Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zouzou, Alya, andéol, Léo, Ducoffe, Mélanie, Boumazouza, Ryma
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910962820317184
author Zouzou, Alya
andéol, Léo
Ducoffe, Mélanie
Boumazouza, Ryma
author_facet Zouzou, Alya
andéol, Léo
Ducoffe, Mélanie
Boumazouza, Ryma
contents We explore the use of conformal prediction to provide statistical uncertainty guarantees for runway detection in vision-based landing systems (VLS). Using fine-tuned YOLOv5 and YOLOv6 models on aerial imagery, we apply conformal prediction to quantify localization reliability under user-defined risk levels. We also introduce Conformal mean Average Precision (C-mAP), a novel metric aligning object detection performance with conformal guarantees. Our results show that conformal prediction can improve the reliability of runway detection by quantifying uncertainty in a statistically sound way, increasing safety on-board and paving the way for certification of ML system in the aerospace domain.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16740
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP
Zouzou, Alya
andéol, Léo
Ducoffe, Mélanie
Boumazouza, Ryma
Computer Vision and Pattern Recognition
Artificial Intelligence
We explore the use of conformal prediction to provide statistical uncertainty guarantees for runway detection in vision-based landing systems (VLS). Using fine-tuned YOLOv5 and YOLOv6 models on aerial imagery, we apply conformal prediction to quantify localization reliability under user-defined risk levels. We also introduce Conformal mean Average Precision (C-mAP), a novel metric aligning object detection performance with conformal guarantees. Our results show that conformal prediction can improve the reliability of runway detection by quantifying uncertainty in a statistically sound way, increasing safety on-board and paving the way for certification of ML system in the aerospace domain.
title Robust Vision-Based Runway Detection through Conformal Prediction and Conformal mAP
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.16740