A New Omnidirectional Vision Sensor for the Spatial Semantic Hierarchy E. Menegatti, M. Wright, E. Pagello Dep. of Electronics and Informatics University.

Slides:



Advertisements
Similar presentations
By: Mani Baghaei Fard.  During recent years number of moving vehicles in roads and highways has been considerably increased.
Advertisements

Automatic determination of skeletal age from hand radiographs of children Image Science Institute Utrecht University C.A.Maas.
ICRA 2002 Topological Mobile Robot Localization Using Fast Vision Techniques Paul Blaer and Peter Allen Dept. of Computer Science, Columbia University.
Kiyoshi Irie, Tomoaki Yoshida, and Masahiro Tomono 2011 IEEE International Conference on Robotics and Automation Shanghai International Conference Center.
Designing an omnidirectional vision system for a goalkeeper robot E. Menegatti, F. Nori, E. Pagello, C. Pellizzari, D. Spagnoli Dept. of Electronics and.
GIS and Image Processing for Environmental Analysis with Outdoor Mobile Robots School of Electrical & Electronic Engineering Queen’s University Belfast.
Uncertainty Representation. Gaussian Distribution variance Standard deviation.
Localization of Piled Boxes by Means of the Hough Transform Dimitrios Katsoulas Institute for Pattern Recognition and Image Processing University of Freiburg.
1 of 25 1 of 22 Blind-Spot Experiment Draw an image similar to that below on a piece of paper (the dot and cross are about 6 inches apart) Close your right.
Applications of Image Processing. Outline What YOU are going to learn Image Processing in use.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
ECE 7340: Building Intelligent Robots QUALITATIVE NAVIGATION FOR MOBILE ROBOTS Tod S. Levitt Daryl T. Lawton Presented by: Aniket Samant.
Cooperative Distributed Vision for Mobile Robots E. Menegatti and E. Pagello IAS-Lab Dept. of Electronics and Informatics The University of Padua Italy.
Overview of Our Sensors For Robotics
CCU VISION LABORATORY Object Speed Measurements Using Motion Blurred Images 林惠勇 中正大學電機系
Visual Odometry for Ground Vehicle Applications David Nister, Oleg Naroditsky, James Bergen Sarnoff Corporation, CN5300 Princeton, NJ CPSC 643, Presentation.
Christian Siagian Laurent Itti Univ. Southern California, CA, USA
Dynamic Medial Axis Based Motion Planning in Sensor Networks Lan Lin and Hyunyoung Lee Department of Computer Science University of Denver
Study on Mobile Robot Navigation Techniques Presenter: 林易增 2008/8/26.
Vision for mobile robot navigation Jannes Eindhoven
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Geometric Probing with Light Beacons on Multiple Mobile Robots Sarah Bergbreiter CS287 Project Presentation May 1, 2002.
Patent Liability Analysis Andrew Loveless. Potential Patent Infringement Autonomous obstacle avoidance 7,587,260 – Autonomous navigation system and method.
Jason Li Jeremy Fowers Ground Target Following for Unmanned Aerial Vehicles.
November 29, 2004AI: Chapter 24: Perception1 Artificial Intelligence Chapter 24: Perception Michael Scherger Department of Computer Science Kent State.
Using Incomplete Online Metric Maps for Topological Exploration with the Gap Navigation Tree Liz Murphy and Paul Newman Mobile Robotics Research Group,
ROBOT LOCALISATION & MAPPING: NAVIGATION Ken Birbeck.
Localisation & Navigation
INSTITUTO DE SISTEMAS E ROBÓTICA Computer and Robot Vision Laboratory OMNIVIEWS DEMOS SURVEILLANCE DEMOS TRANSMISSION.
SPIE'01CIRL-JHU1 Dynamic Composition of Tracking Primitives for Interactive Vision-Guided Navigation D. Burschka and G. Hager Computational Interaction.
9 Introduction to AI Robotics (MIT Press), copyright Robin Murphy 2000 Chapter 9: Topological Path Planning1 Part II Chapter 9: Topological Path Planning.
Biologically-inspired Visual Landmark Navigation for Mobile Robots
3D SLAM for Omni-directional Camera
Vision & Recognition. From a different direction At different times, particularly if it has been modified in the interval In different light A particular.
Localization for Mobile Robot Using Monocular Vision Hyunsik Ahn Jan Tongmyong University.
Metrology 1.Perspective distortion. 2.Depth is lost.
University of Amsterdam Search, Navigate, and Actuate - Qualitative Navigation Arnoud Visser 1 Search, Navigate, and Actuate Qualitative Navigation.
Toward image-based localization for AIBO using wavelet transform Department of Information Engineering University of Padua, Italy A. Pretto, E. Menegatti,
The.mxd File Lecture L4 –Data Models Ch. 2, pp 54-End.
General ideas to communicate Show one particular Example of localization based on vertical lines. Camera Projections Example of Jacobian to find solution.
Negative Power or Negative Rotation makes robot go backwards. But if both are negative, the robot will go forward! Move Steering Block.
Computer Vision Lecture #10 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical.
Dow Now What do you already know about light and how it moves?
Automatic License Plate Location Using Template Matching University of Wisconsin - Madison ECE 533 Image Processing Fall 2004 Project Kerry Widder.
The geometry of the system consisting of the hyperbolic mirror and the CCD camera is shown to the right. The points on the mirror surface can be expressed.
112/5/ :54 Graphics II Image Based Rendering Session 11.
University “Ss. Cyril and Methodus” SKOPJE Cluster-based MDS Algorithm for Nodes Localization in Wireless Sensor Networks Ass. Biljana Stojkoska.
Turning Autonomous Navigation and Mapping Using Monocular Low-Resolution Grayscale Vision VIDYA MURALI AND STAN BIRCHFIELD CLEMSON UNIVERSITY ABSTRACT.
Robotics Club: 5:30 this evening
COMP 417 – Jan 12 th, 2006 Guest Lecturer: David Meger Topic: Camera Networks for Robot Localization.
Colour and Texture. Extract 3-D information Using Vision Extract 3-D information for performing certain tasks such as manipulation, navigation, and recognition.
Curb Detector.
Fixed-Center Pan-Tilt Projector and Its Calibration Methods Ikuhisa Mitsugami Norimichi Ukita Masatsugu Kidode Graduate School of Information Science Nara.
Lecture 9 Feature Extraction and Motion Estimation Slides by: Michael Black Clark F. Olson Jean Ponce.
Light: Geometric Optics. The Ray Model of Light The ray model of light assumes that light travels in straight-line path called rays.
Introduction to Scale Space and Deep Structure. Importance of Scale Painting by Dali Objects exist at certain ranges of scale. It is not known a priory.
Learning Roomba Module 5 - Localization. Outline What is Localization? Why is Localization important? Why is Localization hard? Some Approaches Using.
Reading 1D Barcodes with Mobile Phones Using Deformable Templates.
Portable Camera-Based Assistive Text and Product Label Reading From Hand-Held Objects for Blind Persons.
Sensors For Robotics Robotics Academy All Rights Reserved.
Contents Team introduction Project Introduction Applicability
(C) 2001, Ernest L. Hall, University of Cincinnati
Sensors For Robotics Robotics Academy All Rights Reserved.
Spatial Semantic Hierarchy (SSH)
Zhigang Zhu, K. Deepak Rajasekar Allen R. Hanson, Edward M. Riseman
Vehicle Segmentation and Tracking in the Presence of Occlusions
Dongwook Kim, Beomjun Kim, Taeyoung Chung, and Kyongsu Yi
RGB-D Image for Scene Recognition by Jiaqi Guo
Things translate (slide) when they move in a perfectly straight path.
Brief Review of Recognition + Context
Presentation transcript:

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

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Introduction Robot’s task: Building a topological map of an unknown environment; Building a topological map of an unknown environment;Sensor: Omnidirectional vision system; Work’s aim: Prove effectiveness of omnidirectional sensors for Spatial Semantic Hierarchy;

E. Menegatti - A New Omnidirectional Vision Sensor for SSH 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 robot’s sensory system Control Laws, Transition of State, Distinctiveness Measure View, Action, Distinct Place Abstracts Discrete from Continous Minimal set of Places, Paths and Regions Distance, Direction, Shape Useful, but seldom essential

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Omnidirectional Camera Composed of: n Standard Colour Camera n Convex Mirror n Perspex Cylinder

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Pros e Cons Advantages n Wide vision field n High speed n Vertical Lines n Rotational Invariance Disadvantages n Low Resolution n Distortions n Low readability

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Omnidir. Vision and SSH n View Omnidirectional image n Discriminate b/t “turns” and “travels” n Effective Distinctiveness measure P2 P4P3 P5P1 –Exploring around the block

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Assumptions n Man-made environment n Floor flat and horizontal n Wall and objects surfaces are vertical n Static objects n Constant Lighting n Robot translates or rotates n No encoders

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Features and Events Feature: –Vertical Edges Events: –A new edge –An edge disappear –Two edges 180° apart –Two pairs of edges 180° apart

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Experiments Tasks of Caboto: n Navigation; n Map building; Techniques: n Edge detection; n Colour marking;

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Caboto’s Images

E. Menegatti - A New Omnidirectional Vision Sensor for SSH

Results n Correct tracking of edges n Recognization of actions n Calculation of the turn angle The path segmentation

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Mirror Design n Design custom mirror profile n Maximise resolution in ROIs Mirror Profile Mirror shape should depend on robot task!

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Our new mirror

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Conclusion n Omnidirectional vision sensor is a good sensor for map building with SSH n Egomotion of the robot was estimated without active vision n The use of a mirror designed for this application will improve the system

E. Menegatti - A New Omnidirectional Vision Sensor for SSH Omnidirectional Cameras n Compound-eye camera (from (from Univ. of Maryland, College Park. ) n Panoramic cameras (from Apple) n Omnidirectional cameras (from (from University of Picardie - France)