Using Quasi-Invariants for Automatic Model Building and Object Recognition: An Overview

Patrick Gros 1, 2
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We address the problem of automatic model building for further recognition of objects. Our initial data are a set of images of an object. In a first stage, these images are put into correspondence using quasi-invariants, epipolar geometry and an approximation of the apparent motion by an homography. The different aspects of the objects may thus be computed and each aspect gives raise to a partial model of the object. In a second stage, these models and indexed in a data base which is used for recognition. This work is based on the idea that aspect graphs may (should?) be learned from examples rather than computed from CAD models, and that a planar representation associated with geometric quasi-invariants is a relevant tool for object recognition.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00590030
Contributor : Team Perception <>
Submitted on : Tuesday, May 3, 2011 - 9:09:44 AM
Last modification on : Wednesday, April 11, 2018 - 1:54:32 AM
Long-term archiving on: Friday, November 9, 2012 - 10:20:43 AM

File

gros94using.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Patrick Gros. Using Quasi-Invariants for Automatic Model Building and Object Recognition: An Overview. NSF-ARPA Workshop on Object Representations in Computer Vision, Dec 1994, New York, United States. pp.65-76, ⟨10.1007/3-540-60477-4_4⟩. ⟨inria-00590030⟩

Share

Metrics

Record views

162

Files downloads

138