講演抄録/キーワード |
講演名 |
2020-01-23 17:50
自然状況下インタラクション解析に向けた動物集団の映像に対する姿勢推定 ○村重哲史・久保孝富(奈良先端大)・永澤美保・菊水健史(麻布大)・池田和司(奈良先端大) NC2019-58 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
The social behavior analysis of animals is performed in various research fields such as ethology, neuroscience, and pharmacology.
To observe animal behavior under natural conditions, computer vision-based tracking methods are an effective approach to avoid distraction to animals.
Although many methods for single-animal pose estimation have been proposed,
there are few methods for multi-animal pose estimation that is indispensable to analyze social behaviors.
We aim to develop a method for multi-animal pose estimation using a deep learning technique.
In this preliminary study, we applied our proposed method to videos showing multiple dogs and evaluated its estimation error for body parts of dogs. |
キーワード |
(和) |
/ / / / / / / |
(英) |
social behavior / natural interaction / multi-animal pose estimation / computer vision / / / / |
文献情報 |
信学技報, vol. 119, no. 382, NC2019-58, pp. 1-1, 2020年1月. |
資料番号 |
NC2019-58 |
発行日 |
2020-01-16 (NC) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
NC2019-58 |
|