Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/12767
Title: Label-free retraining for improved ground plane segmentation
Authors: Uzyıldırım, Furkan Eren
Özuysal, Mustafa
Keywords: Deep learning
Ground plane segmentation
Safe landing zone
Unmanned aerial vehicles
Issue Date: 2022
Publisher: Springer
Abstract: Due to increased potential applications of unmanned aerial vehicles over urban areas, algorithms for the safe landing of these devices have become more critical. One way to ensure a safe landing is to locate the ground plane regions of images captured by the device camera that are free of obstacles by deep semantic segmentation networks. In this paper, we study the performance of semantic segmentation networks trained for this purpose at a particular altitude and location. We show that a variation in altitude and location significantly decreases network performance. We then propose an approach to retrain the network using only a new set of images and without marking the ground regions in this novel training set. Our experiments show that we can convert a network’s operating range from low to high altitudes and vice versa by label-free retraining.
URI: https://doi.org/10.1007/s11760-022-02463-1
https://hdl.handle.net/11147/12767
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
s11760-022-02463-1.pdf
  Until 2025-07-01
article1.32 MBAdobe PDFView/Open    Request a copy
Show full item record



CORE Recommender

Page view(s)

124
checked on Feb 23, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.