Data Augmentation Strategies for Robust Lane Marking Detection
This addresses the domain shift problem for side-mounted cameras in autonomous driving, providing a scalable framework to improve lane detection reliability in specific deployment scenarios.
The paper tackled the problem of lane detection models failing to generalize across different camera viewpoints by introducing a generative AI-based data augmentation pipeline. The approach improved precision, recall, and F1 scores in two state-of-the-art models when tested on deployment-specific scenarios.
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.