CN104615150B - A kind of adaptive accurate spraying apparatus and method based on machine vision - Google Patents
A kind of adaptive accurate spraying apparatus and method based on machine vision Download PDFInfo
- Publication number
- CN104615150B CN104615150B CN201410783866.4A CN201410783866A CN104615150B CN 104615150 B CN104615150 B CN 104615150B CN 201410783866 A CN201410783866 A CN 201410783866A CN 104615150 B CN104615150 B CN 104615150B
- Authority
- CN
- China
- Prior art keywords
- module
- spraying
- camera
- task
- spray
- 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
- Catching Or Destruction (AREA)
- Guiding Agricultural Machines (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention relates to a kind of adaptive precise positioning spraying apparatus based on machine vision and method, including mechanical arm, housing, core calculation module, image capture module, spray module, housing is fixed on the robotic arm, core calculation module is fixed in housing, image capture module includes being arranged on main camera, auxiliary camera and the light compensating lamp being connected on housing and with core calculation module, spray module, which includes installing on explosive box, jet pipe and shower nozzle on the robotic arm, jet pipe, is provided with the magnetic valve being connected with core calculation module.The present invention utilizes machine vision technique, obtain spraying task object distributed intelligence in real time in farm machinery running, mechanical motion track in real time is estimated by monocular cam trajectory reconstruction technology combination Kalman filtering algorithm, the correct spraying opportunity of shower nozzle is extrapolated according to Work machine motion track information, realize accurately variable rate spray, the service efficiency of medicament is improved, the pollution of environment is alleviated.
Description
Technical field
The invention belongs to agricultural machinery automatic field, it is related to a kind of auto spraying device and method based on machine vision, especially
It is related to a kind of adaptive precise positioning spraying apparatus based on machine vision and method.
Background technology
Traditional agrosprayer tool is applied to fairly large plantation, with economical, efficient, time saving, significantly reduces work
Many advantages, such as intensity and cost, but it is difficult in operation process growth according to crop and distribution situation is precisely sprayed,
So as to cause a large amount of wastes of agricultural chemicals or fertilizer, cause production cost high and pollution remains the kind brought to agricultural product and environment
The problem of kind.With the development of machine vision technique and agricultural mechanical technology, position is grown to field crops by machine vision technique
Put and carry out acquisition of information and analysis in real time with stand density, and realize that spraying control is agricultural machinery automatic field by targetting variable
One trend of technology development.The precise positioning and real-time variable spraying for realizing spray target are based on the automatic of machine vision
One technological difficulties of spraying apparatus and method, protrusion is embodied in the real-time accurate velocity estimation of spraying mechanical.It is existing
Method is broadly divided into three classes:The first kind be in the case of using farm machinery at a slow speed average speed as the ginseng in whole spraying operation
Speed is examined, the selection on spraying opportunity is controlled with this;Equations of The Second Kind is positioned using GPS, the sprayer unit in acquisition task
Relatively real-time shift position;3rd class is tested the speed using special velocity sensor.
First kind scheme is realized simply, but target location error is larger in actual motion, in the actual popularization of farm work
In often cause spray medicament a large amount of wastes.The off-line analysis side that Equations of The Second Kind method, such as patent ZL02246301.1 are provided
Method, first gathers and prescription map is made after weeds in field position and density information, off-line analysis;, will during specific agricultural machinery spray operations
Offline analysis information and position are sent to spraying apparatus controller.Although the method by solving wanting for variable rate spray offline
Ask, but by being limited by GPS homework precisions, be adapted only to the variable rate spray operation of the larger granularity of big section, it is difficult to real-time and precise
More accurately target spraying is realized to crop in section.3rd class method, such as patent ZL02829239.1 devise a kind of rail
The herbicidal methods of road vehicle, real-time tachometric survey is carried out by velocity sensor, is reduced with the use of rail vehicle in operation
Mechanical shaking and posture changing, with the measurement accuracy for the sensor that gathers way, make spraying opportunity control it is more accurate.But it is this
Method is needed to set up trapped orbit first, and equipment cost is of a relatively high, and velocity sensor is produced in the prolonged course of work
Raw accumulated error influence is difficult to eliminate, and considerable influence can be still produced to the order of accuarcy of spraying operation.
The content of the invention
There is provided a kind of adaptive precise positioning based on machine vision for the deficiencies in the prior art by the present invention
Spraying apparatus and method.
The present invention is achieved by the following technical solutions:
A kind of adaptive precise positioning spraying apparatus based on machine vision, including mechanical arm, housing, core calculations mould
Block, image capture module, spray module;The housing is fixed on the robotic arm;The core calculation module is fixed in housing;
Described image acquisition module includes being arranged on main camera, auxiliary camera and the light filling being connected on housing and with core calculation module
Lamp;The spray module includes installing to be provided with and core calculations mould on explosive box, jet pipe and shower nozzle on the robotic arm, jet pipe
The connected magnetic valve of block.
The core calculation module include the automatic calibration module of distance parameter, module of target detection, velocity measuring module, when
Prolong estimation module and spraying task execution module.
The main camera frame number is 60 frames/second.
The auxiliary camera frame number is 30 frames/second.
A kind of adaptive precise positioning spray method based on machine vision, comprises the following steps:
Step S1:Frame of video is extracted by main camera and auxiliary camera respectively, picture target area entered after normalization
Row feature extraction, characteristic matching, the camera position obtained from parallax in units of pixel are poor, estimate spraying it is actual away from
From;
Step S2:Object detection area in the frame of video that main camera is captured carries out gridding, extracts successively and fast
Speed statistics available point, subject fusion is carried out to grid cell according to available point number, and analysis judges the particular location of spray target
And area, encapsulate and form spraying task;
Step S3:Two adjacent frame of video are obtained from main camera, are carried respectively from the object detection area in image
Characteristic point is taken, characteristic matching and purification is carried out using characteristic point, extrapolates the spatial alternation distance of camera, further calculate
Average translational speed of the camera within a frame of video interval time, is updated with this velocity information and corrects Kalman filtering
Device, utilizes the average translational speed that a camera is estimated every 20 frames of Kalman filter;
Step S4:The camera that the spraying task queue and velocity measuring module obtained according to module of target detection is estimated
Translational speed, method constantly travels through task queue to fix the speed of 20ms a cycles, is constantly moved using current camera
Speed accumulation integrates out the movement locus of individual task.The spacing distance and accumulation set according to detection device and spraying apparatus is accumulated
The task displacement separated accurately calculates the accurate execution time of spraying task.Once task reaches that default is sprayed
Spacing distance, then send spraying task order and give spraying task execution module, and remove the spraying from task queue and appoint immediately
Business.
Step S5:By analyzing the task order sended over, the low and high level signal control magnetic valve for sending setting is opened
Open or close, complete being turned on and off for spraying operation.
Compared with prior art, the present invention utilizes machine vision technique, obtains spray in real time in farm machinery running
Mist task object distributed intelligence, is estimated mechanical real-time by monocular cam trajectory reconstruction technology combination Kalman filtering algorithm
Motion track, the correct spraying opportunity of shower nozzle is extrapolated according to Work machine motion track information, realizes accurately variable rate spray,
So as to solve spraying opportunity control problem present in existing agricultural machinery field spray technology, the service efficiency of medicament is improved,
Alleviate the pollution of environment.
Brief description of the drawings
Fig. 1 is the adaptive accurate spray operations schematic flow sheet of the present invention;
Fig. 2 is the adaptive accurate spraying apparatus stereogram of the present invention;
Fig. 3 is the adaptive accurate spraying apparatus structural representation of the present invention.
Wherein, 1, housing, 2, core calculation module, 3, main camera, 4, auxiliary camera, 5, light compensating lamp, 6, shower nozzle, 7, spray
Pipe, 8, magnetic valve.
Embodiment
Technical scheme is elaborated below in conjunction with drawings and examples.
Fig. 2 and Fig. 3 is the stereogram and structure of the adaptive precise positioning spraying apparatus based on machine vision of the present invention
Schematic diagram, including mechanical arm, fixed housing 1 on the robotic arm, the core calculation module 2 being fixed in housing 1, installed in shell
Image capture module and spray module on body 1;Image capture module includes the main shooting being connected respectively with core calculation module 2
First 3, auxiliary camera 4 and light compensating lamp 5, wherein it is 30 frames/second that main camera frame number, which is 60 frames/second, auxiliary camera frame number,;Spraying mould
Block, which includes installing on explosive box, jet pipe 7 and shower nozzle 6 on the robotic arm, jet pipe 7, is provided with what is be connected with core calculation module 2
Magnetic valve 8.
Fig. 1 is the adaptive precise positioning spray method workflow diagram based on machine vision of the present invention, and its is adaptive
The core calculation module 2 of precise positioning spraying apparatus includes the automatic calibration module of distance parameter, module of target detection, velocity measuring
Module, time delay estimation module and spraying task execution module.This method is obtained under the specific setting height(from bottom) of sprayer unit automatically first
The pixel distance of detection unit and sprayer unit.Then by rule gridding video image, quick detection goes out spray target, shape
Into task queue.The characteristic point in adjacent video image is extracted using main camera, camera phase is obtained by Feature Points Matching
Pixel distance in adjacent video frame period, and obtain the camera specified under time granularity by combining Kalman Filter Technology
Moving speed estimation value.By cumulative integral, the movement locus of camera is reconstructed, so as to obtain the actual optimal of farm machinery
On spraying opportunity, realize final accurate spraying operation.It is comprised the following steps that:
Step S1:The automatic calibration module of distance parameter extracts frame of video, rule by main camera 3 and auxiliary camera 4 respectively
Feature extraction, characteristic matching are carried out to picture target area after formatting, acquisition camera position is poor from parallax, estimates spraying
Actual range.Including:
Step S11:Frame of video is extracted by main camera 3 and auxiliary camera 4 respectively first, extracted respectively after normalization
Characteristic point, calculates characteristic point its description;
Step S12:Quick Feature Points Matching is carried out using ratio method, then using RANSAC algorithms purification matching knot
Really, the higher matching characteristic point pair of confidence level is obtained;
Step S13:Using matching characteristic point to asking for due to the moving average D that parallax is causedcam, formula is as follows:
Due to known main camera 3, the relative distance L of auxiliary camera 4, and main camera is 2L apart from ejection head unit distance,
The pixel distance under unified focal length and height that object detection unit reaches injection apparatus can directly be estimated
Step S2:Object detection area in the frame of video that module of target detection captures main camera 3 carries out gridding,
Extract successively and express statistic available point, subject fusion is carried out to grid cell according to available point number, analysis judges spraying mesh
Target particular location and area, encapsulation form spraying task.Including:
Step S21:The video data detected in real time is extracted by main camera 3.In order to accelerate the speed of Objective extraction
With the stability of positioning, algorithm first carries out gridding to detection zone, and the regular grid divided using in detection zone is used as processing
With the elementary cell of judgement;
Step S22:In grid cell, according to formula
Target pixel points are quickly extracted, and count target pixel points number in single grid;
Step S23:On the basis of single net region, the too low unit of effective dot density is filtered out, in effective dot density
Reach the available point distribution centroid position in statistic unit in the prospect grid of requirement.It is valid pixel number to make N,With
For available point barycenter in prospect grid, formula is as follows:
Adjacent prospect grid cell is quickly merged by seed fill algorithm, the grid cell after fusion is covered
Region, by the grid cell barycenter of cumulative fusion, its quick summation is averaged as single spray target body overlay area
Afterwards as the barycenter of target area, Tx and Ty are the centroid position of fusion target area, and M is monolithic fusion prospect grid UNICOM body
Number, centroid calculation formula is as follows:
According to current target detection state transition information, spraying task is packaged into independent task node, when being pushed to
Prolong estimation module.
Step S3:Velocity measuring module obtains two adjacent frame of video from main camera 3, respectively from the mesh in image
Mark detection zone and extract characteristic point, carry out characteristic matching and purification using characteristic point, extrapolate the spatial alternation distance of camera,
Average translational speed of the camera within a frame of video interval time is further calculated, is updated and corrected with this velocity information
Kalman filter, utilizes the average translational speed that a camera is estimated every 20 frames of Kalman filter.Including:
Step S31:The driving trace for performing spraying task for spraying apparatus sets up linear movement model, and algorithm is created first
The Kalman filter that one time interval is 330ms;
Step S32:Adjacent video view data is obtained using main camera, characteristic point is extracted in desired target area,
And it is described using description;
Step S33:Purified by ratio method and RANSAC, smallest match feature point number is set, at random after purification
Three not conllinear characteristic points are extracted in feature point set;
Step S34:Because image capture module relative mechanical arm is fixed, the video image of extraction only exists rotation, translation
Based on motion mode, system can using calculate kinematic parameter method the two dimensional motion mode of video camera is described,
So as to obtain movement locus of the whole spraying apparatus in spraying operation.Rectangular coordinate system is used herein, so in plane motion
The identical θ of two reference axis anglecs of rotation of XYX=θY=θ, it is possible to use six parameter affine transform models calculate the global fortune of camera
It is dynamic, wherein original position (XT0,YT0), target location (XTP,YTP), in-plane displancement (XSP,YSP), specific formula is as follows:
According to kinematic parameter model, parameter is solved:Scale is scaled, rotation, x-axis offset is rotated
Xtranslation, y-axis offset ytranslation.The extraction time of known consecutive frame is tf, and then obtain adjacent video
The distance of pixel, translational speed v=(xtranslate/t are averagely moved in frame periodf,ytranslate/tf);
Step S35:S32 to S34 process is repeated, updating Kalman with the velocity information under the pixel unit that calculates filters
Ripple device parameter, while estimating the cam movement velocity amplitude in specified time interval using forecast model.
Step S4:The spraying task queue and velocity measuring module that time delay estimation module is obtained according to module of target detection are estimated
The translational speed of main camera 3 calculated, method constantly travels through task queue with the speed for fixing 20ms a cycles, constantly utilizes
The current main translational speed cumulative integral of camera 3 goes out the movement locus of individual task.Set according to detection device and spraying apparatus
Spacing distance and the task displacement that goes out of cumulative integral accurately calculate accurate execution time of spraying task.Once appoint
Business reaches default spray intervals distance, then sends spraying task order immediately and give spraying task execution module, and from task
The spraying task is removed in queue.Including:
Step S41:With fixed cycle T travel through task queue, successively take out individual task queue, carry out displacement integration and more
New parameter.The last update time is t wherein in task node, and current pixel Displacement Cumulative is s, in velocity measuring module most
The near velocity estimation value v and renewal time t of current nodecur, specific renewal operates as follows:
Step S42:Judge current pixel apart from s whether close to spray target scope, once meet | s-2L |<(ε is picture to ε
Element is apart from vT/4) then sent to spraying task execution module and be turned on and off spraying instruction, while by this task from task queue
It is middle to delete.
Step S5:Spraying task execution module sends the low and high level of setting by analyzing the task order sended over
Signal control magnetic valve 8 is turned on or off, and completes being turned on and off for spraying operation.
It is described above, it is only the embodiment in the present invention, but protection scope of the present invention is not limited thereto, and appoints
What be familiar with the people of the technology disclosed herein technical scope in, conceivable conversion and remodeling can be managed, also should be regarded as by
It is included within the scope of the present invention.
Claims (1)
1. a kind of method of the adaptive accurate spraying apparatus based on machine vision, the adaptive accurate spraying based on machine vision
Equipment includes mechanical arm, housing, core calculation module, image capture module, spray module;The housing is fixed on mechanical arm
On;The core calculation module is fixed in housing;Described image acquisition module includes being arranged on housing and and core calculations
Module connected main camera, auxiliary camera and light compensating lamp;The spray module includes installing explosive box on the robotic arm, spray
The magnetic valve being connected with core calculation module is installed on pipe and shower nozzle, jet pipe;The core calculation module includes distance parameter
Automatic calibration module, module of target detection, velocity measuring module, time delay estimation module and spraying task execution module;The master
Camera frame number is 60 frames/second, and auxiliary camera frame number is 30 frames/second;It is characterized in that:The spray method comprises the following steps:
Step S1:Frame of video is extracted by main camera and auxiliary camera respectively, picture target area carried out after normalization special
Extraction, characteristic matching are levied, acquisition camera position is poor from parallax, estimates the actual range of spraying;
Step S2:Object detection area in the frame of video that main camera is captured carries out gridding, extracts and quickly unites successively
Available point is counted, subject fusion is carried out to grid cell according to available point number, analysis judges particular location and the face of spray target
Product, encapsulation forms spraying task;
Step S3:Two adjacent frame of video are obtained from main camera, extract special from the object detection area in image respectively
Levy a little, carry out characteristic matching and purification using characteristic point, extrapolate the spatial alternation distance of camera, further calculate shooting
Average translational speed of the head within a frame of video interval time, is updated with this velocity information and corrects Kalman filter, profit
With the average translational speed that a camera is estimated every 20 frames of Kalman filter;
Step S4:The camera movement that the spraying task queue and velocity measuring module obtained according to module of target detection is estimated
Speed, method constantly travels through task queue to fix the speed of 20ms a cycles, constantly utilizes current camera translational speed
Cumulative integral goes out the movement locus of individual task, and the spacing distance and cumulative integral set according to detection device and spraying apparatus goes out
Task displacement accurately calculate accurate execution time of spraying task, once task reaches default spray intervals
Distance, then send spraying task order and give spraying task execution module, and remove from task queue the spraying task immediately;
Step S5:By analyzing the task order that sends over, send setting low and high level signal control magnetic valve open or
Person closes, and completes being turned on and off for spraying operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410783866.4A CN104615150B (en) | 2014-12-17 | 2014-12-17 | A kind of adaptive accurate spraying apparatus and method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410783866.4A CN104615150B (en) | 2014-12-17 | 2014-12-17 | A kind of adaptive accurate spraying apparatus and method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104615150A CN104615150A (en) | 2015-05-13 |
CN104615150B true CN104615150B (en) | 2017-10-03 |
Family
ID=53149648
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410783866.4A Expired - Fee Related CN104615150B (en) | 2014-12-17 | 2014-12-17 | A kind of adaptive accurate spraying apparatus and method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104615150B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106296799A (en) * | 2015-06-10 | 2017-01-04 | 西安蒜泥电子科技有限责任公司 | Characteristic point for object scanning is supplemented and extracting method |
CN106020245A (en) * | 2016-06-29 | 2016-10-12 | 韩斌 | Movable shower water spraying device based on intelligent home |
EP3403899A1 (en) * | 2017-05-17 | 2018-11-21 | Bayer Aktiengesellschaft | High speed weed control |
CN109285141B (en) * | 2018-07-27 | 2021-06-25 | 仲恺农业工程学院 | Real-time detection method for spraying effect of plant protection unmanned aerial vehicle |
CN110298854B (en) * | 2019-05-17 | 2021-05-11 | 同济大学 | Flight snake-shaped arm cooperative positioning method based on online self-adaption and monocular vision |
CN111753388B (en) * | 2019-12-30 | 2021-06-15 | 广州极飞科技股份有限公司 | Spraying control method, spraying control device, electronic equipment and computer-readable storage medium |
CN113312986A (en) * | 2021-05-10 | 2021-08-27 | 浙江科技学院 | Spraying control system based on visual processing and control method thereof |
CN114145279A (en) * | 2021-11-30 | 2022-03-08 | 福建省鼎贤市政园林工程有限公司 | Intelligent banyan insect pest multi-angle insecticidal sprinkler |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5222324A (en) * | 1991-02-21 | 1993-06-29 | Neall Donald L O | Crop spraying system |
US5924239A (en) * | 1994-10-25 | 1999-07-20 | Rees Equipment Pty Ltd. | Controller for agricultural sprayers |
CN101927220A (en) * | 2010-07-05 | 2010-12-29 | 中国农业大学 | Accurate intelligent targeted spraying machine |
CN101961003A (en) * | 2010-08-10 | 2011-02-02 | 江苏大学 | Precise targeted spraying and weeding device |
CN102800083A (en) * | 2012-06-19 | 2012-11-28 | 中国农业大学 | Crop spraying positioning method based on binocular vision gridding partition matching algorithm |
CN103988824A (en) * | 2014-04-18 | 2014-08-20 | 浙江大学 | Automatic targeting and spraying system based on binocular vision technology |
CN104069970A (en) * | 2014-06-10 | 2014-10-01 | 潍坊美奥农业科技有限公司 | Agriculture intelligent spraying machine |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0712264B2 (en) * | 1990-06-01 | 1995-02-15 | 株式会社丸山製作所 | Method and device for spraying pest control spray |
-
2014
- 2014-12-17 CN CN201410783866.4A patent/CN104615150B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5222324A (en) * | 1991-02-21 | 1993-06-29 | Neall Donald L O | Crop spraying system |
US5924239A (en) * | 1994-10-25 | 1999-07-20 | Rees Equipment Pty Ltd. | Controller for agricultural sprayers |
CN101927220A (en) * | 2010-07-05 | 2010-12-29 | 中国农业大学 | Accurate intelligent targeted spraying machine |
CN101961003A (en) * | 2010-08-10 | 2011-02-02 | 江苏大学 | Precise targeted spraying and weeding device |
CN102800083A (en) * | 2012-06-19 | 2012-11-28 | 中国农业大学 | Crop spraying positioning method based on binocular vision gridding partition matching algorithm |
CN103988824A (en) * | 2014-04-18 | 2014-08-20 | 浙江大学 | Automatic targeting and spraying system based on binocular vision technology |
CN104069970A (en) * | 2014-06-10 | 2014-10-01 | 潍坊美奥农业科技有限公司 | Agriculture intelligent spraying machine |
Also Published As
Publication number | Publication date |
---|---|
CN104615150A (en) | 2015-05-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104615150B (en) | A kind of adaptive accurate spraying apparatus and method based on machine vision | |
US11596139B2 (en) | Method for autonomously weeding crops in an agricultural field | |
CN109122633B (en) | Plant protection unmanned aerial vehicle accurate variable spraying device for neural network decision-making and control method | |
CN109258601B (en) | Intelligent automatic targeting spraying flow control device and method for weeding unmanned aerial vehicle | |
CN103891697A (en) | Drug spraying robot capable of moving indoors autonomously and variable drug spraying method thereof | |
CN111596689A (en) | Intelligent agricultural plant protection operation control system based on big data Internet of things | |
CN105760846B (en) | Target detection and localization method and system based on depth data | |
CN108196580A (en) | The spray method and unmanned plane of a kind of unmanned plane | |
CN106441151A (en) | Measuring system for three-dimensional target Euclidean space reconstruction based on vision and active optical fusion | |
CN103988824A (en) | Automatic targeting and spraying system based on binocular vision technology | |
CN103778645B (en) | Circular target real-time tracking method based on images | |
AU2022256171B2 (en) | Weeding robot and method, apparatus for planning weeding path for the same and medium | |
DE102005013225A1 (en) | Object tracking and situation analysis system | |
CN109471434A (en) | A kind of novel variable rate spray path planning autonomous navigation system and method | |
CN107295818B (en) | Automatic seedling avoiding system and method for paddy field weeding machine | |
CN111066442B (en) | Targeted variable fertilization method and device for corn and application | |
CN114612577A (en) | Orchard intelligent pesticide spraying method and system based on binocular stereoscopic vision | |
CN109947115A (en) | Mower control system and control method thereof | |
CN114527294A (en) | Target speed measuring method based on single camera | |
JP2021045055A (en) | Drone controller, pollen/fruiting agent automatic adhesion system using the same, drone control program, drone control method | |
Jeon et al. | Stereo vision controlled variable rate sprayer for specialty crops: Part I. Controller development | |
CN212300875U (en) | To target spraying test bench based on machine vision | |
US11521382B2 (en) | Machine vision plant tracking system for precision agriculture | |
CN114993895A (en) | Test device and method for synchronously measuring spray far-field droplet particle size and droplet instantaneous velocity distribution | |
Brandon et al. | Vision assisted tractor guidance for agricultural vehicles |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171003 Termination date: 20201217 |
|
CF01 | Termination of patent right due to non-payment of annual fee |