Object Spaces: Context Management for Human Activity Recognition

In this paper, we propose a vision-based method for developing computer awareness of human activities. We present an object-oriented approach called ObjectSpaces that encapsulates context into scene objects. Objects provide clues about which human motions to anticipate, making them powerful tools for discriminating actions and activities. Our hierarchical process leverages both low- and high-level representations of motion to label human interaction with objects in the surroundings. The Hidden Markov Model and Bayesian relations are used to characterize and summarize activity