CN102622755A - Plant limb identification method - Google Patents
Plant limb identification method Download PDFInfo
- Publication number
- CN102622755A CN102622755A CN201210049195XA CN201210049195A CN102622755A CN 102622755 A CN102622755 A CN 102622755A CN 201210049195X A CN201210049195X A CN 201210049195XA CN 201210049195 A CN201210049195 A CN 201210049195A CN 102622755 A CN102622755 A CN 102622755A
- Authority
- CN
- China
- Prior art keywords
- image
- limb
- collects
- plant
- aberration
- 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
Images
Abstract
The invention discloses a plant limb identification method, which includes the following steps: A. obtaining an R-G chromatic aberration image of a collected image; B. utilizing a threshold method to obtain a segmentation image of the R-G chromatic aberration image; C. performing initial denoising on the segmentation image of the R-G chromatic aberration image by using mathematical morphology and area features, and obtaining an initially-denoised chromatic aberration segmentation image; D. processing the initially-denoised chromatic aberration segmentation image respectively according to front-lighting or back-lighting conditions of the collected image; E. performing Hough transformation line detection on the initially-denoised chromatic aberration segmentation image; and F. calculating shape features of different areas of line segmentation obtained through detection of the image, identifying the collected image according to the shape features, and finally obtaining a limb target. The plant limb identification method can identify plant limbs accurately, and can avoid problems such as device damage or fruit tree damage caused by obstacles of the limbs when an apple picking robot performs picking operation.
Description
Technical field
The present invention relates to technical field of image processing, relate in particular to the recognition methods of a kind of plant limb.
Background technology
Apple accounts for 20% of the fruit tree total area as the topmost fruit tree species of China.In the apple production operation, results are plucked 40% of the entire job amount that accounts for.The quality of plucking operation quality directly has influence on storage, processing and the sale of apple, thereby finally influences the market price and economic benefit.Simultaneously, harvest operation is again an operation that labour intensity is big, elapsed time long, work is dull.Along with a large amount of transfers of rural urbanization construction and people in the countryside to the city, be prone to the phenomenon of short-term manpower shortage in the apple maturity stage, the harvesting task that adopts apple picking robot to accomplish apple has good application prospects.
The picking robot technology mainly comprises three aspects: identification positioning technology, harvesting technology and mobile technology.Wherein recognition technology comprises identification and the location to ripening fruits and surrounding environment, and the technology of harvesting mainly is the design and the motion control of mechanical arm, and mobile technology mainly refers to robot navigation's technology.
The realization apple picking robot is plucked apple; The link of most critical be to obtain apple the three-dimensional coordinate position in space with and fruit around the identification and the location of barrier such as limb; It is the three-dimensional reconstruction of apple tree; Thereby, improve the harvesting quality of apple for mechanical arm provides space position parameter accurately.Vision system is one of difficult point of picking robot research, and the accuracy of the three-dimensional reconstruction of apple tree is related to the picking efficiency and harvesting quality of picking robot.
In recent years, domestic and international research personnel study multiple fruit identification and location under field conditions (factors), like citrus, apple and peach etc.In numerous methods, use maximum methods that is based on machine vision, promptly adopt the camera acquisition image, utilize equipment such as computing machine, dsp chip that image is handled, identification and location fruit.Above-mentioned achievement in research has alleviated the influence of available light to a certain extent, has realized the identification and the location of fruit under the natural conditions.
But in plucking operation process, mechanical arm and mechanical arm can with the limb of fruit tree, orchard in support fruit tree " barriers " such as Metallic rod and iron wires bump, thereby make device damage or injure fruit tree.Therefore, only can not satisfy the needs of plucking operation, need discern and locate these " barrier " equally the location of fruit.
Available technology adopting is carried out Ostu (maximum variance between clusters) adaptive threshold to the aberration R-B image of the limb of citrus and is cut apart; Can identify limb; But under the situation of light direct projection, the illumination solar flare causes the image segmentation effect obviously to descend, and is poor to the recognition effect of limb.
Summary of the invention
The technical matters that (one) will solve
The technical matters that the present invention will solve is: the recognition methods of a kind of plant limb is provided; It can identify the limb of plant exactly, and can make apple picking robot when plucking operation, avoid causing because of the obstruction of limb the generation of problems such as device damage or injury fruit tree.
(2) technical scheme
For addressing the above problem, the invention provides the recognition methods of a kind of plant limb, may further comprise the steps:
A: the R-G color difference image of asking for the image that collects;
B: utilize threshold method to obtain the split image of said R-G color difference image;
C: utilize mathematical morphology and area features that the split image of said R-G color difference image is carried out preliminary denoising, obtain the aberration split image of preliminary denoising;
D: respectively according to the said image that collects meet light or the backlight situation is handled the aberration split image of said preliminary denoising;
E: the aberration split image of the said preliminary denoising that the backlight situation is obtained carries out Hough conversion straight-line detection;
F: calculate the shape facility of the zones of different that the aberration split image straight line that obtains to be detected of said preliminary denoising cuts apart, and the said image that collects is discerned, obtain final limb target according to the shape facility of said zones of different.
Preferably, said steps A further comprises: the step that the value of the value of the said image that collects R passage in the RGB color space and G passage is subtracted each other.
Preferably, said step B further comprises: if the pixel value of R-G color difference image between 0～10, is changed to 255 with this pixel value, otherwise, this pixel value is changed to 0 step.
Preferably; Said step D further comprises: if the said image that collects is for meeting light image; Then the aberration split image of said preliminary denoising is not handled; If the said image that collects is the backlight image, then adopt the edge of the aberration split image of the said preliminary denoising of candy operator extraction, obtain its edge image.
Preferably, in the said step e, when carrying out Hough conversion straight-line detection, the angle step of Hough conversion and be respectively 1 degree and 1 pixel apart from step-length detects 5 straight lines of totalizer value maximum.
Preferably; Said step F further comprises: the straight line region is identified as limb; Utilize form parameter
and excentricity
to discern to other zone of being cut apart by straight line; Satisfy F greater than 2.5 and the e step that is identified as limb greater than 4 zone; Wherein, A and B are respectively the area and the girth in zone, and c and a are respectively the border long axis length and the minor axis length in zone.
(3) beneficial effect
The present invention carries out Threshold Segmentation through the aberration R-B image to plant limb; And according to image meet light or the backlight situation is carried out denoising to split image; Can identify the limb of plant exactly, make apple picking robot when plucking operation, avoid causing the generation of problems such as device damage or injury fruit tree because of the obstruction of limb.
Description of drawings
Fig. 1 is the process flow diagram of the recognition methods of plant limb described in the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment, specific embodiments of the invention describes in further detail.Following examples are used to explain the present invention, but are not used for limiting scope of the present invention.
As shown in Figure 1, a kind of plant limb of the present invention recognition methods may further comprise the steps:
A: the R-G color difference image of asking for the image that collects;
In this step, the value of the said image that collects R passage in the RGB color space and the value of G passage are subtracted each other.
B: utilize threshold method to obtain the split image of said R-G color difference image;
In this step, if the pixel value of R-G color difference image is changed to 255 with this pixel value between 0～10, otherwise, this pixel value is changed to 0.
C: utilize mathematical morphology and area features that the split image of said R-G color difference image is carried out preliminary denoising, obtain the aberration split image of preliminary denoising;
In this step, can at first adopt the length of side is that 5 pixels get the square structure element said R-G aberration split image is carried out open and close computing twice, removes small noise spot.R-G aberration split image to removing behind the small noise spot carries out zone marker, and calculates each regional area respectively, removes the zone of area less than maximum region area 1/50, obtains the aberration split image of preliminary denoising.
D: respectively according to the said image that collects meet light or the backlight situation is handled the aberration split image of said preliminary denoising;
In this step; If the said image that collects is for meeting light image; Then the target in the aberration split image of resulting preliminary denoising (pixel value is 255 parts) is limb, and remainder is a background, the aberration split image of said preliminary denoising is not handled; If the said image that collects is the backlight image; Still comprise more noise in the aberration split image of said preliminary denoising, then adopt the edge of the aberration split image of the said preliminary denoising of candy operator extraction, obtain its edge image.
E: the aberration split image of the said preliminary denoising that the backlight situation is obtained carries out Hough conversion straight-line detection;
In this step, when carrying out Hough conversion straight-line detection, the angle step of Hough conversion and be respectively 1 degree and 1 pixel apart from step-length detects 5 straight lines of totalizer value maximum.
In said 5 straight lines; Totalizer is got the pairing straight line of maximum 2 values; The aberration split image of said preliminary denoising is divided into different zones; Said 5 straight line regions are limb, and wherein to get the zone between the pairing straight line of maximum 2 values be trunk to totalizer, and other 3 straight line regions are branch.Outside said 5 straight line regions, there are limb and noise.
F: calculate the shape facility of the zones of different that the aberration split image straight line that obtains to be detected of said preliminary denoising cuts apart, and the said image that collects is discerned, obtain final limb target according to the shape facility of said zones of different.
In this step; Said shape facility has a plurality of parameters; Present embodiment only calculates form parameter and excentricity; The at first form parameter of defined range and excentricity, form parameter
wherein A and B are respectively the area and the girth in zone; Excentricity
wherein c and a is respectively the border long axis length and the minor axis length in zone, and major axis is meant 2 lines of furthest on the zone boundary; On the zone boundary with the line of axis in the longest line segment be called minor axis.
The straight line region is identified as limb; Utilize form parameter
and excentricity
to discern to other zone of being cut apart by straight line, satisfy F greater than 2.5 and e be identified as limb greater than 4 zone.
Above embodiment only is used to explain the present invention; And be not limitation of the present invention; The those of ordinary skill in relevant technologies field under the situation that does not break away from the spirit and scope of the present invention, can also be made various variations and modification; Therefore all technical schemes that are equal to also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.
Claims (6)
1. plant limb recognition methods is characterized in that, may further comprise the steps:
A: the R-G color difference image of asking for the image that collects;
B: utilize threshold method to obtain the split image of said R-G color difference image;
C: utilize mathematical morphology and area features that the split image of said R-G color difference image is carried out preliminary denoising, obtain the aberration split image of preliminary denoising;
D: respectively according to the said image that collects meet light or the backlight situation is handled the aberration split image of said preliminary denoising;
E: the aberration split image of the said preliminary denoising that the backlight situation is obtained carries out Hough conversion straight-line detection;
F: calculate the shape facility of the zones of different that the aberration split image straight line that obtains to be detected of said preliminary denoising cuts apart, and the said image that collects is discerned, obtain final limb target according to the shape facility of said zones of different.
2. plant limb according to claim 1 recognition methods is characterized in that, said steps A further comprises: the step that the value of the value of the said image that collects R passage in the RGB color space and G passage is subtracted each other.
3. plant limb according to claim 1 recognition methods is characterized in that, said step B further comprises: if the pixel value of R-G color difference image between 0～10, is changed to 255 with this pixel value, otherwise, this pixel value is changed to 0 step.
4. plant limb according to claim 1 recognition methods; It is characterized in that; Said step D further comprises: if the said image that collects for meeting light image, is not then handled the aberration split image of said preliminary denoising, be the backlight image as if the said image that collects; Then adopt the edge of the aberration split image of the said preliminary denoising of candy operator extraction, obtain its edge image.
5. plant limb according to claim 1 recognition methods; It is characterized in that, in the said step e, when carrying out Hough conversion straight-line detection; The angle step of Hough conversion and be respectively 1 degree and 1 pixel apart from step-length detects 5 straight lines of totalizer value maximum.
6. plant limb according to claim 1 recognition methods; It is characterized in that; Said step F further comprises: the straight line region is identified as limb; Utilize form parameter
and excentricity
to discern to other zone of being cut apart by straight line; Satisfy F greater than 2.5 and the e step that is identified as limb greater than 4 zone; Wherein, A and B are respectively the area and the girth in zone, and c and a are respectively the border long axis length and the minor axis length in zone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210049195.XA CN102622755B (en) | 2012-02-28 | 2012-02-28 | Plant limb identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210049195.XA CN102622755B (en) | 2012-02-28 | 2012-02-28 | Plant limb identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102622755A true CN102622755A (en) | 2012-08-01 |
| CN102622755B CN102622755B (en) | 2015-01-07 |
Family
ID=46562656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210049195.XA Expired - Fee Related CN102622755B (en) | 2012-02-28 | 2012-02-28 | Plant limb identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102622755B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226709A (en) * | 2013-04-24 | 2013-07-31 | 聊城大学 | Network curtain image recognition method of fall webworm larvae |
| CN103870816A (en) * | 2014-03-26 | 2014-06-18 | 中国科学院寒区旱区环境与工程研究所 | Plant identification method and device with high identification rate |
| CN103996197A (en) * | 2014-05-30 | 2014-08-20 | 北京农业信息技术研究中心 | Character collecting method and system |
| CN106776675A (en) * | 2016-11-01 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of plants identification method and system based on mobile terminal |
| CN106824651A (en) * | 2017-04-11 | 2017-06-13 | 重庆小金人电子商务有限公司 | For the lacquering and stoving varnish device and method of mobile automobile M R service |
| CN107993243A (en) * | 2017-12-21 | 2018-05-04 | 北京林业大学 | A kind of wheat tillering number automatic testing method based on RGB image |
| CN108901540A (en) * | 2018-06-28 | 2018-11-30 | 重庆邮电大学 | Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm |
| CN109522901A (en) * | 2018-11-27 | 2019-03-26 | 中国计量大学 | A kind of tomato plant stalk method for identification of edge based on edge duality relation |
| CN110211133A (en) * | 2019-05-27 | 2019-09-06 | 中国农业大学 | Safeguard tactics acquisition methods, device and electronic equipment with leaf trees |
| CN114027052A (en) * | 2021-10-20 | 2022-02-11 | 华南农业大学 | Illumination regulation and control system for plant reproductive development |
| CN114102591A (en) * | 2021-11-24 | 2022-03-01 | 北京市农林科学院智能装备技术研究中心 | Operation method and device for agricultural robot mechanical arm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101216894A (en) * | 2008-01-08 | 2008-07-09 | 北京林业大学 | A branch identification method based on standing tree occlusion of single image |
| CN102036016A (en) * | 2010-12-03 | 2011-04-27 | 杭州海康威视系统技术有限公司 | Video detection method and system thereof |
-
2012
- 2012-02-28 CN CN201210049195.XA patent/CN102622755B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101216894A (en) * | 2008-01-08 | 2008-07-09 | 北京林业大学 | A branch identification method based on standing tree occlusion of single image |
| CN102036016A (en) * | 2010-12-03 | 2011-04-27 | 杭州海康威视系统技术有限公司 | Video detection method and system thereof |
Non-Patent Citations (3)
| Title |
|---|
| 周小军: "柑橘采摘机器人成熟果实定位及障碍物检测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 30 September 2009 (2009-09-30) * |
| 孙仁山等: "基于整枝抚育目的的立木枝干自动识别研究", 《北京林业大学学报》, 31 July 2005 (2005-07-31) * |
| 尹建军等: "RGB与HIS颜色空间下番茄图像分割的对比研究", 《农机化研究》, 30 November 2006 (2006-11-30) * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226709A (en) * | 2013-04-24 | 2013-07-31 | 聊城大学 | Network curtain image recognition method of fall webworm larvae |
| CN103226709B (en) * | 2013-04-24 | 2015-12-02 | 聊城大学 | A kind of network curtain image recognition method of fall webworm larvae |
| CN103870816A (en) * | 2014-03-26 | 2014-06-18 | 中国科学院寒区旱区环境与工程研究所 | Plant identification method and device with high identification rate |
| CN103870816B (en) * | 2014-03-26 | 2016-11-23 | 中国科学院寒区旱区环境与工程研究所 | The method of the plants identification that a kind of discrimination is high |
| CN103996197A (en) * | 2014-05-30 | 2014-08-20 | 北京农业信息技术研究中心 | Character collecting method and system |
| CN106776675B (en) * | 2016-11-01 | 2020-12-22 | 吴建伟 | Plant identification method and system based on mobile terminal |
| CN106776675A (en) * | 2016-11-01 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of plants identification method and system based on mobile terminal |
| CN106824651A (en) * | 2017-04-11 | 2017-06-13 | 重庆小金人电子商务有限公司 | For the lacquering and stoving varnish device and method of mobile automobile M R service |
| CN106824651B (en) * | 2017-04-11 | 2023-07-14 | 极昊供应链(上海)有限公司 | Paint spraying and baking device and method for mobile automobile maintenance and repair service |
| CN107993243A (en) * | 2017-12-21 | 2018-05-04 | 北京林业大学 | A kind of wheat tillering number automatic testing method based on RGB image |
| CN107993243B (en) * | 2017-12-21 | 2020-06-23 | 北京林业大学 | Wheat tillering number automatic detection method based on RGB image |
| CN108901540A (en) * | 2018-06-28 | 2018-11-30 | 重庆邮电大学 | Fruit tree light filling and fruit thinning method based on artificial bee colony fuzzy clustering algorithm |
| CN109522901A (en) * | 2018-11-27 | 2019-03-26 | 中国计量大学 | A kind of tomato plant stalk method for identification of edge based on edge duality relation |
| CN110211133A (en) * | 2019-05-27 | 2019-09-06 | 中国农业大学 | Safeguard tactics acquisition methods, device and electronic equipment with leaf trees |
| CN110211133B (en) * | 2019-05-27 | 2021-01-15 | 中国农业大学 | Method and device for obtaining safety protection strategy of tree with leaves and electronic equipment |
| CN114027052A (en) * | 2021-10-20 | 2022-02-11 | 华南农业大学 | Illumination regulation and control system for plant reproductive development |
| CN114102591A (en) * | 2021-11-24 | 2022-03-01 | 北京市农林科学院智能装备技术研究中心 | Operation method and device for agricultural robot mechanical arm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102622755B (en) | 2015-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102622755B (en) | Plant limb identification method | |
| CN103947380B (en) | A kind of both arms fruit picking robot and fruit picking method | |
| Jimenez et al. | A survey of computer vision methods for locating fruit on trees | |
| Silwal et al. | Apple identification in field environment with over the row machine vision system | |
| CN103310218B (en) | A kind of overlap blocks fruit precise recognition method | |
| Qingchun et al. | Design of structured-light vision system for tomato harvesting robot | |
| CN107094429A (en) | A kind of multiaxis fruit picking robot | |
| CN108064560A (en) | The automatic picker system of fruit and method based on Kinect depth of field cameras | |
| CN111666883B (en) | Grape picking robot target identification and fruit stalk clamping and cutting point positioning method | |
| CN110599507B (en) | Tomato identification and positioning method and system | |
| CN105719282B (en) | A kind of orchard mcintosh image fruit branches and leaves area obtaining method | |
| CN103295018A (en) | Method for precisely recognizing fruits covered by branches and leaves | |
| CN103177257A (en) | Image identification method and image classification method for coprinus comatus | |
| Adhikari et al. | 3D reconstruction of apple trees for mechanical pruning | |
| CN112990103A (en) | String mining secondary positioning method based on machine vision | |
| Zhao et al. | An end-to-end lightweight model for grape and picking point simultaneous detection | |
| Chen et al. | Segmentation of field grape bunches via an improved pyramid scene parsing network | |
| CN112329506A (en) | Fruit identification method and system, and positioning method and system of wolfberry picking robot | |
| Jin et al. | Far-near combined positioning of picking-point based on depth data features for horizontal-trellis cultivated grape | |
| Li et al. | Identification of the operating position and orientation of a robotic kiwifruit pollinator | |
| CN108090910B (en) | Night outdoor tomato plant image segmentation algorithm based on information entropy gradient simplified PCNN model | |
| CN103226709A (en) | Network curtain image recognition method of fall webworm larvae | |
| CN211020054U (en) | Fruit and vegetable picking device | |
| Quan et al. | Selecting candidate regions of clustered tomato fruits under complex greenhouse scenes using RGB-D data | |
| CN115937314A (en) | Camellia oleifera fruit growth posture detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150107 Termination date: 20190228 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |