Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/6125
Title: A direct approach for object detection with catadioptric omnidirectional cameras
Authors: Çınaroğlu, İbrahim
Baştanlar, Yalın
Çınaroğlu, İbrahim
Baştanlar, Yalın
Keywords: Car detection
Human detection
Object detection
Vehicle detection
Video cameras
Issue Date: 1-Feb-2016
Publisher: Springer Verlag
Source: Çınaroğlu, İ., and Baştanlar, Y. (2016). A direct approach for object detection with catadioptric omnidirectional cameras. Signal, Image and Video Processing, 10(2), 413-420. doi:10.1007/s11760-015-0768-2
Abstract: In this paper, we present an omnidirectional vision-based method for object detection. We first adopt the conventional camera approach that uses sliding windows and histogram of oriented gradients (HOG) features. Then, we describe how the feature extraction step of the conventional approach should be modified for a theoretically correct and effective use in omnidirectional cameras. Main steps are modification of gradient magnitudes using Riemannian metric and conversion of gradient orientations to form an omnidirectional sliding window. In this way, we perform object detection directly on the omnidirectional images without converting them to panoramic or perspective images. Our experiments, with synthetic and real images, compare the proposed approach with regular (unmodified) HOG computation on both omnidirectional and panoramic images. Results show that the proposed approach should be preferred.
URI: http://doi.org/10.1007/s11760-015-0768-2
http://hdl.handle.net/11147/6125
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 Description SizeFormat 
6125.pdfMakale1.66 MBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

SCOPUSTM   
Citations

20
checked on Oct 16, 2021

WEB OF SCIENCETM
Citations

23
checked on Oct 16, 2021

Page view(s)

54
checked on Oct 20, 2021

Download(s)

36
checked on Oct 20, 2021

Google ScholarTM

Check

Altmetric


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