Analysis on a local approach to 3d object recognition

Abstract : We present a method for 3D object modeling and recogni- tion which is robust to scale and illumination changes, and to viewpoint variations. The object model is derived from the local features extracted and tracked on an image sequence of the object. The recognition phase is based on an SVM classier. We analyse in depth all the crucial steps of the method, and report very promising results on a dataset of 11 objects, that show how the method is also tolerant to occlusions and moderate scene clutter.
Document type :
Conference papers
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download


https://hal.inria.fr/inria-00306709
Contributor : Elise Arnaud <>
Submitted on : Tuesday, April 21, 2009 - 1:46:29 PM
Last modification on : Friday, March 16, 2012 - 10:47:55 AM
Long-term archiving on : Friday, November 25, 2016 - 11:19:25 PM

Files

dagm06.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00306709, version 1

Citation

Elisabetta Delponte, Elise Arnaud, Francesca Odone, Alessandro Verri. Analysis on a local approach to 3d object recognition. Symposium of the German Association for Pattern Recognitio, 2006, Berlin, Germany. ⟨inria-00306709⟩

Share

Metrics

Record views

93

Files downloads

220