CN107950402A - Milker autocontrol method based on binocular vision - Google Patents
Milker autocontrol method based on binocular vision Download PDFInfo
- Publication number
- CN107950402A CN107950402A CN201711230544.7A CN201711230544A CN107950402A CN 107950402 A CN107950402 A CN 107950402A CN 201711230544 A CN201711230544 A CN 201711230544A CN 107950402 A CN107950402 A CN 107950402A
- Authority
- CN
- China
- Prior art keywords
- flat image
- milker
- breast
- binocular vision
- cow
- 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
- A01J—MANUFACTURE OF DAIRY PRODUCTS
- A01J5/00—Milking machines or devices
- A01J5/007—Monitoring milking processes; Control or regulation of milking machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Animal Husbandry (AREA)
- Environmental Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of milker autocontrol method based on binocular vision, comprises the following steps：The binocular camera fixed by being arranged on milking area's relative position shoots first flat image and the second flat image in cow breast region；First flat image and second flat image are handled using binocular vision Processing Algorithm, establish the three dimensional coordinate space of the cow breast；According to the specific knowledge feature of mammilla of milk cattle, the positional information of 4 nipples of cow breast in three coordinate spaces is exported, and 4 breast cups of milker are sleeved on 4 nipples of milk cow according to 4 teat placement information.
Description
Technical field
The invention belongs to technical field of machine vision, more particularly to a kind of three-dimensional cognitive approach based on binocular identification.
Background technology
With the development of machine recognition technology, much fields have been applied to machine vision cognition at present.Traditional machine
Identification includes robotic arm positioning, intelligent vehicle navigation, even avoiding barrier, recognition of face, fingerprint recognition etc..However, institute
Have current mechanical recognition system all there are one it is inevitable the defects of, be exactly that recognition speed is slow, error rate is higher.Therefore,
How the fast and effective performance that must improve Machine Vision Recognition, become this area technical problem urgently to be resolved hurrily.
Promote IT application, transform aquaculture tradition milking processes with image processing techniques, improve aquaculture synthesized competitiveness,
It is the important directions of current animal husbandry economy development, and one of hot issue of academia and business circles research.Cow producing milk
Mechanization be modernization dairy cow farm in essential link.Traditional milking processes are by manual type by milker
4 breast cups be sleeved on 4 nipples of milk cow, it is slow to be primarily due to manual operation speed, often due to milk cow in real work
Feed lot scale is big, less efficient；Secondly, manually-operated intervention, easily causes to frighten to milk cow.
The content of the invention
The purpose of the present invention is exactly to overcome the above-mentioned drawback mentioned in the prior art, there is provided a kind of recognition accuracy is high, speed
The fast milker autocontrol method based on binocular vision of degree.
In order to achieve the above object, the present invention takes following technical scheme：
A kind of milker autocontrol method based on binocular vision, comprises the following steps：
The binocular camera fixed by being arranged on milking area's relative position shoots first plan in cow breast region
Picture and the second flat image；
First flat image and second flat image are handled using binocular vision Processing Algorithm, established
The three dimensional coordinate space of the cow breast；
According to the specific knowledge feature of mammilla of milk cattle, the position of 4 nipples of cow breast in three coordinate spaces is exported
Confidence ceases, and 4 breast cups of milker are sleeved on 4 nipples of milk cow according to 4 teat placement information.
Further, it is described to utilize binocular vision Processing Algorithm to first flat image and second flat image
Handled, establishing the three dimensional coordinate space of the cow breast includes：
S1：First flat image and the second flat image are pre-processed；
S2：Intelligent cognition is carried out to the first flat image by pretreatment and the second flat image, determines disparity computation
Preceding extensive cognitive characteristics, and the matching relationship between first flat image and the second flat image is established, to recognize
State the cognition attribute of breast area；
S3：According to the cognition attribute of the breast area, confirm specific with the corresponding one or more of the cognition attribute
Cognitive characteristics；
S4：Disparity computation is carried out according to binocular stereo imaging principle；
S5：With reference to the specific knowledge feature and point cloud chart, the three dimensional coordinate space of cow breast is established.
Further, above-mentioned milker autocontrol method is further comprising the steps of：
S6：Judge whether the resolution of the three dimensional coordinate space meets precision and error requirements；As met, then milk is exported
The positional information of 4 nipples in cow's milk room, and 4 breast cups of milker are sleeved on to according to 4 teat placement information 4 breasts of milk cow
On head；Such as it is unsatisfactory for, goes to step S7；
S7：Return to step S2, redefines the extensive cognitive characteristics, and continues to execute step S3-S6.
Further, the point cloud chart for obtaining the destination object is further included in the step S4.
Further, the extensive cognitive characteristics includes the one or more in texture, profile, color；It is described specific to recognize
Know that feature is included within the extensive cognitive characteristics；The specific species of the cognition attribute includes color, profile, surface texture
And the geometry of profile.
Further, the pretreatment in the step S1 includes filtering, noise reduction, white balance, distortion processing, radiation change.
Further, the method for the extensive cognitive characteristics before disparity computation is determined in the step S3 to be included：Pattern class,
The connection of the geometrical length, the color, the lines for forming figure in the different characteristic region for forming figure that form the lines of figure is closed
System, this figure and other extensive figures geometrical relationship, form figure profile length ratio relation.
Milker autocontrol method proposed by the present invention based on binocular vision is a kind of very advanced cognition machint
Method, can not only differentiate the extensive feature of cow breast, and the spy of cow breast can also be further determined that according to extensive feature
Determine feature, with and can with most accurately and efficiently positioning is identified come 4 nipples to cow breast in feature identification technique,
It is suitable for cultivating the large-scale aquaculture model in garden, reduces cost of labor, effectively raise work efficiency, has very wide
Wealthy application prospect.
Brief description of the drawings
Fig. 1 is that the milker based on binocular vision in the present invention one is implemented automatically controls usage scenario schematic diagram；
Fig. 2 is that the milker based on binocular vision at another visual angle of the present invention automatically controls usage scenario schematic diagram；
Fig. 3 is that the milker based on binocular vision at the another visual angle of the present invention automatically controls usage scenario schematic diagram.
Description of reference numerals：10- binocular cameras.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of not making the creative labor
Embodiment, belongs to the scope of protection of the invention.
Refer to Fig. 1-Fig. 3, the milker autocontrol method based on binocular vision of one embodiment of the invention, including
Following steps：
The binocular camera 10 fixed by being arranged on milking area's relative position shoots first plane in cow breast region
Image and the second flat image；
First flat image and second flat image are handled using binocular vision Processing Algorithm, established
The three dimensional coordinate space of the cow breast；
According to the specific knowledge feature of mammilla of milk cattle, the position of 4 nipples of cow breast in three coordinate spaces is exported
Confidence ceases, and 4 breast cups of milker are sleeved on 4 nipples of milk cow according to 4 teat placement information.
In a preferred embodiment, it is described using binocular vision Processing Algorithm to first flat image and described
Second flat image is handled, and is established the three dimensional coordinate space of the cow breast and is included：
S1：First flat image and the second flat image are pre-processed；
S2：Intelligent cognition is carried out to the first flat image by pretreatment and the second flat image, determines disparity computation
Preceding extensive cognitive characteristics, and the matching relationship between first flat image and the second flat image is established, to recognize
State the cognition attribute of breast area；
S3：According to the cognition attribute of the breast area, confirm specific with the corresponding one or more of the cognition attribute
Cognitive characteristics；
S4：Disparity computation is carried out according to binocular stereo imaging principle；
S5：With reference to the specific knowledge feature and point cloud chart, the three dimensional coordinate space of cow breast is established.
Further, above-mentioned milker autocontrol method is further comprising the steps of：
S6：Judge whether the resolution of the three dimensional coordinate space meets precision and error requirements；As met, then milk is exported
The positional information of 4 nipples in cow's milk room, and 4 breast cups of milker are sleeved on to according to 4 teat placement information 4 breasts of milk cow
On head；Such as it is unsatisfactory for, goes to step S7；
S7：Return to step S2, redefines the extensive cognitive characteristics, and continues to execute step S3-S6.
Further, the point cloud chart for obtaining the destination object is further included in the step S4.
Further, the extensive cognitive characteristics includes the one or more in texture, profile, color；It is described specific to recognize
Know that feature is included within the extensive cognitive characteristics；The specific species of the cognition attribute includes color, profile, surface texture
And the geometry of profile.
Further, the pretreatment in the step S1 includes filtering, noise reduction, white balance, distortion processing, radiation change.
Further, the method for the extensive cognitive characteristics before disparity computation is determined in the step S3 to be included：Pattern class,
The connection of the geometrical length, the color, the lines for forming figure in the different characteristic region for forming figure that form the lines of figure is closed
System, this figure and other extensive figures geometrical relationship, form figure profile length ratio relation.
The present invention is relative to the prior art, maximum innovative point, employs extensive cognitive characteristics and specific knowledge is special
The mode that is combined is levied cow breast nipple to be identified the technological means of positioning.First, the extensive cognitive characteristics bag
Include the one or more in texture, profile, color；And the specific knowledge feature is included within the extensive cognitive characteristics.
The specific species of the cognition attribute includes the geometry of color, profile, surface texture and profile.The specific knowledge is special
Sign is then the deep learning cognitive characteristics based on image, recognizes nipple and its position.
In conclusion the milker autocontrol method proposed by the present invention based on binocular vision is a kind of very advanced
Cognition machint method, can not only differentiate the extensive feature of cow breast, can also further determine that milk cow according to extensive feature
The special characteristic of breast, with and can be with most accurately and efficiently feature identification technique is known come 4 nipples to cow breast
Do not position, be suitable for cultivating the large-scale aquaculture model in garden, reduce cost of labor, effectively raise work efficiency, have
There is boundless application prospect.
One of ordinary skill in the art will appreciate that：Attached drawing is the schematic diagram of one embodiment, module in attached drawing or
Flow is not necessarily implemented necessary to the present invention.
One of ordinary skill in the art will appreciate that：The module in device in embodiment can describe to divide according to embodiment
It is distributed in the device of embodiment, respective change can also be carried out and be disposed other than in one or more devices of the present embodiment.On
The module for stating embodiment can be merged into a module, can also be further split into multiple submodule.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that：It still may be used
To modify to the technical solution described in previous embodiment, or equivalent substitution is carried out to which part technical characteristic；And
These modifications are replaced, and the essence of appropriate technical solution is departed from the spirit and model of technical solution of the embodiment of the present invention
Enclose.
Claims (7)
1. a kind of milker autocontrol method based on binocular vision, it is characterised in that comprise the following steps：
The binocular camera fixed by being arranged on milking area's relative position shoot cow breast region the first flat image and
Second flat image；
First flat image and second flat image are handled using binocular vision Processing Algorithm, described in foundation
The three dimensional coordinate space of cow breast；
According to the specific knowledge feature of mammilla of milk cattle, the position for exporting 4 nipples of cow breast in three coordinate spaces is believed
Breath, and 4 breast cups of milker are sleeved on 4 nipples of milk cow according to 4 teat placement information.
2. the milker autocontrol method according to claim 1 based on binocular vision, it is characterised in that the utilization
Binocular vision Processing Algorithm handles first flat image and second flat image, establishes the cow breast
Three dimensional coordinate space include：
S1：First flat image and the second flat image are pre-processed；
S2：Intelligent cognition is carried out to the first flat image by pretreatment and the second flat image, before determining disparity computation
Extensive cognitive characteristics, and the matching relationship between first flat image and the second flat image is established, to recognize the breast
The cognition attribute in room region；
S3：According to the cognition attribute of the breast area, confirm and the corresponding one or more specific knowledges of the cognition attribute
Feature；
S4：Disparity computation is carried out according to binocular stereo imaging principle；
S5：With reference to the specific knowledge feature and point cloud chart, the three dimensional coordinate space of cow breast is established.
3. the milker autocontrol method according to claim 2 based on binocular vision, it is characterised in that further include with
Lower step：
S6：Judge whether the resolution of the three dimensional coordinate space meets precision and error requirements；As met, then milk cow's milk is exported
The positional information of 4 nipples in room, and 4 breast cups of milker are sleeved on to according to 4 teat placement information 4 nipples of milk cow
On；Such as it is unsatisfactory for, goes to step S7；
S7：Return to step S2, redefines the extensive cognitive characteristics, and continues to execute step S3-S6.
4. the milker autocontrol method according to claim 2 based on binocular vision, it is characterised in that the step
The point cloud chart for obtaining the destination object is further included in S4.
5. the milker autocontrol method according to claim 2 based on binocular vision, it is characterised in that described extensive
Cognitive characteristics includes the one or more in texture, profile, color；It is special that the specific knowledge feature is included in the extensive cognition
Within sign；The specific species of the cognition attribute includes the geometry of color, profile, surface texture and profile.
6. the milker autocontrol method according to claim 2 based on binocular vision, it is characterised in that the step
Pretreatment in S1 includes filtering, noise reduction, white balance, distortion processing, radiation change.
7. the milker autocontrol method according to claim 2 based on binocular vision, it is characterised in that the step
The method of the extensive cognitive characteristics before disparity computation is determined in S3 to be included：Pattern class, form figure lines geometrical length,
Color, the connection relation for the lines for forming figure, this figure and the other extensive figures for forming the different characteristic region of figure
Geometrical relationship, form figure profile length ratio relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711230544.7A CN107950402B (en) | 2017-11-29 | 2017-11-29 | Automatic control method of milking device based on binocular vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711230544.7A CN107950402B (en) | 2017-11-29 | 2017-11-29 | Automatic control method of milking device based on binocular vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107950402A true CN107950402A (en) | 2018-04-24 |
| CN107950402B CN107950402B (en) | 2020-10-30 |
Family
ID=61959565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711230544.7A Active CN107950402B (en) | 2017-11-29 | 2017-11-29 | Automatic control method of milking device based on binocular vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107950402B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109588320A (en) * | 2019-01-21 | 2019-04-09 | 河南埃尔森智能科技有限公司 | A kind of unmanned milk cow milking system based on 3D vision guide |
| CN110969156A (en) * | 2019-05-17 | 2020-04-07 | 丰疆智能科技股份有限公司 | Convolutional neural network model for detecting milk cow nipple and construction method thereof |
| CN112955003A (en) * | 2018-11-01 | 2021-06-11 | 利拉伐控股有限公司 | Tool positioning system and method, rotary milking platform, computer program and non-volatile data carrier |
| CN115281095A (en) * | 2022-05-30 | 2022-11-04 | 北京工业大学 | Milking device and method based on laser image recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144705A (en) * | 2007-07-25 | 2008-03-19 | 中国农业大学 | Method for monitoring pig growth using binocular vision technology |
| WO2010023121A2 (en) * | 2008-08-29 | 2010-03-04 | Delaval Holding Ab | Arrangement and method for determining positions of the teats of a milking animal |
| CN102986372A (en) * | 2012-09-28 | 2013-03-27 | 浙江工业大学 | Picking object recognizing, classifying and space positioning device and picking object recognizing, classifying and space positioning method based on panoramic stereoscopic vision |
| CN205830697U (en) * | 2016-06-29 | 2016-12-28 | 中国农业大学 | A kind of automatic medicated bathing apparatus assisting milk cow milking operation |
| CN107087150A (en) * | 2017-04-26 | 2017-08-22 | 成都通甲优博科技有限责任公司 | A kind of three-dimensional camera shooting method, system and device based on binocular solid and photometric stereo |
| CN107392929A (en) * | 2017-07-17 | 2017-11-24 | 河海大学常州校区 | A kind of intelligent target detection and dimension measurement method based on human vision model |
-
2017
- 2017-11-29 CN CN201711230544.7A patent/CN107950402B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144705A (en) * | 2007-07-25 | 2008-03-19 | 中国农业大学 | Method for monitoring pig growth using binocular vision technology |
| WO2010023121A2 (en) * | 2008-08-29 | 2010-03-04 | Delaval Holding Ab | Arrangement and method for determining positions of the teats of a milking animal |
| CN102986372A (en) * | 2012-09-28 | 2013-03-27 | 浙江工业大学 | Picking object recognizing, classifying and space positioning device and picking object recognizing, classifying and space positioning method based on panoramic stereoscopic vision |
| CN205830697U (en) * | 2016-06-29 | 2016-12-28 | 中国农业大学 | A kind of automatic medicated bathing apparatus assisting milk cow milking operation |
| CN107087150A (en) * | 2017-04-26 | 2017-08-22 | 成都通甲优博科技有限责任公司 | A kind of three-dimensional camera shooting method, system and device based on binocular solid and photometric stereo |
| CN107392929A (en) * | 2017-07-17 | 2017-11-24 | 河海大学常州校区 | A kind of intelligent target detection and dimension measurement method based on human vision model |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112955003A (en) * | 2018-11-01 | 2021-06-11 | 利拉伐控股有限公司 | Tool positioning system and method, rotary milking platform, computer program and non-volatile data carrier |
| CN112955003B (en) * | 2018-11-01 | 2023-04-07 | 利拉伐控股有限公司 | Tool positioning system and method, rotary milking platform, computer program and non-volatile data carrier |
| CN109588320A (en) * | 2019-01-21 | 2019-04-09 | 河南埃尔森智能科技有限公司 | A kind of unmanned milk cow milking system based on 3D vision guide |
| CN110969156A (en) * | 2019-05-17 | 2020-04-07 | 丰疆智能科技股份有限公司 | Convolutional neural network model for detecting milk cow nipple and construction method thereof |
| CN115281095A (en) * | 2022-05-30 | 2022-11-04 | 北京工业大学 | Milking device and method based on laser image recognition |
| CN115281095B (en) * | 2022-05-30 | 2024-03-29 | 北京工业大学 | Milking device and method based on laser image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107950402B (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107950402A (en) | Milker autocontrol method based on binocular vision | |
| CN107992871A (en) | The automatic accounting method in dining room based on image recognition | |
| US20180255743A1 (en) | Vision System with Tail Positioner | |
| CN108834576A (en) | A kind of citrus picking robot and its implementation based on binocular vision | |
| Doignon et al. | Segmentation and guidance of multiple rigid objects for intra-operative endoscopic vision | |
| CN105547153B (en) | Plug-in element stitch vision positioning method and device based on binocular vision | |
| IL284596B1 (en) | Registration of frames of reference | |
| CN107545247B (en) | Stereo cognition method based on binocular recognition | |
| CN109493313B (en) | Vision-based steel coil positioning method and equipment | |
| CN110223345A (en) | Distribution line manipulating object position and orientation estimation method based on cloud | |
| CN102054306B (en) | Method and system for detecting pedestrian flow by adopting deformable two-dimensional curves | |
| CN107957246A (en) | Article geometrical size measuring method on conveyer belt based on binocular vision | |
| CN107977996A (en) | Space target positioning method based on target calibrating and positioning model | |
| CN113538666B (en) | Rapid reconstruction method for three-dimensional model of plant | |
| CN114882109A (en) | Robot grabbing detection method and system for sheltering and disordered scenes | |
| CN115082777A (en) | Binocular vision-based underwater dynamic fish form measuring method and device | |
| CN107256633A (en) | A kind of vehicle type classification method based on monocular cam three-dimensional estimation | |
| CN110908374A (en) | Mountain orchard obstacle avoidance system and method based on ROS platform | |
| CN108280837B (en) | Method for extracting BGA solder ball contour in X-ray image based on transformation | |
| CN110097540A (en) | The visible detection method and device of polygon workpeace | |
| CN117021059B (en) | Picking robot, fruit positioning method and device thereof, electronic equipment and medium | |
| CN104268551B (en) | The controlling steering angle method of view-based access control model characteristic point | |
| CN108827250A (en) | A kind of robot monocular vision ranging technology method | |
| CN110909571B (en) | High-precision face recognition space positioning method | |
| CN103919556A (en) | Cow body shape trait index data collecting method based on three-dimensional measuring |
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 | ||
| CB02 | Change of applicant information |
Address after: 100094 603, floor 6, building 3, zone 1, No. 81, Beiqing Road, Haidian District, Beijing Applicant after: BEIJING VIZUM INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 100088 Beijing City, Haidian District Zhichun Road Jinqiu International Building No. 6 A block 1311 Applicant before: BEIJING VIZUM INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |