Semantic Classification of Boundaries of an RGBD Image

Nishit Soni, Anoop M. Namboodiri, CV Jawahar and Srikumar Ramalingam

Abstract

The problem of labeling the edges present in a single color image as convex, concave, and occluding entities is one of the fundamental problems in computer vision. It has been shown that this information can contribute to segmentation, reconstruction and recognition problems. Recently, it has been shown that this classification is not straightforward even using RGBD data. This makes us wonder whether this apparent simple cue has more information than a depth map? In this paper, we propose a novel algorithm using random forest for classifying edges into convex, concave and occluding entities. We release a data set with more than 500 RGBD images with pixel-wise ground labels. Our method produces promising results and achieves an F-score of $0.84$ on the data set.

Session

Poster 2

Files

PDF iconExtended Abstract (PDF, 1219K)
PDF iconPaper (PDF, 2M)

DOI

10.5244/C.29.114
https://dx.doi.org/10.5244/C.29.114

Citation

Nishit Soni, Anoop M. Namboodiri, CV Jawahar and Srikumar Ramalingam. Semantic Classification of Boundaries of an RGBD Image. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 114.1-114.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_114,
	title={Semantic Classification of Boundaries of an RGBD Image},
	author={Nishit Soni and Anoop M. Namboodiri and CV Jawahar and Srikumar Ramalingam},
	year={2015},
	month={September},
	pages={114.1-114.12},
	articleno={114},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.114},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.114}
}