Detection of SIFTKeypointsin Spherical Omnidirectional View Sensor

Thispaperproposed a methodtodetectobject/scenethroughScaleInvariantFeatureTransform(SIFT) keypointsforahybrid sensor systemcomprises of aperspective viewsensor and aspherical omnidirectional viewsensor.A referenceimageisobtained from the perspective view sensor and matching is attempted with another...

Full description

Saved in:
Bibliographic Details
Published in:Procedia engineering 2012, Vol.41, p.90-96
Main Authors: Chong, N.S., Kho, Y.H., Wong, M.L.D.
Format: Article
Language:English
Subjects:
Non-single viewpoint
Scale Invariant Feature Transform
Scene Recognition
Spherical omnidirectional view sensor
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Thispaperproposed a methodtodetectobject/scenethroughScaleInvariantFeatureTransform(SIFT) keypointsforahybrid sensor systemcomprises of aperspective viewsensor and aspherical omnidirectional viewsensor.A referenceimageisobtained from the perspective view sensor and matching is attempted with another distorted image acquired from the omnidirectional camera.Theomnidirectional viewimageisfirst subjected todistortioncorrection(commonly termed “unwrapping”) using closed form mappingfunctions and thenSIFTkeypoints of the correctedimage areextracted and matched againstthereferenceimage's features. Experiment results show that the distortion correction produces acceptable performance of SIFT keypoint matching without modification to the classicSIFT algorithm.
ISSN:1877-7058
1877-7058
DOI:10.1016/j.proeng.2012.07.147