TRACKING FEATURES WITH CAMERA MANEUVERING FOR VISION-BASED NAVIGATION

In this article we present a method to obtain corresponding contour fe atures in a sequence of images. Our final goal is to compute camera mo tion and structure, for navigation based on vision. We make a feature tracking in the image considering not only the contour geometric infor mation, but also a brightness-based description. A kinematic model of brightness attributes has been proposed in order to obtain a brightnes s evolution constraint more reliable than the classical brightness con stancy model. Camera maneuvers, like sudden orientation changes, are d etected, estimated and used to obtain a better correspondence of featu res. Experimental results, using real images, are shown. Our main cont ributions are the proposed evolution model of brightness attributes an d the detection of camera maneuvers. (C) 1998 John Wiley & Sons, Inc.