CN206832260U - A kind of Navigation System for Mobile Robot of view-based access control model - Google Patents
A kind of Navigation System for Mobile Robot of view-based access control model Download PDFInfo
- Publication number
- CN206832260U CN206832260U CN201720492391.2U CN201720492391U CN206832260U CN 206832260 U CN206832260 U CN 206832260U CN 201720492391 U CN201720492391 U CN 201720492391U CN 206832260 U CN206832260 U CN 206832260U
- Authority
- CN
- China
- Prior art keywords
- image
- mobile robot
- lane line
- navigation system
- based access
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The utility model discloses a kind of Navigation System for Mobile Robot of view-based access control model;Including vision sensor, image processor, motion-control module and mobile robot car body.It is responsible for gathering scene image by vision sensor, image processor carries out image Treatment Analysis, then sends the operation of instruction control machine people by motion-control module.Lane line is preset in mobile work robot environment, and identifier is set in ad-hoc location;Mobile robot collection institute scene image at ambient, and the image with ground in orthographic projection is obtained by perspective transform;Gained image is melted into bianry image through gray processing and threshold value, then is split to obtain the image and the only image containing lane line only containing identifier;Approximate track trajectory is only being found out on the image containing lane line and is being tracked, then is identifying identifier, position and acceleration information is being obtained, realizes mobile robot precision navigation.
Description
Technical field
It the utility model is related to robot navigation field, more particularly to a kind of Mobile Robotics Navigation system of view-based access control model
System.
Background technology
Mobile robot can effectively improve logistics progress in workshop, reduce enterprise's labour cost and improves production effect
Rate, had a wide range of applications demand in multiple industries such as automobile, food, printing, material transportation.
One key technology of mobile robot is airmanship, and Mobile Robotics Navigation has had various ways, such as used
Property navigation, tape navigation, laser navigation and vision guided navigation etc..The mobile robot of different navigation mode has the characteristics of respective,
And determine the flexible degree and cost of formed logistics system.Inertial navigation utilizes gyroscope and photoelectric encoder, its
Influence easily is disturbed, control performance is relatively poor;Tape navigation need in advance laying tape, safeguard with transformation cost compared with
It is high;Laser navigation needs extra installation reflector, and laser sensor involves great expense, and maintenance cost is higher.So vision guided navigation
Mobile robot has higher practical value and wide application prospect.
Because the environment where mobile robot is usually relatively complex, and because the dynamic characteristic of its own is to need reality
When image caused by motion process is handled, if to establish accurate environmental map, the data volume of processing is huge,
Requirement to hardware is very high, and cost is high, implements difficult.The existing vision navigation method based on Quick Response Code and navigation band
Although simple, quick, due in mobile robot practical application scene Quick Response Code easily by dust or spot influence so as to
Recognition success rate is caused to decline, its validity has much room for improvement.
The content of the invention
The shortcomings that the purpose of this utility model is to overcome above-mentioned prior art and deficiency, there is provided a kind of simple and reliable, real
The Navigation System for Mobile Robot for the view-based access control model that when property is good, controllability is good.
The utility model is achieved through the following technical solutions:
A kind of Navigation System for Mobile Robot of view-based access control model, including such as lower component:
Vision sensor;
Image processor;
Motion-control module;
Mobile robot car body;
The vision sensor, image processor and motion-control module carry by mobile robot car body;By vision
Sensor is responsible for collection scene image in real time, and image processor carries out Treatment Analysis to the image collected, then by motion control
Module sends the operation of instruction control machine people according to analysis result.
The vision sensor uses USB cameras, and is centrally mounted at the front end of mobile robot car body.
The USB cameras are additionally provided with a LED light source supporting with it.
Described image processor selects ARM Cortex-a9.
The air navigation aid of the Navigation System for Mobile Robot of view-based access control model, is comprised the steps of:
Step 1:The ambient image on vision sensor collection ground in front of the mobile robot car body in traveling;
The tape of dark color is preset with the scene of ambient image on light ground as lane line, in the pre-determined bit of tape
Install and be equipped with multiple identifiers;There is a black (or dark) annulus outside identifier;Identifier includes mobile robot
The positional information and velocity variations information of car body;
Step 2:The image obtained in step 1 is subjected to perspective transform by image processor, is changed into image and regards
Feel image of the camera of sensor with ground in orthographic projection;
Step 3:Image obtained in step 2 is subjected to noise reduction process and is converted to gray level image;
Again image progress thresholding is handled to obtain bianry image and carry out image dividing processing, obtain one only comprising mark
Know the ROI image and a ROI image for only including lane line of symbol.
The only ROI image containing lane line that will be obtained again, two discontinuous processing regions, traversal are specified on image
The all pixels of pixel column are set, easily obtain the midpoint of lane line on intended pixel row in two processing regions, 2 points of connection obtains
To with the approximate trajectory of lane line, and trajectory is tracked so as to realize navigation;
The only ROI image containing identifier obtained, by the predefined identifier identified in image obtain positional information with
Acceleration change information.
The step 1 also comprises the following steps:
Step a:The camera putting position and posture of vision sensor are first determined, and camera is adjusted according to actual scene
The brightness of supporting light source;
Step b:According to the light-source brightness currently adjusted, clearly road can be collected by adjusting the parameter of vision sensor
Road image;
Step c:The continuous clearly ambient image, and the image collected is passed into image processor and carried out down of collection in real time
The image procossing of one step.
The utility model is had the following advantages and effect relative to prior art:
The utility model is responsible for gathering scene image by vision sensor, and image processor carries out Treatment Analysis to image,
The operation of instruction control machine people is sent by motion-control module again.Lane line is preset in mobile work robot environment, and
In ad-hoc location, identifier is set;Mobile robot collection institute scene image at ambient, and obtained by perspective transform and
Ground is in the image of orthographic projection;Gained image is melted into bianry image through gray processing and threshold value, then is split to obtain only containing mark
The image of symbol and the only image containing lane line;Approximate track trajectory is only being found out on the image containing lane line and is being tracked, then
Identifier is identified, position and acceleration information is obtained, realizes navigation feature.The utility model can be significantly simplified moving machine
The control of device people and tracking process, realize the precision navigation of mobile robot.
Brief description of the drawings
Fig. 1 is the air navigation aid schematic flow sheet of the Navigation System for Mobile Robot of view-based access control model.
Fig. 2 is the demarcation schematic diagram of camera perspective transform.
Fig. 3 is lane line and identifier.
Fig. 4 is the bianry image after thresholding.
Fig. 5 is the lane line ROI image schematic diagram after segmentation.
Fig. 6 is the identifier ROI image schematic diagram after segmentation.
Fig. 7 is the lane line ROI image processing region schematic diagram after segmentation.
Fig. 8 is the track approximate trajectories line obtained after image procossing.
Fig. 9 is the Navigation System for Mobile Robot structural representation of view-based access control model.
Embodiment
The utility model is more specifically described in detail with reference to specific embodiment.
As shown in Figure 1.Step S100:Scene image under default environment where gathering the mobile robot, and will obtain
The image obtained is by perspective transform, as shown in Fig. 2 making image be changed into image of the camera with ground in orthographic projection.It is described pre-
If being covered with lane line in the road under environment in advance, multiple identifiers, the mark are provided with the ad-hoc location of the lane line
Fu Jun has a circular profile higher with identifier background contrasts, as shown in Figure 3.
The track line width being layered in advance in the present embodiment on road is 3cm, and identifier circular profile exradius is 10cm,
Internal diameter is 6cm.
Above-mentioned steps S100, in addition to following sub-step:
Step S101:Camera putting position is determined with posture and the bright of the supporting light source of camera is adjusted according to actual scene
Degree.
Camera uses USB cameras in the present embodiment, and it is 30cm to put height as vertical range from the ground, and shooting angle is phase
Machine axial line and level ground are in 45° angle.
Step S102:Light-source brightness adjustment camera parameter according to currently adjusting can collect clearly mileage chart
Picture.
Step S103:The continuous clearly ambient image of collection in real time, and the image collected is passed into microprocessor and carried out
The image procossing of next step.
Processor model is ARM Cortex-a9 in the present embodiment.
Step S200:Noise reduction process is carried out to the image obtained through step S100 and is converted into gray level image, then is passed through
Thresholding carries out global binary conversion treatment, image is eventually converted into bianry image, as shown in Figure 4.
The obtained images of step S100 are smoothed using mean filter in the present embodiment, average core size is 3*
3。
Step S300:By through binary image segmentation obtained by step S200 obtain one only the ROI image comprising lane line and
One ROI image for only including identifier, as shown in Figures 5 and 6.
On step S300, in addition to following sub-step:
Step S301, to bianry image obtained by step S200, pass through the lane line side in Hough transformation algorithm detection image
Edge, then split to obtain the only ROI image containing lane line.
Step S302, to bianry image obtained by step S200, by the circle in hough-circle transform algorithm detection image, work as inspection
Measure the ROI images for when circle contour is included in bianry image, just dividing the image into only containing identifier.
Straight-line detection is carried out with accumulated probability Hough transformation in the present embodiment, sets the progress size of its linear search
Unit radius is 1, and most short straight line length is 3cm, to shorten detection time.
The a diameter of 9cm of smallest circle, the greatest circle a diameter of 11cm of hough-circle transform are set in the present embodiment, to shorten detection
Time.
Step S400:The ROI image and the only ROI image containing identifier only containing lane line obtained by identification step S300,
Navigation is tracked to lane line, and obtains the current positional information of mobile robot and acceleration information.
On step S400, also comprising following sub-step:
Step S401, to the only ROI image containing lane line obtained through step S301, specified two do not connect on image
Continuous processing region, as shown in fig. 7, all pixels of traversal particular row.Due to being bianry image, the gray scale on lane line
It is worth for 255, the gray value outside lane line is 0, easily obtains the midpoint on the lane line of particular row in two processing regions,
Connect 2 points obtain with the approximate trajectory of lane line, as shown in figure 8, and trajectory is tracked so as to realize navigation.
Step S402, it is specific in image by identifying to the only ROI image containing identifier obtained through step 302
Identifier obtains positional information and acceleration change information.
Identifier discrimination in the present embodiment is high, and lane line tracking effect is good.
As described above, it can preferably realize the utility model.
Embodiment of the present utility model is simultaneously not restricted to the described embodiments, and other are any without departing from of the present utility model
Spirit Essence with made under principle change, modification, replacement, combine, simplification, should be equivalent substitute mode, be included in
Within the scope of protection of the utility model.
Claims (4)
1. a kind of Navigation System for Mobile Robot of view-based access control model, it is characterised in that including such as lower component:
Vision sensor;
Image processor;
Motion-control module;
Mobile robot car body;
The vision sensor, image processor and motion-control module carry by mobile robot car body;By visual sensing
Device is responsible for collection scene image in real time, and image processor carries out Treatment Analysis to the image collected, then by motion-control module
The operation of instruction control machine people is sent according to analysis result.
2. the Navigation System for Mobile Robot of view-based access control model according to claim 1, it is characterised in that:The vision sensor
Using USB cameras, and it is centrally mounted at the front end of mobile robot car body.
3. the Navigation System for Mobile Robot of view-based access control model according to claim 2, it is characterised in that:The USB cameras are also
Provided with a LED light source supporting with it.
4. the Navigation System for Mobile Robot of view-based access control model according to claim 3, it is characterised in that:Described image processor
From ARM Cortex-a9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720492391.2U CN206832260U (en) | 2017-05-05 | 2017-05-05 | A kind of Navigation System for Mobile Robot of view-based access control model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201720492391.2U CN206832260U (en) | 2017-05-05 | 2017-05-05 | A kind of Navigation System for Mobile Robot of view-based access control model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN206832260U true CN206832260U (en) | 2018-01-02 |
Family
ID=60770386
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201720492391.2U Expired - Fee Related CN206832260U (en) | 2017-05-05 | 2017-05-05 | A kind of Navigation System for Mobile Robot of view-based access control model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN206832260U (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108898589A (en) * | 2018-06-19 | 2018-11-27 | 南通大学 | The quick-fried pearl intelligent detecting method of filter stick based on high speed machines vision |
CN109032125A (en) * | 2018-05-31 | 2018-12-18 | 上海工程技术大学 | A kind of air navigation aid of vision AGV |
CN110414511A (en) * | 2019-07-30 | 2019-11-05 | 深圳市普渡科技有限公司 | Cooperate sign and system |
-
2017
- 2017-05-05 CN CN201720492391.2U patent/CN206832260U/en not_active Expired - Fee Related
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109032125A (en) * | 2018-05-31 | 2018-12-18 | 上海工程技术大学 | A kind of air navigation aid of vision AGV |
CN108898589A (en) * | 2018-06-19 | 2018-11-27 | 南通大学 | The quick-fried pearl intelligent detecting method of filter stick based on high speed machines vision |
CN108898589B (en) * | 2018-06-19 | 2022-06-07 | 南通大学 | Filter rod bead explosion intelligent detection method based on high-speed machine vision |
CN110414511A (en) * | 2019-07-30 | 2019-11-05 | 深圳市普渡科技有限公司 | Cooperate sign and system |
CN110414511B (en) * | 2019-07-30 | 2022-05-03 | 深圳市普渡科技有限公司 | Cooperative sign recognition method and system for robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107421540A (en) | A kind of Mobile Robotics Navigation method and system of view-based access control model | |
CN112184818B (en) | Vision-based vehicle positioning method and parking lot management system applying same | |
CN102789234B (en) | Robot navigation method and robot navigation system based on color coding identifiers | |
CN103064417B (en) | A kind of Global localization based on many sensors guiding system and method | |
CN106774313B (en) | A kind of outdoor automatic obstacle-avoiding AGV air navigation aid based on multisensor | |
CN105700532B (en) | The Intelligent Mobile Robot navigator fix control method of view-based access control model | |
CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
CN206832260U (en) | A kind of Navigation System for Mobile Robot of view-based access control model | |
CN104023228A (en) | Self-adaptive indoor vision positioning method based on global motion estimation | |
CN108364466A (en) | A kind of statistical method of traffic flow based on unmanned plane traffic video | |
CN110108269A (en) | AGV localization method based on Fusion | |
JP2007316685A (en) | Traveling path boundary detection device and traveling path boundary detection method | |
JP4967758B2 (en) | Object movement detection method and detection apparatus | |
CN106444774B (en) | Vision navigation method of mobile robot based on indoor illumination | |
CN116901089A (en) | Multi-angle vision distance robot control method and system | |
JP6916975B2 (en) | Sign positioning system and program | |
Mutka et al. | A low cost vision based localization system using fiducial markers | |
CN110727269A (en) | Vehicle control method and related product | |
CN107436610A (en) | A kind of vehicle and robot delivery navigation methods and systems of intelligent outdoor environment | |
CN114782639A (en) | Rapid differential latent AGV dense three-dimensional reconstruction method based on multi-sensor fusion | |
CN112530270B (en) | Mapping method and device based on region allocation | |
CN108665473B (en) | Visual guidance and visual odometer multiplexing method | |
CN203077301U (en) | Real-time detection device for positions and angles of wheel type motion robot | |
Aqel et al. | Estimation of image scale variations in monocular visual odometry systems | |
JP2020076714A (en) | Position attitude estimation device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180102 Termination date: 20210505 |