ElasticLaneNet: An Efficient Geometry-Flexible Approach for Lane Detection

arXiv:2312.10389v2 Announce Type: replace
Abstract: The task of lane detection involves identifying the boundaries of driving areas in real-time. Recognizing lanes with variable and complex geometric structures remains a challenge. In this paper, we explore a novel and flexible way of implicit lanes representation named \textit{Elastic Lane map (ELM)}, and introduce an efficient physics-informed end-to-end lane detection framework, namely, ElasticLaneNet (Elastic interaction energy-informed Lane detection Network). The approach considers predicted lanes as moving zero-contours on the flexibly shaped \textit{ELM} that …

abstract arxiv challenge cs.cv detection driving elastic explore geometry lane detection map novel paper real-time representation type