Learning objects from RGB-D sensors using point cloud-based neural networks.

In this paper we present a scene understanding approach for assistive robotics based on learning to recognize different objects from RGB-D devices. Using the depth information it is possible to compute descriptors that capture the geometrical relations among the points that constitute an object or extract features from multiple viewpoints. We developed a framework for testing different neural models that receive this depth information as input. Also, we propose a novel approach using three-dimensional RGB-D information as input to Convolutional Neural Networks. We found F1-scores greater than 0.9 for the majority of the objects tested, showing that the adopted approach is effective as well for classification.

@InProceedings{BBPW15,
 	 author =  {Borghetti, Marcelo and Barros, Pablo and Parisi, German I. and Wermter, Stefan},
 	 title = {Learning objects from RGB-D sensors using point cloud-based neural networks.},
 	 booktitle = {Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)},
 	 journal = {None},
 	 editors = {}
 	 number = {}
 	 volume = {}
 	 pages = {439-444},
 	 year = {2015},
 	 month = {Jan},
 	 publisher = {None},
 	 doi = {}
 }