Simone Milani's Home page

Milani's Research Page

The Robotic 3D Video Home Page

Articles, presentations, videos, and softwares are available for download.

Quick Biography

Last update: Oct 14th, 2014



The Robotic 3D Video (R3D) project aims at establishing a bridge between current robotics and 3D video. The reasons behind this are several and they can be summarized in a nutshell by saying that, data capture, a major issue for 3D video and for some applications of immersive reality, can benefit from the use of mobile and heterogeneous sensors (either passive or active) and, on the other side, human-robot interaction, an emerging issue for robotics, can benefit from 3D information. Such a synergy can be very powerful in many applications. On the practical side, the objective of this project is to build a system featuring an integrated network of static sensors and of mobile sensors (mounted either on robotic arms or on mobile robots) for the real-time extraction and exploitation of the 3D information of dynamic scenes. The system will be mainly used within several intermingled applications:

  • photorealistic representation and transmission of 3D dynamic scenes;
  • smart robotic environments;
  • scene understanding and classification;
  • Human-machine interaction.


The 3D project involves people from the LTTM lab and IAS lab of the Department of Information Engineering, University of Padova, Padova, Italy.

<

Papers published on journals

  • S. Milani, Compression of multiple user photo galleries, Image and Vision Computing, Available online 4 January 2016, ISSN 0262-8856, http://dx.doi.org/10.1016/j.imavis.2015.12.002.
  • S. Milani, G. Calvagno, "Correction and interpolation of depth maps from structured light infrared sensors", Signal Processing: Image Communication, Volume 41, February 2016, Pages 28-39, ISSN 0923-5965, http://dx.doi.org/10.1016/j.image.2015.11.008.

Papers published on proceedings

  • Milani, S., "Three-dimensional reconstruction from heterogeneous video devices with camera-in-view information," in Image Processing (ICIP), 2015 IEEE International Conference on , vol., no., pp.2050-2054, 27-30 Sept. 2015 doi: 10.1109/ICIP.2015.7351161
  • Milani, S.; Zanuttigh, P., "Compression of photo collections using geometrical information," in Multimedia and Expo (ICME), 2015 IEEE International Conference on , vol., no., pp.1-6, June 29 2015-July 3 2015 doi: 10.1109/ICME.2015.7177379
  • Zennaro, S.; Munaro, M.; Milani, S.; Zanuttigh, P.; Bernardi, A.; Ghidoni, S.; Menegatti, E., "Performance evaluation of the 1st and 2nd generation Kinect for multimedia applications," in Multimedia and Expo (ICME), 2015 IEEE International Conference on , vol., no., pp.1-6, June 29 2015-July 3 2015 doi: 10.1109/ICME.2015.7177380 Bibtex PDF Web site Additional results
  • G. Pozzato, S. Michieletto, E. Menegatti, F. Dominio, G. Marin, L. Minto, S. Milani, P. Zanuttigh, “Human-Robot Interaction with Depth-Based Gesture Recognition“, Proc. of IAS-13 – Workshop “Real Time Gesture Recognition for Human-Robot Interaction”, Padova, Italy, Jul. 2014.



Web site navigation:

  • Top of the Page
  • Conference papers

Web site navigation:

  • Oct 1st, 2014: 2nd Project meeting.
  • June 18th, 2014: 1st Project meeting.
  • May 4th, 2014: The project has started!
  • Apr. 4th, 2014: Starting meeting.
  • Oct. 10th, 2014: Second meeting.
  • Dec. 10th, 2014: first deadline.
  • Feb. 2016: 2 years evaluation.