Binary confidence evaluation for a stereo vision based depth field processor SoC

This paper presents a methodology to construct a binary confidence value for every pixel of a depth map. We start by constructing 72 different confidence metrics, including the traditional ones and new metrics based on neighborhood information. Construction of the binary confidence value from these metrics is hence viewed as a two-class classification problem where we evaluated three different classifiers, with increasing complexity. Only metrics and classifiers that are suitable for VLSI hardware implementation will be evaluated. Evaluation of the constructed classifiers is performed on an indoor dataset of Stereo Images.