Precise morphological analysis of the cow body during parturition by 3D depth sensor camera

Research Project

Project/Area Number	18K05935
Research Category	Grant-in-Aid for Scientific Research (C)
Allocation Type	Multi-year Fund
Section	一般
Review Section	Basic Section 42010:Animal production science-related
Research Institution	Ibaraki University
Principal Investigator	Kohari Daisuke 茨城大学, 農学部, 准教授 (50396595)
Co-Investigator(Kenkyū-buntansha)	岡山毅茨城大学, 農学部, 教授 (90575226)
Project Period (FY)	2018-04-01 – 2021-03-31
Project Status	Completed (Fiscal Year 2020)
Budget Amount *help	¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000) Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000) Fiscal Year 2019: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000) Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords	分娩 / 牛 / 仙骨靭帯 / 形態 / 深度センサーカメラ / 赤外線深度センサーカメラ / 繁殖牛 / 行動 / 靭帯 / 赤外線深度センサー
Outline of Final Research Achievements	We attempted to capture the cow’s body shape change before parturition using an infrared depth sensor (three-dimensional camera). Japanese Black cattle kept in our university was used as subject. We set an infrared depth sensor (Kinectv2, MS) in the parturition pen, and a three-dimensional point cloud was acquired every minute. From the obtained point cloud, the standing data of the cow that can measure the posterior region was extracted. Curvature was calculated as a feature of the posterior shape of the cow and analyzed by a pattern matching method using them as a template. The data suitable for comparing the posterior body shape was standing and could be obtained in the area directly below the depth sensor. It was confirmed that the dent due to the tension of the sacral ligament became larger before parturition and their average depth became large about 5 hours before parturition.
Academic Significance and Societal Importance of the Research Achievements	本研究から，赤外線深度センサにより連続的な形態変化を長時間かつ高精度に捉えることが確認できた。近赤外光による記録は動物に対しては極めて非侵襲的かつストレスフリーな手法であり、あらためて直接センサーなどを体に装着できない動物(動物園動物・野生動物)のスキャニングなどにも応用可能性が確認されるとともに，センサーから得られた値は、リアルタイムにデータ化されることから、特定の動物行動の自動評価システムへの応用可能性も期待できることが確認された。一方で，センサーカメラの精度上，撮影範囲が限定されることや耐久性などの問題も明らかとなり，汎用化にはデータ取得条件の調整の必要性も示唆された。