CN108271531A - The fruit automation picking method and device of view-based access control model identification positioning - Google Patents
The fruit automation picking method and device of view-based access control model identification positioning Download PDFInfo
- Publication number
- CN108271531A CN108271531A CN201711476528.6A CN201711476528A CN108271531A CN 108271531 A CN108271531 A CN 108271531A CN 201711476528 A CN201711476528 A CN 201711476528A CN 108271531 A CN108271531 A CN 108271531A
- Authority
- CN
- China
- Prior art keywords
- fruit
- image
- target
- crawl
- gripper
- 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.)
- Granted
Links
Classifications
-
- 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
- A01D46/30—Robotic devices for individually picking crops
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Harvesting Machines For Specific Crops (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of fruit automation picking methods of view-based access control model identification positioning and device, method to include the following steps：S1, Color Image Acquisition；S2, extraction tri- single channel gray level images of RGB；S3, the apparent single channel image of the component that gets colors；S4, image preprocessing；S5, judge whether there is fruit target in image；S6, coordinate of the fruit target in computer pixel coordinate system is obtained；S7, by pixel coordinate conversion be world coordinate system coordinate；S8, the planar movement amount for calculating crawl gripper；S9, control crawl gripper movement, make fruit target be located at video camera imaging planar central；S10, control crawl gripper are moved forward perpendicular to imaging plane；S11, crawl fruit target, cut off carpopodium；S12, crawl gripper unclamp, and fruit falls into collecting box.The present invention, to determine fruit target, and accurately picks target following positioning to be accurately positioned the position of fruit by image procossing and characteristic matching to guide, and reduces fruit surface and damages.
Description
Technical field
The invention belongs to the technical fields of fruit picking, and in particular to a kind of fruit automation of view-based access control model identification positioning
Picking method and device.
Background technology
The harvesting of this kind of seasonal fruit of apple need to be completed in a short time, this work is mainly manually complete at present
At cost of labor accounts for a big chunk of entire production cost.In order to reduce labor cost, propose in the related technology several
The scheme of Mechaniaed harvest fruit, still, the solution of most of mechanizations can not accurately determine the position of fruit in picking
It will produce impact when setting, thus picking and fruit surface caused to damage, so that the product of harvest is reduced quality, especially as apple etc.
Fruit, it is necessary to avoid the bruise of fruit.
Invention content
A kind of fruit of view-based access control model identification positioning is provided it is an object of the invention to avoid in the prior art insufficient
Picking method and device are automated, the position of fruit is determined by image processing and analysis, is accurately picked with guiding,
It is damaged to reduce the fruit surface caused by picking impact.
The purpose of the present invention is achieved through the following technical solutions：
A kind of fruit automation picking method of view-based access control model identification positioning is provided, picker, the picking are applied to
Device includes folding type mechanical arm, is set to crawl gripper, cutter and the video camera of folding type mechanical arm end, described to adopt
The method of plucking includes the following steps：
S1, picking fruit tree progress Color Image Acquisition is treated using video camera；
Tri- single channel gray level images of RGB of the coloured image obtained in S2, extraction step S1；
S3, the color component feature according to fruit, color component in tri- single channel gray level images of RGB in selecting step S2
Apparent single channel image；
S4, image preprocessing is carried out to the single channel image chosen in step S3；
S5, the extraction that characteristics of image is carried out to pretreated image in step S4, by extraction result and training sample database
Characteristic matching is carried out, judges whether there is fruit target in image, if the terminal position for adjusting folding type mechanical arm without if, returns
Step S1 is returned, if there is then entering step S6；
S6, coordinate and picture centre coordinate of the fruit target in computer pixel coordinate system are obtained；
S7, coordinate of each fruit target obtained in step S6 in computer pixel coordinate system is transformed to world coordinates
Coordinate in system；
S8, the coordinate according to the fruit target obtained in step S7 in world coordinate system, in conjunction with the ratio of camera calibration
The example factor and pixel coordinate mathematic interpolation are set to the planar movement amount Δ x and Δ of the crawl gripper of folding type mechanical arm end
y；
S9, control crawl gripper mobile Δ x and Δ y in the plane parallel with imaging plane, make fruit target be located at
Video camera imaging planar central；
S10, control crawl gripper are moved forward perpendicular to imaging plane, measure fruit target and crawl when mobile in real time
The distance between gripper；
S11, crawl gripper close up crawl fruit target, and control cutter cut-out carpopodium；
S12, crawl gripper unclamp, and fruit falls into collecting box；
If there are two above fruit target, return to step S8, until by other fruit mesh in image in S13, image
Mark picking finishes.
As a further improvement, the step S4 specifically includes following sub-step：
S41, denoising is carried out to image；
S42, enhancing processing is carried out to image；
S43, binary conversion treatment is carried out to image.
As a further improvement, the step S5 is specially：
Whether judge has fruit target to be based on circularity in image calculates progress, and circularity is according to extracted characteristics of image area
Area, the circumference calculating in domain obtain, and calculation formula is：
E=(4 π × S)/L2；
Wherein e is circularity, and S is area, and L is perimeter；
The threshold value of e is set, when the circularity of extracted image characteristic region is less than the threshold value of setting, it is believed that be the back of the body
Scene area, when the circularity of extracted image characteristic region is more than the threshold value of setting, then it is assumed that it is to have fruit target area, from
Fruit target is separated in image.
As a further improvement, the step S6 specifically includes following sub-step：
S61, video camera is demarcated；
S62, limit correction is carried out to obtaining image；
S63, the computer picture coordinate for obtaining fruit target.
As a further improvement, in the step S8, if Δ x<A, Δ y<B, wherein A, B are the folding that system gives
The offset displacement of formula mechanical arm, then carry out next step, and otherwise folding type mechanical arm moves, and is back to step S1.
As a further improvement, in the step S8, the imaging size of fruit target in the picture and camera to water
The distance of fruit target is inversely proportional, according to this relationship calculate fruit target between gripper it is rough at a distance from.
As a further improvement, in the step S10, fruit and crawl machinery are measured using ultrasonic distance-measuring sensor
The distance between pawl Δ d, as Δ d<When C, folding type mechanical arm stop motion is controlled, wherein C is the given crawl machinery of system
Displacement between pawl and fruit.
As a further improvement, crawl gripper close up crawl fruit target when, according to be set to crawl gripper with
The pressure signal size that pressure sensor between fruit target is fed back, control crawl gripper stopping is closed up, and is controlled and cut
Cutter, which is started to work, cuts off carpopodium.
The present invention also provides a kind of fruit of view-based access control model identification positioning to automate picker, and the picker includes
Folding type mechanical arm, crawl gripper, cutter and the video camera for being set to folding type mechanical arm end, the picker are adopted
Fruit picking is carried out with picking method as described above.
The fruit of view-based access control model identification positioning provided by the invention automates picking method, is applied to picker, described
Picker includes folding type mechanical arm, is set to crawl gripper, cutter and the video camera of folding type mechanical arm end, institute
Picking method is stated to include the following steps：S1, picking fruit tree progress Color Image Acquisition is treated using video camera；S2, extraction step
Tri- single channel gray level images of RGB of the coloured image obtained in S1；S3, the color component feature according to fruit, selecting step
The apparent single channel image of color component in tri- single channel gray level images of RGB in S2；S4, the single channel to being chosen in step S3
Image carries out image preprocessing；S5, the extraction that characteristics of image is carried out to pretreated image in step S4, will extraction result with
Training sample database carries out characteristic matching, judges whether there is fruit target in image, if adjusting folding type mechanical arm without if
Terminal position, return to step S1, if there is then entering step S6；S6, fruit target is obtained in computer pixel coordinate system
Coordinate and picture centre coordinate；S7, coordinate of each fruit target obtained in step S6 in computer pixel coordinate system is become
The coordinate being changed in world coordinate system；S8, the coordinate according to the fruit target obtained in step S7 in world coordinate system, in conjunction with
The scale factor and pixel coordinate mathematic interpolation of camera calibration are set to the flat of the crawl gripper of folding type mechanical arm end
Face amount of movement Δ x and Δ y；Δ x and Δ are moved in S9, the end for controlling folding type mechanical arm in the plane parallel with imaging plane
Y makes fruit target be located at video camera imaging planar central；S10, control folding type mechanical arm ending vertical in imaging plane to
Preceding movement measures the distance between fruit target and crawl gripper in real time when mobile；S11, crawl gripper close up crawl water
Fruit target, and control cutter cut-out carpopodium；S12, crawl gripper unclamp, and fruit falls into collecting box.If having in S13, image
More than two fruit targets, return to step S8, until other fruit targets picking in image is finished.The picking of the present invention
The coloured image that method treats picking fruit tree carries out correct image processing and analysis, according to image procossing and characteristic matching come really
Determine the accurate location of fruit target, and folding type mechanical arm is guided to complete automation picking work.The present invention realizes fruit
The automation control of intelligent recognition, positioning and mechanical arm is picked, and the accuracy and efficiency of picking is improved, and is reduced because picking is rushed
Fruit surface damages caused by hitting, and greatly reduces hand labor cost.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the flow chart of the fruit automation picking method of view-based access control model identification positioning.
Fig. 2 is the structural schematic diagram of the fruit automation picker of view-based access control model identification positioning.
Specific implementation mode
It is below in conjunction with the accompanying drawings and specific real in order to make those skilled in the art more fully understand technical scheme of the present invention
Applying example, the present invention is described in further detail, it should be noted that in the absence of conflict, embodiments herein and
Feature in embodiment can be combined with each other.
As depicted in figs. 1 and 2, the fruit automation picking of a kind of view-based access control model identification positioning provided in an embodiment of the present invention
Method is applied to picker, includes mainly Image Acquisition, image conversion, image procossing, fruit target identification, fruit target
Positioning, computer machinery claw amount of movement, gripper movement, ranging, crawl fruit target cut off carpopodium, complete the processes such as acquisition.Institute
Picker is stated to include folding type mechanical arm 1, the crawl gripper 2 that is set to 1 end of folding type mechanical arm, cutter 3 and take the photograph
Camera 11, video camera 11 are located at the posterior central of crawl gripper 2, and when capturing the opening of gripper 2, video camera 11 can shoot and grab
The image in 2 front of gripper is taken, cutter 3 are located at the top of crawl gripper 2, after crawl gripper 2 closes up crawl fruit,
Cutter 3 can cut carpopodium.The picking method includes the following steps：
S1, using video camera picking fruit tree progress Color Image Acquisition is treated from distant view；Since the color characteristic of fruit has
Institute is different, in order to extract the color component of fruit in coloured image, therefore acquires coloured image.
Tri- single channel gray level images of RGB of the coloured image obtained in S2, extraction step S1；
S3, the color component feature according to fruit, color component in tri- single channel gray level images of RGB in selecting step S2
Apparent single channel image；
S4, image preprocessing is carried out to the single channel image chosen in step S3；Image preprocessing specifically includes following son
Step：S41, denoising is carried out to image；S42, enhancing processing is carried out to image；S43, binary conversion treatment is carried out to image.
S5, the extraction that characteristics of image is carried out to pretreated image in step S4, by extraction result and training sample database
Characteristic matching is carried out, judges whether there is fruit target in image, if the terminal position for adjusting folding type mechanical arm 1 without if,
Return to step S1, if there is then entering step S6；Whether there is fruit target to be based on circularity in judging image and calculates progress, circle
Shape degree is obtained according to area, the circumference calculating of extracted image characteristic region, and calculation formula is：
E=(4 π × S)/L2；
Wherein e is circularity, and S is area, and L is perimeter；
It is as round when e is 1, a threshold value is set at first, for example apple is close to circle, and leaf is not
It is round, so the threshold value of e is set, when the circularity e of extracted image characteristic region is less than the threshold value of setting, system
It is considered background area, is set as white, when the circularity e of extracted image characteristic region is more than the threshold value of setting, then it is assumed that
It is the emerging region (fruit target area) of sense, fruit target is separated from image.
S6, coordinate and picture centre coordinate of the fruit target in computer pixel coordinate system are obtained, calculates fruit target
Centre coordinate and imaging plane centre coordinate difference；The step S6 specifically includes following sub-step：S61, video camera is carried out
Calibration；S62, limit correction is carried out to obtaining image；S63, the computer picture coordinate for obtaining fruit target.
S7, coordinate of each fruit target obtained in step S6 in computer pixel coordinate system is transformed to world coordinates
Coordinate in system；
S8, the coordinate according to the fruit target obtained in step S7 in world coordinate system, in conjunction with the ratio of camera calibration
Example the factor and pixel coordinate mathematic interpolation be set to 1 end of folding type mechanical arm crawl gripper 2 planar movement amount Δ x and
Δy；If Δ x<A, Δ y<B, wherein A, B are the offset displacement for the folding type mechanical arm that system gives, then carry out in next step
Suddenly, otherwise folding type mechanical arm moves, and is back to step S1.Since the imaging size of fruit target in the picture is arrived with camera
The distance of fruit target is inversely proportional, can also be calculated according to this relationship fruit target it is rough between gripper at a distance from.
Δ x and Δ y is moved in S9, the end for controlling folding type mechanical arm 1 in the plane parallel with imaging plane, makes fruit
Target is located at video camera imaging planar central；
S10, the ending vertical for controlling folding type mechanical arm 1 are moved forward in imaging plane, and fruit is measured in real time when mobile
Target and crawl the distance between gripper, specifically usable ultrasonic distance-measuring sensor 10 measure fruit and crawl gripper it
Between distance, delta d, as Δ d<When C, control folding type mechanical arm stop motion, wherein C be the given crawl gripper of system with
Displacement between fruit.
S11, crawl gripper close up crawl fruit target, and control cutter cut-out carpopodium；Crawl gripper, which closes up, grabs
When fruit target of fetching water, according to the pressure signal that is fed back of pressure sensor 9 being set between crawl gripper and fruit target
Size, control crawl gripper stopping are closed up, and control cutter start-up operation cut-out carpopodium.
S12, crawl gripper unclamp, and fruit falls into collecting box.
If there are two above fruit target, return to step S8, until by other fruit mesh in image in S13, image
Mark picking finishes.
The coloured image that the picking method of the present invention treats picking fruit tree carries out correct image processing and analysis, according to figure
The accurate location of fruit target is determined as processing and characteristic matching, to guide folding type mechanical arm to complete automation picking work
Make.The present invention realizes intelligent recognition, positioning and the automation control picking of mechanical arm of fruit, improves the accurate of picking
Property and efficiency, reduce because pick impact caused by fruit surface damage, greatly reduce hand labor cost.
As shown in Fig. 2, the embodiment of the present invention also provides a kind of fruit automation picker of view-based access control model identification positioning,
The picker includes folding type mechanical arm 1, controller 8, the crawl gripper 2 for being set to 1 end of folding type mechanical arm, cuts
Cutter 3, pressure sensor 9, ultrasonic distance-measuring sensor 10 and video camera 11.The video camera 11 is located at crawl gripper 2
Posterior central, when capturing the opening of gripper 2, video camera 11 can shoot the image in 2 front of crawl gripper, capture gripper
2 center is located on image center line, and the cutter 3 are located at the top of crawl gripper 2, and crawl gripper 2 closes up crawl
After fruit, cutter 3 can cut carpopodium.The arm joint and drive phase that the folding type mechanical arm 1 is hinged by three sections
The arm joint driver composition that adjacent arms section relatively rotates, arm joint driver can be decelerating motor or oil cylinder or cylinder.It is described collapsible
The end of mechanical arm 1 is provided with crawl gripper 2 and cutter 3, and the cutter 3 are arranged in the top of crawl gripper 2, institute
It states crawl gripper 2 to open or close up under the action of capturing driver, crawl driver can be motor or cylinder.The cutting
Knife 3 stretches under the action of cutting driver, and cutting driver can be motor or cylinder.The butt of the folding type mechanical arm 1
It is provided with mounting flange 7, mounting flange 7 is used to entire fruit picker being fixedly mounted on collecting cart.The folding
Each arm joint of stacked mechanical arm 1 is hollow structure, and opposite both sides are respectively arranged with one and are extended to from end inside arm joint
The soft conveyer belt 4 of butt, soft conveyer belt 4 are closed loop configuration, and zone face is soft material, and the both ends of soft conveyer belt 4 pass through
Roller tensioning, the soft conveyer belt 4 is supported to be moved from the end of arm joint to butt under the action of feed drive device, conveying is driven
Dynamic device can be decelerating motor.Roller is moved there are one in each soft conveyer belt 4 based on support roller, the driving of feed drive device is actively
Roller rotation is to drive soft conveyer belt 4 to move.The end of soft conveyer belt 4 in each arm joint is sequentially connected, wherein least significant end
Arm joint in the arrival end of soft conveyer belt 4 be arranged in the lower section of crawl gripper 2, lower section is soft defeated in least significant end arm joint
Send band 4 more slightly longer than the soft conveyer belt 4 of top, the soft conveyer belt 4 of lower section is located at the lower section of crawl gripper 2, most butt
The outlet end of soft conveyer belt 4 in arm joint is connected with fruit delivery outlet 5.It is propped up by elasticity the end of the soft conveyer belt 4
Support wheel 6 is supported on the inside of arm joint.For the wheel shaft of resilient support wheel 6 by spring supporting on the inside of arm joint, resilient support wheel 6 can edge
It is moved perpendicular to the direction of arm joint medial surface, when the fruit conveyed in soft conveyer belt 4 is larger, fruit passes through soft conveyer belt
When 4 end, fruit can open-top resilient support wheel 6 pass through, spring-compressed at this time, after fruit passes through, soft conveyer belt 4
End reset under the action of the spring.The surface of the soft conveyer belt 4 is provided with hairbrush layer.Hairbrush layer can preferably drive
Fruits, and provide preferable protection to fruit.After the fruit for capturing the crawl of gripper 2 cuts off carpopodium by cutter 3, grab
Gripper 2 is taken to unclamp, fruit drops in the arrival end of the soft conveyer belt 4 in the arm joint of least significant end, in the defeated of soft conveyer belt 4
It send under effect, fruit passes sequentially through each arm joint, is finally exported from fruit delivery outlet 5 to collecting cart.Due in folding type mechanical
Soft conveyer belt is provided in arm, the fruit after picking can be transported to ground via soft conveyer belt, and the fruit of picking will not be straight
It connects under placement in height, avoids damage of the fruit in picking process, reduce fruit bruising while realizing Mechaniaed harvest.
The controller 8 and arm joint driver, crawl driver, cutting driver, pressure sensor 9, ultrasonic ranging
Sensor 10, video camera 11 connect, and 8 plug-in of controller carries out automation fruit to realize picking method as described above
Picking.Specifically, controller 8 sends out control signal control arm joint driver, crawl driver, cutting driver action, in turn
It controls folding type mechanical arm 1, crawl gripper 2 and cutter 3 to act, realizes automatically controlling for whole device.In addition, pressure passes
Sensor 9 is arranged in the crawl gripper 2, and pressure sensor 9 is used to detect the clamping pressure that crawl gripper 2 is applied to fruit
Power, controller 8 is according to the size of clamp pressure to determine whether clip or clamp pressure is excessive, and controller 8 is according to clamp pressure
Control crawl driver action, ensures fruit firm grip, while also avoiding clamp pressure excessive and damaged fruit.In addition, institute
Ultrasonic distance-measuring sensor 10 is stated for detecting the end of folding type mechanical arm 1 at a distance from fruit, controller 8 is controlled according to distance
Arm joint driver action processed captures fruit convenient for crawl gripper 2.
Many details are elaborated in above description to facilitate a thorough understanding of the present invention, still, the present invention can be with
Implemented different from other modes described here using other, it is thus impossible to be interpreted as limiting the scope of the invention.
In short, although the present invention lists above-mentioned preferred embodiment, although it should be noted that those skilled in the art
Member can carry out various change and remodeling, unless such variation and remodeling deviate from the scope of the present invention, otherwise should all wrap
It includes within the scope of the present invention.
Claims (9)
1. a kind of fruit of view-based access control model identification positioning automates picking method, it is applied to picker, the picker packet
Include folding type mechanical arm (1), the crawl gripper (2) for being set to folding type mechanical arm (1) end, cutter (3) and video camera
(11), which is characterized in that the picking method includes the following steps：
S1, picking fruit tree progress Color Image Acquisition is treated using video camera；
Tri- single channel gray level images of RGB of the coloured image obtained in S2, extraction step S1；
S3, the color component feature according to fruit, color component is apparent in tri- single channel gray level images of RGB in selecting step S2
Single channel image；
S4, image preprocessing is carried out to the single channel image chosen in step S3；
S5, the extraction that characteristics of image is carried out to pretreated image in step S4, extraction result and training sample database are carried out
Characteristic matching judges whether there is fruit target in image, if the terminal position for adjusting folding type mechanical arm (1) without if, returns
Step S1 is returned, if there is then entering step S6；
S6, coordinate and picture centre coordinate of the fruit target in computer pixel coordinate system are obtained；
S7, coordinate of each fruit target obtained in step S6 in computer pixel coordinate system is transformed in world coordinate system
Coordinate；
S8, the coordinate according to the fruit target obtained in step S7 in world coordinate system, in conjunction with camera calibration ratio because
Son and pixel coordinate mathematic interpolation be set to folding type mechanical arm (1) end crawl gripper (2) planar movement amount Δ x and
Δy；
S9, control crawl gripper (2) the mobile Δ x and Δ y in the plane parallel with imaging plane, make fruit target be located at and take the photograph
Camera imaging plane center；
S10, control crawl gripper (2) are moved forward perpendicular to imaging plane, measure fruit target and crawl when mobile in real time
The distance between gripper；
S11, crawl gripper close up crawl fruit target, and control cutter cut-out carpopodium；
S12, crawl gripper unclamp, and fruit falls into collecting box；
If there are two above fruit target, return to step S8 in S13, image, until other fruit targets in image are adopted
It plucks and finishes.
2. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, it is characterised in that：It is described
Step S4 specifically includes following sub-step：
S41, denoising is carried out to image；
S42, enhancing processing is carried out to image；
S43, binary conversion treatment is carried out to image.
3. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, it is characterised in that：It is described
Step S5 is specially：
Whether judge has fruit target to be based on circularity in image calculates progress, and circularity is according to extracted image characteristic region
Area, circumference calculating obtain, and calculation formula is：
E=(4 π × S)/L2；
Wherein e is circularity, and S is area, and L is perimeter；
The threshold value of e is set, when the circularity of extracted image characteristic region is less than the threshold value of setting, it is believed that be background area
Domain, when the circularity of extracted image characteristic region is more than the threshold value of setting, then it is assumed that be to have fruit target area, from image
It is middle that fruit target is separated.
4. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, it is characterised in that：It is described
Step S6 specifically includes following sub-step：
S61, video camera is demarcated；
S62, limit correction is carried out to obtaining image；
S63, the computer picture coordinate for obtaining fruit target.
5. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, which is characterized in that described
In step S8, if Δ x<A, Δ y<B, wherein A, B are the offset displacement for the folding type mechanical arm that system gives, then carry out down
One step, otherwise the movement of folding type mechanical arm, is back to step S1.
6. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, which is characterized in that described
In step S8, the imaging size of fruit target in the picture is inversely proportional at a distance from camera to fruit target, according to this relationship
Calculate fruit target it is rough between gripper at a distance from.
7. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, which is characterized in that described
In step S10, the distance between fruit and crawl gripper Δ d are measured using ultrasonic distance-measuring sensor, as Δ d<When C, control
Folding type mechanical arm stop motion processed, wherein C are the displacements between system given crawl gripper and fruit.
8. the fruit of view-based access control model identification positioning according to claim 1 automates picking method, which is characterized in that described
In step S11, when crawl gripper closes up crawl fruit target, according to the pressure being set between crawl gripper and fruit target
The pressure signal size that force snesor is fed back, control crawl gripper stopping is closed up, and controls cutter start-up operation cut-out
Carpopodium.
9. a kind of fruit of view-based access control model identification positioning automates picker, which is characterized in that the picker includes folding
Stacked mechanical arm (1), the crawl gripper (2) for being set to folding type mechanical arm (1) end, cutter (3) and video camera (11),
The picker uses picking method described in any item of the claim 1 to 8 such as to carry out fruit picking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711476528.6A CN108271531B (en) | 2017-12-29 | 2017-12-29 | The fruit automation picking method and device of view-based access control model identification positioning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711476528.6A CN108271531B (en) | 2017-12-29 | 2017-12-29 | The fruit automation picking method and device of view-based access control model identification positioning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108271531A true CN108271531A (en) | 2018-07-13 |
| CN108271531B CN108271531B (en) | 2019-10-01 |
Family
ID=62802789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711476528.6A Active CN108271531B (en) | 2017-12-29 | 2017-12-29 | The fruit automation picking method and device of view-based access control model identification positioning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108271531B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109451995A (en) * | 2018-12-29 | 2019-03-12 | 贺州学院 | A kind of picking control method, device and device for picking |
| CN109531533A (en) * | 2018-11-30 | 2019-03-29 | 北京海益同展信息科技有限公司 | A kind of computer room cruising inspection system and its working method |
| CN110178547A (en) * | 2019-06-24 | 2019-08-30 | 东北林业大学 | A kind of Cone picking equipment |
| CN110192472A (en) * | 2019-03-25 | 2019-09-03 | 山东交通学院 | Both arms apple-picking circle is classified collecting robot people |
| CN112124825A (en) * | 2020-09-22 | 2020-12-25 | 同济大学 | Mechanical claw positioning control system of garbage transfer equipment |
| CN112136505A (en) * | 2020-09-07 | 2020-12-29 | 华南农业大学 | Fruit picking sequence planning method based on visual attention selection mechanism |
| CN112197705A (en) * | 2020-10-16 | 2021-01-08 | 中国农业科学院农业资源与农业区划研究所 | Fruit positioning method based on vision and laser ranging |
| CN113615398A (en) * | 2021-10-11 | 2021-11-09 | 深圳市越疆科技有限公司 | Fruit stem positioning and fruit picking method, device, robot and medium |
| CN113920056A (en) * | 2021-08-31 | 2022-01-11 | 北京影谱科技股份有限公司 | Method and device for controlling mechanical arm to shoot object |
| CN114228850A (en) * | 2021-11-25 | 2022-03-25 | 蒙光深 | Bell milk crystal salt automatic acquisition vehicle for salt pan |
| US20220193914A1 (en) * | 2019-04-11 | 2022-06-23 | Shanghai Jiao Tong University | Method and device for collaborative servo control of motion vision of robot in uncalibrated agricultural scene |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034440A (en) * | 2007-01-12 | 2007-09-12 | 浙江工业大学 | Identification method for spherical fruit and vegetables |
| CN101807247A (en) * | 2010-03-22 | 2010-08-18 | 中国农业大学 | Fine-adjustment positioning method of fruit and vegetable picking point |
| CN104067781A (en) * | 2014-06-16 | 2014-10-01 | 华南农业大学 | Virtual robot and real robot integration based picking system and method |
-
2017
- 2017-12-29 CN CN201711476528.6A patent/CN108271531B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101034440A (en) * | 2007-01-12 | 2007-09-12 | 浙江工业大学 | Identification method for spherical fruit and vegetables |
| CN101807247A (en) * | 2010-03-22 | 2010-08-18 | 中国农业大学 | Fine-adjustment positioning method of fruit and vegetable picking point |
| CN104067781A (en) * | 2014-06-16 | 2014-10-01 | 华南农业大学 | Virtual robot and real robot integration based picking system and method |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109531533A (en) * | 2018-11-30 | 2019-03-29 | 北京海益同展信息科技有限公司 | A kind of computer room cruising inspection system and its working method |
| CN109531533B (en) * | 2018-11-30 | 2019-11-05 | 北京海益同展信息科技有限公司 | A kind of computer room cruising inspection system and its working method |
| WO2020107957A1 (en) * | 2018-11-30 | 2020-06-04 | 北京海益同展信息科技有限公司 | Machine room patrol system and working method therefor |
| CN109451995A (en) * | 2018-12-29 | 2019-03-12 | 贺州学院 | A kind of picking control method, device and device for picking |
| CN110192472A (en) * | 2019-03-25 | 2019-09-03 | 山东交通学院 | Both arms apple-picking circle is classified collecting robot people |
| CN110192472B (en) * | 2019-03-25 | 2024-02-27 | 山东交通学院 | Round grading collection robot for picking apples with two arms |
| US20220193914A1 (en) * | 2019-04-11 | 2022-06-23 | Shanghai Jiao Tong University | Method and device for collaborative servo control of motion vision of robot in uncalibrated agricultural scene |
| CN110178547A (en) * | 2019-06-24 | 2019-08-30 | 东北林业大学 | A kind of Cone picking equipment |
| CN112136505A (en) * | 2020-09-07 | 2020-12-29 | 华南农业大学 | Fruit picking sequence planning method based on visual attention selection mechanism |
| CN112124825A (en) * | 2020-09-22 | 2020-12-25 | 同济大学 | Mechanical claw positioning control system of garbage transfer equipment |
| CN112197705A (en) * | 2020-10-16 | 2021-01-08 | 中国农业科学院农业资源与农业区划研究所 | Fruit positioning method based on vision and laser ranging |
| CN113920056A (en) * | 2021-08-31 | 2022-01-11 | 北京影谱科技股份有限公司 | Method and device for controlling mechanical arm to shoot object |
| CN113615398B (en) * | 2021-10-11 | 2022-03-11 | 深圳市越疆科技有限公司 | Fruit stem positioning and fruit picking method, device, robot and medium |
| CN113615398A (en) * | 2021-10-11 | 2021-11-09 | 深圳市越疆科技有限公司 | Fruit stem positioning and fruit picking method, device, robot and medium |
| CN114228850A (en) * | 2021-11-25 | 2022-03-25 | 蒙光深 | Bell milk crystal salt automatic acquisition vehicle for salt pan |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108271531B (en) | 2019-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108271531B (en) | The fruit automation picking method and device of view-based access control model identification positioning | |
| CN109063575B (en) | Intelligent mower autonomous and orderly mowing method based on monocular vision | |
| Hannan et al. | Current developments in automated citrus harvesting | |
| US11134617B2 (en) | Self-guided blossom picking device | |
| CN101807247B (en) | Fine-adjustment positioning method of fruit and vegetable picking point | |
| CA3024573C (en) | Bale detection and classification using stereo cameras | |
| EP2086308B1 (en) | Autonomous fruit picking machine | |
| AU2017228929A1 (en) | A robotic harvester | |
| CN111758395A (en) | Prickly ash picking device and prickly ash vision picking robot that constitutes thereof | |
| CN116686545B (en) | Litchi picking robot shade removing method based on machine vision control | |
| CN106327467A (en) | Method for quickly tracking and indentifying target fruits picked by apple picking robot | |
| CN109453500A (en) | Ball picking robot | |
| CN109618670B (en) | Intelligent robot for picking and sorting fruits and vegetables | |
| CN113615398B (en) | Fruit stem positioning and fruit picking method, device, robot and medium | |
| CN108470165A (en) | A kind of picking robot fruit vision collaboratively searching method | |
| CN208016381U (en) | A kind of fruit and vegetable picking machinery | |
| CN106233937A (en) | A kind of array extension type mechanical arm kiwifruit fruit picking robot | |
| CN110431999B (en) | Gantry type automatic fruit harvesting robot | |
| CN110414384B (en) | Intelligent rice and wheat harvester leading line tracking method | |
| Feng et al. | Fruit Location And Stem Detection Method For Strawbery Harvesting Robot | |
| CN210093992U (en) | Hawthorn picking robot | |
| CN114600641B (en) | Strawberry picking machine based on image recognition technology and picking method thereof | |
| JP3396920B2 (en) | Harvesting robot imaging method | |
| CN117104870A (en) | Equipment for grabbing unordered stacked soles by mechanical arm | |
| Cao et al. | Basic Study on Strawberry Harvesting Robot (Part I):—Algorithm for Locating and Feature Extracting of Strawberry Fruits— |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |