We address the problem where an autonomous system equipped with an infrared camera "learns" a designated rigid 3-D scene so that later it can recognize and guide itself relative to the reconstructed scene, starting from an approximately known viewpoint, to reach a given destination. This scenario is relevant to several domains, in particular military missions and robotic navigation. A goal of our system is that a real-time implementation be feasible on special hardware. In this paper, we describe the software version of such a system and show results on real infrared images.
展开▼