期刊
COMPUTER VISION AND IMAGE UNDERSTANDING
卷 96, 期 2, 页码 129-162出版社
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.cviu.2004.02.005
关键词
video-based event detection; event mining; activity recognition
We present a new representation and recognition method for human activities. An activity is considered to be composed of action threads, each thread being executed by a single actor. A single-thread action is represented by a stochastic finite automaton of event states, which are recognized from the characteristics of the trajectory and shape of moving blob of the actor using Bayesian methods. A multi-agent event is composed of several action threads related by temporal constraints. Multi-agent events are recognized by propagating the constraints and likelihood of event threads in a temporal logic network. We present results on real-world data and performance characterization on perturbed data. (C) 2004 Elsevier Inc. All rights reserved.
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