Semantic monocular depth estimation based on artificial intelligence

Date
2021
Editor(s)
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
IEEE Intelligent Transportation Systems Magazine
Print ISSN
1939-1390
Electronic ISSN
1941-1197
Publisher
IEEE
Volume
13
Issue
4
Pages
99 - 103
Language
English
Journal Title
Journal ISSN
Volume Title
Series
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.

Course
Other identifiers
Book Title
Keywords
Citation
Published Version (Please cite this version)