Combining multiple manifold-valued descriptors for improved object recognition

Sadeep Jayasumana, Richard Hartley, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

18 Citations (Scopus)

Abstract

We present a learning method for classification using multiple manifold-valued features. Manifold techniques are becoming increasingly popular in computer vision since Riemannian geometry often comes up as a natural model for many descriptors encountered in different branches of computer vision. We propose a feature combination and selection method that optimally combines descriptors lying on different manifolds while respecting the Riemannian geometry of each underlying manifold. We use our method to improve object recognition by combining HOG [1] and Region Covariance [2] descriptors that reside on two different manifolds. To this end, we propose a kernel on the n-dimensional unit sphere and prove its positive definiteness. Our experimental evaluation shows that combining these two powerful descriptors using our method results in significant improvements in recognition accuracy.

Original languageEnglish
Title of host publication2013 International Conference on Digital Image Computing
Subtitle of host publicationTechniques and Applications, DICTA 2013
DOIs
Publication statusPublished - 1 Dec 2013
Externally publishedYes
EventDigital Image Computing Techniques and Applications 2013 - Wrest Point Hotel, Hobart, Australia
Duration: 26 Nov 201328 Nov 2013
Conference number: 15th
http://staff.itee.uq.edu.au/lovell/aprs/dicta13/index.html
https://ieeexplore.ieee.org/xpl/conhome/6689677/proceeding (Proceedings)

Publication series

Name2013 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2013

Conference

ConferenceDigital Image Computing Techniques and Applications 2013
Abbreviated titleDICTA 2013
CountryAustralia
CityHobart
Period26/11/1328/11/13
OtherThe International Conference on Digital Image Computing: Techniques and Applications (DICTA) is the main Australian Conference on computer vision, image processing, pattern recognition, and related areas. DICTA was established as a biennial conference in 1991 and became an annual event in 2007. It is the premier conference of the Australian Pattern Recognition Society (APRS).

The conference will be held at Wrest Point Hotel, Hobart, Tasmania, Australia from 26 - 28 November 2013.
Internet address

Cite this