Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios

Youssef Shoeb, Youssef Shoeb, Nazir Nayal, Azarm Nowzad, Fatma Güney, Hanno Gottschalk

2025

Abstract

Detecting road obstacles is essential for autonomous vehicles to navigate dynamic and complex traffic environments safely. Current road obstacle detection methods typically assign a score to each pixel and apply a threshold to generate final predictions. However, selecting an appropriate threshold is challenging, and the per-pixel classification approach often leads to fragmented predictions with numerous false positives. In this work, we propose a novel method that leverages segment-level features from visual foundation models and likelihood ratios to predict road obstacles directly. By focusing on segments rather than individual pixels, our approach enhances detection accuracy, reduces false positives, and offers increased robustness to scene variability. We benchmark our approach against existing methods on the RoadObstacle and LostAndFound datasets, achieving state-of-the-art performance without needing a predefined threshold.

Paper Citation

in Harvard Style

Shoeb Y., Nayal N., Nowzad A., Güney F. and Gottschalk H. (2025). Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 306-315. DOI: 10.5220/0013126700003912

in Bibtex Style

@conference{visapp25,
author={Youssef Shoeb and Nazir Nayal and Azarm Nowzad and Fatma Güney and Hanno Gottschalk},
title={Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={306-315},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013126700003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios
SN - 978-989-758-728-3
AU - Shoeb Y.
AU - Nayal N.
AU - Nowzad A.
AU - Güney F.
AU - Gottschalk H.
PY - 2025
SP - 306
EP - 315
DO - 10.5220/0013126700003912
PB - SciTePress