Incremental disparity space image computation for automotive applications

Generating a depth map from a pair of stereo images is a challenging task, which is often further complicated by the additional restrictions imposed by the target application; in the automotive field, for example, real-time environment reconstruction is essential for safety and autonomous navigation systems, thus requiring reduced processing times, often at the expense of a somewhat limited degree of accuracy in the results. Nevertheless, a-priori knowledge on the intended use of the algorithm can also be exploited to improve its performance, both in terms of precision and computational burden. This paper presents three different approaches to incremental Disparity Space Image (DSI) computation, which leverage the properties of a stereo-vision system installed on a vehicle to produce accurate depth maps at sustained frame rates on commodity hardware.