Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lian, Flora, Huynh, Dinh Quang, Penades, Hector, Perez, J. Stephany Berrio, Shan, Mao, Worrall, Stewart
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.18668
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917100301320192
author Lian, Flora
Huynh, Dinh Quang
Penades, Hector
Perez, J. Stephany Berrio
Shan, Mao
Worrall, Stewart
author_facet Lian, Flora
Huynh, Dinh Quang
Penades, Hector
Perez, J. Stephany Berrio
Shan, Mao
Worrall, Stewart
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18668
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data Augmentation Strategies for Robust Lane Marking Detection
Lian, Flora
Huynh, Dinh Quang
Penades, Hector
Perez, J. Stephany Berrio
Shan, Mao
Worrall, Stewart
Computer Vision and Pattern Recognition
Image and Video Processing
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.
title Data Augmentation Strategies for Robust Lane Marking Detection
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2511.18668