ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Stochastic Representation and Recognition of High-Level Group Activities
Cited 81 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
유상원, J. K. Aggarwal
발행일
201106
출처
International Journal of Computer Vision, v.93 no.2, pp.1-16
ISSN
0920-5691
출판사
Springer
DOI
https://dx.doi.org/10.1007/s11263-010-0355-5
협약과제
10MC4100, u-Robot 인지인프라 기술개발(주관 : u-City 환경기반 하이브리드 u-로봇 서비스 시스템 기술개발), 유원필
초록
This paper describes a stochastic methodology for the recognition of various types of high-level group activities. Our system maintains a probabilistic representation of a group activity, describing how individual activities of its group members must be organized temporally, spatially, and logically. In order to recognize each of the represented group activities, our system searches for a set of group members that has the maximum posterior probability of satisfying its representation. A hierarchical recognition algorithm utilizing a Markov chain Monte Carlo (MCMC)-based probability distribution sampling has been designed, detecting group activities and finding the acting groups simultaneously. The system has been tested to recognize complex activities such as 'a group of thieves stealing an object from another group' and 'a group assaulting a person'. Videos downloaded from YouTube as well as videos that we have taken are tested. Experimental results show that our system recognizes a wide range of group activities more reliably and accurately, as compared to previous approaches. © 2010 Springer Science+Business Media, LLC.
키워드
Description-based event detection, Group activity recognition, Human activity recognition, Stochastic grammar
KSP 제안 키워드
Event detection, Group activity recognition, Human activity recognition(HAR), Markov chain monte carlo, Maximum posterior, Probability distribution, Recognition algorithm, Stochastic methodology, Stochastic representation, Wide range, group members