Robust Lane Detection with Wavelet-Enhanced Context Modeling and Adaptive Sampling

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Kunyang, Hou, Ming
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916660777058304
author Li, Kunyang
Hou, Ming
author_facet Li, Kunyang
Hou, Ming
contents Lane detection is critical for autonomous driving and ad-vanced driver assistance systems (ADAS). While recent methods like CLRNet achieve strong performance, they struggle under adverse con-ditions such as extreme weather, illumination changes, occlusions, and complex curves. We propose a Wavelet-Enhanced Feature Pyramid Net-work (WE-FPN) to address these challenges. A wavelet-based non-local block is integrated before the feature pyramid to improve global context modeling, especially for occluded and curved lanes. Additionally, we de-sign an adaptive preprocessing module to enhance lane visibility under poor lighting. An attention-guided sampling strategy further reffnes spa-tial features, boosting accuracy on distant and curved lanes. Experiments on CULane and TuSimple demonstrate that our approach signiffcantly outperforms baselines in challenging scenarios, achieving better robust-ness and accuracy in real-world driving conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18631
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Lane Detection with Wavelet-Enhanced Context Modeling and Adaptive Sampling
Li, Kunyang
Hou, Ming
Computer Vision and Pattern Recognition
Lane detection is critical for autonomous driving and ad-vanced driver assistance systems (ADAS). While recent methods like CLRNet achieve strong performance, they struggle under adverse con-ditions such as extreme weather, illumination changes, occlusions, and complex curves. We propose a Wavelet-Enhanced Feature Pyramid Net-work (WE-FPN) to address these challenges. A wavelet-based non-local block is integrated before the feature pyramid to improve global context modeling, especially for occluded and curved lanes. Additionally, we de-sign an adaptive preprocessing module to enhance lane visibility under poor lighting. An attention-guided sampling strategy further reffnes spa-tial features, boosting accuracy on distant and curved lanes. Experiments on CULane and TuSimple demonstrate that our approach signiffcantly outperforms baselines in challenging scenarios, achieving better robust-ness and accuracy in real-world driving conditions.
title Robust Lane Detection with Wavelet-Enhanced Context Modeling and Adaptive Sampling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.18631