Abstract | ||
---|---|---|
Autonomous driving is a key factor for future mobility. Properly perceiving the environment of the vehicles is essential for a safe driving, which requires computing accurate geometric and semantic information in real-time. In this paper, we challenge state-of-the-art computer vision algorithms for building a perception system for autonomous driving. An inherent drawback in the computation of visual semantics is the trade-off between accuracy and computational cost. We propose to circumvent this problem by following an offline-online strategy. During the offline stage dense 3D semantic maps are created. In the online stage the current driving area is recognized in the maps via a re-localization process, which allows to retrieve the pre-computed accurate semantics and 3D geometry in real-time. Then, detecting the dynamic obstacles we obtain a rich understanding of the current scene. We evaluate quantitatively our proposal in the KITTI dataset and discuss the related open challenges for the computer vision community. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/WACV.2015.38 | WACV |
Keywords | Field | DocType |
semantics,sensors,computer vision,vehicle dynamics | Drawback,Computer vision,Computer science,Vision based,Vehicle dynamics,Computer vision algorithms,Artificial intelligence,Perception,Semantics,Semantic map,Computation | Conference |
ISSN | Citations | PageRank |
2472-6737 | 27 | 1.22 |
References | Authors | |
30 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Germán Ros | 1 | 223 | 11.13 |
Sebastian Ramos | 2 | 785 | 22.15 |
Manuel Granados | 3 | 27 | 1.22 |
Amir Bakhtiary | 4 | 27 | 1.22 |
David Vázquez | 5 | 488 | 28.04 |
Antonio Manuel López | 6 | 49 | 3.74 |