6533b82efe1ef96bd1293cf3
RESEARCH PRODUCT
Keypoint descriptor matching with context-based orientation estimation
Domenico TegoloCesare ValentiFabio Bellaviasubject
GLOHComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-invariant feature transformContext basedReference orientationImage descriptorLIOPDiscriminative modelMROGHHistogramKeypoint matchingSIFTComputer Science::MultimediaComputer visionInvariant (mathematics)MathematicsDominant orientationSettore INF/01 - Informaticabusiness.industryPattern recognitionGridLocal featureRotation invarianceComputer Science::Computer Vision and Pattern RecognitionSignal ProcessingImage descriptors; Local features; Dominant orientation; Rotation invariance; Keypoint matching; SIFT; LIOP; MROGHComputer Vision and Pattern RecognitionArtificial intelligencebusinessdescription
Abstract This paper presents a matching strategy to improve the discriminative power of histogram-based keypoint descriptors by constraining the range of allowable dominant orientations according to the context of the scene under observation. This can be done when the descriptor uses a circular grid and quantized orientation steps, by computing or providing a global reference orientation based on the feature matches. The proposed matching strategy is compared with the standard approaches used with the SIFT and GLOH descriptors and the recent rotation invariant MROGH and LIOP descriptors. A new evaluation protocol based on an approximated overlap error is presented to provide an effective analysis in the case of non-planar scenes, thus extending the current state-of-the-art results.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2014-09-01 |