NEW VISUAL INVARIANTS FOR TERRAIN NAVIGATION WITHOUT 3D RECONSTRUCTION

For autonomous vehicles to achieve terrain navigation, obstacles must be discriminated from terrain before any path planning and obstacle av oidance activity is undertaken. In this paper, a novel approach to obs tacle detection has been developed. The method finds obstacles in the 2D image space, as opposed to 3D reconstructed space, using optical fl ow. Our method assumes that both nonobstacle terrain regions, as well as regions with obstacles, will be visible in the imagery. Therefore, our goal is to discriminate between terrain regions with obstacles and terrain regions without obstacles. Our method uses new visual linear invariants based on optical flow. Employing the linear invariance prop erty, obstacles can be directly detected by using reference flow lines obtained from measured optical flow. The main features of this approa ch are: (1) 2D visual information (i.e., optical flow) is directly use d to detect obstacles; no range, 3D motion, or 3D scene geometry is re covered; (2) knowledge about the camera-to-ground coordinate transform ation is not required; (3) knowledge about vehicle (or camera) motion is not required; (4) the method is valid for the vehicle (or camera) u ndergoing general six-degree-of-freedom motion; (5) the error sources involved are reduced to a minimum, because the only information requir ed is one component of optical flow. Numerous experiments using both s ynthetic and real image data are presented. Our methods are demonstrat ed in both ground and air vehicle scenarios.