Sendero Group, Davis
SKERI, San Francisco
Harvard Medical School
SKERI, San Francisco
UC, Santa Cruz
University of Oxford
University of Verona
|Workshop Goals | Program (New!) | Financial Support for Attendees (New!)
A growing number of computer vision researchers are becoming interested in applications for persons with visual impairments (VI), including low vision and blindness. Recent advances in algorithms, sensors and embedded computing hold the promise to enable computer vision technology that can address the needs of this disadvantaged population. Developing assistive tools for the VI community requires informed knowledge of several relevant human factor and technological issues:
- The actual problems impairing the daily quality of life of these users;
- An awareness of existing assistive aids;
- A realistic understanding of the possibilities offered by the available interfaces (visual, audio, tactile);
- A system-level approach to the design of algorithms and hardware that takes into consideration practical factors such as size, speed and cost.
This one-day workshop aims to bring together computer vision researchers and experts in VI rehabilitation and assistive technology. Three invited keynote talks given by VI experts will provide an overview of assistive technology for persons with disabilities, concentrating on the needs of the VI community. Attendance by VI experts outside the computer vision community will also be encouraged. By addressing the context in which assistive technology is used and designed, the workshop seeks to help researchers identify fruitful areas of overlap between the most pressing needs of the VI population and the capabilities of computer vision technology. A general discussion session at the end of the workshop will facilitate the exchange of ideas between computer vision researchers and VI experts.
Workshop Program (Final)
Keynote Talk #1
E. Peli, The Shepens Eye Research Institute, Harvard Medical School.
Image Processing Based Aids for Visually Impaired People
Session 1: Travel and Wayfinding - Part I
- W. Zhang and J. Kosecka, George Mason University.
Localization Based on Building Recognition.
- M. S. Uddin and T. Shioyama, Kyoto Institute of Technology.
Bipolarity- and Projective Invariant-Based Zebra-Crossing Detection for the Visually Impaired.
- J. M. Sáez, F. Escolano and A. Peñalver, University of Alicante.
First Steps towards Stereo-based 6DOF SLAM for the Visually Impaired
Session 2: Visual, Audio and Tactile Interfaces
- V. Rabaud and S. Belongie, UC San Diego.
Big Little Icons.
- K. Kahol, Arizona State University.
Rendering Block Diagrams Accessible through Audio-Haptic interface.
- H. Ngo, L. Tao, A. Livingston, M. Zhang and V. Asari, Old Dominion University.
A Visibility Improvement System for Low Vision Drivers by Nonlinear Enhancement of Fused Visible and Infrared Video.
Keynote Talk #2
M. May, Sendero Group.
Accessible Location Information (GPS Indoors and Outdoors): Technologies for Getting Around when You Can't Read Printed Signs.
Session 3: Information Access
- P. Silapachote, J. Weinman, A. Hanson, R. Weiss and M. Mattar, University of Massachusetts.
Automatic Sign Detection and Recognition in Natural Scenes.
- M. A. Mattar, A. R. Hanson and E. G. Learned-Miller, University of Massachusetts.
Sign Classification using Local and Meta-Features.
- A. Chen and A. Yuille, UCLA.
A Time-Efficient Cascade for Real-Time Object Detection: With Applications for the Visually Impaired.
Keynote Talk #3
J. A. Miele, Smith-Kettlewell Eye Research Institute.
User Interface: The Afterthought at the End of the Project
Session 4: Travel and Wayfinding - Part II
- C. Costanzo and G. Iannizzotto, University of Messina.
Badge3D for Visually Impaired.
- B.S. Tjan, P.J. Beckmann, R. Roy, N. Giudice and G.E. Legge, University of Minnesota.
Digital Sign System for Indoor Wayfinding for the Visually Impaired.
Session 5: Special Topics
- F. Dellaert and S. Tariq, Georgia Institute of Technology.
A Multi-Camera Pose Tracker for Assisting the Visually Impaired.
- J. Dowling, W. Boles and A. Maeder, Queensland University of Technology.
Mobility Assessment Using Simulated Artificial Human Vision.
A limited amount of financial support for attendees of CVAVI'05 is available thanks to a grant from the National Science Foundation. There are two (exclusive) types of support:
- Workshop fees. Only workshop attendees who are not
participating in the main CVPR conference qualify for this type of support. Note that the workshop fees are already included in the main conference fees for CVPR.
- Lodging for one day at the conference hotel. Attendees who are also attending CVPR but need an extra day to participate to the workshop qualify for this type of support.
In order to apply for financial support, you need to send an email to Roberto Manduchi (email@example.com) stating:
- Your name, institution, and position;
- Which type of support you are applying for;
- A statement describing the reasons why attending the workshop is an important professional activity for you;
- If you are applying for the first type of support (workshop
fees), a statement attesting that you are not registering for the CVPR main conference.
Applications must be received by May 20 to be considered.