Hunt Duffy, Aidan (2006) Teat detection for an automated milking system. Master of Engineering thesis, Dublin City University.
Abstract
Application time when placing all four cups to the udder of a cow is the primary time constraint in high capacity group milking. A human labourer can manually apply four cups per animal as it passes on a rotary carousel in less than ten seconds. Existing automated milking machines typically have an average attachment time in excess of one minute. These systems apply the cups to each udder quadrant individually. To speed up the process it is proposed to attach all four cups simultaneously. To achieve this, the 3D position and orientation of each teat must be known in approximate real time. This thesis documents the analysis of a stereo-vision system for teat location and presents further developments of the system for detection of teat orientation. Test results demonstrate the suitability of stereovision for teat location but indicate that further refinement of the system is required to produce increased accuracy and precision. The additional functionality developed for the system to determine teat orientation has also been tested. Results show that while accurate determination of teat orientation is possible issues still exist with reliability and robustness.
Metadata
Item Type: | Thesis (Master of Engineering) |
---|---|
Date of Award: | 2006 |
Refereed: | No |
Supervisor(s): | Esmonde, Harry and Corcoran, Brian |
Uncontrolled Keywords: | stereo vision; teat location; dairy processing |
Subjects: | Engineering > Mechanical engineering |
DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Mechanical and Manufacturing Engineering |
Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 3.0 License. View License |
ID Code: | 17194 |
Deposited On: | 16 Aug 2012 14:56 by Fran Callaghan . Last Modified 19 Jul 2018 14:56 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
5MB |
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record