期刊
SCIENCE ADVANCES
卷 7, 期 46, 页码 -出版社
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/sciadv.abi4883
关键词
-
资金
- EPSRC [Seebibyte EP/M013774/1, Visual AI EP/T028572/1]
- Google PhD Fellowship
- Clarendon Fund
- Boise Trust Fund
- Wolfson College, University of Oxford
- Keble College Sloane-Robinson Clarendon Scholarship, University of Oxford
- Fundacao para a Ciencia e a Tecnologia, Portugal [SFRH/BD/108185/2015]
- Templeton World Charity Foundation [TWCF0316]
- National Geographic Society
- St Hugh's College, University of Oxford
- Kyoto University Primate Research Institute for Cooperative Research Program
- MEXT-JSPS [16H06283]
- Japan Society for the Promotion of Science
- Darwin Initiative [26-018]
- LGP-U04
- EPSRC [EP/M013774/1, EP/T028572/1] Funding Source: UKRI
- Fundação para a Ciência e a Tecnologia [SFRH/BD/108185/2015] Funding Source: FCT
The study presents a deep learning approach for automatically recognizing and tracking wild chimpanzee behaviors with high precision. This method provides an important strategy for utilizing large datasets in ethology and conservation efforts.
Large video datasets of wild animal behavior are crucial to produce longitudinal research and accelerate conservation efforts; however, large-scale behavior analyses continue to be severely constrained by time and resources. We present a deep convolutional neural network approach and fully automated pipeline to detect and track two audiovisually distinctive actions in wild chimpanzees: buttress drumming and nut cracking. Using camera trap and direct video recordings, we train action recognition models using audio and visual signatures of both behaviors, attaining high average precision (buttress drumming: 0.87 and nut cracking: 0.85), and demonstrate the potential for behavioral analysis using the automatically parsed video. Our approach produces the first automated audiovisual action recognition of wild primate behavior, setting a milestone for exploiting large datasets in ethology and conservation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据