Computing Stereo Correspondences in the Presence of Narrow Occluding Objects

Abstract

Contemporary stereo correspondence algorithms disambiguate multiple candidate matches by using a spatial hierarchy mechanism. Narrow occluding objects in 3-D scenes cannot be handled by the spatial hierarchy mechanism alone. The authors propose a dynamic disparity search (DDS) framework that combines the spatial hierarchy mechanism with a new disparity hierarchy mechanism, to reduce the stereo matching errors caused by narrow occluding objects. They demonstrate the merits of the DDS approach on real stereo images.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite

Text

Dhond and Aggarwal. "Computing Stereo Correspondences in the Presence of Narrow Occluding Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992. doi:10.1109/CVPR.1992.223180

Markdown

[Dhond and Aggarwal. "Computing Stereo Correspondences in the Presence of Narrow Occluding Objects." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1992.](https://mlanthology.org/cvpr/1992/dhond1992cvpr-computing/) doi:10.1109/CVPR.1992.223180

BibTeX

@inproceedings{dhond1992cvpr-computing,
  title     = {{Computing Stereo Correspondences in the Presence of Narrow Occluding Objects}},
  author    = {Dhond, Umesh R. and Aggarwal, Jake K.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1992},
  pages     = {758-760},
  doi       = {10.1109/CVPR.1992.223180},
  url       = {https://mlanthology.org/cvpr/1992/dhond1992cvpr-computing/}
}