The objective of this proposal is to tackle the problem of way finding (finding one's way in an environment), faced by blind and severely visually impaired persons who are unable to find or read signs, landmarks and locations. We propose a novel and very inexpensive environmental labeling system to provide this population with access to information needed for indoor way finding (where GPS is not available). The system uses simple passive landmark symbols printed on paper or other material, placed next to text, Braille signs or barcode at locations of interest (offices, bathrooms, etc.) in an environment such as an office building. These printed patterns contain spatial and semantic information that is detected using computer vision algorithms running on a standard camera cell phone. By scanning the environment with the device, which detects all landmark symbols in its line of sight up to distances of 10 meters, the user can determine his or her approximate location in the environment as well as the information encoded near each landmark symbol. The system extracts this information in real-time and communicates it to the user by sound, synthesized speech and/or tactile feedback. This information includes spatial (e.g. audio tones to indicate the presence and direction of a label in the camera's field of view) and semantic information (""""""""Mr. Johnson's office, room 429, at 11 o'clock""""""""). The research proposed here will produce a prototype system that will be tested by blind and low vision subjects. Our team includes a blind expert on psychoacoustics (and other in-house blind staff) and an expert consultant on low-vision way finding and navigation to help optimize the user interface and guide development into a practical, easy-to-use system. ? ? ? ?

Agency
National Institute of Health (NIH)
Institute
National Eye Institute (NEI)
Type
Exploratory/Developmental Grants (R21)
Project #
1R21EY017003-01A1
Application #
7143942
Study Section
Special Emphasis Panel (ZRG1-BDCN-F (12))
Program Officer
Oberdorfer, Michael
Project Start
2006-09-30
Project End
2008-08-31
Budget Start
2006-09-30
Budget End
2007-08-31
Support Year
1
Fiscal Year
2006
Total Cost
$224,601
Indirect Cost
Name
Smith-Kettlewell Eye Research Institute
Department
Type
DUNS #
073121105
City
San Francisco
State
CA
Country
United States
Zip Code
94115
Gallo, Orazio; Manduchi, Roberto (2011) Reading 1D Barcodes with Mobile Phones Using Deformable Templates. IEEE Trans Pattern Anal Mach Intell 33:1834-43
Coughlan, James; Manduchi, Roberto (2009) FUNCTIONAL ASSESSMENT OF A CAMERA PHONE-BASED WAYFINDING SYSTEM OPERATED BY BLIND AND VISUALLY IMPAIRED USERS. Int J Artif Intell Tools 18:379-397
Coughlan, J; Manduchi, R (2009) A Mobile Phone Wayfinding System for Visually Impaired Users. Assist technol Res Ser 25:849
Gallo, Orazio; Manduchi, Roberto (2009) Reading Challenging Barcodes with Cameras. Proc IEEE Workshop Appl Comput Vis 2009:1-6
Manduchi, R; Coughlan, J; Ivanchenko, V (2008) Search Strategies of Visually Impaired Persons using a Camera Phone Wayfinding System. Lect Notes Comput Sci 5105:1135-1140