CN105259832A - Intelligent cotton picker control system based on multi-view stereo vision - Google Patents
Intelligent cotton picker control system based on multi-view stereo vision Download PDFInfo
- Publication number
- CN105259832A CN105259832A CN201510700294.3A CN201510700294A CN105259832A CN 105259832 A CN105259832 A CN 105259832A CN 201510700294 A CN201510700294 A CN 201510700294A CN 105259832 A CN105259832 A CN 105259832A
- Authority
- CN
- China
- Prior art keywords
- cotton
- stereo vision
- view stereo
- information
- control system
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D46/00—Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs
- A01D46/08—Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs of cotton
- A01D46/12—Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs of cotton using boll-from-plant strippers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Gyroscopes (AREA)
Abstract
The invention discloses an intelligent cotton picker control system based on multi-view stereo vision, and relates to the field of machine vision and electromechanical control. The system comprises a multi-view stereo vision technology which is mainly used for recognizing and spatially locating mature cotton bolls to obtain the spatial location information of mature cotton bolls. The system further comprises a three-axis acceleration sensor and a three-axis gyroscope which are used for acquiring motion information of a unit and posture information of an array electric cylinder. The information acquired by the multi-view stereo vision technology and the information acquired by the three-axis acceleration sensor and the three-axis gyroscope are integrated. A controller and an actuator make the array electric cylinder move to a specified position to pick mature cotton bolls. The intelligent cotton picker control system of the invention has the advantages of precise control, good real-time performance, high efficiency, and the like.
Description
Technical field
The present invention relates to a kind of control system being applied to cotton picker, particularly relate to a kind of intelligent cotton picker control system based on multi-view stereo vision, relate to field of machine vision and electromechanical control field.
Background technology
Nearly 2,800 ten thousand mu of the sown areas of cotton of China, traditional cotton picking mode is artificial cotton picking, every cotton picking season, all will drop into a large amount of manpower and materials costs.In recent years, constantly decline owing to planting cotton benefit, cause labor cost to rise year by year, therefore mechanization cotton picking technology was arisen at the historic moment.The cotton picker overwhelming majority that current domestic cotton grower uses is by external import, and cotton picker requires that cotton knot bell is more concentrated, and fruit branch aspect ratio is more consistent with liftoff more than 18cm, and fruit branch wants short and upper punch, and plant type is compact, and blow-of-cottons are concentrated, and condition of plucking is very harsh; When gathering, disposable harvesting, destroys cotton plants, and net picking rate is not high, reduces output of cotton, and machine cotton picking contains assorted height, length is partially short, short fibre content is high, crudy is poor.Along with the develop rapidly of the present computer technology, field bus technique and large scale integrated circuit technology, stereovision technique is ripe day by day, has been widely used in agricultural production.In recent years, domestic also have the research being applied to cotton picker about stereoscopic vision, and what research was more at present is use binocular stereo vision to carry out digital map navigation, cotton location, and adopt mechanical arm cotton picking, cotton picking efficiency is not high, locates not accurate enough, and net picking rate is not high.Therefore, the present invention proposes a kind of intelligent cotton picker control system of the multi-sensor information fusion based on multi-view stereo vision, use multi-view stereo vision accurately to locate, and adopt high-speed data processor, precisely, quick, the cotton picking topworks of control is in real time efficient, high-quality cotton picking.
Summary of the invention
The invention provides a kind of cotton picker control system of the multi-sensor information fusion based on multi-view stereo vision, the image information of cotton plant can be obtained in real time, and electric cylinder harvesting ripe cotton can be controlled quickly and accurately, there is the features such as real-time, accurate, efficient.
Technical scheme of the present invention is: a kind of intelligent cotton picker control system of the multi-sensor information fusion based on multi-view stereo vision, comprises multi-view stereo vision module (1), unit operation and posture information acquisition module (2) and control module (3).
Multi-view stereo vision module comprises 3 colorful CCD cameras, 1 DSP Digital Image Processor, 1 FPGA field programmable gate array and 1 SRIO HSSI High-Speed Serial Interface, 3 colorful CCD cameras obtain the image information of target from three angles, gathered by the view data of FPGA to CCD camera and pre-service is carried out to image, by SRIO HSSI High-Speed Serial Interface, the view data after FPGA process is sent to DSP Digital Image Processor again, by DSP according to specifically algorithm image data processing at high speed, to complete identification to ripe cotton boll and space orientation, then control module is sent the data to.
Unit operation and posture information acquisition module comprise 1 3-axis acceleration sensor and 1 three-axis gyroscope, 3-axis acceleration sensor obtains travelling speed, the acceleration information of cotton picker, three-axis gyroscope obtains the angular position information of electric cylinder array relative cotton plants, and FPGA gathers information that 3-axis acceleration sensor and three-axis gyroscope obtain and carries out processing eliminating the relativity shift of electric cylinder array because ground out-of-flatness causes and cotton plants by specific algorithm.
Control module comprises controller and driver, the unit operation obtained after the ripe cotton boll spatial position data that controller obtains after receiving DSP process and FPGA process and pose data, carry out judging and generating instruction according to specific rule, then by the motion of driver drives electric cylinder array to capture ripe cotton boll.
In sum, the intelligent cotton picker control system based on multi-view stereo vision provided by the invention can control electric cylinder and win ripe cotton boll fast and accurately.Adopt multi-view stereo vision technology, not only can obtain the spatial positional information of cotton, determine the relative space position of cotton plants relative to electric cylinder array, also obtained image can be utilized effectively to split, cotton and background are separated, thus determines the locus of ripe cotton boll accurately; Employing 3-axis acceleration sensor and three-axis gyroscope can effectively reduce the sterically defined impact of electric cylinder array relative maturity cotton because ground out-of-flatness causes; DSP and FPGA combines can the fused data of image data processing and each sensor at high speed, meets the requirement of control system real-time and high efficiency.
Accompanying drawing explanation
The present invention is further illustrated below in conjunction with accompanying drawing.
Fig. 1 is general structure block diagram of the present invention.
Fig. 2 is the installation site schematic diagram of 3 CCD color cameras of the present invention.
Fig. 3 is multi-view stereo vision modular structure block diagram of the present invention.
Fig. 4 is control module structured flowchart of the present invention.
Embodiment
Fig. 1 is general structure block diagram of the present invention.Multi-view stereo vision module is by being arranged on 3 CCD camera on unit picture from the real-time shooting cotton plants of 3 different angles, FPGA carries out collection and pre-service to the view data of CCD camera, eliminate the interfere information such as background and noise, by SRIO HSSI High-Speed Serial Interface, the view data after FPGA process is sent to DSP Digital Image Processor, by DSP according to specifically algorithm image data processing at high speed, to complete identification to ripe cotton boll and space orientation, then send the data to control module and process; Simultaneously, speed, the acceleration information of the motion of unit is gathered by 3-axis acceleration sensor and three-axis gyroscope, and topworks is relative to the angle information of cotton plants, and send the data to control module and process, via controller will be written as specific instruction according to certain rule after data fusion again, then captures ripe cotton boll accurately by driver drives electric cylinder array.
Fig. 2 is the installation site schematic diagram of 3 CCD color cameras of the present invention.3 CCD camera obtain image information with both sides respectively above cotton plant, more completely can be obtained the positional information of plant and cotton boll by the image of 3 angle acquisitions.
Fig. 3 is multi-view stereo vision modular structure block diagram of the present invention.The image of 3 CCD camera shooting cotton plants, by FPGA, collection is carried out and pre-service to view data, to remove background information and other noises, then pass through SRIO HSSI High-Speed Serial Interface by pretreated image data transmission in dsp processor, DSP data processor carries out identification and the segmentation of cotton location and cotton and ripe cotton boll simultaneously.Wherein, the location of cotton needs to carry out parameter calibration and optimization to camera, then the data of 3 CCD camera is calculated according to specific algorithm, thus obtains the depth information of cotton, to complete the location to cotton; The specific dividing method of image after denoising is split, accurately to isolate ripe cotton boll and cotton boll, for the accurate crawl of ripe cotton boll provides authentic communication simultaneously.
Fig. 4 is control module structured flowchart of the present invention.The unit operation obtained after the ripe cotton boll spatial position data that controller obtains after receiving DSP process and FPGA process and pose data, carry out judging and generating instruction according to specific rule, then instruction is sent to driver, then by the motion of driver drives electric cylinder array to capture ripe cotton boll.
Claims (4)
1., based on an intelligent cotton picker control system for multi-view stereo vision, it is characterized in that:
This system comprises multi-view stereo vision module (1), unit operation and posture information acquisition module (2) and control module (3); Multi-view stereo vision module (1) quick and precisely identifies ripe cotton boll, and obtains its spatial positional information; Unit operation and posture information acquisition module (2) provide the movable information of cotton picker and the spatial pose information of electric cylinder array for control system; Control module (3) receives by the information of multi-view stereo vision module and unit operation and pose acquisition module and generates steering order, control electric cylinder array fast, the accurate ripe cotton boll of crawl.
2. require the described intelligent cotton picker control system based on multi-view stereo vision according to right 1, it is characterized in that, described multi-view stereo vision module comprises 3 colorful CCD cameras, 1 DSP Digital Image Processor, 1 FPGA field programmable gate array and 1 SRIO HSSI High-Speed Serial Interface, 3 colorful CCD cameras obtain the image information of target from three angles, gathered by the view data of FPGA to CCD camera and pre-service is carried out to image, by SRIO HSSI High-Speed Serial Interface, the view data after FPGA process is sent to DSP Digital Image Processor again, by DSP according to specifically algorithm image data processing at high speed, to complete identification to ripe cotton boll and space orientation, then control module is sent the data to.
3. require the described intelligent cotton picker control system based on multi-view stereo vision according to right 1, it is characterized in that, described unit operation and posture information acquisition module comprise 1 3-axis acceleration sensor and 1 three-axis gyroscope, 3-axis acceleration sensor obtains the travelling speed of cotton picker, acceleration information, three-axis gyroscope obtains the angular position information of the relative cotton plants of electric cylinder array, FPGA gathers information that 3-axis acceleration sensor and three-axis gyroscope obtain and carries out processing eliminating the relativity shift of electric cylinder array because ground out-of-flatness causes and cotton plants by specific algorithm.
4. require the described intelligent cotton picker control system based on multi-view stereo vision according to right 1, it is characterized in that, described control module comprises controller and driver, the unit operation obtained after the ripe cotton boll spatial position data that controller obtains after receiving DSP process and FPGA process and pose data, carry out judging and generating instruction according to specific rule, then instruction is sent to driver, then by the motion of driver drives electric cylinder array to capture ripe cotton boll.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510700294.3A CN105259832A (en) | 2015-10-26 | 2015-10-26 | Intelligent cotton picker control system based on multi-view stereo vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510700294.3A CN105259832A (en) | 2015-10-26 | 2015-10-26 | Intelligent cotton picker control system based on multi-view stereo vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105259832A true CN105259832A (en) | 2016-01-20 |
Family
ID=55099572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510700294.3A Pending CN105259832A (en) | 2015-10-26 | 2015-10-26 | Intelligent cotton picker control system based on multi-view stereo vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105259832A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527367A (en) * | 2017-10-19 | 2017-12-29 | 新疆秦域工业设备制造安装有限公司 | A kind of cotton identification and localization method based on binocular camera |
| CN107966944A (en) * | 2017-11-30 | 2018-04-27 | 贵州财经大学 | Smart greenhouse zone control system and subregion picking method |
| CN107984482A (en) * | 2017-12-27 | 2018-05-04 | 中国科学院合肥物质科学研究院 | A kind of intelligent matrimony vine picker and method based on TOF depth perceptions |
| CN108073097A (en) * | 2016-11-11 | 2018-05-25 | 昆山艾派精密工业有限公司 | The image processing apparatus of industrial robot |
| CN110501958A (en) * | 2019-09-06 | 2019-11-26 | 中国科学院长春光学精密机械与物理研究所 | A kind of control system of 6-dof motion platform |
| WO2020172992A1 (en) * | 2019-02-25 | 2020-09-03 | 上海交通大学 | Method for harvesting hidden vegetables and fruits on basis of depth association perception algorithm |
| CN113508685A (en) * | 2021-04-19 | 2021-10-19 | 北京化工大学 | Marigold picking mobile robot |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101112150A (en) * | 2007-09-07 | 2008-01-30 | 南京工程学院 | Intelligent cotton harvester |
| US20080046154A1 (en) * | 2006-07-31 | 2008-02-21 | Robert Matthew Bares | Cotton harvester row unit speed synchronization control |
| CN103019123A (en) * | 2012-12-26 | 2013-04-03 | 上海大学 | Intelligent control system for cotton picker |
-
2015
- 2015-10-26 CN CN201510700294.3A patent/CN105259832A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080046154A1 (en) * | 2006-07-31 | 2008-02-21 | Robert Matthew Bares | Cotton harvester row unit speed synchronization control |
| CN101164401A (en) * | 2006-07-31 | 2008-04-23 | 迪尔公司 | Cotton harvester row unit speed synchronization control |
| CN101112150A (en) * | 2007-09-07 | 2008-01-30 | 南京工程学院 | Intelligent cotton harvester |
| CN103019123A (en) * | 2012-12-26 | 2013-04-03 | 上海大学 | Intelligent control system for cotton picker |
Non-Patent Citations (2)
| Title |
|---|
| 刘坤: "采棉机器人视觉识别技术研究", 《万方数据》 * |
| 韦皆顶等: "智能型采棉机器人电气控制系统设计", 《制造业自动化》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073097A (en) * | 2016-11-11 | 2018-05-25 | 昆山艾派精密工业有限公司 | The image processing apparatus of industrial robot |
| CN108073097B (en) * | 2016-11-11 | 2021-06-11 | 昆山艾派精密工业有限公司 | Image processing device of industrial robot |
| CN107527367A (en) * | 2017-10-19 | 2017-12-29 | 新疆秦域工业设备制造安装有限公司 | A kind of cotton identification and localization method based on binocular camera |
| CN107966944A (en) * | 2017-11-30 | 2018-04-27 | 贵州财经大学 | Smart greenhouse zone control system and subregion picking method |
| CN107966944B (en) * | 2017-11-30 | 2020-12-08 | 贵州财经大学 | Intelligent greenhouse partition control system and partition picking method |
| CN107984482A (en) * | 2017-12-27 | 2018-05-04 | 中国科学院合肥物质科学研究院 | A kind of intelligent matrimony vine picker and method based on TOF depth perceptions |
| WO2020172992A1 (en) * | 2019-02-25 | 2020-09-03 | 上海交通大学 | Method for harvesting hidden vegetables and fruits on basis of depth association perception algorithm |
| CN110501958A (en) * | 2019-09-06 | 2019-11-26 | 中国科学院长春光学精密机械与物理研究所 | A kind of control system of 6-dof motion platform |
| CN113508685A (en) * | 2021-04-19 | 2021-10-19 | 北京化工大学 | Marigold picking mobile robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105259832A (en) | Intelligent cotton picker control system based on multi-view stereo vision | |
| RU2771097C2 (en) | Agricultural working machine | |
| CN103503639B (en) | A kind of both arms fruits and vegetables are gathered robot system and fruits and vegetables collecting method thereof | |
| EP3337307B1 (en) | A self-guided blossom picking device | |
| CN110122073B (en) | Strawberry picking robot based on machine vision | |
| Kitamura et al. | Recognition and cutting system of sweet pepper for picking robot in greenhouse horticulture | |
| CN103950033B (en) | The mechanical arm of fruit picking robot and end effector and fruit picking method | |
| CN203340870U (en) | Remote controlled weeding robot | |
| CN105165255B (en) | A kind of intelligent cotton picker system based on computer vision technique | |
| CN111165176A (en) | Tea artificial intelligence picking robot | |
| CN105993393A (en) | Picking method for flower harvesting robot | |
| CN203467238U (en) | Intelligent tomato picking device based on machine vision | |
| Yuan et al. | An autonomous pollination robot for hormone treatment of tomato flower in greenhouse | |
| CN108811766B (en) | Man-machine interactive greenhouse fruit and vegetable harvesting robot system and harvesting method thereof | |
| CN102368158A (en) | Navigation positioning method of orchard machine | |
| CN113597874B (en) | Weeding robot and weeding path planning method, device and medium thereof | |
| CN107436340B (en) | Plant root and crown integrated monitoring system and method | |
| CN103793895A (en) | Method for stitching fruit tree crown layer organ images | |
| Ji et al. | Research on key technology of truss tomato harvesting robot in greenhouse | |
| Hu et al. | Simplified 4-DOF manipulator for rapid robotic apple harvesting | |
| CN108093868A (en) | A kind of picker system based on embedded intelligence control and binocular machine vision | |
| CN108279678A (en) | A kind of field automatic travelling device and its ambulation control method for detecting plant growth condition | |
| CN114830915A (en) | Litchi vision picking robot based on laser radar navigation and implementation method thereof | |
| CN113812262B (en) | Tea-oil camellia fruit picking robot based on machine vision | |
| CN115937314B (en) | Method for detecting growth posture of oil tea fruits |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160120 |
|
| WD01 | Invention patent application deemed withdrawn after publication |