Title :
Recognizing Human Activities in Video by Multi-resolutional Optical Flows
Author_Institution :
Digital Human Res. Center, National Inst. of Adv. Industrial Sci. & Technol., Tokyo
Abstract :
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-resolutional 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-resolutional feature components. These results on recognition of coarse video will be useful for designing surveillance camera system
Keywords :
feature extraction; gesture recognition; image resolution; video signal processing; Burt-Adelson Pyramid approach; coarse video recognition; coarseness limit; feature extraction; human activity recognition; multi-resolutional optical flows; spatial resolution; surveillance camera system; Animals; Biomedical optical imaging; Cameras; Humans; Image motion analysis; Image recognition; Joints; Robustness; Surveillance; Tracking; Hidden Markov Model; Human activity recognition; Optical flow; Video Recognition;
Conference_Titel :
Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0258-1
Electronic_ISBN :
1-4244-0259-X
DOI :
10.1109/IROS.2006.282220
