Context-aware agents for people detection and stereoscopic analysis

Abstract

This paper presents a multiagent system that can process stereoscopic images and detect people with a stereo camera. In the first of two phases, the system creates a model of the environment using a disparity map. It can be constructed in real time, even if there are moving objects present in the area (such as people passing by). In the second phase, the system is able to detect people by combining a series of novel techniques. A multi-agent system (MAS) is used to deal with the problem. The system is based on cooperative and distributed mechanisms and was tested under different conditions and environments.