Neural network based 2D/3D fusion for robotic object recognition - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Neural network based 2D/3D fusion for robotic object recognition

Abstract

We present a neural network based fusion approach for real- time robotic object recognition which integrates 2D and 3D descriptors in a flexible way. The presented recognition architecture is coupled to a real-time segmentation step based on 3D data, since a focus of our investigations is real-world operation on a mobile robot. As recognition must operate on imperfect segmentation results, we conduct tests of recognition performance using complex everyday objects in order to quantify the overall gain of performing 2D/3D fusion, and to discover where it is particularly useful. We find that the fusion approach is most powerful when generalization is required, for example to significant viewpoint changes and a large number of object categories, and that a perfect segmentation is apparently not a necessary prerequisite for successful discrimination.
Fichier principal
Vignette du fichier
paper_submitted.pdf (427.57 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01012090 , version 1 (25-06-2014)

Identifiers

  • HAL Id : hal-01012090 , version 1

Cite

Louis-Charles Caron, Yang Song, David Filliat, Alexander Gepperth. Neural network based 2D/3D fusion for robotic object recognition. European Symposium on artificial neural networks (ESANN), May 2014, Bruges, Belgium. pp.127 - 132. ⟨hal-01012090⟩
233 View
235 Download

Share

Gmail Mastodon Facebook X LinkedIn More