English

Towards Lightweight Lane Detection by Optimizing Spatial Embedding

Computer Vision and Pattern Recognition 2020-08-28 v2

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.

Keywords

Cite

@article{arxiv.2008.08311,
  title  = {Towards Lightweight Lane Detection by Optimizing Spatial Embedding},
  author = {Seokwoo Jung and Sungha Choi and Mohammad Azam Khan and Jaegul Choo},
  journal= {arXiv preprint arXiv:2008.08311},
  year   = {2020}
}

Comments

Preprint - work in progress

R2 v1 2026-06-23T17:57:26.136Z