Occlusions and binocular stereo

Occlusions and binocular stereo

0.00 Avg rating0 Votes
Article ID: iaor1997137
Country: United States
Volume: 14
Issue: 3
Start Page Number: 211
End Page Number: 226
Publication Date: Jul 1995
Journal: International Journal of Computer Vision
Authors: , ,
Keywords: programming: dynamic
Abstract:

Binocular stereo is the process of obtaining depth information from a pair of cameras. In the past, stereo algorithms have had problems at occlusions and have tended to fail there (though sometimes post-processing has been added to mitigate the worst effects). The authors show that, on the contrary, occlusions can help stereo computation by providing cues for depth discontinuities. They describe a theory for stereo based on the Bayesian approach, using adaptive windows and a prior weak smoothness constraint, which incorporates occlusion. The present model assumes that a disparity discontinuity, along the epipolar line, in one eye always corresponds to an occluded region in the other eye thus, leading to an occlusion constraint. This constraint restricts the space of possible disparity values, thereby simplifying the computations. An estimation of the disparity at occluded features is also discussed in light of psychophysical experiments. Using dynamic programming the authors can find the optimal solution to the system and the experimental results are good and support the assumptions made by the model.

Reviews

Required fields are marked *. Your email address will not be published.