AirEyeSeg: Teacher-Student Insights into Robust Fisheye UAV Detection

Zhenyue Gu, Benedikt Kolbeinsson, Krystian Mikolajczyk

2024

Abstract

Accurate obstacle detection in Unmanned Aerial Vehicles (UAVs) using fisheye lenses is challenged by image distortions. While advanced algorithms like Fast Region-Based Convolutional Neural Network (Fast R-CNN), Spatial Pyramid Pooling-Net (SPP-Net), and You Only Look Once (YOLO) are proficient with standard images, they underperform on fisheye images due to serious distortions. We introduce a real-time fisheye object detection system for UAVs, underpinned by specialized fisheye datasets. Our contributions encompass the creation of UAV-centric fisheye datasets, a distillation-based (also termed Teacher-Student) training method, and AirEyeSeg, a pioneering fisheye detector. AirEyeSeg achieved a Mask(mAP50) of 88.6% for cars on the combined Visdorone and UAVid datasets and 84.5% for people on the SEE dataset using the Box(P) metric. Our results demonstrate AirEyeSeg’s superiority over traditional detectors and validate our Teacher-Student training approach, setting a benchmark in fisheye-lensed UAV object detection. The code is available at https://github.com/Zane-Gu/AirEyeSeg.

Paper Citation

in Harvard Style

Gu Z., Kolbeinsson B. and Mikolajczyk K. (2024). AirEyeSeg: Teacher-Student Insights into Robust Fisheye UAV Detection. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 546-557. DOI: 10.5220/0012388600003654

in Bibtex Style

@conference{icpram24,
author={Zhenyue Gu and Benedikt Kolbeinsson and Krystian Mikolajczyk},
title={AirEyeSeg: Teacher-Student Insights into Robust Fisheye UAV Detection},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={546-557},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012388600003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - AirEyeSeg: Teacher-Student Insights into Robust Fisheye UAV Detection
SN - 978-989-758-684-2
AU - Gu Z.
AU - Kolbeinsson B.
AU - Mikolajczyk K.
PY - 2024
SP - 546
EP - 557
DO - 10.5220/0012388600003654
PB - SciTePress