A New Omnidirectional Vision Sensor for the Spatial Semantic Hierarchy PowerPoint PPT Presentation

presentation player overlay
About This Presentation
Transcript and Presenter's Notes

Title: A New Omnidirectional Vision Sensor for the Spatial Semantic Hierarchy


1
A New Omnidirectional Vision Sensor for the
Spatial Semantic Hierarchy
  • E. Menegatti, M. Wright, E. Pagello

Dep. of Electronics and Informatics
University of Padua ITALY
2
Introduction
  • Robots task
  • Building a topological map of an unknown
    environment
  • Sensor
  • Omnidirectional vision system
  • Works aim
  • Prove effectiveness of omnidirectional sensors
    for Spatial Semantic Hierarchy

3
Spatial Semantic Hierarchy...
  • ... A model of the human knowledge of large
    spaces
  • Layers
  • Sensory Level
  • Control Level
  • Causal Level
  • Topological Level
  • Metrical Level

Interface with the robots sensory system
Control Laws, Transition of State,
Distinctiveness Measure
Minimal set of Places, Paths and Regions
View, Action, Distinct Place Abstracts Discrete
from Continous
Distance, Direction, Shape Useful, but seldom
essential
4
Omnidirectional Camera
  • Composed of
  • Standard Colour Camera
  • Convex Mirror
  • Perspex Cylinder

5
Pros e Cons
  • Advantages
  • Wide vision field
  • High speed
  • Vertical Lines
  • Rotational Invariance
  • Disadvantages
  • Low Resolution
  • Distortions
  • Low readability

6
Omnidir. Vision and SSH
  • View Omnidirectional image
  • Exploring around the block
  • Discriminate b/t turns and travels
  • Effective Distinctiveness measure

7
Assumptions
  • Man-made environment
  • Floor flat and horizontal
  • Wall and objects surfaces are vertical
  • Static objects
  • Constant Lighting
  • Robot translates or rotates
  • No encoders

8
Features and Events
  • Feature
  • Vertical Edges
  • Events
  • A new edge
  • An edge disappear
  • Two edges 180 apart
  • Two pairs of edges 180 apart

9
Experiments
  • Tasks of Caboto
  • Navigation
  • Map building
  • Techniques
  • Edge detection
  • Colour marking

10
Cabotos Images
11
(No Transcript)
12
Results
  • Correct tracking of edges
  • Recognization of actions
  • Calculation of the turn angle

The path segmentation
13
Mirror Design
Mirror shape should depend on robot task!
  • Design custom mirror profile
  • Maximise resolution in ROIs

Mirror Profile
14
Our new mirror
15
Conclusion
  • Omnidirectional vision sensor is a good sensor
    for map building with SSH
  • Egomotion of the robot was estimated without
    active vision
  • The use of a mirror designed for this application
    will improve the system

16
Omnidirectional Cameras
  • Compound-eye camera
  • (from Univ. of Maryland, College Park. )
  • Panoramic cameras (from Apple)
  • Omnidirectional cameras
  • (from University of Picardie - France)
Write a Comment
User Comments (0)
About PowerShow.com