Detection of SIFTKeypointsin Spherical Omnidirectional View Sensor

Nguan Soon Chong, Yau Hee Kho, M. L. D. Wong

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


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
Pages (from-to)90-96
Number of pages7
JournalProcedia Engineering
Publication statusPublished - 2012


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

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Detection of SIFTKeypointsin Spherical Omnidirectional View Sensor'. Together they form a unique fingerprint.

Cite this