2006年
Recognizing human activities in video by multi-resolutional optical flows
IEEE International Conference on Intelligent Robots and Systems
- 開催年月日
- 2006年 - 2006年
- 記述言語
- 英語
- 会議種別
- 主催者
- IEEE
A method to recognize human activities captured in video is proposed. The method classifies basic human body activities, such as walking, running, gymnastic exercises and others. Applying Burt-Adelson Pyramid approach, the system extracts useful features consisting of multi-resoutional optical flows. This paper also reports coarseness limit of spatial resolution of optical flow for activity recognition; optical flows of 8 sub-areas covering the human body area are minimum requirement for the recognition. Also, the experiment examines effective weighting of multi-resoutional feature components. These results on recognition of coarse video will be useful for designing surveillance camera system. ©2006 IEEE.
- リンク情報
-
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=34250636649&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=34250636649&origin=inward
- DOI
- https://doi.org/10.1109/IROS.2006.282220
- Dblp Cross Ref
- https://dblp.uni-trier.de/conf/iros/2006
- Dblp Url
- https://dblp.uni-trier.de/db/conf/iros/iros2006.html#Nakata06