Detection of SIFT keypoints in spherical omnidirectional view sensor

N. S. Chong, Y. H. Kho, M. L D Wong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper proposed a method to detect object/scene through Scale Invariant Feature Transform (SIFT) keypoints for a hybrid sensor system comprises of a perspective view sensor and a spherical omnidirectional view sensor. A reference image is obtained from the perspective view sensor and matching is attempted with another distorted image acquired from the omnidirectional camera. The omnidirectional view image is first subjected to distortion correction (commonly termed "unwrapping") using closed form mapping functions and then SIFT keypoints of the corrected image are extracted and matched against the reference image's features. Experiment results show that the distortion correction produces acceptable performance of SIFT keypoint matching without modification to the classic SIFT algorithm.

Original languageEnglish
Title of host publicationProcedia Engineering
PublisherElsevier
Pages90-96
Number of pages7
Volume41
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2nd International Symposium on Robotics and Intelligent Sensors 2012, IRIS 2012 - Kuching, Sarawak, Malaysia
Duration: Sep 4 2012Sep 6 2012

Other

Other2nd International Symposium on Robotics and Intelligent Sensors 2012, IRIS 2012
CountryMalaysia
CityKuching, Sarawak
Period9/4/129/6/12

    Fingerprint

Keywords

  • Non-single viewpoint
  • Scale invariant feature transform
  • Scene recognition
  • Spherical omnidirectional view sensor

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Chong, N. S., Kho, Y. H., & Wong, M. L. D. (2012). Detection of SIFT keypoints in spherical omnidirectional view sensor. In Procedia Engineering (Vol. 41, pp. 90-96). Elsevier. https://doi.org/10.1016/j.proeng.2012.07.147