Matching of omnidirectional and perspective images using the hybrid fundamental matrix

Luis Puig 1 Josechu Guerrero 1 Peter Sturm 2
2 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper we present an automatic hybrid matching system mixing images coming from central catadioptric systems and conventional cameras. We analyze three models of hybrid fundamental matrices. We perform experiments with synthetic and real data to test the behavior of these three approaches. The sensitivy to noise of lifted coordinates induces to select the simplest model to build an automatic matching system between these kind of images. Scale invariant features with a simple unwarping tool are considered to help initial putative matching. Then a robust estimation gives an estimation of the hybrid fundamental matrix and allows to detect wrong matches. Experimental results show the feasibility of this system.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/inria-00325330
Contributor : Peter Sturm <>
Submitted on : Sunday, September 28, 2008 - 10:21:32 PM
Last modification on : Thursday, February 14, 2019 - 3:33:30 PM
Long-term archiving on : Monday, October 8, 2012 - 1:41:42 PM

File

A23CR.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00325330, version 1

Citation

Luis Puig, Josechu Guerrero, Peter Sturm. Matching of omnidirectional and perspective images using the hybrid fundamental matrix. OMNIVIS 2008 - 8th Workshop on Omnidirectional Vision, Camera Networks and Non-classical Cameras, Rahul Swaminathan and Vincenzo Caglioti and Antonis Argyros, Oct 2008, Marseille, France. ⟨inria-00325330⟩

Share

Metrics

Record views

494

Files downloads

471