Data Augmentation Strategies for Robust Lane Marking Detection

TL;DR

This paper presents a generative AI-based data augmentation pipeline that enhances lane detection models' robustness across different camera viewpoints and conditions, addressing domain shift challenges in autonomous driving.

Contribution

It introduces a novel combination of geometric transformation, AI inpainting, and vehicle overlays to simulate deployment-specific viewpoints for improved lane detection.

Findings

Improved model robustness to different viewpoints and shadows.

Enhanced precision, recall, and F1 scores with augmented data.

Scalable framework bridging dataset gaps for real-world deployment.

Abstract

Robust lane detection is essential for advanced driver assistance and autonomous driving, yet models trained on public datasets such as CULane often fail to generalise across different camera viewpoints. This paper addresses the challenge of domain shift for side-mounted cameras used in lane-wheel monitoring by introducing a generative AI-based data enhancement pipeline. The approach combines geometric perspective transformation, AI-driven inpainting, and vehicle body overlays to simulate deployment-specific viewpoints while preserving lane continuity. We evaluated the effectiveness of the proposed augmentation in two state-of-the-art models, SCNN and UFLDv2. With the augmented data trained, both models show improved robustness to different conditions, including shadows. The experimental results demonstrate gains in precision, recall, and F1 score compared to the pre-trained model. By bridging the gap between widely available datasets and deployment-specific scenarios, our method provides a scalable and practical framework to improve the reliability of lane detection in a pilot deployment scenario.