Please use this identifier to cite or link to this item:
Title: Semantic segmentation of outdoor panoramic images
Authors: Orhan, Semih
Baştanlar, Yalın
Keywords: Semantic segmentation
Panoramic images
Omnidirectional vision
Convolutional neural networks
Issue Date: 2021
Publisher: Springer
Abstract: Omnidirectional cameras are capable of providing 360. field-of-view in a single shot. This comprehensive view makes them preferable for many computer vision applications. An omnidirectional view is generally represented as a panoramic image with equirectangular projection, which suffers from distortions. Thus, standard camera approaches should be mathematically modified to be used effectively with panoramic images. In this work, we built a semantic segmentation CNN model that handles distortions in panoramic images using equirectangular convolutions. The proposed model, we call it UNet-equiconv, outperforms an equivalent CNN model with standard convolutions. To the best of our knowledge, ours is the first work on the semantic segmentation of real outdoor panoramic images. Experiment results reveal that using a distortion-aware CNN with equirectangular convolution increases the semantic segmentation performance (4% increase in mIoU). We also released a pixel-level annotated outdoor panoramic image dataset which can be used for various computer vision applications such as autonomous driving and visual localization. Source code of the project and the dataset were made available at the project page (https:// semihorhan/semseg-outdoor- pano).
ISSN: 1863-1703
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 SizeFormat 
  Until 2025-01-01
2.97 MBAdobe PDFView/Open    Request a copy
Show full item record

CORE Recommender


checked on Dec 2, 2023


checked on Jun 17, 2023

Page view(s)

checked on Dec 4, 2023

Google ScholarTM



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