3D object detection with deep learning
- Escalona, Félix
- Cazorla, Miguel
- Rodríguez, Ángel
- Martínez-Gómez, Jesús
- Gomez-Donoso, Francisco
ISSN: 1888-0258
Year of publication: 2017
Issue Title: Special Issue on Advances on Physical Agents
Volume: 8
Issue: 1
Pages: 3-10
Type: Article
More publications in: JoPha: Journal of Physical Agents
Abstract
Finding an appropriate environment representation is a crucial problem in robotics. 3D data has been recently used thanks to the advent of low cost RGB-D cameras. We propose a new way to represent a 3D map based on the information provided by an expert. Namely, the expert is the output of a Convolutional Neural Network trained with deep learning techniques. Relying on such information, we propose the generation of 3D maps using individual semantic labels, which are associated with environment objects or semantic labels. So, for each label we are provided with a partial 3D map whose data belong to the 3D perceptions, namely point clouds, which have an associated probability above a given threshold. The final map is obtained by registering and merging all these partial maps. The use of semantic labels provide us a with way to build the map while recognizing objects.