BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20181028T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20180325T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RDATE:20190331T020000
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.13515.field_data.0@www.ugovricerca.uniroma1.it
DTSTAMP:20260404T185105Z
CREATED:20180908T055431Z
DESCRIPTION:Modern robotic systems are often equipped with a direct 3D data
  acquisition device\, e.g. LiDAR\, which provides a rich 3D point cloud re
 presentation of the surroundings. This representation is commonly used for
  obstacle avoidance and mapping. Here we propose a new approach for using 
 point clouds for another critical robotic capability\, semantic understand
 ing of the environment (i.e. object classification). Convolutional neural 
 networks (CNN)\, that perform extremely well for object classification in 
 2D images\, are not easily extendible to 3D point clouds analysis. It is n
 ot straightforward due to point clouds’ irregular format and a varying num
 ber of points. The common solution of transforming the point cloud data in
 to a 3D voxel grid needs to address severe accuracy vs memory size tradeof
 fs. In this paper we propose a novel\, intuitively interpretable\, 3D poin
 t cloud representation called 3D Modified Fisher Vectors (3DmFV). Our repr
 esentation is hybrid as it combines a coarse discrete grid structure with 
 continuous generalized Fisher vectors. Using the grid enables us to design
  a new CNN architecture for real-time point cloud classification. In a ser
 ies of performance analysis experiments\, we demonstrate competitive resul
 ts or even better than state-of-the-art on challenging benchmark datasets 
 while maintaining robustness to various data corruptions. Joint work with 
 Yizhak Ben-Shabat and Anath Fischer\, ME\, Technion.
DTSTART;TZID=Europe/Paris:20180913T150000
DTEND;TZID=Europe/Paris:20180913T150000
LAST-MODIFIED:20191008T082902Z
LOCATION:Aula MAgna
SUMMARY:3DmFV: 3D Point Cloud Classification in Real-Time using Convolution
 al Neural Network  - Prof. Michael Lindenbaum\, Technion
URL;TYPE=URI:http://www.ugovricerca.uniroma1.it/node/13515
END:VEVENT
END:VCALENDAR