Gradient operators for feature extraction from omnidirectional panoramic images

Kenji Hara, Kohei Inoue, Kiichi Urahama

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

We propose an extension of the Laplacian operator and the class of differential corner detectors for omnidirectional panoramic images covering 360° views. It solves two problems of nonuniformity of spatial resolution and spherical polar coordinates singularity. For the first problem, we derive a Laplacian operator and a class of differential corner detectors that can handle spatial inhomogeneities in omnidirectional panoramic images using differential schemes. To solve the second problem, we use an overset grid system on the sphere called the Yin-Yang grid. This is realized based on the property that each of the modified Laplacian operator and corner detector is invariant with respect to coordinate transformation between the two spherical polar coordinate systems associated with the Yin-Yang grid system.

Original languageEnglish
Pages (from-to)89-96
Number of pages8
JournalPattern Recognition Letters
Volume54
DOIs
Publication statusPublished - Mar 1 2015

Fingerprint

Feature extraction
Detectors

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Gradient operators for feature extraction from omnidirectional panoramic images. / Hara, Kenji; Inoue, Kohei; Urahama, Kiichi.

In: Pattern Recognition Letters, Vol. 54, 01.03.2015, p. 89-96.

Research output: Contribution to journalArticle

@article{4be98c3b526044989764c1dd27434648,
title = "Gradient operators for feature extraction from omnidirectional panoramic images",
abstract = "We propose an extension of the Laplacian operator and the class of differential corner detectors for omnidirectional panoramic images covering 360° views. It solves two problems of nonuniformity of spatial resolution and spherical polar coordinates singularity. For the first problem, we derive a Laplacian operator and a class of differential corner detectors that can handle spatial inhomogeneities in omnidirectional panoramic images using differential schemes. To solve the second problem, we use an overset grid system on the sphere called the Yin-Yang grid. This is realized based on the property that each of the modified Laplacian operator and corner detector is invariant with respect to coordinate transformation between the two spherical polar coordinate systems associated with the Yin-Yang grid system.",
author = "Kenji Hara and Kohei Inoue and Kiichi Urahama",
year = "2015",
month = "3",
day = "1",
doi = "10.1016/j.patrec.2014.12.010",
language = "English",
volume = "54",
pages = "89--96",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - Gradient operators for feature extraction from omnidirectional panoramic images

AU - Hara, Kenji

AU - Inoue, Kohei

AU - Urahama, Kiichi

PY - 2015/3/1

Y1 - 2015/3/1

N2 - We propose an extension of the Laplacian operator and the class of differential corner detectors for omnidirectional panoramic images covering 360° views. It solves two problems of nonuniformity of spatial resolution and spherical polar coordinates singularity. For the first problem, we derive a Laplacian operator and a class of differential corner detectors that can handle spatial inhomogeneities in omnidirectional panoramic images using differential schemes. To solve the second problem, we use an overset grid system on the sphere called the Yin-Yang grid. This is realized based on the property that each of the modified Laplacian operator and corner detector is invariant with respect to coordinate transformation between the two spherical polar coordinate systems associated with the Yin-Yang grid system.

AB - We propose an extension of the Laplacian operator and the class of differential corner detectors for omnidirectional panoramic images covering 360° views. It solves two problems of nonuniformity of spatial resolution and spherical polar coordinates singularity. For the first problem, we derive a Laplacian operator and a class of differential corner detectors that can handle spatial inhomogeneities in omnidirectional panoramic images using differential schemes. To solve the second problem, we use an overset grid system on the sphere called the Yin-Yang grid. This is realized based on the property that each of the modified Laplacian operator and corner detector is invariant with respect to coordinate transformation between the two spherical polar coordinate systems associated with the Yin-Yang grid system.

UR - http://www.scopus.com/inward/record.url?scp=84921825752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921825752&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2014.12.010

DO - 10.1016/j.patrec.2014.12.010

M3 - Article

AN - SCOPUS:84921825752

VL - 54

SP - 89

EP - 96

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -