mobility

Document Sample
mobility Powered By Docstoc
					Mobility Aid For The Blind



    By Amir Gonnen
      The oldest aids
 Walking Cane
 Guide dog
 Problems:
 – Skills and Training phase
 – Range
 – Very little information conveyed
  A Technological Solution
  Sensor       Computer       Output Device
Information      Digital         Perceptual
 about the     Processing     input perceived
environment                     by the blind



This is where I’m going to focus
  Recent Developments
 Soundscapes  from “The vOICe”
 “Stereo vision system for the Visually
  Impaired”, University of Guelph,
  Canada
 The “NavBelt”
 The “GuideCane”
“The vOICe”
Stereo Vision
The “NavBelt”
The “GuideCane”
            Problems
 Too much information
 Missing sub-conscious vision
  processes
  – Interpretation of a continuous 2D
    signal into a set of recognizable
    objects in a 3D space
  – Movement velocity and direction
              Solution
 Emulating   some of the sub-
  conscious processes in a computer
 Describe the world as a set of
  objects in a 3D space
Intro to the Simulation
       Do We Get A Better
          Perception?
   The Simulation:
    – A 3D room with several objects
    – Each object has its own sound
   The sound is located at the object
    – Stereo sound  the direction of the object
    – Volume  How far is the object
   The beat scanner
    – divides the field view into sectors
    – More accurate perceptual direction
 More About the Simulation
 Thesimulation solves several
 problems:
  – How to separate sounds of different
    objects, so that not all objects will be
    heard at once ?
  – How to give a good indication of object’s
    type, direction and distance at the same
    time ?
 Tradeoffbetween Resolution in Time
 and in Space.
           Experiment
 Let the subject close her eyes and
  guess which object is visible, its
  direction and its distance.
 Results:
  – Recognition was correct in 80%-90% of
    the cases.
  – Notable improvement over time.
Experiment Video
           Conclusion
 Still a lot of work to be done
  – Computer vision: how do we recognize
    objects on 3D space using a raw 2D
    signal ?
  – How do we assign sounds to different
    objects ?
  – How much information can be perceived
    using sound in a given time frame ?
 Realprogress could be achieved when
 we understand and able to emulate the
 cognitive processes of human vision

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:49
posted:8/21/2012
language:English
pages:16