Stereoscopic depth estimation for online vision systems

A lot of work has been done in the area of machine stereo vision, but a severe drawback of today's algorithms is that they either achieve high accuracy and robustness by sacrificing real-time speed or they are real-time capable but with major deficiencies in quality. In order to tackle this problem this thesis presents two new methods which exhibit a very good balance between computational effort and depth accuracy. First, the summed normalized cross-correlation is proposed which constitutes a new cost function for block-matching stereo processing. In contrast to most standard cost functions it hardly suffers from the fattening effect while being computationally very effi cient. Second, the direct surface fi tting, a new algorithm for fi tting parametric surface models to stereo images, is introduced. This algorithm is inspired by the homography-constrained gradient descent methods but in contrast to these allows also for the estimation of non-planar surfaces. Experimental evaluations demonstrate that both newly introduced algorithms are competitive to state-of-the-art in terms of accuracy while having a much lower computational time.