Project/Area Number |
25560278
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Multi-year Fund |
Research Field |
Rehabilitation science/Welfare engineering
|
Research Institution | University of Tsukuba |
Principal Investigator |
|
Co-Investigator(Kenkyū-buntansha) |
MIZUNO Shinji 愛知工業大学, 情報科学部, 教授 (20314099)
EZAKI Nobuo 鳥羽商船高等専門学校, 制御情報工学科, 教授 (30311038)
AOYAGI Mayumi 愛知教育大学, 教育学部, 准教授 (40550562)
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2013: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
Keywords | 視覚障がい者 / 支援システム / 測距センサー / 画像処理 / ユーザインターフェース / 福祉工学 / Microsoft Kinect / 物体認識 / 音声認識エンジン / ユーザ実験 |
Outline of Final Research Achievements |
In this research project, we proposed an assistive system to help visually impaired individuals (users) not only detect obstacles in their vicinity, but also recognize what these objects are. The following three items were conducted: (1) we built recognition methods of several objects, such as chairs, desks, stairs, elevators, and handrails, by use of RGB-D sensors, such as Microsoft Kinect. (2) We also developed user interface systems based on vibrators, loudspeakers, microphones, and voice recognition technique. The user interface system allowed users to instruct the system and to understand the output of the system easily. (3) We conducted user studies to evaluate our assistive system. We compare our system with a conventional white cane, and confirmed that our system was more effective to find target objects.
|