Upload
others
View
1
Download
0
Embed Size (px)
Citation preview
Welcome Message from the General Chair
Welcome to ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC) 2014 conference! ICDSC series started in Vienna in 2007, and other six successful editions followed in Stanford (2008), Como (2009), Atlanta (2010), Ghent (2011), Hong Kong (2012) and Palm Springs (2013). Many people have worked hard to turn the 2014 edition into as great a success. We hope you will find this a mission accomplished.
As General Chair of this conference, I would like to express my gratitude to the Program Chairs (Christian Micheloni, Senem Velipasalar and Roberto Vezzani) which have put together a high‐quality program and managed to organize the review process in a timely manner. Many thanks also to the Publication Chair (Niki Martinel) which makes these proceedings possible, the Demo Chair (Roman Pflugfelder) and the PhD Forum Chair (Christophe Bobda) for their effort in getting interesting demo and PhD papers, the Special Session organizers (Andrea Cavallaro and Oswald Lanz) for putting together an excellent session, and the Finance and Local Chair (Ivan Huerta Casado) which helped me in arranging the conference. My special thanks to all the reviewers which have done a great job in selecting the best papers for oral and poster presentations at the conference. All these people have contributed on a voluntary basis, but just as a service for our community!
My personal thanks go also to the ICDSC Steering Committee members (Hamid Aghajan, Richard Kleihorst and Bernhard Rinner) which have given me the opportunity to organize this year’s edition. But most important, I would like to thank all the authors and participants. It is evident that this event would not exist without your contribution!
I’d like to cordially thank our technical (ACM and IEEE) and commercial (NVIDIA and ROTAS Srl) sponsors. Their support was vital for creating what, I hope, you all will find a successful event.
Finally, benvenuti a Venezia. I sincerely hope you will have the chance to visit this
wonderful city! NOVEMBER 2014 ICDSC 2014 GENERAL CHAIR Venezia, Italy Andrea Prati
Technical sponsors Commercial sponsor ROTAS srl (www.rotas.com)
Award sponsor NVIDIA (www.nvidia.com)
Welcome Message from the
Technical Program Committee Chairs Welcome to the 2014 edition of the ACM/IEEE International Conference on Distributed
Smart Cameras in Venice, Italy. This year, as in past editions, we received multidisciplinary submissions demonstrating that this conference is a unique venue to gather researchers from different fields under the same umbrella. 23 papers were selected for oral presentation and 10 papers as poster presentations. This year, the conference program also includes a special session on “Smart Cameras for Smart Environments” with seven selected papers. The program is also enriched by the Ph.D. Forum and demo sessions. The Ph.D. Forum includes three papers, and there will be six demos.
The following is a brief description of the review process. Before submission, the members of the Technical Program Committee were organised according to the subject areas. Paper submission required authors to select a primary and a secondary subject area. Three reviewers were assigned for each paper, such that at least two of the reviewers have matching subject areas with the primary selected area of the paper. Each reviewer had a maximum of three papers to review, and the review process was double‐blind. After the review deadline, the Technical Program Committee Chairs reassigned the papers with missing reviews to expert members of the Program Committee. Upon completion of the review process, the Program Chairs ranked the papers on the basis of the review scores and opportunely divided the accepted papers between oral and poster sessions. The final program is organised into six oral sessions, one poster session, one oral special session, a PhD Forum, and a Demo Session.
For the best paper award, three candidate papers with the best review scores were selected first. The best paper award committee consisted of three expert reviewers, who had not originally reviewed any of the candidate papers. This committee received the original reviews and the camera ready papers. After a thorough evaluation of the candidate papers, the award committee members reached a consensus on the best paper. The Technical Program Committee Chairs, given the high quality of all three candidate papers, decided to give a “Best paper runner‐up” award to the other two papers not selected by the best paper award committee. Special thanks go to the members of the Technical Program Committee, who helped us form a high quality program with their thorough reviews. We are very grateful for their time, effort and valuable support. We also thank the Best Paper Award Committee for the thorough evaluation of the candidate papers. We also extend special thanks to the General Chair of the 2014 edition, Andrea Prati, for his advice and guidance.
We also would like to thank all the authors and attendees of the conference. Your contributions allow us build an engaging and high‐quality technical program. We hope that you will find the program stimulating and that the conference will provide you a valuable opportunity to interact with other researchers and practitioners from around the world. Please enjoy your time at the conference. Hopefully, you will have time in your schedule to enjoy Venice as well.
NOVEMBER 2014 ICDSC 2014 TECHNICAL PROGRAM COMMITTEE CHAIRS Venezia, Italy Christian Micheloni, Senem Velipasalar, Roberto Vezzani
Conference Organizers
General Chair:
Andrea Prati – University IUAV of Venice, Italy
Technical Program Committee Chairs:
Christian Micheloni – University of Udine, Italy
Senem Velipasalar – Syracuse University, USA
Roberto Vezzani – University of Modena and Reggio Emilia, Italy
Steering Committee:
Hamid Aghajan – Stanford University, USA & Ghent University, Belgium
Bernhard Rinner – Klagenfurt University, Austria
Richard Kleihorst – Xetal NV & Ghent University, Belgium
Local & Finance Chair:
Ivan Huerta Casado – University IUAV of Venice, Italy
Publication Chair:
Niki Martinel – University of Udine, Italy
Demo Chair:
Roman Pflugfelder – Austrian Institute of Technology, Austria
PhD Forum Chair:
Christophe Bobda – University of Arkansas, USA
Technical program committee:
Adrian Munteanu ‐ Vrije Universiteit Brussel, ETRO Dept, Belgium
Ahmed Belbachir ‐ Austrian Institute of Technology, Austria
Amit Roy‐Chowdhury ‐ University of California Riverside, USA
Andrea Cavallaro ‐ Queen Mary University of London, UK
Axel Weissenfeld ‐ Leibniz Universitat Hannover, Germany
Ayesha Choudhary ‐ IIT Delhi, India
Babak Khalaj ‐ Sharif University of Technology, Iran
Bernhard Rinner ‐ Alpen‐Adria‐Universitat Klagenfurt, Austria
Bi Song ‐ Sony Corporation, USA
Bir Bhanu ‐ University of California Riverside, USA
Carlo Regazzoni ‐ University of Genoa, Italy
Christian Conrad ‐ Goethe University Frankfurt, Germany
Christophe Bobda ‐ University of Arkansas, USA
Claudio Piciarelli ‐ Univeristà di Udine, Italy
Csaba Beleznai ‐ Austrian Institute of Technology, Austria
Daeyong Park ‐ Yonsei University, Korea
Denis Marraud ‐ European Aeronautic Defence & Space Comp., France
Faisal Qureshi ‐ University of Ontario, Canada
Farhad Dadgostar ‐ NICTA, Australia
Federico Castanedo ‐ University of Deusto, Spain
Frank Ma ‐ OnMoble, USA, and Univ. of Sydney, Australia
Gian Luca Foresti ‐ University of Udine, Italy
Hamid Aghajan ‐ Stanford University, USA
Irene Gu ‐ Chalmers University of Technology, Sweden
Jeroen Vendrig ‐ Canon Information Systems Research Australia
Jinshi Cui ‐ Peking University, China
Joerg Haehner ‐ Universitaet Augsburg, Germany
Kai Huang ‐ Univ. of Southern California, USA
Luhong Liang ‐ ASTRI, Hong Kong
Ming‐Hsuan Yang ‐ UC Merced, USA
Mohan Kankanhalli ‐ National University of Singapore, Singapore
Nathan Frey – Google, USA
Niki Martinel – University of Udine, Italy
Norimichi Ukita ‐ Nara Institute of Science and Technology, Japan
Oswald Lanz ‐ Fondazione Bruno Kessler, Italy
Pradeep Atrey ‐ University of Winnipeg, Canada
Roman Pflugfelder ‐ Austrian Research Centers, Austria
Ronald Poppe ‐ Twente University of Technology, The Netherlands
Stan Li ‐ Chinese Academy of Sciences, China
Stefano Tubaro ‐ Politecnico di Milano, Italy
Sven Fleck ‐ SmartSurv Vision Systems GmbH, Germany
Varun Santhaseelan ‐ University of Dayton, USA
Vijayan Asari ‐ University of Dayton, USA
Vinod Kulathumani ‐ West Virginia University, USA
Wilfried Philips ‐ University of Ghent, Belgium
Yang Hu ‐ Chinese Academy of Sciences, China
Zhen Lei ‐ Chinese Academy of Sciences, China
Practical Information
How to reach the Conference Venue
ICDSC 2014 will be held at NH Laguna Palace Conference Center, located in Viale Ancona, 2. 30172
Venezia Mestre. Venice (Italy).
How to reach NH Laguna Palace Conference Center from Venezia Mestre train station
Conference venue can be reached by Venezia Mestre train station in different ways.
By foot
Distance: 1,7 km – Estimated travel time: 21 mins
Just exit from the main entrance of the train station (exit direction Mestre, not Marghera) and
follow the directions above.
CONFERENCE VENUE
VENEZIA MESTRE TRAIN STATION
VENEZIA “SAN MARCO” AIRPORT (VCE)
VENEZIA SANTA LUCIA TRAIN STATION
VENEZIA PIAZZALE ROMA
By public transportation (bus)
The bus #31 stops in front of NH Laguna Palace. The bus stop nearest to the Venezia Mestre train
station is NOT in front of the main entrance but a short walk away, turning right (not crossing the
main street) as soon as you exit from the train station (exit direction Mestre):
After you catch the bus, the stop corresponding to NH Laguna Palace is the sixth (Via Ancona
crossing Via Torino). In any case, you will see the building of NH Laguna Palace or may ask to the
driver.
The cost of a single bus ride is € 1.30. You need to validate the ticket when you get on board and,
from that moment, the ticket will be valid for one hour. You can also purchase cumulative tickets:
Pool of 10 tickets at € 20.00
A single ticket lasting 24 hours (1 day) at € 20.00, or lasting 48 hours (2 days) at € 30.00, or
lasting 72 hours (3 days) at € 40.00, or lasting 7 days at € 60.00
All these tickets are valid in all buses (even if you change the bus line during the trip), including those
going to Venezia island (Piazzale Roma).
Bus tickets can be purchased at the Venezia Mestre train station. Tickets can be purchased on board
at the cost of 2.50 €.
How to reach NH Laguna Palace Conference Center from Venezia island, Piazzale Roma
Piazzale Roma is the main hub of Venice island for cars, taxis and buses. All the buses start from
there to reach the mainland (including Venezia Mestre).
Conference venue can be reached by Piazzale Roma by either taxi (approx. cost 20‐25 euro) or
public transportation.
EXIT OF TRAIN STATION
BUS #31 STOP
By public transportation (bus)
The bus #12 or #12B or #12L stops few minutes of walk away from the NH Laguna Palace. The bus
can be caught at Piazzale Roma (just look at the right platform by looking at the signs or by asking
at the ticket information center in the corner of Piazzale Roma).
The trip will last about 20‐25 mins and the right stop is “San Marco – Sansovino” (7th stop). From
there, you can walk (distance: 750 m – estimated travel time: 9 mins):
The cost of a single bus ride is € 1.30. You need to validate the ticket when you get on board and,
from that moment, the ticket will be valid for one hour. You can also purchase cumulative tickets:
Pool of 10 tickets at € 20.00
A single ticket lasting 24 hours (1 day) at € 20.00, or lasting 48 hours (2 days) at € 30.00, or
lasting 72 hours (3 days) at € 40.00, or lasting 7 days at € 60.00
All these tickets are valid in all buses (even if you change the bus line during the trip).
Bus tickets can be purchased at the Venezia Santa Lucia train station or at the ticket information
center in the corner of Piazzale Roma. Tickets can be purchased on board at the cost of 2.50 €
How to reach NH Laguna Palace Conference Center from Venezia Santa Lucia train station
In this case, you can either take a train to Venezia Mestre (all the trains leaving from Venezia Santa
Lucia stop at Venezia Mestre) at a cost ranging from € 1.50 to € 10.00 (depending on the type of
train) and then follow the above instructions on how to reach the conference venue from Venezia
Mestre train station. Or you can walk from Venezia Santa Lucia train station to Piazzale Roma
(distance: 450 m – estimated travel time: 6 mins) and then follow the above instruction on how to
reach the conference venue from Piazzale Roma:
How to reach NH Laguna Palace Conference Center by car and where to park
If you are reaching the conference venue by car, you may arrive from different directions:
From the north: coming from A22 highway:
o take the exit Venezia/Verona Sud;
o enter highway A4 and proceed to highway A57 (following the directions for Trieste/
Tarvisio/ Belluno/ Mestre/ Via Miranese/ Via Castellana);
o Take the exit to Venezia/Ravenna/Mestre Centro/Porto and go straight. The
roundabout called Romea, take the third exit toward E55, direction
Trieste/Belluno/Tarvisio/Venezia.
o Take the direction to Venezia and enter in SR11
o Turn left in corso del Popolo and then turn right in via Torino
o Turn right again to stay in via Torino and then turn left at the second street, viale
Ancona
From the south: coming from A13 highway:
o Take the exit toward Padova/Milano/Venezia and keep right at the crossroad.
Follow the direction toward A4/Venezia
o Proceed on A57 highway (direction to Trieste/Tarvisio/Belluno/Mestre/Via
Miranese/Via Castellana).
o Take the exit to Venezia/Ravenna/Mestre Centro/Porto and go straight. The
roundabout called Romea, take the third exit toward E55, direction
Trieste/Belluno/Tarvisio/Venezia.
o Take the direction to Venezia and enter in SR11
o Turn left in corso del Popolo and then turn right in via Torino
o Turn right again to stay in via Torino and then turn left at the second street, viale
Ancona
From the west: coming from A4 highway:
o Proceed on A57 highway (direction to Trieste/Tarvisio/Belluno/Mestre/Via
Miranese/Via Castellana).
o Take the exit to Venezia/Ravenna/Mestre Centro/Porto and go straight. The
roundabout called Romea, take the third exit toward E55, direction
Trieste/Belluno/Tarvisio/Venezia.
o Take the direction to Venezia and enter in SR11
o Turn left in corso del Popolo and then turn right in via Torino
o Turn right again to stay in via Torino and then turn left at the second street, viale
Ancona
From the east: coming from A4 highway:
o Take the exit toward Milano and proceed on A57 highway
o Take the exit toward Venezia/Mestre and enter on route SR11
o Turn left in corso del Popolo and then turn right in via Torino
o Turn right again to stay in via Torino and then turn left at the second street, viale
Ancona
The NH Laguna Palace has its own parking lot just in front of the entrance of the Convention
Center which cost 12 euro for 24h. You can also look for a free parking in the nearby.
How to reach NH Laguna Palace Conference Center from the nearby airports
Venezia (island and Mestre) is served by two international airports: Venezia “Marco Polo” (VCE) and
Venezia Treviso (TSF).
From Venezia “Marco Polo” airport you can reach the conference venue by either the bus (bus #15
has a stop at 5 minutes walk from the conference venue, while bus #35B will bring you to the Venezia
Mestre train station) or the texi/motorboat.
From Venezia Treviso you can take the ATVO shuttle to either Venezia Mestre train station or
Venezia Piazzale Roma (Treviso Airport Bus Shuttle leaving every hour ‐
www.atvo.it/allegati/aeroporti/aeroporto_treviso_‐_venezia_dal_26.10.14_al_23.12.14.pdf).
Alternatively, you can take a taxi, but it may take a while and be rather expensive.
ADDITIONAL INFORMATION ON HOW TO REACH VENICE ISLAND, HOW TO MOVE THERE AND WHAT TO VISIT WILL BE IN
A SPECIFIC BOOKLET INSIDE YOUR CONFERENCE BAG.
Inside the Conference Venue
The NH Laguna Palace is composed of both the hotel and the conference center and it is located
between Via Torino and Viale Ancona. The best entrance is the one located in Viale Ancona and
clearly indicated with “NH Laguna Palace Convention Center”. This is indicated as Entrance 3 below.
ENTRANCE 1 – VIA TORINO
Entrance 1 – on Via Torino (photo from Google StreetView©)
Entrance 2 – on Viale Ancona (photo from Google StreetView©)
Entrance 3 – on Viale Ancona (photo from Google StreetView©)
ENTR
ANCE 1 – VIA TORINO
ENTRANCE 2 – VIALE ANCONAENTRANCE 3 – VIALE ANCONA
CONFERENCE ROOM
LUNCH ROOM
Lunches
The lunches for all the four days of the conference are offered to every participants and will take
place at Laguna Restaurant shown in the map in the previous page. Please bring with you the ticket
for that specific day included in your badge envelope.
If you want to have lunch outside the conference center, there are several places nearby the
conference venue.
Gala Dinner
The gala dinner will take place on Thursday 6 November starting at 19:30 in Venice Island. More
specifically, the Gala Dinner will take place at Westin Europa & Regina restaurant (San Marco 2159
• 30124 Venice, Italy ‐ http://www.westineuropareginavenice.com) at few steps from Piazza San
Marco in an astonishing position with terrific views.
The conference will organize the transportation to and from the restaurant. A reserved boat will
leave from the conference venue at 19.00/19.30 and will return at the conference venue leaving
from the restaurant around 24.00. Please bring with you the dinner ticket included in your badge
envelope. Additional dinner ticket can be purchased during the conference at the cost of 100 euro.
Detailed and updated information will be given during the conference.
If you plan to reach the restaurant on your own, see the following maps and directions:
Internet connection
All the participants will have access to a free wifi (SSID: nh, password: wifi). Additional high‐speed
wifi connections will be made available to the speakers which will need to show online videos or
other material.
Invited speakers
ICDSC 2014 is proud to announce three high‐quality invited talks.
Wednesday, November 5 – 9:00‐10:00
“How smart sensors will facilitate future automated border crossings?” by Andreas Kriechbaum‐
Zabini, AIT Austrian Institute of Technology Gmb
Abstract:
Due to specific immigration problems in the last years (e.g., Italy, Ukraine), European frontiers have
become unstable. There is a real and ever‐growing need for secure borders. On the other hand,
Europe's economic relevance as well as the Schengen Code, regulating the right of free movement
within the EU, drive to an increasing passenger flow at border crossings: thus, air border crossings
are expected to increase by 80% from 400 million in 2009 to 720 million in 2030. Consequently, the
demand both on passenger facilitation and on security necessitate innovation at border crossings.
Automation seems to be one option to mitigate the passenger flow problem. However, current
installations reveal multiple difficulties. Moreover, the redesign of such a complex security process
requires a multi‐stakeholder environment. Indeed, various security technologies are used for such
a complex process, joined together in automated border control (ABC) solutions, integrating
biometrics, surveillance, certificate exchange, data protection, secure user interaction and
information security. In this talk, we will introduce you to a state‐of‐the‐art ABC system, describe
the evolving issues of the field and discuss on how smart sensors – in particular optical systems ‐
can help to solve many of these challenges and be used to improve our borders security while
enhancing the passengers' experience. Thus, we will present the current drawbacks and advantages
of this technology in order to derive possible options for improvements. Many important challenges
in ABC are interdisciplinary and related to several topics of this conference: distributed video
analytics, multi‐sensor data aggregation, information fusion, object recognition, vision‐based smart
environments, surveillance, tracking applications and middleware applications. Therefore, ABC is a
very interesting concrete case in which we can integrate your solutions.
Biography:
Andreas Kriechbaum‐Zabini is project manager at the Safety & Security Department of AIT Austrian
Institute of Technology GmbH. Within the Business Unit "Video and Security Technology", he is the
key contact for airport related topics. Since 2011, he works as an expert in the field of automated
border control (ABC), coordinates national and international projects and has valuable insights in
existing operative solutions, end user requirements, important stakeholders and scientific analysis
of such environments. Currently, he is the technical coordinator of the EU‐FP7 Integrated Project
FastPass ( https://www.fastpass‐project.eu/). Targeting the harmonisation of ABC systems in
Europe, this project gathers more than 25 partners along the entire ABC value chain. Andreas
studied Telematics, with specialisation in "Computer Vision and Graphics" and "Telecommunication
Systems and Mobile Computing" at Graz University of Technology, Austria. His professional career
started in 2000 in the area of computer vision and automated surveillance where he worked in
several national funded projects, such as "Future Border Control" or "AREA MUMOSIS next" within
the Austrian security research program (KIRAS), as well as in EU projects, such as "FascinatE",
"porTiVity", "K‐Space", "Polymnia", "MECiTV", "Detect" and "VIZARD".
Thursday, November 6 – 9:00‐10:00
“Hierarchical Compositional Representations of Object Structure” by Ales Leonardis, University of
Birmingham
Abstract:
Visual categorisation has been an area of intensive research in the vision community for several
decades. Ultimately, the goal is to efficiently detect and recognize an increasing number of object
classes. The problem entangles three highly interconnected issues: the internal object
representation, which should compactly capture the visual variability of objects and generalize well
over each class; a means for learning the representation from a set of input images with as little
supervision as possible; and an effective inference algorithm that robustly matches the object
representation against the image and scales favorably with the number of objects. In this talk I will
present our approach which combines a learned compositional hierarchy, representing (2D) shapes
of multiple object classes, and a coarse‐to‐fine matching scheme that exploits a taxonomy of objects
to perform efficient object detection. I will conclude with a discussion about a number of possible
extensions of compositional hierarchical representations to other visual and non‐visual modalities.
Biography:
Ales Leonardis is Professor of Robotics at the University of Birmingham and co‐Director of the Centre
for Computational Neuroscience and Cognitive Robotics. He is also adjunct professor at the Faculty
of Computer Science, Graz University of Technology. He worked at the GRASP Lab at the University
of Pennsylvania, at PRIP, TU Wien, ETH Zurich and University of Ljubljana. His research interests
include robust and adaptive methods for computer vision, object and scene recognition and
categorization, statistical visual learning, 3D object modeling, and biologically motivated vision. He
is (co)author of more than 200 refereed papers. He has been an associate editor of the IEEE PAMI,
an editorial board member of Pattern Recognition, and an editor of the Springer book series
Computational Imaging and Vision. His paper "Multiple Eigenspaces" won the 29th Annual Pattern
Recognition Society award. In 2004 he was awarded a prestigious national award for his research
achievements.
Friday, November 7 – 9:00‐10:00
“Structured Robust PCA and Dynamics‐based Invariants for Multi‐Camera Video Understanding”
by Octavia I. Camps, Dept. of Electrical and Computer Engineering ‐ Northeastern University
Abstract:
The power of geometric invariants to provide solutions to computer vision problems has been
recognized for a long time. On the other hand, dynamics‐based invariants remain largely untapped.
Yet, visual data come in streams: videos are temporal sequences of frames, images are ordered
sequences of rows of pixels and contours are chained sequences of edges. In this talk, I will show
how making this ordering explicit allows to exploit dynamics‐based invariants to capture useful
information from video and image data. In particular, I will describe how to efficiently estimate
dynamics‐based invariants from incomplete and corrupted data by formulating the problem as a
structured robust PCA problem, where a structured matrix built from the data is decomposed into
structured low rank and sparse matrices. Finally, I will show how to use these invariants to perform
data association and classification in the context of computer vision applications for multi‐camera
tracking and cross‐view activity recognition
Biography:
Octavia Camps received a B.S. degree in computer science and a B.S. degree in electrical engineering
from the Universidad de la Republica (Uruguay), and a M.S. and a Ph.D. degree in electrical
engineering from the University of Washington. Prof. Camps was a visiting researcher at the
Computer Science Department at Boston University during Spring 2013. Since 2006, she is a
Professor in the Electrical and Computer Engineering Department at Northeastern University. From
1991 to 2006 she was a faculty of Electrical Engineering and of Computer Science and Engineering
at The Pennsylvania State University. In 2000, she was a visiting faculty at the California Institute of
Technology and at the University of Southern California. Her main research interests include robust
computer vision, image processing, and machine learning. She is a former associate editor of Pattern
Recognition and Machine Vision Applications. She is a member of the IEEE society.