once dust is blown up, and after rain and snow fall, the window glass is easily polluted, the traditional window cleaning is carried out manually, manual cleaning is carried out in the air by using a lifting rope, the cost is high, the efficiency is low, the safety is extremely poor, and the independent cleaning of residents is very troublesome, and only the inner surfaces of the window glass can be cleaned.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides a glass cleaning method based on multiple times of image acquisition and a manipulator;
the invention provides a glass cleaning method based on multiple times of image acquisition and a mechanical arm, which comprises the following steps:
s1, collecting the current image R of the target glass under light transmission1;
S2, to R1Carrying out gray scale processing to obtain a first image T1Counting of T1The middle gray value is greater than the first gray value A1Area sum Q of the regions of1;
S3, shading the target glass;
s4, collecting the current image R under the shading of the target glass2;
S5, to R2Performing gray scale processing to obtain a second image T2Counting of T2The middle gray scale value is larger than the second gray scale value A2Area sum Q of the regions of2;
S6, mixing Q1And Q2And Q3And comparing the target glass with a preset area value, and cleaning the target glass through the cleaning manipulator according to a comparison result.
Preferably, step S6 specifically includes: the preset area value comprises a first area value W1Second area value W2Third area value W3;
Calculating Q1And Q2And Q3=Q1+Q2Is mixing Q with3Compared with the preset area value, the method can be used,
when W is1<Q3<W2When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t1Time;
when W is2<Q3<W3When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t2Time;
when Q is3>W3When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t3Time;
wherein, W1、W2、W3、t1、t2、t3Are all preset values, and W1<W2<W3,t1<t2<t3。
Preferably, in step S6, the cleaning of the target glass by the cleaning robot includes: and cleaning the target glass according to a preset path by using a cleaning manipulator.
Preferably, step S3 specifically includes: the target glass is shielded from light by a roller shutter.
Preferably, step S1 specifically includes: acquiring current image R of target glass under light transmission through a plurality of high-definition cameras1;
Preferably, step S4 specifically includes: acquiring current image R under shading of target glass through a plurality of high-definition cameras2。
The invention collects the current image R of the target glass under light transmission1To R, to R1Carrying out gray scale processing to obtain a first image T1Counting of T1The middle gray value is greater than the first gray value A1Area sum Q of the regions of1Shading the target glass, and collecting the current image R under the shading of the target glass2To R, to R2Performing gray scale processing to obtain a second image T2Counting of T2The middle gray scale value is larger than the second gray scale value A2Area sum Q of the regions of2Is mixing Q with1And Q2And Q3And comparing the target glass with a preset area value, and cleaning the target glass through the cleaning manipulator according to a comparison result. So, through the image information after glass's image information and shading during comprehensive printing opacity, the judgement glass that can be accurate appears dirty to carry out the cleanness when different according to dirty area to glass, both can real-time guarantee glass's cleanness like this, let resident family glass keep clean constantly, saved simultaneously through the abluent cost of professional, danger when also having avoided the professional to wash glass.
Drawings
Fig. 1 is a schematic flow chart of a glass cleaning method based on multiple image acquisitions and a manipulator according to the present invention.
Detailed Description
Referring to fig. 1, the invention provides a glass cleaning method based on multiple image acquisition and a manipulator, which comprises the following steps:
step S1, collecting the current image R of the target glass under light transmission1Step S1 specifically includes: acquiring current image R of target glass under light transmission through a plurality of high-definition cameras1。
In a specific scheme, a plurality of high-definition cameras are used for collecting current images of the target glass under light transmission, and the situation that a single camera collects the images incompletely is prevented.
Step S2, for R1Carrying out gray scale processing to obtain a first image T1Counting of T1The middle gray value is greater than the first gray value A1Area sum Q of the regions of1;
In the specific scheme, the purpose of carrying out gray processing on the current image of the target glass under light transmission is to conveniently distinguish a dirty area from a clean area, so that whether the target glass is dirty or not is conveniently judged.
Step S3, shading the target glass, specifically including: the target glass is shielded from light by a roller shutter.
Step S4, collecting the current image R under the shading of the target glass2The method specifically comprises the following steps: acquiring current image R under shading of target glass through a plurality of high-definition cameras2。
In a specific scheme, a plurality of high-definition cameras are used for collecting current images of target glass under shading, and the situation that a single camera collects the images incompletely is prevented.
Step S5, for R2Performing gray scale processing to obtain a second image T2Counting of T2The middle gray scale value is larger than the second gray scale value A2Area sum Q of the regions of2;
In the specific scheme, the purpose of carrying out gray processing on the current image under the shading of the target glass is to conveniently distinguish a dirty area from a clean area, so that whether the target glass is dirty or not is conveniently judged.
Step S6, mixing Q1And Q2And Q3Compare with the area value of predetermineeing, clear up target glass through cleaning the manipulator according to the comparative result, specifically include: the preset area value comprises a first area value W1Second area value W2Third area value W3;
Calculating Q1And Q2And Q3=Q1+Q2Is mixing Q with3Compared with the preset area value, the method can be used,
when W is1<Q3<W2When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t1Time;
when W is2<Q3<W3When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t2Time;
when Q is3>W3When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t3Time;
wherein, W1、W2、W3、t1、t2、t3Are all preset values, and W1<W2<W3,t1<t2<t3。
In this step, clear up target glass through clean manipulator, specifically include: and cleaning the target glass according to a preset path by using a cleaning manipulator.
In the concrete scheme, because some dirt is discerned easily in the printing opacity, some dirt is discerned easily in the shading, then gather current image under the printing opacity of target glass and the current image under the shading of target glass, carry out grey scale processing back to two images, synthesize grey value comparison result and area value comparison result, judge whether the dirt appears in target glass, when the judgement result is, carry out not equidimension's cleanness to target glass through the manipulator, so both can real-time guarantee glass's cleanness, let glass keep clean at the resident family at all times, the cost of wasing through the professional has been saved simultaneously.
The embodiment collects the current image R of the target glass under light transmission1To R, to R1Carrying out gray scale processing to obtain a first image T1Counting of T1The middle gray value is greater than the first gray value A1Of (2) aSum of area Q1Shading the target glass, and collecting the current image R under the shading of the target glass2To R, to R2Performing gray scale processing to obtain a second image T2Counting of T2The middle gray scale value is larger than the second gray scale value A2Area sum Q of the regions of2Is mixing Q with1And Q2And Q3And comparing the target glass with a preset area value, and cleaning the target glass through the cleaning manipulator according to a comparison result. So, through the image information after glass's image information and shading during comprehensive printing opacity, the judgement glass that can be accurate appears dirty to carry out the cleanness when different according to dirty area to glass, both can real-time guarantee glass's cleanness like this, let resident family glass keep clean constantly, saved simultaneously through the abluent cost of professional, danger when also having avoided the professional to wash glass.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (5)
1. A glass cleaning method based on multiple image acquisition and a mechanical arm is characterized by comprising the following steps:
s1, collecting the current image R of the target glass under light transmission1;
S2, to R1Carrying out gray scale processing to obtain a first image T1Counting of T1The middle gray value is greater than the first gray value A1Area sum Q of the regions of1;
S3, shading the target glass;
s4, collecting the current image R under the shading of the target glass2;
S5, to R2Performing gray scale processing to obtain a second image T2Counting of T2The middle gray scale value is larger than the second gray scale value A2Area sum Q of the regions of2;
S6, mixing Q1And Q2And Q3And comparing the target glass with a preset area value, and cleaning the target glass through the cleaning manipulator according to a comparison result.
2. The method for cleaning glass based on multiple image acquisitions and a manipulator as claimed in claim 1, wherein the step S6 specifically comprises: the preset area value comprises a first area value W1Second area value W2Third area value W3;
Calculating Q1And Q2And Q3=Q1+Q2Is mixing Q with3Compared with the preset area value, the method can be used,
when W is1<Q3<W2When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t1Time;
when W is2<Q3<W3When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t2Time;
when Q is3>W3When the glass cleaning machine is used, the control module commands the cleaning manipulator to clean the target glass t3Time;
wherein, W1、W2、W3、t1、t2、t3Are all preset values, and W1<W2<W3,t1<t2<t3。
3. The method for cleaning glass based on multiple image acquisitions and mechanical hands as claimed in claim 1, wherein the step S6 of cleaning the target glass by the cleaning mechanical hand specifically comprises: and cleaning the target glass according to a preset path by using a cleaning manipulator.
4. The method for cleaning glass based on multiple image acquisitions and a manipulator as claimed in claim 1, wherein the step S3 specifically comprises: the target glass is shielded from light by a roller shutter.
5. The method for cleaning glass based on multiple image acquisitions and a manipulator as claimed in claim 1, wherein the step S1 specifically comprises: acquiring current image R of target glass under light transmission through a plurality of high-definition cameras1;
Preferably, step S4 specifically includes: acquiring current image R under shading of target glass through a plurality of high-definition cameras2。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710678575.2A CN107392906B (en) | 2017-08-10 | 2017-08-10 | Glass cleaning method based on multiple image acquisition and mechanical arm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710678575.2A CN107392906B (en) | 2017-08-10 | 2017-08-10 | Glass cleaning method based on multiple image acquisition and mechanical arm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107392906A CN107392906A (en) | 2017-11-24 |
CN107392906B true CN107392906B (en) | 2020-09-25 |
Family
ID=60355015
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710678575.2A Active CN107392906B (en) | 2017-08-10 | 2017-08-10 | Glass cleaning method based on multiple image acquisition and mechanical arm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107392906B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108042032A (en) * | 2017-12-11 | 2018-05-18 | 邓鹏� | A kind of Intelligent shower device of combination shower person exercise data |
CN108065839A (en) * | 2017-12-11 | 2018-05-25 | 黄锋平 | A kind of Intelligent shower device based on image |
CN107928501A (en) * | 2017-12-11 | 2018-04-20 | 黄锋平 | A kind of shower bath |
CN108056691A (en) * | 2017-12-11 | 2018-05-22 | 邓鹏� | A kind of shower bath based on big data |
CN108301729A (en) * | 2018-02-07 | 2018-07-20 | 曾洁 | Automatic-cleaning type Intelligent home device |
CN109138732B (en) * | 2018-02-07 | 2020-07-10 | 广州亿享云软件技术有限公司 | Automatic cleaning method for intelligent household device |
CN110251004B (en) * | 2019-07-16 | 2022-03-11 | 深圳市杉川机器人有限公司 | Sweeping robot, sweeping method thereof and computer-readable storage medium |
CN111795329A (en) * | 2020-07-15 | 2020-10-20 | 扬州市润熙照明科技有限公司 | Lamp post device of clean street lamp convenient to dismantle |
CN113620614A (en) * | 2021-07-27 | 2021-11-09 | 深圳市若菲特科技有限公司 | Method, device and equipment for removing ink on glass surface and storage medium |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20040015728A (en) * | 2001-07-05 | 2004-02-19 | 닛폰 이타가라스 가부시키가이샤 | Method and device for inspecting defect of sheet-shaped transparent body |
CN101936915B (en) * | 2010-07-30 | 2012-10-24 | 哈尔滨工业大学(威海) | Method for detecting dirt on central region of bottom of beer bottle |
WO2013184835A1 (en) * | 2012-06-07 | 2013-12-12 | The Regents Of The University Of California | Wide-field microscopy using self-assembled liquid lenses |
CN105212844B (en) * | 2015-10-16 | 2018-07-24 | 上海电巴新能源科技有限公司 | A kind of unmanned plane having cleaning function |
CN105882607A (en) * | 2016-04-25 | 2016-08-24 | 乐视控股(北京)有限公司 | Device and method for cleaning windshield of vehicle |
CN106572349B (en) * | 2016-11-18 | 2019-04-12 | 维沃移动通信有限公司 | A kind of detection method and mobile terminal of camera cleannes |
-
2017
- 2017-08-10 CN CN201710678575.2A patent/CN107392906B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107392906A (en) | 2017-11-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107392906B (en) | Glass cleaning method based on multiple image acquisition and mechanical arm | |
US11070720B2 (en) | Directed image capture | |
CN108113595A (en) | A kind of energy-saving sweeping machine device people system, method and robot | |
CN110025268B (en) | Method for cleaning stubborn stains | |
WO2015196616A1 (en) | Image edge detection method, image target recognition method and device | |
WO2020077707A1 (en) | Automatic control method for operations of road operating vehicle and road operating vehicle | |
CN107997692A (en) | A kind of control method of sweeping robot | |
CN109871013A (en) | Clean robot paths planning method and system, storage medium, electronic equipment | |
CN111012254A (en) | Intelligent floor sweeping robot | |
CN107507163A (en) | A kind of method and system for identifying photovoltaic solar panel surface smut degree | |
JP2005054356A (en) | Electric blind remote control system | |
JP2005292066A (en) | Condition diagnostic device, condition diagnostic program, and condition diagnostic system | |
CN108093175B (en) | A kind of adaptive defogging method of real-time high-definition video and device | |
CN111010079B (en) | Multi-sensor-based photovoltaic intelligent cleaning control system and method | |
JP2022032411A (en) | Cleaning service supporting system, cleaning service support method and cleaning service support device | |
CN107481230B (en) | Intelligent glass cleaning robot hand control system based on image acquisition | |
CN107123108B (en) | Machine vision-based automatic detection method for honeycomb defects of remote sensor lens hood | |
CN109579934A (en) | Water logging multiple monitoring method and system | |
CN103533278B (en) | A kind of large format Free Surface many projections method for automatically split-jointing | |
CN107013155B (en) | Curtain automatic rolls up system | |
CN110211102B (en) | Badminton racket broken line detection method for unmanned network renting and selling machine | |
CN1272666A (en) | Automatic testing system for driver pile examination process based on image sequence analysis | |
JP2021119802A (en) | Sweeping control method | |
CN114680753A (en) | Big data-based monitoring system and method for display state of scrubber | |
WO2020218113A1 (en) | Contamination inspection device, contamination inspection method, and solar power generation module management method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |