CN106500714B - A kind of robot navigation method and system based on video - Google Patents
A kind of robot navigation method and system based on video Download PDFInfo
- Publication number
- CN106500714B CN106500714B CN201610839909.5A CN201610839909A CN106500714B CN 106500714 B CN106500714 B CN 106500714B CN 201610839909 A CN201610839909 A CN 201610839909A CN 106500714 B CN106500714 B CN 106500714B
- Authority
- CN
- China
- Prior art keywords
- robot
- ground location
- camera
- video image
- pixel
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3626—Details of the output of route guidance instructions
- G01C21/3647—Guidance involving output of stored or live camera images or video streams
Abstract
The present invention relates to navigation field more particularly to a kind of robot navigation methods and system based on video.The present invention is by establishing the corresponding relationship of video image pixel position and ground location;Obtain video image pixel;According to the position acquisition ground location of the pixel.It realizes by installing camera in robot, the actual scene that robot can detect is obtained in real time, obtain video image, a pixel is chosen in video image, and ground location represented by robot to the pixel is driven, so that realizing can be for the actual scene navigating robot around robot.
Description
Technical field
The present invention relates to navigation field more particularly to a kind of robot navigation methods and system based on video.
Background technique
The robot navigation of industry at present clicks some pixel on map substantially in a width navigation map
Or some position is selected, then Aspect Ratio by selected location relative to entire map is converted into reality scene to calculate
Then target position controls robot and moves again to that position.It is using the mobile disadvantage of digital map navigation control robot
Map is a static images, finishes the markers such as route, obstacle in proportion on map in advance, can not reflect actual field in real time
Variation in scape.
Summary of the invention
The technical problems to be solved by the present invention are: a kind of robot navigation method and system based on video is provided, it is real
It now can be for the actual scene navigating robot around robot.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention are as follows:
The present invention provides a kind of robot navigation method based on video, comprising:
Establish the corresponding relationship of video image pixel position and ground location;
Obtain video image pixel;
According to the position acquisition ground location of the pixel.
The above-mentioned robot navigation method based on video, the beneficial effect is that: it is different from the prior art and is led using map
Boat control robot is mobile, can not be navigated according to the variation in actual scene.The present invention is taken the photograph by installing in robot
As head, the actual scene that robot can detect is obtained in real time, video image is obtained, resettles pixel position in video image
With the corresponding relationship of ground location, a pixel can be chosen in video image, and drives robot to pixel institute table
The ground location shown, so that realizing can be for the actual scene navigating robot around robot.
The present invention also provides a kind of Algorithms of Robots Navigation System based on video, comprising:
Module is established, for establishing the corresponding relationship of video image pixel position and ground location;
First obtains module, for obtaining video image pixel;
Second obtains module, for the position acquisition ground location according to the pixel.
The above-mentioned Algorithms of Robots Navigation System based on video, the beneficial effect is that: video image is established by establishing module
The corresponding relationship of middle pixel position and ground location chooses a pixel by the first acquisition module in video image, then
Module is obtained by second and obtains ground location corresponding to the pixel chosen, so as to drive robot to the pixel
Represented ground location, realizing can be for the actual scene navigating robot around robot.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the robot navigation method based on video of the present invention;
Fig. 2 is a kind of structural block diagram of the Algorithms of Robots Navigation System based on video of the present invention;
Label declaration:
1, module is established;2, first module is obtained;3, second module is obtained;31, the first computing unit;32, it second calculates
Unit;4, third obtains module;5, computing module;6, the 4th module is obtained;7, drive module.
Specific embodiment
To explain the technical content, the achieved purpose and the effect of the present invention in detail, below in conjunction with embodiment and cooperate attached
Figure is explained.
The most critical design of the present invention is: by obtaining the scene video image around robot in real time, in scene visual
Pixel is selected in frequency image, and position of the pixel in video image is converted into ground location, drives robot
To the ground location, realizing can be for the actual scene navigating robot around robot.
As shown in Figure 1, the present invention provides a kind of robot navigation method based on video, comprising:
Establish the corresponding relationship of video image pixel position and ground location;
Obtain video image pixel;
According to the position acquisition ground location of the pixel.
Further, according to the position acquisition ground location of the pixel, specifically:
According to the position of the pixel, Vertical Square of the camera of robot relative to the ground location is calculated
To drift angle and horizontal direction drift angle;
According to the vertical direction drift angle and the horizontal direction drift angle, the ground location is calculated relative to machine
The vertical range and horizontal distance of the camera of people.
Seen from the above description, the pixel can be calculated according to the position of pixel corresponding to ground location apart from machine
The offset of the camera of device people.
Preferably, the camera of calculating robot is inclined relative to the vertical direction drift angle of the ground location and horizontal direction
The method and step at angle specifically:
Using the upper left corner of the video image of monitoring client as origin, right is X-axis positive axis, and lower section is the foundation of Y-axis positive axis
Rectangular coordinate system obtains the first coordinate system.A pixel is chosen in the video image of monitoring client as target pixel points, the picture
Coordinate of the vegetarian refreshments in the first coordinate system is (x1, y1), and the resolution ratio of monitoring client is width1*height1.Calculate the pixel
Vertical scale and horizontal proportion of the point in the video image of monitoring client, rateX1=x1/width1, rateY1=y1/
height1;
Using the upper left corner of the video image of monitoring client as origin, right is X-axis positive axis, and lower section is the foundation of Y-axis positive axis
Rectangular coordinate system obtains the second coordinate system.Obtain the resolution ratio width2*height2 of robotic end video image;Described in calculating
Coordinate (x2, y2) of the target pixel points in robotic end video image, x2=width2*rateX1, y2=height2*
rateY1;
Obtain the horizontal view angle angW and vertical angle of view angH of camera;The target pixel points are calculated correspondingly
Level angle angX and vertical drift angle angY between face position and camera, angX=(x2/width2-0.5) * angW,
AngY=(Y2/height2-0.5) * angH;
Obtain vertical height z of the camera away from ground;The corresponding ground location of the target pixel points is calculated relative to taking the photograph
As the horizontal offset x3 and vertical offset y3, y3=z/tan (angY) of corresponding ground location;X3=y3*tan
(angX).Further, further includes:
The camera of robot is obtained relative to the angle immediately ahead of robot;
Vertical range and horizontal distance and the angle according to the ground location relative to the camera of robot, meter
Calculation obtains vertical range and horizontal distance of the ground location relative to robot.
Seen from the above description, the ground can be calculated relative to the offset of the camera of robot according to ground location
Offset of the position relative to robot.The camera of robot may be mounted at arbitrary orientation, when robot camera not
When being mounted in the front of robot, need by ground location relative to the offset of robot camera be converted to relative to
Offset immediately ahead of robot correctly could drive robot to the ground location according to offset.
Preferably, vertical range and horizontal distance of the ground location relative to robot are calculated specifically:
With the artificial origin of machine, front is Y-axis positive axis, and right is X-axis positive axis, and top is the foundation of Z axis positive axis
Coordinate system obtains third coordinate system.Obtain coordinate (x4, y4, z4) of the camera of robot in third coordinate system, camera
Relative to the angle angC immediately ahead of robot, the corresponding ground location of the target pixel points relative to camera correspondingly
The horizontal offset x3 and vertical offset y3 of face position, be calculated the corresponding ground location of the target pixel points relative to
The horizontal offset x5 and vertical offset y5, x5=x3*cos (- angC)-y3*sin (- angC)+x4 of robot;Y5=x3*
sin(-angC)+y3*cos(-angC)+y4。
Further, further includes:
The picture for obtaining the camera shooting of robot in real time, obtains the video image.
Seen from the above description, the actual scene obtained around robot in real time is realized.
Further, further includes:
Drive robot to the ground location.
Seen from the above description, realize that driving robot to the pixel chosen in video image corresponds to actual scene
In ground location.
As shown in Fig. 2, the present invention also provides a kind of Algorithms of Robots Navigation System based on video, comprising:
Module 1 is established, for establishing the corresponding relationship of video image pixel position and ground location;
First obtains module 2, for obtaining video image pixel;
Second obtains module 3, for the position acquisition ground location according to the pixel.
Further, the second acquisition module 3 includes:
First computing unit 31, for the position according to the pixel, be calculated the camera of robot relative to
The vertical direction drift angle and horizontal direction drift angle of the ground location;
Second computing unit 32, for institute to be calculated according to the vertical direction drift angle and the horizontal direction drift angle
State vertical range and horizontal distance of the ground location relative to the camera of robot.
Further, further includes:
Third obtains module 4, for obtaining the camera of robot relative to the angle immediately ahead of robot;
Computing module 5, for according to the ground location relative to the camera of robot vertical range and it is horizontal away from
From with the angle, vertical range and horizontal distance of the ground location relative to robot is calculated.
Further, further includes:
4th obtains module 6, and the picture that the camera for obtaining robot in real time is shot obtains the video image.
Further, further includes:
Drive module 7, for driving robot to the ground location.
The embodiment of the present invention one are as follows:
The picture for obtaining the camera shooting of robot in real time, obtains video image;
Establish the corresponding relationship of video image pixel position and ground location;
Obtain video image pixel;
According to the position of the pixel, Vertical Square of the camera of robot relative to the ground location is calculated
To drift angle and horizontal direction drift angle;
According to the vertical direction drift angle and the horizontal direction drift angle, the ground location is calculated relative to machine
The vertical range and horizontal distance of the camera of people;
Drive robot to the ground location.
Seen from the above description, the present embodiment realizes the video image that can obtain the actual scene around robot in real time,
And the pixel navigating robot in selecting video image can be passed through.
The embodiment of the present invention two are as follows:
On the basis of example 1, further includes:
The camera of robot is obtained relative to the angle immediately ahead of robot;
Vertical range and horizontal distance and the angle according to the ground location relative to the camera of robot, meter
Calculation obtains vertical range and horizontal distance of the ground location relative to robot.
Seen from the above description, the camera for obtaining actual scene video image around robot in the present embodiment can pacify
Arbitrary orientation loaded on robot, by the way that ground location is converted to ground location phase relative to the offset of robot camera
For the offset of robot, robot can be driven to the ground location.
The embodiment of the present invention three are as follows:
The pixel resolution of the video image of robot camera is 1280*720, the resolution ratio of video image on monitoring client
For 1440*810.Monitoring client obtains video image from robotic end in real time, and carries out distortion correction to the video image got.
Using the upper left corner of video image as origin, right is X-axis positive axis, and lower section is that Y-axis positive axis establishes rectangular co-ordinate
System.Target pixel points of the pixel (800,710) as navigating robot are chosen in the video image of monitoring client.
Vertical scale of the target pixel points in the video image of monitoring client: 710/810=0.8765;Horizontal proportion:
800/1440=0.5556;Pixel coordinate of the target pixel points in the video image of robot camera is (711,631),
Calculating process is 1280*0.5556=711,720*0.8765=631;According to 28.64 degree of the vertical angle of view of camera, horizontal view
The pixel coordinate of 61.18 degree of angle, camera 1 meter of height and target pixel points away from ground in the video image of camera calculates
Ground location corresponding to target pixel points out, i.e. target floor position relative to camera vertical drift angle be 10.78 degree with
Level angle is 3.39 degree.Using camera as origin, the front of camera is X-axis positive axis, and the front-right of camera is Y-axis
Positive axis establishes rectangular coordinate system, calculates mesh relative to the vertical drift angle of camera and level angle according to target floor position
It is 0.31 that ground location, which is marked, relative to the horizontal offset of camera, vertical offset 5.25.It is origin, machine with robot
The front of device people is Y-axis positive axis, and the front-right of robot is that X-axis positive axis establishes rectangular coordinate system.By target floor position
It sets and is converted to target floor position relative to the horizontal inclined of robot relative to the horizontal offset and vertical offset of camera
Shifting amount and vertical offset.According to the corresponding relationship of video image and ground location, target can be calculated according to the offset
Real standard distance and practical vertical range of the ground location relative to camera.According to target floor positional distance robot
Real standard distance and practical vertical range drive robot to target position.
The embodiment of the present invention four are as follows:
4th acquisition module obtains the picture of the camera shooting of robot in real time, obtains the video image;
Establish the corresponding relationship that module establishes video image pixel position and ground location;
First, which obtains module, obtains video image pixel;
Robot is calculated for the position according to the pixel in the first computing unit in second acquisition module
Vertical direction drift angle and horizontal direction drift angle of the camera relative to the ground location;Second computing unit is used for basis
Camera of the ground location relative to robot is calculated in the vertical direction drift angle and the horizontal direction drift angle
Vertical range and horizontal distance;
Third obtains module, for obtaining the camera of robot relative to the angle immediately ahead of robot;
Computing module, for the vertical range and horizontal distance according to the ground location relative to the camera of robot
With the angle, vertical range and horizontal distance of the ground location relative to robot is calculated;
Drive module drives robot to the ground location.
Seen from the above description, the present embodiment provides a kind of Algorithms of Robots Navigation System based on video, the system comprises
4th acquisition module establishes module, the first acquisition module, the second acquisition module, third acquisition module, computing module and driving mould
Block.Wherein, the second acquisition module includes the first computing unit and the second computing unit.Real-time acquisition can be realized by above system
The video image of actual scene around robot, and the pixel navigating robot in selecting video image can be passed through.
In conclusion a kind of robot navigation method based on video provided by the invention, by being installed in robot
Camera obtains the actual scene that robot can detect in real time, obtains video image, resettle pixel point in video image
The corresponding relationship with ground location is set, a pixel can be chosen in video image, and drives robot to the pixel institute
The ground location of expression, so that realizing can be for the actual scene navigating robot around robot;It further, can be according to picture
The position of vegetarian refreshments calculates the offset of camera of the ground location corresponding to the pixel apart from robot;Further,
Offset of the ground location relative to robot can be calculated relative to the offset of the camera of robot according to ground location
Amount;Further, the actual scene obtained around robot in real time is realized;Further, realize driving robot in video
The pixel chosen in image corresponds to the ground location in actual scene.The present invention also provides a kind of robots based on video
Navigation system the system comprises the 4th acquisition module, establishes module, the first acquisition module, the second acquisition module, third acquisition
Module, computing module and drive module;Wherein, the second acquisition module includes the first computing unit and the second computing unit;Pass through
Above system can realize the video image for obtaining the actual scene around robot in real time, and can be by selecting video image
Pixel navigating robot.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalents made by bright specification and accompanying drawing content are applied directly or indirectly in relevant technical field, similarly include
In scope of patent protection of the invention.
Claims (6)
1. a kind of robot navigation method based on video characterized by comprising
Establish the corresponding relationship of video image pixel position and ground location;
Obtain video image pixel;
According to the position acquisition ground location of the pixel;Wherein, according to the position acquisition ground location of the pixel, tool
Body are as follows:
According to the resolution ratio of coordinate of the pixel in video image, video image, in conjunction with camera horizontal view angle and
Vertical angle of view, the camera that robot is calculated are inclined relative to the vertical direction drift angle of the ground location and horizontal direction
Angle;
Vertical height according to camera away from ground, the vertical direction drift angle and the horizontal direction drift angle, are calculated institute
State vertical range and horizontal distance of the ground location relative to the camera of robot;
Further include:
The camera of robot is obtained relative to the angle immediately ahead of robot;
Vertical range and horizontal distance and the angle according to the ground location relative to the camera of robot, calculate
Vertical range and horizontal distance to the ground location relative to robot.
2. a kind of robot navigation method based on video according to claim 1, which is characterized in that further include:
The picture for obtaining the camera shooting of robot in real time, obtains the video image.
3. a kind of robot navigation method based on video according to claim 1, which is characterized in that further include:
Drive robot to the ground location.
4. a kind of Algorithms of Robots Navigation System based on video characterized by comprising
Module is established, for establishing the corresponding relationship of video image pixel position and ground location;
First obtains module, for obtaining video image pixel;
Second obtains module, for the position acquisition ground location according to the pixel;Wherein, described second module packet is obtained
It includes:
First computing unit, for the resolution ratio according to coordinate of the pixel in video image, video image, in conjunction with taking the photograph
As the horizontal view angle and vertical angle of view of head, the camera that robot is calculated is inclined relative to the vertical direction of the ground location
Angle and horizontal direction drift angle;
Second computing unit, for the vertical height according to the camera away from ground, vertical direction drift angle and the level side
To drift angle, vertical range and horizontal distance of the ground location relative to the camera of robot is calculated;
Further include:
Third obtains module, for obtaining the camera of robot relative to the angle immediately ahead of robot;
Computing module, for according to the ground location relative to the camera of robot vertical range and horizontal distance and institute
Angle is stated, vertical range and horizontal distance of the ground location relative to robot is calculated.
5. a kind of Algorithms of Robots Navigation System based on video according to claim 4, which is characterized in that further include:
4th obtains module, and the picture that the camera for obtaining robot in real time is shot obtains the video image.
6. a kind of Algorithms of Robots Navigation System based on video according to claim 4, which is characterized in that further include:
Drive module, for driving robot to the ground location.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610839909.5A CN106500714B (en) | 2016-09-22 | 2016-09-22 | A kind of robot navigation method and system based on video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610839909.5A CN106500714B (en) | 2016-09-22 | 2016-09-22 | A kind of robot navigation method and system based on video |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106500714A CN106500714A (en) | 2017-03-15 |
CN106500714B true CN106500714B (en) | 2019-11-29 |
Family
ID=58290950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610839909.5A Active CN106500714B (en) | 2016-09-22 | 2016-09-22 | A kind of robot navigation method and system based on video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106500714B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110733424B (en) * | 2019-10-18 | 2022-03-15 | 深圳市麦道微电子技术有限公司 | Method for calculating horizontal distance between ground position and vehicle body in driving video system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102156481A (en) * | 2011-01-24 | 2011-08-17 | 广州嘉崎智能科技有限公司 | Intelligent tracking control method and system for unmanned aircraft |
CN103459099A (en) * | 2011-01-28 | 2013-12-18 | 英塔茨科技公司 | Interfacing with mobile telepresence robot |
CN104034316A (en) * | 2013-03-06 | 2014-09-10 | 深圳先进技术研究院 | Video analysis-based space positioning method |
CN105171756A (en) * | 2015-07-20 | 2015-12-23 | 缪学良 | Method for controlling remote robot through combination of videos and two-dimensional coordinate system |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4055603B2 (en) * | 2003-02-21 | 2008-03-05 | 日本ビクター株式会社 | Image position detection method and image position detection apparatus |
CN102999051B (en) * | 2011-09-19 | 2016-06-22 | 广州盈可视电子科技有限公司 | A kind of method of cradle head control and device |
CN102682292B (en) * | 2012-05-10 | 2014-01-29 | 清华大学 | Method based on monocular vision for detecting and roughly positioning edge of road |
CN104034305B (en) * | 2014-06-10 | 2016-05-11 | 杭州电子科技大学 | A kind of monocular vision is the method for location in real time |
CN104200469B (en) * | 2014-08-29 | 2017-02-08 | 暨南大学韶关研究院 | Data fusion method for vision intelligent numerical-control system |
CN104835173B (en) * | 2015-05-21 | 2018-04-24 | 东南大学 | A kind of localization method based on machine vision |
CN104954747B (en) * | 2015-06-17 | 2020-07-07 | 浙江大华技术股份有限公司 | Video monitoring method and device |
-
2016
- 2016-09-22 CN CN201610839909.5A patent/CN106500714B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102156481A (en) * | 2011-01-24 | 2011-08-17 | 广州嘉崎智能科技有限公司 | Intelligent tracking control method and system for unmanned aircraft |
CN103459099A (en) * | 2011-01-28 | 2013-12-18 | 英塔茨科技公司 | Interfacing with mobile telepresence robot |
CN104034316A (en) * | 2013-03-06 | 2014-09-10 | 深圳先进技术研究院 | Video analysis-based space positioning method |
CN105171756A (en) * | 2015-07-20 | 2015-12-23 | 缪学良 | Method for controlling remote robot through combination of videos and two-dimensional coordinate system |
Also Published As
Publication number | Publication date |
---|---|
CN106500714A (en) | 2017-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101590530B1 (en) | Automatic scene calibration | |
CN104848858B (en) | Quick Response Code and be used for robotic vision-inertia combined navigation system and method | |
US9043146B2 (en) | Systems and methods for tracking location of movable target object | |
US9679385B2 (en) | Three-dimensional measurement apparatus and robot system | |
WO2015089403A1 (en) | Estimating three-dimensional position and orientation of articulated machine using one or more image-capturing devices and one or more markers | |
EP1262909A3 (en) | Calculating camera offsets to facilitate object position determination using triangulation | |
CN104976950B (en) | Object space information measuring device and method and image capturing path calculating method | |
CN104552341A (en) | Single-point multi-view meter-hanging posture error detecting method of mobile industrial robot | |
WO2020156923A3 (en) | Map and method for creating a map | |
EP3847617A1 (en) | Vision system for a robotic machine | |
JP2010112731A (en) | Joining method of coordinate of robot | |
CN106500714B (en) | A kind of robot navigation method and system based on video | |
Muffert et al. | The estimation of spatial positions by using an omnidirectional camera system | |
KR101706092B1 (en) | Method and apparatus for 3d object tracking | |
CN107442973A (en) | Welding bead localization method and device based on machine vision | |
KR101153221B1 (en) | Computation of Robot Location and Orientation using Repeating Feature of Ceiling Textures and Optical Flow Vectors | |
KR101438514B1 (en) | Robot localization detecting system using a multi-view image and method thereof | |
JP2007171018A (en) | Object position recognition method and device | |
JP6598552B2 (en) | Position measurement system | |
US20150172606A1 (en) | Monitoring camera apparatus with depth information determination | |
Sauer et al. | Occlusion handling in augmented reality user interfaces for robotic systems | |
CN110672009B (en) | Reference positioning, object posture adjustment and graphic display method based on machine vision | |
Aliakbarpour et al. | Inertial-visual fusion for camera network calibration | |
KR101380123B1 (en) | Location recognizing apparatus for smart robot | |
Safin et al. | Experiments on mobile robot stereo vision system calibration under hardware imperfection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |