Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915178224812032 |
|---|---|
| author | Shoeb, Youssef Nayal, Nazir Nowzad, Azarm Güney, Fatma Gottschalk, Hanno |
| author_facet | Shoeb, Youssef Nayal, Nazir Nowzad, Azarm Güney, Fatma Gottschalk, Hanno |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_05707 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios Shoeb, Youssef Nayal, Nazir Nowzad, Azarm Güney, Fatma Gottschalk, Hanno Computer Vision and Pattern Recognition 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. |
| title | Segment-Level Road Obstacle Detection Using Visual Foundation Model Priors and Likelihood Ratios |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.05707 |