CN109757219A - A kind of view-based access control model picker system and method - Google Patents
A kind of view-based access control model picker system and method Download PDFInfo
- Publication number
- CN109757219A CN109757219A CN201910179075.3A CN201910179075A CN109757219A CN 109757219 A CN109757219 A CN 109757219A CN 201910179075 A CN201910179075 A CN 201910179075A CN 109757219 A CN109757219 A CN 109757219A
- Authority
- CN
- China
- Prior art keywords
- picked
- crawl section
- access control
- fruit
- based access
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The present invention discloses a kind of view-based access control model picker system, and the system comprises picking robot, control system, visual sensor and data processing units；The visual sensor is for obtaining multiple targets to be picked；The data processing unit is used to carry out feature extraction according to the multiple target to be picked, and identification has fruit region, and records the coordinate for having fruit region；The control system has the coordinate in fruit region and the picking robot is driven to be picked described in being used to receive.Above system in the present invention can be realized the full-automatic picking to fruit.
Description
Technical field
The present invention relates to picking fields, more particularly to a kind of view-based access control model picker system and method.
Background technique
Currently, the picking for crops mainly still relies on manpower, China is as a large agricultural country, for crops
Picking be a large-engineering.Also, with the aging of population with the reduction of agricultural workforce, agriculture production cost
Correspondingly increase, will be greatly reduced the competitiveness of product in market in this way, crops picking operation be in production estimation chain it is most time-consuming,
A most laborious link.Meanwhile the quality for picking operation quality also directly influences the following process and storage of product.
In actual operation, picker system is work under extremely complex environment, and picking object is to there is life
Plant, picking object is delicate, brittle, and shape individual is complicated, and is easily blocked by leaf.Existing picker system was being picked
Cheng Zhong, it will usually hurt fruit, this also brings certain difficulty to subsequent processing and storage.
Therefore, how to realize that the automation precise acquisition to agricultural product must be paid attention to and be considered in production estimation link
The problem of.
Summary of the invention
The object of the present invention is to provide a kind of view-based access control model picker system and methods, realize the full-automatic acquisition to fruit.
To achieve the above object, the present invention provides following schemes:
A kind of view-based access control model picker system, the system comprises picking robot, control system, visual sensor and numbers
According to processing unit；
The visual sensor is for obtaining multiple targets to be picked；
The data processing unit is used to carry out feature extraction according to the multiple target to be picked, and identification has fruit area
Domain, and record the coordinate for having fruit region；
The control system has the coordinate in fruit region and the picking robot is driven to be picked described in being used to receive.
Optionally, the picking robot specifically includes: pedestal, pneumatic-finger cylinder, the first crawl section, the second crawl
Portion, first connecting portion, second connecting portion, conveyance conduit, collecting box, the first slideway, the second slideway and telescopic rod；
The collecting box setting is on the base；
One end of the first connecting portion, first crawl section and second crawl section is arranged in first slideway
It is arranged on first slideway, the other end of the first connecting portion is connect with one end of the telescopic rod, the telescopic rod
The other end connect with the mobile terminal of the pneumatic-finger cylinder；
Second slideway is arranged in the second connecting portion, and the other end of the pneumatic-finger cylinder is arranged described
On second slideway, the second connecting portion setting is on the base；
One end of the conveyance conduit is located at the underface of first crawl section and second crawl section, the conveying
The other end of pipeline is connect with the collecting box.
Optionally, the inner wall of the inner wall of the conveyance conduit and the collecting box is provided with damping cotton.
Optionally, acquisition of multiple targets to be picked particular by the realization of color filter algorithm to multiple targets is obtained.
Optionally, the data processing unit is used to carry out feature extraction according to the multiple target to be picked specifically to wrap
It includes:
Feature extraction is carried out to multiple targets to be picked using scale learning algorithm.
Optionally, first crawl section, the second crawl section inner wall be laid with damping cotton.
Optionally, the side of the collecting box is additionally provided with door body.
The present invention still further provides a kind of view-based access control model picking method, and the method is applied to above-mentioned system, method packet
It includes:
Visual sensor obtains multiple targets to be picked；
Data processing unit carries out feature extraction to the multiple target to be picked, and identification has fruit region, and record has
The coordinate in fruit region；
The coordinate for having fruit region is sent to control system by data processing unit；
Control system drives pneumatic-finger cylinder to drive the first crawl section and the second crawl section to Forward according to the coordinate
It is dynamic, fruit is grabbed；
First crawl section and second crawl section expand outwardly, and unclamp the fruit to conveyance conduit, complete picking.
Optionally, the multiple targets to be picked of acquisition specifically use the realization of color filter algorithm to adopt multiple targets
Collection.
Optionally, described specifically to use scale learning algorithm to multiple the multiple target progress feature extraction to be picked
Target to be picked carries out feature extraction.
The specific embodiment provided according to the present invention, the invention discloses following technical effects:
Multiple targets to be picked are obtained by setting visual sensor in the present invention, data processing unit is set according to
Multiple targets to be picked carry out feature extraction, and identification has fruit region, and records the coordinate for having fruit region；Control system is set
There is the coordinate in fruit region described in reception and the picking robot is driven to be picked, fruit region can have been accurately identified simultaneously
It is accurately won, substantially increases the degree of automation of picking.
Further, it by the way that damping cotton is arranged on the first crawl section and the second crawl section, further reduces to fruit
Injury.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is view-based access control model of embodiment of the present invention picker system structural schematic diagram；
Fig. 2 is picking robot of embodiment of the present invention structural schematic diagram；
Fig. 3 is view-based access control model of embodiment of the present invention picking method flow chart.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide a kind of view-based access control model picker system and methods, realize the full-automatic acquisition to fruit.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is view-based access control model of embodiment of the present invention picker system structural schematic diagram, as shown in Figure 1, the system comprises views
Feel sensor 1001,1002 picking robot 1004 of data processing unit and control system 1003；
The visual sensor 1001 obtains the image of target to be picked, and lead to for obtaining multiple targets to be picked
It crosses color filter algorithm and fast implements acquisition under complex background to target；
The data processing unit 1002 is used to carry out feature extraction according to the multiple target to be picked, i.e., to target into
Row segmentation, the color characteristic of analysis background grove and fruit are filtered the filtering of pairs of grove using color threshold, and identification has fruit
Real region, and record the coordinate for having fruit region；
The control system described have the coordinate in fruit region and the picking robot 1004 is driven to carry out for receiving
Picking.
Fig. 2 is view-based access control model of embodiment of the present invention picking robot structural schematic diagram, as shown in Fig. 2, the picking machine
People specifically includes: pedestal 1, collecting box 2, conveyance conduit 3, pneumatic-finger cylinder 4, the first crawl section 501, the second crawl section 502,
First connecting portion 601, second connecting portion 602, the first slideway 701, the second slideway 702 and telescopic rod 8；The pedestal 1 is ten thousand
To wheel.The side of the collecting box is additionally provided with door body 9, and the door body 9 is transparent material, the collecting fruit in collecting box 2
Man Shi, openable door body take out fruit.
The collecting box 2 is arranged on the pedestal 1；
First slideway 701 is arranged in one end of the first connecting portion 601, first crawl section 501 and described
Second crawl section 502 is arranged 701 on first slideway, the other end of the first connecting portion 601 and the telescopic rod 8
One end connection, the other end of the telescopic rod 8 are connect with the mobile terminal of the pneumatic-finger cylinder 4；
Second slideway 702 is arranged in the second connecting portion 602, and the other end of the pneumatic-finger cylinder 4 is set
It sets on second slideway 702, the second connecting portion 602 is arranged on the collecting box；The pneumatic-finger cylinder 4 can
First crawl section 501 and second crawl section 502 is driven to move on second slideway.
One end of the conveyance conduit 3 is located at the underface of first crawl section 501 and second crawl section 502,
The other end of the conveyance conduit 3 is connect with the collecting box 2.
Specifically, the top of the conveyance conduit 3, is in open-like shape, when the first crawl section 501 and the second crawl section 502 are grabbed
When fruit being taken to discharge, it is ensured that each fruit can enter in conveyance conduit 3.
Wherein, it is provided with damping cotton 10 in the inner wall of the conveyance conduit 3 and the inner wall of the collecting box 2, works as fruit
It is honest enter conveyance conduit inside when, to guarantee the integrality of fruit, avoid colliding with.
Page is also provided with damping cotton (not shown) on first crawl section 501 and second crawl section 502, into one
Step reduces the injury to fruit,
At work, the pneumatic-finger cylinder 4 drives the first crawl section 501 and the second crawl section 502 described first
It is mobile to the opposite direction of other side on slideway 701, while the telescopic rod 8 being driven to uphold to fruit region, according to the seat of fruit
Mark carries out the specified picking of fruit, when the first crawl section 501 and the second crawl section 502 grab fruit, pneumatic-finger cylinder 4
It drives the first crawl section 501 and the second crawl section 502 to open, discharges in fruit to conveyance conduit, it is complete further to collecting box
At the automatic picking of fruit.
Fig. 3 is view-based access control model of embodiment of the present invention picking method flow chart, as shown in Figure 3, which comprises
Step 101: obtaining multiple targets to be picked；
Step 102: feature extraction being carried out to the multiple target to be picked, identification has fruit region, and record has fruit
The coordinate in region；
Step 103: the coordinate for having fruit region is sent to control system；
Step 104: the control system drives pneumatic-finger cylinder to drive the first crawl section and second according to the coordinate
Crawl section moves forward, and grabs to fruit；
Step 105: first crawl section and second crawl section expand outwardly, and unclamp the fruit to delivery pipe
Picking is completed in road.
In specific step 101, obtains multiple targets to be picked and color filter algorithm is specifically used to realize to multiple targets
Acquisition.
In step 102, feature extraction is carried out to the multiple target to be picked and specifically uses scale learning algorithm to multiple
Target to be picked carries out feature extraction.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of view-based access control model picker system, which is characterized in that the system comprises picking robot, control system, visions to pass
Sensor and data processing unit；
The visual sensor is for obtaining multiple targets to be picked；
The data processing unit is used to carry out feature extraction according to the multiple target to be picked, and identification has fruit region, and
Record has the coordinate in fruit region；
The control system has the coordinate in fruit region and the picking robot is driven to be picked described in being used to receive.
2. view-based access control model picker system according to claim 1, which is characterized in that the picking robot specifically includes:
Pedestal, pneumatic-finger cylinder, the first crawl section, the second crawl section, first connecting portion, second connecting portion, conveyance conduit, collection
Case, the first slideway, the second slideway and telescopic rod；
The collecting box setting is on the base；
One end of the first connecting portion is arranged in first slideway, and first crawl section and second crawl section are all provided with
It sets on first slideway, the other end of the first connecting portion is connect with one end of the telescopic rod, the telescopic rod
The other end is connect with the mobile terminal of the pneumatic-finger cylinder；
Second slideway is arranged in the second connecting portion, and the other end of the pneumatic-finger cylinder is arranged described second
On slideway, the second connecting portion setting is on the base；
One end of the conveyance conduit is located at the underface of first crawl section and second crawl section, the conveyance conduit
The other end connect with the collecting box.
3. view-based access control model picker system according to claim 2, which is characterized in that the inner wall of the conveyance conduit and institute
The inner wall for stating collecting box is provided with damping cotton.
4. view-based access control model picker system according to claim 1, which is characterized in that obtaining multiple targets to be picked is specifically
The acquisition to multiple targets is realized by color filter algorithm.
5. view-based access control model picker system according to claim 1, which is characterized in that the data processing unit is used for basis
The multiple target to be picked carries out feature extraction and specifically includes:
Feature extraction is carried out to multiple targets to be picked using scale learning algorithm.
6. view-based access control model picker system according to claim 2, which is characterized in that first crawl section, the second crawl
The inner wall even distribution in portion is equipped with damping cotton.
7. view-based access control model picker system according to claim 1, which is characterized in that the side of the collecting box is additionally provided with
Door body.
8. a kind of view-based access control model picking method, which is characterized in that the method is applied to as claim 1-7 is described in any item
System, method include:
Visual sensor obtains multiple targets to be picked；
Data processing unit carries out feature extraction to the multiple target to be picked, and identification has fruit region, and record has fruit
The coordinate in region；
The coordinate for having fruit region is sent to control system by data processing unit；
Control system drives pneumatic-finger cylinder that the first crawl section and the second crawl section is driven to move forward according to the coordinate, right
Fruit is grabbed；
First crawl section and second crawl section expand outwardly, and unclamp the fruit to conveyance conduit, complete picking.
9. view-based access control model picking method according to claim 8, which is characterized in that described to obtain multiple target tools to be picked
Body realizes the acquisition to multiple targets using color filter algorithm.
10. view-based access control model picking method according to claim 8, which is characterized in that described to the multiple mesh to be picked
Mark carries out feature extraction and scale learning algorithm is specifically used to carry out feature extraction to multiple targets to be picked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910179075.3A CN109757219A (en) | 2019-03-11 | 2019-03-11 | A kind of view-based access control model picker system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910179075.3A CN109757219A (en) | 2019-03-11 | 2019-03-11 | A kind of view-based access control model picker system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109757219A true CN109757219A (en) | 2019-05-17 |
Family
ID=66458193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910179075.3A Pending CN109757219A (en) | 2019-03-11 | 2019-03-11 | A kind of view-based access control model picker system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109757219A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101273688A (en) * | 2008-05-05 | 2008-10-01 | 江苏大学 | Apparatus and method for flexible pick of orange picking robot |
| CN104221601A (en) * | 2014-09-23 | 2014-12-24 | 海南大学 | Guide rail movable type banana picking machine |
| CN106105566A (en) * | 2016-07-25 | 2016-11-16 | 柳州铁道职业技术学院 | Intelligence Citrus picking robot and Citrus picking method |
| US20180146618A1 (en) * | 2016-11-29 | 2018-05-31 | Invia Robotics, Inc. | Harvesting Robots for Hydroponics |
| CN108966833A (en) * | 2018-06-07 | 2018-12-11 | 徐州工业职业技术学院 | A kind of fruit picking sorting equipment |
| CN109005923A (en) * | 2018-08-13 | 2018-12-18 | 上海电机学院 | A kind of full-automatic fruit picking device |
| CN109197153A (en) * | 2018-11-01 | 2019-01-15 | 天津城建大学 | Without knife Rotary Water fruit picking machine |
| CN109220225A (en) * | 2018-10-22 | 2019-01-18 | 湖北理工学院 | A kind of full-automatic fruit picker |
-
2019
- 2019-03-11 CN CN201910179075.3A patent/CN109757219A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101273688A (en) * | 2008-05-05 | 2008-10-01 | 江苏大学 | Apparatus and method for flexible pick of orange picking robot |
| CN104221601A (en) * | 2014-09-23 | 2014-12-24 | 海南大学 | Guide rail movable type banana picking machine |
| CN106105566A (en) * | 2016-07-25 | 2016-11-16 | 柳州铁道职业技术学院 | Intelligence Citrus picking robot and Citrus picking method |
| US20180146618A1 (en) * | 2016-11-29 | 2018-05-31 | Invia Robotics, Inc. | Harvesting Robots for Hydroponics |
| CN108966833A (en) * | 2018-06-07 | 2018-12-11 | 徐州工业职业技术学院 | A kind of fruit picking sorting equipment |
| CN109005923A (en) * | 2018-08-13 | 2018-12-18 | 上海电机学院 | A kind of full-automatic fruit picking device |
| CN109220225A (en) * | 2018-10-22 | 2019-01-18 | 湖北理工学院 | A kind of full-automatic fruit picker |
| CN109197153A (en) * | 2018-11-01 | 2019-01-15 | 天津城建大学 | Without knife Rotary Water fruit picking machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN201600330U (en) | System for recognizing and locating mature pineapples | |
| CN103529855B (en) | A kind of object recognition and detection device of rotary adjustable binocular vision and the application at agriculture fruit picking mechanical thereof | |
| CN107094429A (en) | A kind of multiaxis fruit picking robot | |
| CN105719282B (en) | A kind of orchard mcintosh image fruit branches and leaves area obtaining method | |
| CN107694962A (en) | A kind of fruit automatic sorting method based on machine vision and BP neural network | |
| CN113330915B (en) | Self-adaptive cotton harvesting method based on binocular vision recognition and intelligent mechanical harvesting device | |
| CN108064560A (en) | The automatic picker system of fruit and method based on Kinect depth of field cameras | |
| CN102622755A (en) | Plant limb identification method | |
| Adhikari et al. | 3D reconstruction of apple trees for mechanical pruning | |
| CN107309876A (en) | The control method of manipulator harvesting | |
| Rath et al. | Robotic harvesting of Gerbera Jamesonii based on detection and three-dimensional modeling of cut flower pedicels | |
| CN105993393A (en) | Picking method for flower harvesting robot | |
| CN112990103A (en) | String mining secondary positioning method based on machine vision | |
| CN105701812A (en) | Visual identification system suitable for cotton picking robot | |
| Ji et al. | Research on key technology of truss tomato harvesting robot in greenhouse | |
| WO2022222822A1 (en) | Method and device for identifying and positioning abelmoschus manihot on basis of cameras placed in non-parallel manner | |
| Arima et al. | Strawberry harvesting robot on table-top culture | |
| CN109757219A (en) | A kind of view-based access control model picker system and method | |
| CN110175582B (en) | Intelligent tea tree tender shoot identification method based on pixel distribution | |
| CN210093992U (en) | Hawthorn picking robot | |
| CN108718704A (en) | A kind of man-machine interactive field fruits and vegetables harvesting robot system and its collecting method | |
| CN115937314B (en) | Method for detecting growth posture of oil tea fruits | |
| CN207219437U (en) | A kind of strawberry picking vehicle | |
| CN110741790A (en) | Multi-claw transplanting-sorting processing method for plug seedlings based on depth camera | |
| CN113099870B (en) | Self-adaptive flower thinning machine and flower thinning 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190517 |