Semantic monocular depth estimation based on artificial intelligence
Gurram, Akhil (Universitat Autònoma de Barcelona)
Urfalioglu, Onay (Bilkent University)
Halfaoui, Ibrahim (Technical University of Munich)
Bouzaraa, Fahd (Technical University of Munich)
López Peña, Antonio M. (Universitat Autònoma de Barcelona)

Date:	2021
Description:	5 pàg.
Abstract:	Depth estimation provides essential information to perform autonomous driving and driver assistance. A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels where the same raw training data is associated with both types of ground truth, i. e. , depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, i. e. , that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on monocular depth estimation.
Grants:	Agencia Estatal de Investigación TIN2017-88709-R
Rights:	Tots els drets reservats.
Language:	Anglès
Document:	Article ; recerca ; Versió acceptada per publicar
Subject:	Monocular depth estimation ; Semantic segmentation ; Multi-task learning
Published in:	IEEE Intelligent Transportation Systems Magazine, Vol. 13, issue 4 (2021) , p. 99-103, ISSN 1941-1197

DOI: 10.1109/MITS.2019.2926263

Postprint 6 p, 6.0 MB

The record appears in these collections:
Articles > Research articles
Articles > Published articles