Efficient Stereo and Optical Flow with Robust Similarity Measures

In this paper we address the problem of dense stereo matching and computation of optical flow. We propose a generalized dense correspondence computation algorithm, so that stereo matching and optical flow can be performed robustly and efficiently at the same time. We particularly target automotive applications and test our method on real sequences from the vehicles. We performed extensive quantitative evaluation of our method using different similarity measures and focused mainly on difficult sequences with abrupt exposure changes and did evaluations on Middlebury data sets. In addition we provided many qualitative results on real images from the vehicles, some of which are provided by the adverse vision conditions challenge of the conference.     «

In this paper we address the problem of dense stereo matching and computation of optical flow. We propose a generalized dense correspondence computation algorithm, so that stereo matching and optical flow can be performed robustly and efficiently at the same time. We particularly target automotive applications and test our method on real sequences from the vehicles. We performed extensive quantitative evaluation of our method using different similarity measures and focused mainly on diffi...     »