Publication
Learning depth-aware deep representations for robotic perception
Journal Article (2017)
Journal
IEEE Robotics and Automation Letters
Pages
468-475
Volume
2
Number
2
Doc link
http://dx.doi.org/10.1109/LRA.2016.2637444
File
Authors
-
Porzi, Lorenzo
-
Rota-Bulò, Samuel
-
Peñate Sánchez, Adrián
-
Ricci, Elisa
-
Moreno Noguer, Francesc
Projects associated
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.
Categories
computer vision.
Author keywords
RGB-D Perception; Visual Learning
Scientific reference
L. Porzi, S. Rota-Bulò, A. Penate-Sanchez, E. Ricci and F. Moreno-Noguer. Learning depth-aware deep representations for robotic perception. IEEE Robotics and Automation Letters, 2(2): 468-475, 2017.
Follow us!