arXiv Analytics

Sign in

arXiv:1612.07695 [cs.CV]AbstractReferencesReviewsResources

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

Marvin Teichmann, Michael Weber, Marius Zoellner, Roberto Cipolla, Raquel Urtasun

Published 2016-12-22Version 1

While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal, we present an approach to joint classification, detection and semantic segmentation via a unified architecture where the encoder is shared amongst the three tasks. Our approach is very simple, can be trained end-to-end and performs extremely well in the challenging KITTI dataset, outperforming the state-of-the-art in the road segmentation task. Our approach is also very efficient, taking less than 100 ms to perform all tasks.

Comments: 9 pages, 7 tables and 9 figures; first place on Kitti Road Segmentation; Code on GitHub (coming soon)
Categories: cs.CV, cs.RO
Related articles: Most relevant | Search more
arXiv:1907.08136 [cs.CV] (Published 2019-07-16)
Autonomous Driving in the Lung using Deep Learning for Localization
arXiv:1901.09270 [cs.CV] (Published 2019-01-26)
Challenges in Designing Datasets and Validation for Autonomous Driving
arXiv:1903.08746 [cs.CV] (Published 2019-03-20)
Affordance Learning In Direct Perception for Autonomous Driving