Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/117928
Title: | Learning depth-aware deep representations for robotic perception | Authors: | Porzi, Lorenzo Rota Buló, Samuel Penate-Sanchez, Adrian Ricci, Elisa Moreno-Noguer, Frances |
Keywords: | RGB-D perception Visual learning |
Issue Date: | 2017 | Journal: | IEEE Robotics and Automation Letters | Abstract: | Exploiting RGB-D data by means of convolutional neural networks (CNNs) is at the core of a number of robotics applications, including object detection, scene semantic segmentation, and grasping. Most existing approaches, however, exploit RGB-D data by simply considering depth as an additional input channel for the network. In this paper we show that the performance of deep architectures can be boosted by introducing DaConv, a novel, general-purpose CNN block which exploits depth to learn scale-aware feature representations. We demonstrate the benefits of DaConv on a variety of robotics oriented tasks, involving affordance detection, object coordinate regression, and contour detection in RGB-D images. In each of these experiments we show the potential of the proposed block and how it can be readily integrated into existing CNN architectures. | URI: | http://hdl.handle.net/10553/117928 | ISSN: | 2377-3766 | DOI: | 10.1109/LRA.2016.2637444 | Source: | IEEE Robotics and Automation Letters, v. 2 (2), p. 468 - 475 (1997) |
Appears in Collections: | Artículos |
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.