Geometry Aware Convolutional Filters for Omnidirectional Images Representation

Due to their wide field of view, omnidirectional cameras are frequently used by autonomous vehicles, drones and robots for navigation and other computer vision tasks. The images captured by such cameras, are often analyzed and classified with techniques designed for planar images that unfortunately fail to properly handle the native geometry of such images and therefore results in suboptimal performance. In this paper we aim at improving popular deep convolutional neural networks so that they can properly take into account the specific properties of omnidirectional data. In particular we propose an algorithm that adapts convolutional layers, which often serve as a core building block of a CNN, to the properties of omnidirectional images. Thus, our filters have a shape and size that adapt to the location on the omnidirectional image. We show that our method is not limited to spherical surfaces and is able to incorporate the knowledge about any kind of projective geometry inside the deep learning network. As depicted by our experiments, our method outperforms the existing deep neural network techniques for omnidirectional image classification and compression tasks.


Publié dans:
Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, 3351-3359
Présenté à:
ICML 2019 - 36th International Conference on Machine Learning, Long Beach, CA, USA, Jan 18-23, 2019
Année
2019
Mots-clefs:
Lien supplémentaire:
Laboratoires:




 Notice créée le 2019-08-08, modifiée le 2019-08-12


Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)