Health condition estimation of dairy cows using spatio-temporal sensing

2016 Fiscal Year Final Research Report

• Project/Area Number: 15H06362
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Single-year Grants
• Research Field: Agricultural environmental engineering/Agricultural information engineering
• Research Institution: Osaka University
• Principal Investigator: Okura Fumio 大阪大学, 産業科学研究所, 助教 (60754223)
• Project Period (FY): 2015-08-28 – 2017-03-31
• Keywords: 酪農 / 画像解析 / 歩容解析 / 時空間センシング

Outline of Final Research Achievements

Monitoring the health condition of dairy cows is an essential task in dairy farming. Dairy farmers and veterinarians traditionally assess health using manual observation; however, the condition of every cow is not often observed every day because this observation imposes a significant burden. The resulting lack of daily health management is an important cause of economic loss.
We developed novel approaches for health condition estimation of dairy cows using spatio-temporal sensing using RGB-D cameras. The RGB-D videos are stored with knowledges of dairy farmers such as measurements of health conditions of cows. In the JSPS research project, we focused on 1) the individual identification task by unifying texture and gait features, 2) early lameness detection using gait features, and 3) a spatio-temporal database construction that enabling the health condition estimation.
Related to the outcome of the projects, we applied patents as well as submitting papers.

Free Research Field

コンピュータビジョン・コンピュータグラフィックス