CN104181920A - Vision-based AGV positioning method - Google Patents
Vision-based AGV positioning method Download PDFInfo
- Publication number
- CN104181920A CN104181920A CN201310189378.6A CN201310189378A CN104181920A CN 104181920 A CN104181920 A CN 104181920A CN 201310189378 A CN201310189378 A CN 201310189378A CN 104181920 A CN104181920 A CN 104181920A
- Authority
- CN
- China
- Prior art keywords
- mark
- image
- color
- information
- agv
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a vision-based AGV positioning method. According to the vision-based AGV positioning method, statistical positioning is realized in a manner of configuring a color mark line (2) in an operation path (1) and forming a cross with the operation path (1). The vision-based AGV positioning method aims at the following defects in common vision-based AGV positioning system: single positioning strategy, large accumulative error, easy interference, high mounting cost, etc. The vision-based AGV positioning method has advantages of: abundant information acquisition, multiple positioning strategies, high expandability, low cost, convenient mark configuration, simple and reliable algorithm processing, etc.
Description
Technical field
The present invention relates to a kind of AGV localization method, especially relate to a kind of AGV localization method based on vision.
Background technology
AGV (Automatic Guided Vehicle, automatic Guided Vehicle) be a kind of unmanned automatic transportation equipment, can carry certain weight autonomous operation between departure place and destination, be the important composition equipment of automatic logistics system and flexible manufacturing system, there is good market outlook and using value.Navigational system is the core control section of AGV, and location is extremely important functional component in navigational system.
At present, common AGV localization method has mileage location, inertial positioning, RFID location, laser positioning etc., and its strengths and weaknesses is as follows:
(1) mileage location: position according to dolly travel distance, the method is simple and easy to use, cost is low, but its positioning strategy is single, positioning precision is lower, and easily occurs cumulative errors;
(2) inertial positioning: utilize gyroscope accurately to obtain AGV traffic direction and speed, by known start position coordinate, can calculate the position of AGV., easily there is cumulative errors in the method simple and flexible but cost is higher.
(3) RFID location: utilize less radio-frequency to position, have advantages of that volume is little, low in energy consumption, but RFID reach is shorter, is easily disturbed under complicated electromagnetic environment;
(4) laser positioning: accurate positioning, reliable, precision is very high, but its cost is higher, and the installation of sensor and transmitting, reflection unit is complicated.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of AGV localization method based on vision, and the method forms the mode of cross by arrange color mark line 2 and operating path 1 on operating path 1, realizes statistics location.Positioning strategy for the easy appearance existing in common AGV positioning system is single, cumulative errors greatly, be easily disturbed, the high deficiency of installation cost, this method has that acquisition of information is abundant, positioning strategy is various, extensibility is strong, with low cost, the feature such as sign arrangement convenience, algorithm process are simple and reliable.
The technical solution used in the present invention is as follows: a kind of AGV localization method based on vision, is characterized in that:
Step 1, arranges that on trolley travelling path 1 mark line 2 is as identification marking;
Step 2, image capture module gathers image information;
Step 3, image processing module reads in image information and is translated into the information of road surface of parameterized form;
Step 4, locating module reads in information of road surface, determines characteristic type, contrast historical data location current location;
Step 5, locating module sends locating information to primary control program, determines control strategy.
As preferably, in described step 1, the point in dolly starting point, terminal and intermediate demand location arranges identification marking.
As preferably, described mark line 2 is color mark line.
As preferably, described mark line 2 forms cross curve with trolley travelling path 1.
As preferably, in described step 3, the concrete grammar step of image processing module work is:
The pavement image that a, reading images acquisition module gather;
B, utilize morphological image burn into expand to carry out filtering, filtering interference signals;
C, according to image outline, determine that whether dolly is in mark;
D if, extract the marker color information of the image before gray processing, further according to color of image, judge that whether dolly is in mark;
E is if the parameter information that colouring information is treated to binaryzation is exported to locating module, determines color type and contrasts the position that historical data is judged representative.
As preferably, in described step c, according to image outline, determine that whether dolly at the concrete grammar of mark is: first image is carried out to gray scale processing, progressive scanning picture, extracts the gray-scale value of each pixel, according to setting threshold, it is carried out to binary conversion treatment, make image only have dividing of black-and-white two color, if the maximum a line black picture element number of black picture element number surpasses certain value, think at present in mark.
As preferably, in described steps d, according to color of image, judge that whether dolly at the concrete grammar of mark is: if be currently located at mark, to carrying out color treatments for the view data before gray processing, if belong to the pixel count of certain color, surpass setting value, think and there is this color mark in this two field picture, thereby further determine that dolly is in mark.
As preferably, in described step 4, the concrete grammar step of locating module work is:
A, read in the road surface parameter that image processing module is finally handled well;
B, according to road surface parameter, confirm the color characteristic type of mark, marker color feature is sorted out to statistics;
C, according to sorting out statistics, comparison historical data, positions AGV;
D, transmission locating information, to primary control program, are carried out the formulation of AGV control strategy for it.
As preferably, in described step b, described classification statistics has referred to after action decision-making, and the color characteristic of this mark is added to historical data base.
As preferably, the concrete grammar contrasting in described step c is: historical data is deposited in chained list, each node i.e. a gauge point place that comprises colouring information, cartographic information is defined as to binary tree, by the colouring information of chained list node one by one with binary tree in colouring information contrast, obtain position.
Compared with prior art, the invention has the beneficial effects as follows: positioning strategy for the easy appearance existing in common AGV positioning system is single, cumulative errors greatly, be easily disturbed, the high deficiency of installation cost, this method has that acquisition of information is abundant, positioning strategy is various, extensibility is strong, with low cost, the feature such as sign arrangement convenience, algorithm process are simple and reliable.
Accompanying drawing explanation
Fig. 1 is the wherein mark schematic diagram of an embodiment of the present invention.
Fig. 2 is middle mark positioning principle schematic diagram embodiment illustrated in fig. 1.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Disclosed all features in this instructions, except the feature of mutual eliminating, all can combine by any way.
Disclosed arbitrary feature in this instructions (comprising any accessory claim, summary and accompanying drawing), unless narration especially all can be replaced by other equivalences or the alternative features with similar object.That is,, unless narration especially, each feature is an example in a series of equivalences or similar characteristics.
A kind of AGV localization method based on vision:
Step 1, arranges that on trolley travelling path 1 mark line 2 is as identification marking;
Step 2, image capture module gathers image information;
Step 3, image processing module reads in image information and is translated into the information of road surface of parameterized form;
Step 4, locating module reads in information of road surface, determines characteristic type, contrast historical data location current location;
Step 5, locating module sends locating information to primary control program, determines control strategy.
Image capture module 1 is caught actual road surface situation as the input of vision navigation system by CCD or CMOS camera, and the quality of picture quality directly affects processing speed and the precision of system, and good illumination condition is the prerequisite of obtaining qualitative picture.
As shown in Figure 2, in described step 1, the point in dolly starting point, terminal and intermediate demand location (as: pause, crossing etc.) arranges identification marking.
The starting point that A point is dolly, A, B, C, D, E, F, G, H, I, M are all places that arrive and pause of may needing of dolly.
As shown in Figure 1, described mark line 2 is color mark line, forms cross curve with trolley travelling path 1.
In described step 3, the concrete grammar step of image processing module work is:
The pavement image that a, reading images acquisition module gather;
B, utilize morphological image burn into expand to carry out filtering, filtering interference signals;
C, according to image outline, determine that whether dolly is in mark;
D if, extract the marker color information of the image before gray processing, further according to color of image, judge that whether dolly is in mark;
E is if the parameter information that colouring information is treated to binaryzation is exported to locating module, determines color type and contrasts the position that historical data is judged representative.
In described step c, according to image outline, determine that whether dolly at the concrete grammar of mark is: first image is carried out to gray scale processing, progressive scanning picture, extract the gray-scale value of each pixel, according to setting threshold, it is carried out to binary conversion treatment, make image only have dividing of black-and-white two color, if a line black picture element number that black picture element number is maximum surpasses certain value, think at present in mark.
In this specific embodiment, take cruciform profile as example, after binaryzation, just there will be one to take white as background, the cross profile that black is prospect.
In described steps d, according to color of image, judge that whether dolly at the concrete grammar of mark is: if be currently located at mark, to carrying out color treatments for the view data before gray processing, if belong to the pixel count of certain color, surpass setting value, think and there is this color mark in this two field picture, thereby further determine that dolly is in mark.
Consider that ground may exist color stain, progressive scanning picture, obtains the designated color pixel (as blue, red, yellow) existing in image, judge whether to surpass setting value T1, if so, according to the kind of color, int type variable colorNum is carried out to assignment.
Can represent with structure
struct?mark
{
bool?isCross;
int?colorNum;
};
IsCross is that true shows in mark, for false shows not in mark;
ColorNum can be different integers, such as colorNum=1 represents redness; ColorNum=2 represents blueness ...
In described step 4, the concrete grammar step of locating module work is:
A, read in the road surface parameter that image processing module is finally handled well;
B, according to road surface parameter, confirm the color characteristic type of mark, according to set action is tactful, the color characteristic of mark is sorted out to statistics;
C, according to sorting out statistics, comparison historical data (as cartographic information), positions AGV, comprises whether arriving mark, is positioned at present which section path etc.;
D, send locating information to primary control program, for it, carry out the formulation of AGV control strategy (whether slow down, whether stop, whether turn etc.).
Set action strategy: from origin-to-destination, the mark that AGV will pass through, should do which kind of decision-making (upper and lower goods whether, speed whether change etc.) in each mark.
In described step b, described classification statistics has referred to after action decision-making, and the color characteristic of this mark is added to historical data base.
The concrete grammar contrasting in described step c is: historical data is deposited in chained list, each node i.e. a gauge point place that comprises colouring information, cartographic information is defined as to binary tree, by the colouring information of chained list node one by one with binary tree in colouring information contrast, obtain position.
Suppose that AGV is from mark A, through successively and having comprised A and arrive 5 points in being marked at, if do not consider the colouring information of historical data, arrive gauge point can in D, F, G, I any one, by with historical data (such as: successively through indigo plant, indigo plant, red, indigo plant) contrast after, add current mark colouring information (such as: Huang), can determine that current AGV has run to G point.
AGV, in operational process, while passing through mark, deposits in marker color information in database at every turn.
A kind of method that adopts color, the additional comparison historical data of cross mark to locate as AGV in this specific embodiment, its calculated amount is little, and speed is fast.
The method of the invention with lower cost enriched AGV road pavement information the extensibility of having obtained, strengthened positioning strategy (such as: by character, numeral identification, can form new localization method), reduce the cost of locating module, adapted to part automatic logistics system, flexible manufacturing system to requirement low-cost, high flexibility.
Claims (10)
1. the AGV localization method based on vision, is characterized in that:
Step 1, above arranges that in trolley travelling path (1) mark line (2) is as identification marking;
Step 2, image capture module gathers image information;
Step 3, image processing module reads in image information and is translated into the information of road surface of parameterized form;
Step 4, locating module reads in information of road surface, determines characteristic type, contrast historical data location current location;
Step 5, locating module sends locating information to primary control program, determines control strategy.
2. a kind of AGV localization method based on vision according to claim 1, is characterized in that:
In described step 1, the point in dolly starting point, terminal and intermediate demand location arranges identification marking.
3. a kind of AGV localization method based on vision according to claim 2, is characterized in that:
Described mark line (2) is color mark line.
4. a kind of AGV localization method based on vision according to claim 3, is characterized in that:
Described mark line (2) forms cross curve with trolley travelling path (1).
5. a kind of AGV localization method based on vision according to claim 4, is characterized in that:
In described step 3, the concrete grammar step of image processing module work is:
The pavement image that a, reading images acquisition module gather;
B, utilize morphological image burn into expand to carry out filtering, filtering interference signals;
C, according to image outline, determine that whether dolly is in mark;
D if, extract the marker color information of the image before gray processing, further according to color of image, judge that whether dolly is in mark;
E is if export to locating module by color parameter information, according to marker color and contrast the position that historical data is judged representative.
6. a kind of AGV localization method based on vision according to claim 5, is characterized in that:
In described step c, according to image outline, determine that whether dolly at the concrete grammar of mark is: first image is carried out to gray scale processing, progressive scanning picture, extract the gray-scale value of each pixel, according to setting threshold, it is carried out to binary conversion treatment, make image only have dividing of black-and-white two color, if a line black picture element number that black picture element number is maximum surpasses certain value, think at present in mark.
7. a kind of AGV localization method based on vision according to claim 6, is characterized in that:
In described steps d, according to color of image, judge that whether dolly at the concrete grammar of mark is: if be currently located at mark, to carrying out color treatments for the view data before gray processing, if belong to the pixel count of certain color, surpass setting value, think and there is this color mark in this two field picture, thereby further determine that dolly is in mark.
8. a kind of AGV localization method based on vision according to claim 5, is characterized in that:
In described step 4, the concrete grammar step of locating module work is:
A, read in the road surface parameter information that image processing module is finally handled well;
B, according to road surface parameter, confirm the color characteristic type of mark, marker color is sorted out to statistics;
C, according to sorting out statistics, comparison historical data, positions AGV;
D, transmission locating information, to primary control program, are carried out the formulation of AGV control strategy for it.
9. a kind of AGV localization method based on vision according to claim 8, is characterized in that:
In described step b, described classification statistics has referred to after action decision-making, and the color characteristic of this mark is added to historical data base.
10. a kind of AGV localization method based on vision according to claim 9, is characterized in that:
The concrete grammar contrasting in described step c is: historical data is deposited in chained list, each node i.e. a gauge point place that comprises colouring information, cartographic information is defined as to binary tree, by the colouring information of chained list node one by one with binary tree in colouring information contrast, obtain position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310189378.6A CN104181920B (en) | 2013-05-21 | 2013-05-21 | A kind of AGV localization method of view-based access control model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310189378.6A CN104181920B (en) | 2013-05-21 | 2013-05-21 | A kind of AGV localization method of view-based access control model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104181920A true CN104181920A (en) | 2014-12-03 |
| CN104181920B CN104181920B (en) | 2017-03-08 |
Family
ID=51963057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310189378.6A Active CN104181920B (en) | 2013-05-21 | 2013-05-21 | A kind of AGV localization method of view-based access control model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104181920B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915705A (en) * | 2015-07-08 | 2015-09-16 | 上海德马物流技术有限公司 | Visual identity combination type color block tag for warehouse logistics navigation |
| CN105278530A (en) * | 2015-09-16 | 2016-01-27 | 成都四威高科技产业园有限公司 | Magnetic stripe signal fault tolerance and error correction processing method and system |
| CN105354648A (en) * | 2015-12-12 | 2016-02-24 | 深圳力子机器人有限公司 | Modeling and optimizing method for AGV dispatching management |
| CN106292652A (en) * | 2015-05-14 | 2017-01-04 | 苏州宝时得电动工具有限公司 | Automatic working system, automatic work equipment and the method identifying homeposition thereof |
| CN107084716A (en) * | 2017-05-16 | 2017-08-22 | 苏州艾吉威机器人有限公司 | A kind of localization method of the areflexia plate laser navigation of use adminicle |
| CN108398946A (en) * | 2018-01-25 | 2018-08-14 | 成都图灵智控科技有限公司 | Intelligent tracking accurate positioning device and method |
| CN109283928A (en) * | 2018-09-25 | 2019-01-29 | 华南农业大学 | A kind of self-navigation transport vehicle and its automatic running method based on machine vision |
| CN112815783A (en) * | 2021-01-07 | 2021-05-18 | 西安凯胜智能科技有限公司 | Prismatic arraying electronic target scoring system |
| CN113119790A (en) * | 2019-12-31 | 2021-07-16 | 杭州海康机器人技术有限公司 | Battery replacing method and device for automatic guided transport vehicle and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11271074A (en) * | 1998-03-20 | 1999-10-05 | Fujitsu Ltd | Device and method for comparing mark image and program storage medium |
| CN1885317A (en) * | 2006-07-06 | 2006-12-27 | 上海交通大学 | Adaptive edge detection method based on morphology and information entropy |
| EP1983397A2 (en) * | 2007-04-17 | 2008-10-22 | Itt Manufacturing Enterprises, Inc. | Landmark navigation for vehicles using blinking optical beacons |
| CN102789234A (en) * | 2012-08-14 | 2012-11-21 | 广东科学中心 | Robot navigation method and robot navigation system based on color coding identifiers |
| CN102997910A (en) * | 2012-10-31 | 2013-03-27 | 上海交通大学 | Positioning and guiding system and method based on ground road sign |
| CN103020632A (en) * | 2012-11-20 | 2013-04-03 | 北京航空航天大学 | Fast recognition method for positioning mark point of mobile robot in indoor environment |
-
2013
- 2013-05-21 CN CN201310189378.6A patent/CN104181920B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11271074A (en) * | 1998-03-20 | 1999-10-05 | Fujitsu Ltd | Device and method for comparing mark image and program storage medium |
| CN1885317A (en) * | 2006-07-06 | 2006-12-27 | 上海交通大学 | Adaptive edge detection method based on morphology and information entropy |
| EP1983397A2 (en) * | 2007-04-17 | 2008-10-22 | Itt Manufacturing Enterprises, Inc. | Landmark navigation for vehicles using blinking optical beacons |
| CN102789234A (en) * | 2012-08-14 | 2012-11-21 | 广东科学中心 | Robot navigation method and robot navigation system based on color coding identifiers |
| CN102997910A (en) * | 2012-10-31 | 2013-03-27 | 上海交通大学 | Positioning and guiding system and method based on ground road sign |
| CN103020632A (en) * | 2012-11-20 | 2013-04-03 | 北京航空航天大学 | Fast recognition method for positioning mark point of mobile robot in indoor environment |
Non-Patent Citations (1)
| Title |
|---|
| 李向文: "《物流实用信息技术》", 31 March 2010 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292652A (en) * | 2015-05-14 | 2017-01-04 | 苏州宝时得电动工具有限公司 | Automatic working system, automatic work equipment and the method identifying homeposition thereof |
| CN104915705A (en) * | 2015-07-08 | 2015-09-16 | 上海德马物流技术有限公司 | Visual identity combination type color block tag for warehouse logistics navigation |
| CN105278530A (en) * | 2015-09-16 | 2016-01-27 | 成都四威高科技产业园有限公司 | Magnetic stripe signal fault tolerance and error correction processing method and system |
| CN105278530B (en) * | 2015-09-16 | 2017-12-29 | 成都四威高科技产业园有限公司 | A kind of fault-tolerant correction processing method of magnetic stripe signal and system |
| CN105354648B (en) * | 2015-12-12 | 2020-02-14 | 深圳力子机器人有限公司 | Modeling and optimizing method for AGV (automatic guided vehicle) scheduling management |
| CN105354648A (en) * | 2015-12-12 | 2016-02-24 | 深圳力子机器人有限公司 | Modeling and optimizing method for AGV dispatching management |
| CN107084716A (en) * | 2017-05-16 | 2017-08-22 | 苏州艾吉威机器人有限公司 | A kind of localization method of the areflexia plate laser navigation of use adminicle |
| CN108398946A (en) * | 2018-01-25 | 2018-08-14 | 成都图灵智控科技有限公司 | Intelligent tracking accurate positioning device and method |
| CN108398946B (en) * | 2018-01-25 | 2021-12-21 | 成都图灵时代科技有限公司 | Intelligent tracking accurate positioning device and method |
| CN109283928A (en) * | 2018-09-25 | 2019-01-29 | 华南农业大学 | A kind of self-navigation transport vehicle and its automatic running method based on machine vision |
| CN113119790A (en) * | 2019-12-31 | 2021-07-16 | 杭州海康机器人技术有限公司 | Battery replacing method and device for automatic guided transport vehicle and storage medium |
| CN112815783A (en) * | 2021-01-07 | 2021-05-18 | 西安凯胜智能科技有限公司 | Prismatic arraying electronic target scoring system |
| CN112815783B (en) * | 2021-01-07 | 2024-01-19 | 西安凯胜智能科技有限公司 | Prismatic array electronic target reporting system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104181920B (en) | 2017-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104181920A (en) | Vision-based AGV positioning method | |
| CN104392212B (en) | The road information detection and front vehicles recognition methods of a kind of view-based access control model | |
| Mu et al. | Traffic light detection and recognition for autonomous vehicles | |
| CN102773862B (en) | Quick and accurate locating system used for indoor mobile robot and working method thereof | |
| CN104848851B (en) | Intelligent Mobile Robot and its method based on Fusion composition | |
| CN104217427B (en) | Lane line localization method in a kind of Traffic Surveillance Video | |
| CN101358836B (en) | Method for recognizing weld spot central position based on computer vision | |
| CN109541634A (en) | A kind of paths planning method, device and mobile device | |
| CN202702247U (en) | Rapid and accurate positioning system used for indoor mobile robot | |
| CN101398907B (en) | Two-dimension code structure and decoding method for movable robot | |
| CN106584451B (en) | automatic transformer substation composition robot and method based on visual navigation | |
| CN101929867A (en) | Clear path detection using road model | |
| CN110068818A (en) | The working method of traffic intersection vehicle and pedestrian detection is carried out by radar and image capture device | |
| CN107218927B (en) | A kind of cargo pallet detection system and method based on TOF camera | |
| CN101944176A (en) | Exist the more excellent clear path of means of transportation sign to detect | |
| CN102592454A (en) | Intersection vehicle movement parameter measuring method based on detection of vehicle side face and road intersection line | |
| CN108594244B (en) | Obstacle recognition transfer learning method based on stereoscopic vision and laser radar | |
| JP6347918B2 (en) | System and method for guiding a mobile device | |
| CN107077784A (en) | Method and system for providing the information at least one object in the environmental area of motor vehicle | |
| CN105865438A (en) | Autonomous precise positioning system based on machine vision for indoor mobile robots | |
| CN110532961A (en) | A kind of semantic traffic lights detection method based on multiple dimensioned attention mechanism network model | |
| CN105444741A (en) | Double view window based route characteristic identifying, deviation measuring, and accurate positioning method | |
| CN108171154A (en) | A kind of method that target detection is combined with lane detection in automatic Pilot | |
| CN110083099A (en) | One kind meeting automobile function safety standard automatic Pilot architecture system and working method | |
| CN114051628A (en) | Method and device for determining target object point cloud set |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |