next up previous contents
Next: Exploiting scene constraints Up: Dense depth estimation Previous: Examples   Contents


Stereo matching

Stereo matching is a problem that has been studied over several decades in computer vision and many researchers have worked at solving it. The proposed approaches can be broadly classified into feature- and correlation-based approaches [24]. Some important feature based approaches were proposed by Marr and Poggio [86], Grimson [40], Pollard, Mayhem and Frisby [98] (all relaxation based methods), Gimmel'Farb [38] and Baker and Binford [6] and Ohta and Kanade [94] (using dynamic programming).

Successful correlation based approaches were for example proposed by Okutomi and Kanade [95] or Cox et al.[16]. The latter was recently refined by Koch [69] and Falkenhagen [25,26]. It is this last algorithm that will be presented in this section. Another approach based on optical flow was proposed by Proesmans et al. [125].



Subsections

Marc Pollefeys 2002-11-22