Graph-Based Classification of Omnidirectional Images

Omnidirectional cameras are widely used in such areas as robotics and virtual reality as they provide a wide field of view. Their images are often processed with classical methods, which might unfortunately lead to non-optimal solutions as these methods are designed for planar images that have different geometrical properties than omnidirectional ones. In this paper we study image classification task by taking into account the specific geometry of omnidirectional cameras with graph-based representations. In particular, we extend deep learning architectures to data on graphs; we propose a principled way of graph construction such that convolutional filters respond similarly for the same pattern on different positions of the image regardless of lens distortions. Our experiments show that the proposed method outperforms current techniques for the omnidirectional image classification problem.

Published in:
Proceedings of ICCV Workshops, 860-869
Presented at:
IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy, October 22-29, 2017
Oct 29 2017

 Record created 2018-02-17, last modified 2019-10-07

Download fulltext

Rate this document:

Rate this document:
(Not yet reviewed)