A Bayesian computer vision system for modeling human interactions
A Bayesian computer vision system for modeling human interactions
复制标题
DOI：
10.1109/34.868684
复制
发表时间：
2000-08-01
影响因子：
23.6
通讯作者：
Pentland, AP
中科院分区：
文献类型：
--
作者：
Oliver, NM;Rosario, B;Pentland, AP
我们描述了一个实时计算机视觉和机器学习系统，用于在视觉监控任务中建模和识别人类行为[1]。该系统特别关注检测何时发生人与人之间的交互并对交互类型进行分类。有趣的交互行为的示例包括跟随另一个人、改变一个人的路径以遇见另一个人等等。我们的系统将自上而下和自下而上的信息结合在一个封闭的反馈回路中，两个组件都采用统计贝叶斯方法[2]。我们提出并比较了两种不同的基于状态的学习架构，即，Hacking和CHacking的建模行为和交互。CHMM模型的工作效率更高，更准确。最后，为了解决有限的训练数据的问题，一个综合的“Aliife式”的训练系统被用来开发灵活的先验模型，用于识别人类的相互作用。我们展示了使用这些先验模型准确分类真实的人类行为和交互的能力，无需额外的调整或训练。
We describe a real-time computer vision and machine learning system for modeling and recognizing human behaviors in a visual surveillance task [1]. The system is particularly concerned with detecting when interactions between people occur and classifying the type of interaction. Examples of interesting interaction behaviors include following another person, altering one's path to meet another, and so forth. Our system combines top-down with bottom-up information in a closed feedback loop, with both components employing a statistical Bayesian approach [2]. We propose and compare two different state-based learning architectures, namely, HMMs and CHMMs for modeling behaviors and interactions. The CHMM model is shown to work much more efficiently and accurately. Finally, to deal with the problem of limited training data, a synthetic "Alife-style" training system is used to develop flexible prior models for recognizing human interactions. We demonstrate the ability to use these a priori models to accurately classify real human behaviors and interactions with no additional tuning or training.