6533b859fe1ef96bd12b6fd3
RESEARCH PRODUCT
Central catadioptric image processing with geodesic metric
Yohan FougerollePascal VasseurCédric Demonceauxsubject
0209 industrial biotechnologyGeodesicComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processing02 engineering and technologyCatadioptric system020901 industrial engineering & automation0202 electrical engineering electronic engineering information engineering[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]Computer visionImage gradientFeature detection (computer vision)MathematicsCatadioptric imagebusiness.industry[ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO]Spherical imageimage processingInterest point detectionEuclidean distancespherical image * Corresponding author Tel : +33-385-731-128Computer Science::Computer Vision and Pattern RecognitionSignal ProcessingMetric (mathematics)020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessdescription
International audience; Because of the distortions produced by the insertion of a mirror, catadioptric images cannot be processed similarly to classical perspective images. Now, although the equivalence between such images and spherical images is well known, the use of spherical harmonic analysis often leads to image processing methods which are more difficult to implement. In this paper, we propose to define catadioptric image processing from the geodesic metric on the unitary sphere. We show that this definition allows to adapt very simply classical image processing methods. We focus more particularly on image gradient estimation, interest point detection, and matching. More generally, the proposed approach extends traditional image processing techniques based on Euclidean metric to central catadioptric images. We show in this paper the efficiency of the approach through different experimental results and quantitative evaluations.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2011-11-01 |