Welcome

Today, computer vision plays a key role in vehicle technology research. Applications like obstacle detection, tracking, visual odometry, night vision or trajectory planning are shared by advanced driver assistance systems on Earth as well as by exploratory robotics in distant planets.

The goal of CVVT2012 workshop, to be hosted in ECCV 2012, is to get together researchers in Computer Vision for automotive and unmanned aerial systems, underwater and planetary exploration as well as robotics, in order to and promote development and spreading of new ideas and results across the fields. We invite the submission of original research contributions in Computer Vision addressed to:

• Autonomous navigation and exploration
• Advanced driving assistance systems
• Driver-vehicle advanced interfaces and driver monitoring
• On-board calibration of multi-camera acquisition systems (stereo rig, multimodal, networks)
• Systems for underwater vehicles and robots
• Unmanned aerial systems

The previous editions of the workshop are the CVVT2010 workshop, organized at the ACCV 2010 in Queenstown (New Zealand) and the CVVT2011 workshop, organized at the ICCV 2011 in Barcelona (Spain).

Photos

Best Paper Award

Among non invited papers/talks Voted by the program committee, the CVVT 2012 awarded the best paper of the workshop to:

"Fast stixel computation for fast pedestrian detection"
by Rodrigo Benenson, Markus Mathias, Radu Timofte and Luc van Gool.

Organizing Commitee

General Chairs
Atsushi Imiya (IMIT, Chiba University, Japan)
Antonio M. López (Universitat Autònoma de Barcelona and Computer Vision Center, Spain)

Program and Area Chairs
Theo Gevers (University of Amsterdam, The Netherlands)
Urbano Nunes (University of Coimbra, Portugal)
Dariu M. Gavrila (Daimler AG and University of Amsterdam, Germany)
Steven Beauchemin (University of Western Ontario, Canada)

PRoVisG Mars 3D Challenge Chair
Tomas Pajdla (The Czech Technical University in Prague, Czech Republic)

Website, Submissions and Sponsors Chair
David Gerónimo (Universitat Autònoma de Barcelona and Computer Vision Center, Spain)

Program Committee

H. Ackermann (Leibniz Universität Hannover, Germany)
J.M Álvarez (Computer Vision Center, Spain)
J.P.Barreto (Universidade de Coimbra, Portugal)
S. Beauchemin (The University of Western Ontario, Canada)
P. Campoy (Universidad Politécnica de Madrid, Spain)
A. de la Escalera (Universidad Carlos III de Madrid, Spain)
A. Elibol (Yildiz Technical University, Turkey)
P. Grisleri (Universita di Parma & Vislab, Italy)
A. Hernáandez (Computer Vision Center and Univ. Autònoma de Barcelona, Spain)
Y. Kang (Tokyo Polytechnic University, Japan)
L. Krüger (Daimler AG, Germany)
N. Krüger (The Maersk Mc-Kinney Moller Institute, Denmark)
F. Lerasle (LAAS-CNRS and Université Paul Sabatier, France)
R. Li (The Ohio State University, USA)
K. Mikolajczyk (University of Surrey, United Kingdom)
H. Murase (Nagoya University, Japan)
L. Nalpantidis (Royal Institute of Technology - KTH, Sweden)
S. Nedevschi (Technical University of Cluh-Napoca, Romania)
U. Nunes (University of Coimbra, Portugal)
G. Paar (Joanneum Research in Graz, Austria)
D. Ponsa (Computer Vision Center and Univ. Autònoma de Barcelona, Spain)
R. Rojas (Free University of Berlin, Germany)
B. Rosenhahn (University of Hannover, Germany)
V. Santos (Universidade de Aveiro, Portugal)
A.D. Sappa (Computer Vision Center, Spain)
J. Sato (Nagoya Institute of Technology, Japan)
H. Singh (Wood-hole oceanographic institution, USA)
A. Torii (Tokyo Institute of Technology, Japan)
T. Vaudrey (The University of Auckland, New Zealand)

Program

The workshop will last a full day, with 25 minutes presentations and a poster session. Download the detailed program here.

09:00	Welcome
09:10	Invited talk by Tomas Pajdla: "PROVISG and PROVISCOUT planetary robotics"
09:40	Orals: "Monocular Rear-View Obstacle Detection Using Residual Flow", J. Molineros et al. "Subtraction-Based Forward Obstacle Detection using Illumination Insensitive Feature for Driving-Support", H. Kyutoku et al.
10:05	Coffee Break
11:00	Orals: "Adaptive Visual Obstacle Detection for Mobile Robots Using Monocular Camera", I. K. Iyidir et al. "Data-driven Vehicle Identification by Image Matching", J. A. Rodriguez-Serrano et al.
11:50	Short Posters Presentations: "A Vision-Based Navigation Facility for Planetary Entry Descent Landing", P. Lanza et al. "CYKLS: Detect Pedestrian's Dart Focusing on an Appearance Change", M. Ogawa et al. "Pose-Invariant Face Recognition in Videos for Human-Machine Interaction", B. Raducanu et al. "Hierarchical Properties of Multi-resolution Optical Flow Computation", Y. Kameda et al.
12:10	Posters Session
13:00	Lunch
14:30	Keynote speaker: Dariu M. Gavrila, "Smart Cars for Safe Pedestrians"
14:30	Orals: "Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features", J.M. Alvarez et al. "Monocular Visual Odometry and Dense 3D Reconstruction for On-Road Vehicles", M. Zhu et al.
16:10	Coffee Break
16:40	Invited Paper: D. Pfeiffer et al., "Pixels, Stixels, and Objects"
17:30	Orals: "Fast Stixel Computation for Fast Pedestrian Detection", R. Benenson et al.
18:15	Best paper announcement and Closing

Invited Talks

Smart cars for safe pedestrians
Dariu M. Gavrila (Daimler R&D, Ulm, Germany)

One of the most significant large-scale deployment of intelligent systems in our daily life nowadays involves driver assistance in smart cars.
The past decade has seen a steady increase of interest in the plight of the vulnerable road users (e.g. pedestrians, bicyclists), motivated by accident statistics, and accentuated by regulatory and consumer rating initiatives. Devising an effective driver assistance system for vulnerable road users has long been impeded, however, by the "perception bottleneck", i.e. not being able to detect and localize vulnerable road users sufficiently accurate.
In this talk, I give an overview of the remarkable research progress that has been achieved in this area. I discuss its main enablers and highlight future developments, on the road towards accident-free driving.

bio: Dariu M. Gavrila received the Ph.D. degree in computer science from the University of Maryland at College Park in 1996. Since 1997, he has been a Senior Research Scientist at Daimler R&D in Ulm, Germany. In 2003, he was appointed professor in the Faculty of Science at the University of Amsterdam, chairing the area of Intelligent Perception Systems (part time). Over the last decade, Prof. Gavrila has addressed perception systems for detecting humans and their activity. He particularly focused on active pedestrian safety, where was responsible for several EU and German projects on behalf of Daimler (PROTECTOR, SAVE-U, WATCH-OVER, AKTIV). He wrote a sizeable number of highly cited publications and received the I/O 2007 Award from the Netherlands Organisation for Scientific Research (NWO), as well as several conference paper awards. His personal website is www.gavrila.net.

PROVISG and PROVISCOUT planetary robotics
Tomas Pajda (The Czech Technical University in Prague, Czech Republic)

The results from projects PROVISG and PROVISCOUT on computer vision applied to plantetary robotics will be explained.

bio Tomas Pajdla is Assistant Professor at the Czech Technical University in Prague. He works in geometry and algebra of computer vision and robotics with emphasis on non-classical camera systems, 3D reconstruction and industrial vision. T. Pajdla published more than 75 works in journals and proceedings and received awards for his work OAGM 1998, BMVC 2002 and ICCV 2005. He served as a programme chair of ECCV 2004 and more than ten times as area chair of ICCV, CVPR, ECCV, ACCV, ICRA and BMVC. He is a member of the ECCV Board, a co-editor of IPSJ Transactions on Computer Vision and Applications and was a co-editor of special issues of the International Journal on Computer Vision and Robotics and Automation Systems. T. Pajdla has connections to planetary research community through EU projects with NASA and EADS Astrium and to automotive industry via Daimler AG.

Submission

Important Dates

Submissions open:	7th June 2012
Submissions deadline:	6th July 2012, 23:59 UTC (extended)
Author notification:	25th July 2012
Camera-ready papers:	1st August 2012
Workshop:	13th October 2012

Submission Procedure
How to submit a paper to the workshop:

1. Go to https://cmt.research.microsoft.com/ECCVWS2012.
2. Select Function "New Users".
3. Create your CMT account.
4. Log in using the new account.
5. Access the submission page.

Submission Style
Authors should take into account the following:

• All papers must be written in English and submitted in PDF format.
• The maximum paper length is 10 pages. The workshop paper format guidelines are the same as the Main Conference papers.
• Submissions will be rejected without review if they: contain more than 10 pages, violate the double-blind policy or violate the dual-submission policy.
• Authors will have the opportunity to submit up to 30MB of supporting material.

The author kit provides a LaTeX2e template for submissions, and an example paper to demonstrate the format. Please refer to this example for detailed formatting instructions. If you intend to use something other than LaTeX to prepare your paper (e.g. MS Word), you may refer to this Springer LNCS site.

• Example submission with detailed instructions: eccv2012ws-submission.pdf
• Author Kit (gzipped tar file): eccv2012ws-submissionkit.tar.gz
• Author Kit (zip file): eccv2012kit-workshop.zip

A paper ID will be allocated to you during submission. Please replace the asterisks in the example paper with your paper's own ID before uploading your file.