Today, computer vision technique provides methodology to assist a long-distance explorer project using visual sensing system such as mars rover project. Modern cars drive with assistance of various sensor data. In this workshop, we focus to exchange new ideas in applications of computer vision theory to vehicle technology. In computer vision vehicle technology, tracking, reconstruction, prediction are important ideas. Furthermore, real-time and on-line algorithms for these problems are required. Successful authors are invited to submit papers on applications for computer vision techniques to vehicle technology. The expected topics to be addressed in the workshop include, but are not limited.

  • Computer vision methods for vehicle-mounted camera system and exploration purposes
  • Sensor fusion and quality control of static and dynamic camera systems
  • Real-time, on-line, and on-board computer vision algorithms and systems
  • Pattern recognition and cognitive sciences for autonomous navigation and exploration
  • Simulation and evaluation systems for navigation and exploration

Program

Time Title Author(s)
**:**–09:00 Opening
09:00–09:30 Ground Truth Evaluation of Stereo Algorithms for Real World Applications
  • Pablo Sandino Morales Chavez and Reinhard Klette
09:30–10:00 Vehicle Ego-localization by Matching In-vehicle Camera Images to an Aerial Image
  • Masafumi Noda, Tomokazu Takahashi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Yoshiko Kojima and Takashi Naito
10:00–10:30 Comparative Study of Two Vertical Road Modelling Techniques
  • Konstantin Schauwecker and Reinhard Klette
10:30–11:00 Coffee break
11:00–11:30 The Six Point Algorithm Revisited
  • Akihiko Torii, Zuzana Kukelova, Martin Bujnak and Tomas Pajdla
11:30–12:00 Multi-body Segmentation and Motion Number Estimation via Over-Segmentation Detection
  • Guodong Pan and Kenneth Wong
12:00–12:30 Improvement of a Traffic Sign Detector by Retrospective Gathering of Training Samples from In-vehicle Camera Image Sequences
  • Daisuke Deguchi, Keisuke Doman, Ichiro Ide and Hiroshi Murase
12:30–14:00 Lunch break
14:00–14:30 Statistical Modeling of Long-range Drift in Visual Odometry
  • Ruyi Jiang, Reinhard Klette and Shigang Wang
14:30–15:00 Object Discrimination and Tracking in the Surroundings of a Vehicle by a Combined Laser Scanner Stereo System
  • Mathias Haberjahn and Ralf Reulke
15:00–15:30 Realistic Modeling of Water Droplets for Monocular Adherent Raindrop Recognition using Bézier Curves
  • Martin Roser, Julian Kurz and Andreas Geiger
15:30–16:00 Coffee break
16:00–16:30 Illumination Invariant Cost Functions in Semi-Global Matching
  • Simon Hermann, Sandino Morales, Tobi Vaudrey and Reinhard Klette
16:30–17:00 Relative Pose Estimation for Planetary Entry Descent Landing
  • Luca Zini, Francesca Odone, Alessandro Verri, Piergiorgio Lanza and Alessandra Mercer
17:00–**:** Closing

Co-Organizers

  • Steven Beauchemin (Department of Computer Science, University of Western Ontario, Canada)
  • Atsushi Imiya (IMIT, Chiba University, Japan)
  • Tomas Pajdla (The Czech Technical University in Prague, Czech)

Program Committee

  • Hanno Ackermann (Leibniz Universität Hannover, Germany)
  • Yousun Kang (NII, Japan)
  • Kazuhiko Kawamoto (Chiba University, Japan)
  • Lars Krüger (Daimler AG, Germany)
  • Norbert Krüger (University of Southern Denmark, Denmark)
  • Ron Li (The Ohio State University, USA)
  • Hiroshi Murase (Nagoya University, Japan)
  • Gerhard Paar (Joanneum Research, Austria)
  • Bodo Rosenhahn (University Hannover, Germany)
  • Jun Sato (Nagoya Institute of Technology, Japan)
  • Akihiko Torii (Tokyo Institute of Technology, Japan)
  • Tobi Vaudrey (The University of Auckland, New Zealand)
  • Lester Waugh (Astrium Ltd, UK)

Important Dates

Submission deadline3rd September, 2010 (extended) LNCS 10 pages (author instructions)
Author notification20th September, 2010
Camera-ready1st October, 2010
Workshop8th November, 2010

Submission

Submission Policy

The review process is double blind as to fit with the ACCV double submission policy. Double submission is allowed with ACCV main conference only. If your paper is submitted to ACCV main conference, please add your paper ID of the ACCV main conference. If a paper is accepted to ACCV main conference, the paper cannot be published both at the ACCV and the workshop. If reviews from the ACCV submission exist, these should be taken into account in the review process of the workshop.

Submission Style

PDF in LNCS 10 pages. Final camera ready due of the accepted papers is 1st of October (midnight of GMT). If the final paper would not be uploaded until 1st of October (midnight of GMT), the paper would not be contained in the final post-workshop proceeding as the workshop volume of ACCV from Springer-Verlag.

Submission Site

Submission through EasyChair

In conjunction with:


http://www.accv2010.org/
The 10th Asian Conference on Computer Vision (ACCV2010) Queenstown, New Zealand