Hierarchical Depth Mapping from Multiple Cameras

We present a method to estimate a dense and sharp depth map using multiple cameras. A key issue in obtaining sharp depth map is how to overcome the harmful in uence of occlusion. Thus, we rst propose an occlusion-overcoming strategy which selectively use the depth information from multiple cameras. With a simple sort and discard technique, we resolve the occlusion problem considerably at a slight sacri ce of noise tolerance. Another key issue in area-based stereo matching is the size of matching window. We propose a hierarchical scheme that attempts to acquire a sharp depth map such that edges of the depth map coincide with object boundaries on the one hand, reduce noisy estimates due to insu cient size of matching window on the other hand. We show the hierarchical method can produce a sharp and correct depth map.