MAC-RANSAC: a robust algorithm for the recognition of multiple objects

Julien Rabin; Julie Delon; Yann Gousseau; Lionel Moisan

MAC-RANSAC: a robust algorithm for the recognition of multiple objects

Julien Rabin ¹ Julie Delon ¹ Yann Gousseau ¹ Lionel Moisan ²

1 LTCI - Laboratoire Traitement et Communication de l'Information

2 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5

Abstract : This paper addresses the problem of recognizing multiple rigid objects that are common to two images. We propose a generic algorithm that allows to simultaneously decide if one or several objects are common to the two images and to estimate the corresponding geometric transformations. The considered transformations include similarities, homographies and epipolar geometry. We first propose a generalization of an "a contrario" formulation of the RANSAC algorithm proposed in [Moisan and Stival 04]. We then introduce an algorithm for the detection of multiple transformations between images and show its efficiency on various experiments.

Keywords : Object recognition object pose estimation a contrario method RANSAC SIFT local descriptors planar transformation epipolar geometry

Document type :

Conference papers

Domain :

Computer Science [cs] / Computer Vision and Pattern Recognition [cs.CV]

Complete list of metadatas

Cited literature [19 references] Display Hide Download

https://hal.archives-ouvertes.fr/hal-00466487
Contributor : Julien Rabin <>
Submitted on : Thursday, March 25, 2010 - 5:18:40 PM
Last modification on : Thursday, April 11, 2019 - 4:02:09 PM
Long-term archiving on : Wednesday, November 30, 2016 - 4:03:58 PM

MAC_RANSAC_final.pdf

Files produced by the author(s)

MAC-RANSAC: a robust algorithm for the recognition of multiple objects

File

Identifiers

Collections

Citation

Export

Metrics

976

2405

Contact

MAC-RANSAC: a robust algorithm for the recognition of multiple objects

File

Identifiers

Collections

Citation

Export

Share

Metrics

976

2405

Contact