Journal article
Seokwoo Jung, Sungha Choi, Mohammad Azam Khan, J. Choo
arXiv.org, 2020
arXiv.org, 2020
Semantic Scholar
ArXiv
DBLP
Cite
Cite
APA
Click to copy
Jung, S., Choi, S., Khan, M. A., & Choo, J. (2020). Towards Lightweight Lane Detection by Optimizing Spatial Embedding. ArXiv.org.
Chicago/Turabian
Click to copy
Jung, Seokwoo, Sungha Choi, Mohammad Azam Khan, and J. Choo. “Towards Lightweight Lane Detection by Optimizing Spatial Embedding.” arXiv.org (2020).
MLA
Click to copy
Jung, Seokwoo, et al. “Towards Lightweight Lane Detection by Optimizing Spatial Embedding.” ArXiv.org, 2020.
BibTeX Click to copy
@article{seokwoo2020a,
title = {Towards Lightweight Lane Detection by Optimizing Spatial Embedding},
year = {2020},
journal = {arXiv.org},
author = {Jung, Seokwoo and Choi, Sungha and Khan, Mohammad Azam and Choo, J.}
}
Abstract
A number of lane detection methods depend on a proposal-free instance segmentation because of its adaptability to flexible object shape, occlusion, and real-time application. This paper addresses the problem that pixel embedding in proposal-free instance segmentation based lane detection is difficult to optimize. A translation invariance of convolution, which is one of the supposed strengths, causes challenges in optimizing pixel embedding. In this work, we propose a lane detection method based on proposal-free instance segmentation, directly optimizing spatial embedding of pixels using image coordinate. Our proposed method allows the post-processing step for center localization and optimizes clustering in an end-to-end manner. The proposed method enables real-time lane detection through the simplicity of post-processing and the adoption of a lightweight backbone. Our proposed method demonstrates competitive performance on public lane detection datasets.
