A probabilistic exemplar approach to combine laser and vision for person tracking

Abstract

This article presents an approach to person tracking that combines camera images and laser range data. The method uses probabilistic exemplar models, which represent typical appearances of persons in the sensor data by metric mixture distributions. Our approach learns such models from laser and from camera data and applies a Rao-Blackwellized particle filter in order to track a person's appearance in the data. The filter samples joint exemplar states and tracks the person's position conditioned on the exemplar states using a Kalman filter. We describe an implementation of the approach based on contours in images and laser point set features. Additionally, we describe how the models can be learned from training data using clustering and EM. Our experimental results show that the appearance of persons in camera image scan be tracked reliably using this approach and that it also allows to distinguish between persons during tracking.