Data Augmentation Strategies for Robust Lane Marking Detection

2025-11-23

AI Summary

To address the poor generalization and severe domain shift of lane detection models trained on front-facing datasets (e.g., CULane) when deployed with side-mounted cameras, this paper proposes a novel data augmentation pipeline integrating generative AI and geometric modeling. Specifically, controllable perspective transformation simulates side-view geometry; AI-based inpainting handles occlusions and shadows; and vehicle-body overlays model realistic deployment conditions. This approach effectively mitigates distribution mismatch between the front-view training domain and the side-view inference domain, enhancing model robustness against challenging lighting, occlusions, and discontinuous lane markings. Experiments on SCNN and UFLDv2 demonstrate that the augmented models achieve significant improvements in precision, recall, and F1-score over baselines—particularly excelling in shadowed and low-contrast scenarios, where lane continuity preservation is markedly enhanced.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• 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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Addressing domain shift for side-mounted camera lane detection
• Improving model generalization across different camera viewpoints
• Enhancing robustness of lane marking detection in shadows

Innovation

• Generative AI pipeline enhances lane detection data
• Combines geometric transformation with AI inpainting techniques
• Vehicle overlays simulate specific camera viewpoints effectively