A Robust Real-Time Lane Detection Method with Fog-Enhanced Feature Fusion for Foggy Conditions

2025-04-08

AI Summary

To address the severe performance degradation of lane detection under foggy conditions and the lack of dedicated datasets and methods, this paper introduces FoggyLane—the first real-world foggy lane detection dataset—along with two synthetic counterparts: FoggyCULane and FoggyTuSimple. We further propose the Fog-Enhanced Network (FEN), featuring a novel multi-level feature fusion architecture: (i) a Global Feature Fusion Module (GFFM) for semantic context modeling, (ii) a Kernel-level Feature Fusion Module (KFFM) to enhance structural representation of lanes, and (iii) a Low-level Edge Enhancement Module (LEEM) to recover blurred edge details. Optimized via TensorRT, FEN achieves 38.4 FPS on an NVIDIA Jetson AGX Orin. Extensive experiments demonstrate state-of-the-art performance, achieving F1-scores of 95.04%, 79.85%, and 96.95% on FoggyLane, FoggyCULane, and FoggyTuSimple, respectively—substantially outperforming existing approaches.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Lane detection is a critical component of Advanced Driver Assistance Systems (ADAS). Existing lane detection algorithms generally perform well under favorable weather conditions. However, their performance degrades significantly in adverse conditions, such as fog, which increases the risk of traffic accidents. This challenge is compounded by the lack of specialized datasets and methods designed for foggy environments. To address this, we introduce the FoggyLane dataset, captured in real-world foggy scenarios, and synthesize two additional datasets, FoggyCULane and FoggyTusimple, from existing popular lane detection datasets. Furthermore, we propose a robust Fog-Enhanced Network for lane detection, incorporating a Global Feature Fusion Module (GFFM) to capture global relationships in foggy images, a Kernel Feature Fusion Module (KFFM) to model the structural and positional relationships of lane instances, and a Low-level Edge Enhanced Module (LEEM) to address missing edge details in foggy conditions. Comprehensive experiments demonstrate that our method achieves state-of-the-art performance, with F1-scores of 95.04 on FoggyLane, 79.85 on FoggyCULane, and 96.95 on FoggyTusimple. Additionally, with TensorRT acceleration, the method reaches a processing speed of 38.4 FPS on the NVIDIA Jetson AGX Orin, confirming its real-time capabilities and robustness in foggy environments.

Problem

• Improving lane detection accuracy in foggy weather conditions
• Addressing lack of specialized datasets for foggy environments
• Enhancing real-time processing speed for fog-robust lane detection

Innovation

• Fog-Enhanced Network for lane detection
• Global Feature Fusion Module (GFFM)
• Low-level Edge Enhanced Module (LEEM)