Please use this identifier to cite or link to this item:
https://hdl.handle.net/11147/11368
Title: | Semantic Segmentation of Outdoor Panoramic Images | Authors: | Orhan, Semih Baştanlar, Yalın |
Keywords: | Semantic segmentation Computer vision applications Panoramic images Convolutional neural networks Omnidirectional vision Panoramic images Semantic segmentation Cameras Computer vision Convolution Semantics Autonomous driving Omni-directional view Omnidirectional cameras Panoramic images Semantic segmentation Standard cameras Visual localization Image segmentation Omnidirectional vision Convolutional neural networks |
Publisher: | Springer Springer Science and Business Media Deutschland GmbH |
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://github.com/semihorhan/semseg-outdoor-pano). © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature. | URI: | https://doi.org/10.1007/s11760-021-02003-3 https://hdl.handle.net/11147/11368 |
ISSN: | 1863-1703 1863-1711 |
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 | Size | Format | |
---|---|---|---|
11368.pdf Until 2025-01-01 | 2.97 MB | Adobe PDF | View/Open Request a copy |
CORE Recommender
SCOPUSTM
Citations
24
checked on Dec 13, 2024
WEB OF SCIENCETM
Citations
22
checked on Nov 9, 2024
Page view(s)
65,766
checked on Dec 16, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.