Identifying Human Interactions in Indoor Environments

A laser range-finder-based system for detecting interactions between people in indoor environments is presented. An entropy-based measure is used to recursively segment tracks of individuals into distinct activities. Probability distributions corresponding to co-occurring activities are compared and similar distributions are flagged as representing possible interactions. Experimental results from two environments are described.

• Type: Conference
• Year: 2004
• Where: ATAL
• Authors: Anand Panangadan, Maja J. Mataric, Gaurav S. Sukhatme
• Keywords: ATAL 2004, Indoor Environments, Probability Distributions, Similar Distributions