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.

Learning Depth-Aware Deep Representations for Robotic Perception / Porzi, Lorenzo; Rota Bulò, Samuel; Penate-Sanchez, Adrian; Ricci, Elisa; Moreno-Noguer, Francesc. - In: IEEE ROBOTICS AND AUTOMATION LETTERS. - ISSN 2377-3766. - 2:2(2017), pp. 468-475. [10.1109/LRA.2016.2637444]

Learning Depth-Aware Deep Representations for Robotic Perception

Ricci, Elisa;
2017-01-01

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.
2017
2
Porzi, Lorenzo; Rota Bulò, Samuel; Penate-Sanchez, Adrian; Ricci, Elisa; Moreno-Noguer, Francesc
Learning Depth-Aware Deep Representations for Robotic Perception / Porzi, Lorenzo; Rota Bulò, Samuel; Penate-Sanchez, Adrian; Ricci, Elisa; Moreno-Noguer, Francesc. - In: IEEE ROBOTICS AND AUTOMATION LETTERS. - ISSN 2377-3766. - 2:2(2017), pp. 468-475. [10.1109/LRA.2016.2637444]
File in questo prodotto:
File Dimensione Formato  
07778240.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 538.32 kB
Formato Adobe PDF
538.32 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/194234
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 24
  • ???jsp.display-item.citation.isi??? 18
social impact