A Bayesian approach to the Hough transform for video and ultrasonic data fusion in mobile robot navigation

Abstract

A characteristic of structured environments is that objects tend to lie in straight lines representing the vertical surfaces of walls, doors, objects, etc. This paper proposes feature-based modeling of the environment in which line segments or surfaces are used for modeling an indoor environment and for improving the pose estimation of a mobile robot. Line features are detected making use of occupancy grids, based on ultrasonic range readings, and of a digital camera. A multisensor fusion approach for fusing ultrasonic and video data is proposed. The Hough transform (HT) is used for line feature extraction from both an occupancy grid map and digital images. Using a Bayesian approach to the HT, a rigorous probability value of the main straight line features extracted from a digital image is also proposed.