CN110411452A - A kind of farmland spray machine device people's navigation path identification method based on binocular vision - Google Patents
A kind of farmland spray machine device people's navigation path identification method based on binocular vision Download PDFInfo
- Publication number
- CN110411452A CN110411452A CN201910741782.7A CN201910741782A CN110411452A CN 110411452 A CN110411452 A CN 110411452A CN 201910741782 A CN201910741782 A CN 201910741782A CN 110411452 A CN110411452 A CN 110411452A
- Authority
- CN
- China
- Prior art keywords
- point
- navigation
- navigation path
- image
- binocular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
-
- 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
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention discloses a kind of farmland spray machine device people's navigation path identification method based on binocular vision, it solves guidance path frequently to turn the equilibrium problem of sensitivity and stability in scene, it realizes and not only meets navigation requirement of real-time, but also the smooth guidance path of energy stablizes the effect of operation.The present invention acquires farmland image using binocular camera, image is handled come the method for obtaining navigation path data by a kind of navigation route information based in left and right image, and the spray practical navigation path data of robot is obtained, finally by the identification of improved horizontal sweep method and smooth guidance path.
Description
Technical field
The invention belongs to intelligent mobile robot vision navigation system field, more particularly, to a kind of for farmland operation
The navigation path identification method of spray robot.
Background technique
With mechanization of agriculture, informationization and intelligent development, more and more intelligence Agricultural Machinery Equipment tools come into being,
Its investment that can greatly reduce manual labor reduces cost, improves agricultural operation efficiency.Intelligent mobile spray robot tool
There is the features such as efficiently precisely spraying insecticide, save the activity duration and reduce pesticide waste pollution.Guidance path is not agricultural spraying
The basis of medicine robot manipulating task and premise, especially under complicated farmland operation environment, the identification of spray robot guidance path was both
Need to meet implementation quickly needs smooth guidance path to be easy to robot autonomous mobile control process again.
Currently, existing spray robot navigation path identification method tends not to accomplish that guidance path is smooth, to lead
It causes robot control especially difficult, needs extremely frequently to adjust itself walking path and homeostasis during robot manipulating task
Property is not high.The present invention exactly in this context, discloses a kind of farmland spray machine device people's guidance path knowledge based on binocular vision
Other method, so that the advantages that having both high sensitivity and stability during farmland spray machine device people intelligent mobile, has real-time
Quickly, be easy to robot navigation's control and precisely it is accurate the features such as.
Summary of the invention
The purpose of the present invention is to provide a kind of precisely real-time, easily controllable and can frequently turn field in guidance path
Farmland spray machine device people's guidance path identification side based on binocular vision of balance spray robot sensitivity and stability in scape
Method guarantees quick and precisely calculate the guidance path for obtaining robot in complicated farmland operation environment and has both height
Stability；Acquire navigation picture in real time using binocular camera and by a kind of navigation route information based in left and right image
It obtains the method for practical navigation path data and obtains current navigation path data to handle image；It is swept by a kind of improved level
It retouches method to handle navigation path data, identification and smooth guidance path.The present invention have fast accurate, real-time response and
It is easy to not only have many advantages, such as high flexibility in the mobile control of robot and robot moving process but also there is high stability.
To achieve the above object, technical solution of the present invention is as follows: a kind of farmland spray machine device people based on binocular vision leads
Bit path recognition methods, which is characterized in that the binocular vision navigation path identification method includes binocular camera calibration side
Method, navigation path data acquisition methods and guidance path identification and smoothing method.
The binocular camera scaling method is to demarcate binocular camera parameter to by measurement binocular camera
Overlapping region and depth information acquire image；
The navigation path data acquisition methods, i.e., a kind of navigation route information based in left and right image, acquisition are actually led
The method of bit path data；
The guidance path identification and smoothing method, i.e., a kind of improved horizontal sweep method.
Further, the calibration binocular camera parameter, i.e. binocular camera use honest disposing way, make the two
Optical axis it is parallel and set two optical center point lines as baseline, set on the left of camera as benchmark camera, and set
The optical axis of left side camera and the intersection point of baseline are the origin of three-dimensional space,Axis is parallel with baseline,Axis is taken the photograph for left side
As the optical axis of head；
Further, a kind of navigation route information based in left and right image obtains the side of practical navigation path data
Method handles the left and right image of binocular camera acquisition, and identifies corresponding guidance path number in left and right image
According to；
Further, a kind of improved horizontal sweep method utilizes a left side (right side) side of lastrow in crop row image at same frame
Edge point limits the scanning range an of left side (right side) marginal point of next line, then is fitted to obtain using Bezier smooth
Guidance path.
Detailed description of the invention
Fig. 1 is a kind of frame of farmland spray machine device people's navigation path identification method based on binocular vision of the embodiment of the present invention
Frame schematic diagram.
Fig. 2 is a kind of the double of farmland spray machine device people's navigation path identification method based on binocular vision of the embodiment of the present invention
The overlapping region schematic diagram of mesh camera shooting head erect disposing way binocular vision.
Fig. 3 is a kind of the double of farmland spray machine device people's navigation path identification method based on binocular vision of the embodiment of the present invention
Visually feel that navigation path data obtains schematic diagram.
Fig. 4 is a kind of farmland spray machine device people's navigation path identification method based on binocular vision of the embodiment of the present invention
Guidance path identifies schematic diagram.
Fig. 5 is a kind of farmland spray machine device people's navigation path identification method based on binocular vision of the embodiment of the present invention
Nominal data schematic diagram.
Specific embodiment
Present embodiment is illustrated in conjunction with Fig. 1, Fig. 2, Fig. 3, Fig. 4, Fig. 5.A kind of farmland based on binocular vision
Spray robot navigation path identification method mainly include binocular camera scaling method, navigation path data acquisition methods and
Guidance path identification and smoothing method.
Binocular camera scaling method is as follows: two video cameras use honest disposing way, and the optical axis for setting them is parallel
And two optical center point line be baseline.Set cardinal distance asb, focal length bef, three-dimensional space arbitrary pointIt is flat in left picture
Face is projected as, right as being projected as in plane.With left cameraC L On the basis of, ifC L Optical axis with
The intersection point of baseline is the origin of three-dimensional space,Axis is parallel with baseline,Axis isC L Optical axis.Using honest disposing way
The region that shoots jointly of two cameras, then can determine the overlapping region of binocular vision, two of them cameraC L WithC R Axle center
Apartb,I L WithI R RespectivelyC L WithC R The corresponding plane of delineation,WithRespectivelyI L WithI R Center.It takes the photograph
As the overlapping region of head erect disposing way binocular vision is required effective image-region.Specific nominal data such as Fig. 5 institute
Show.
Navigation path data acquisition methods, i.e., a kind of navigation route information based in left and right image obtain practical navigation
The method of path data, as shown in Figure 3.Specific step is as follows:
(1) to the left and right image of location navigation to handling, and corresponding guidance path in left and right image is identified；
(2) intersection point of guidance path in the 1st horizontal scanning line and left and right image is takenLeft picture point,Right picture point, seek with it is left and right
The corresponding spatial point of picture pointSpace coordinate.Calculation is as follows:
(3) intersection point of guidance path in the 5th horizontal scanning line and left and right image is takenLeft picture point,Right picture point, as above seek with
The corresponding spatial point of left and right picture pointSpace coordinate.And so on, until finding out a littleSpace coordinate；
(4) left as, as plane, being determined on the basis of plane using left video camera as benchmark video cameraRelative to left camera shooting
The data information of machine；
(5) willMeasured data relative to left video camera projects in left image, can be according in left image
Routing information navigates.
Guidance path identification and smoothing method, i.e., a kind of improved horizontal sweep method, as shown in Figure 4.Specific step is as follows:
(1) it is scanned since the last line of image, detects the left and right edge point position of crop areaWith.If left and right
Marginal point exists, and into (2), otherwise continues to test next line crop area, the position until detecting left and right marginal point, note
ForWith；
(2) position of the left and right marginal point of the first row is being determinedWithAfterwards, empirically it is worth determining one as unit of pixel
Suitable width value；
(3) when determining the left and right edge point position of the second row, without scanning full line, but in the second rowIn the range of scan, so that it is determined that the left and right edges point position of the second rowWith.And so on,
In the i-th rowIn the range of scan, so that it is determined that the left and right edges point of i+1 row, to the last one
Row；
(4) it is fitted using Bezier, entire window is divided into 4 parts, chosen two points of the first row and last line and make
It is fitted for the point at the row of start-stop point, 1/3 and 2/3 as control point, smooth guidance path can be obtained.
The above embodiments are only used to illustrate the present invention, and not limitation of the present invention, in relation to the common of technical field
Technical staff can also make a variety of changes and modification without departing from the spirit and scope of the present invention, therefore all
Equivalent technical solution also belongs to scope of the invention, and scope of patent protection of the invention should be defined by the claims.
Claims (5)
1. a kind of farmland spray machine device people's navigation path identification method based on binocular vision, which is characterized in that taken the photograph including binocular
As head scaling method, navigation path data acquisition methods and guidance path identification and smoothing method, binocular camera calibration side
Method is used to demarcate binocular camera parameter to acquire image by the overlapping region for measuring binocular camera and depth information；
Navigation path data acquisition methods are a kind of navigation route information based in left and right image, obtain practical guidance path number
According to method；Navigation path identification method, i.e., a kind of improved horizontal sweep method.
2. a kind of farmland spray machine device people's navigation path identification method based on binocular vision according to claim 1,
Be characterized in that, the binocular camera scaling method is as follows: two video cameras set their light using honest disposing way
Axis is parallel and two optical centers point line is baseline；If cardinal distance isb, focal length bef, three-dimensional space arbitrary pointIn
It is left to be projected as plane, right as being projected as in plane；With left cameraC L On the basis of, ifC L The intersection point of optical axis and baseline is the origin of three-dimensional space,Axis is parallel with baseline,Axis isC L Optical axis；Using just
The region that two cameras of straight disposing way are shot jointly then can determine the overlapping region of binocular vision, two of them camera shooting
HeadC L WithC R Axle center is apartb,I L WithI R RespectivelyC L WithC R The corresponding plane of delineation,WithRespectivelyI L WithI R Center.
3. a kind of farmland spray machine device people's navigation path identification method based on binocular vision according to claim 1,
It is characterized in that, a kind of navigation route information based in left and right image, the method for obtaining practical navigation path data,
It is characterized in that, algorithm steps are as follows:
(1) to the left and right image of location navigation to handling, and corresponding guidance path in left and right image is identified；
(2) intersection point of guidance path in the 1st horizontal scanning line and left and right image is takenLeft picture point,Right picture point, seek with it is left and right
The corresponding spatial point of picture pointSpace coordinate,
Calculation is as follows:
(3) intersection point of guidance path in the 5th horizontal scanning line and left and right image is takenLeft picture point,Right picture point, as above seek with
The corresponding spatial point of left and right picture pointSpace coordinate,
And so on, until finding out a littleSpace coordinate；
(4) left as, as plane, being determined on the basis of plane using left video camera as benchmark video cameraRelative to left camera shooting
The data information of machine；
(5) willMeasured data relative to left video camera projects in left image, can be according to the road in left image
Diameter information is navigated.
4. a kind of farmland spray machine device people's navigation path identification method based on binocular vision according to claim 1,
It is characterized in that, a kind of improved horizontal sweep method, which is characterized in that algorithm steps are as follows:
(1) it is scanned since the last line of image, detects the left and right edge point position of crop areaWith；
If left and right edges point exists, into (2), next line crop area is otherwise continued to test, until detecting left and right edge
The position of point, is denoted asWith；
(2) position of the left and right marginal point of the first row is being determinedWithAfterwards, empirically it is worth determining one as unit of pixel
Suitable width value；
(3) when determining the left and right edge point position of the second row, full line is not scanned, but in the second rowIn the range of scan, so that it is determined that the left and right edges point position of the second rowWith,
And so on,CapableIn the range of scan, so that it is determined thatCapable left and right edges
Point, to the last a line.
5. a kind of farmland spray machine device people's navigation path identification method based on binocular vision according to claim 1,
It is characterized in that, the smoothing method, which is characterized in that entire window is divided into 4 parts, chooses the first row and last line two
Point is fitted as control point using Bezier as the point at the row of start-stop point, 1/3 and 2/3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910741782.7A CN110411452A (en) | 2019-08-12 | 2019-08-12 | A kind of farmland spray machine device people's navigation path identification method based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910741782.7A CN110411452A (en) | 2019-08-12 | 2019-08-12 | A kind of farmland spray machine device people's navigation path identification method based on binocular vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110411452A true CN110411452A (en) | 2019-11-05 |
Family
ID=68367026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910741782.7A Pending CN110411452A (en) | 2019-08-12 | 2019-08-12 | A kind of farmland spray machine device people's navigation path identification method based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110411452A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413313A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Binocular vision navigation system and method based on power robot |
| CN104186451A (en) * | 2014-08-19 | 2014-12-10 | 西北农林科技大学 | Insect-killing weeding pesticide spraying robot based on machine vision |
| CN109885063A (en) * | 2019-03-15 | 2019-06-14 | 江苏大学 | A kind of application robot farmland paths planning method merging vision and laser sensor |
-
2019
- 2019-08-12 CN CN201910741782.7A patent/CN110411452A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103413313A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Binocular vision navigation system and method based on power robot |
| CN104186451A (en) * | 2014-08-19 | 2014-12-10 | 西北农林科技大学 | Insect-killing weeding pesticide spraying robot based on machine vision |
| CN109885063A (en) * | 2019-03-15 | 2019-06-14 | 江苏大学 | A kind of application robot farmland paths planning method merging vision and laser sensor |
Non-Patent Citations (1)
| Title |
|---|
| 唐晶磊: "喷药机器人杂草识别与导航参数获取方法研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11320834B2 (en) | Methods and systems for mapping, localization, navigation and control and mobile robot | |
| CN110377015B (en) | Robot positioning method and robot positioning device | |
| CN106969730B (en) | A kind of top fruit sprayer volume measuring method based on unmanned plane Detection Techniques | |
| US20200173777A1 (en) | Real time position and orientation tracker | |
| CN108881825A (en) | Rice weed monitoring unmanned system and its monitoring method based on Jetson TK1 | |
| CN108226938A (en) | A kind of alignment system and method for AGV trolleies | |
| WO2019136714A1 (en) | 3d laser-based map building method and system | |
| CN105785989B (en) | Utilize the system and correlation technique of Robot calibration distributed network video camera in traveling | |
| CN105700525B (en) | Method is built based on Kinect sensor depth map robot working environment uncertainty map | |
| CN102927908A (en) | Robot eye-on-hand system structured light plane parameter calibration device and method | |
| WO2015180021A1 (en) | Pruning robot system | |
| CN109032174B (en) | Unmanned aerial vehicle operation route planning method and operation execution method | |
| CN106291278A (en) | A kind of partial discharge of switchgear automatic testing method based on many visual systemes | |
| CN103891697A (en) | Drug spraying robot capable of moving indoors autonomously and variable drug spraying method thereof | |
| WO2020220522A1 (en) | Intelligent visual sampling method, system and device | |
| CN105389543A (en) | Mobile robot obstacle avoidance device based on all-dimensional binocular vision depth information fusion | |
| CN106650701A (en) | Binocular vision-based method and apparatus for detecting barrier in indoor shadow environment | |
| CN110433467B (en) | Operation method and device of table tennis ball picking robot based on binocular vision and ant colony algorithm | |
| CN106370160A (en) | Robot indoor positioning system and method | |
| Momeni-k et al. | Height estimation from a single camera view | |
| CN106352871A (en) | Indoor visual positioning system and method based on artificial ceiling beacon | |
| CN113276106A (en) | Climbing robot space positioning method and space positioning system | |
| CN111612823A (en) | Robot autonomous tracking method based on vision | |
| CN108952742A (en) | A kind of shield machine guidance method and system based on machine vision | |
| CN111780715A (en) | Visual ranging 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191105 |
|
| WD01 | Invention patent application deemed withdrawn after publication |