StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation

Dan Levi, Noa Garnett and Ethan Fetaya

Abstract

General obstacle detection is a key enabler for obstacle avoidance in mobile robotics and autonomous driving. In this paper we address the task of detecting the closest obstacle in each direction from a driving vehicle. As opposed to existing methods based on 3D sensing we use a single color camera. The main novelty in our approach is the reduction of the task to a column-wise regression problem. The regression is then solved using a deep convolutional neural network (CNN). In addition, we introduce a new loss function based on a semi-discrete representation of the obstacle position probability to train the network. The network is trained using ground truth automatically generated from a laser-scanner point cloud. Using the KITTI dataset, we show that the our monocular-based approach outperforms existing camera-based methods including ones using stereo. We also apply the network on the related task of road segmentation achieving among the best results on the KITTI road segmentation challenge.

Session

Poster 2

Files

Extended Abstract (PDF, 343K)
Paper (PDF, 1716K)
Supplemental Materials (ZIP, 23M)

DOI

10.5244/C.29.109
https://dx.doi.org/10.5244/C.29.109

Citation

Bibtex

@inproceedings{BMVC2015_109,
	title={StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation},
	author={Dan Levi and Noa Garnett and Ethan Fetaya},
	year={2015},
	month={September},
	pages={109.1-109.12},
	articleno={109},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.109},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.109}
}