SLIDE 1
Outline
- Why Localization?
- Why Computer Vision?
- GPS
- Motion Capture System
- Triangulation
- PnP
- 3D Cameras
- SLAM
- Summary
Robot Indoor Localization Robot Based on Computer Vision - - PowerPoint PPT Presentation
Robot Indoor Localization Robot Based on Computer Vision - - PowerPoint PPT Presentation
Indoor Localization Robot Indoor Localization Robot Based on Computer Vision Ubiquitous Computing Course 2015 Soliman Nasser Outline Why Localization? Why Computer Vision? GPS Motion Capture System Triangulation PnP
SLIDE 2
SLIDE 3
Why Localization ?
1)History …....
SLIDE 4
Why Localization ?
2)Robot Navigation and Mapping
SLIDE 5
Why Localization ?
3)Guiding (Museum...) 4)Airports, Malls, Supermarket, … 5)more and more... . . .
SLIDE 6
Why Computer Vision ?
In previous lectures, we saw a lot of techniques for Indoor Localization !
(Which is not CV)
Question:
Problem solved?
SLIDE 7
Why Computer Vision ?
In previous lectures, we saw a lot of techniques for Indoor Localization !
(Which is not CV)
Question:
Problem solved?
Answer:
SLIDE 8
Why Computer Vision ?
Microsoft Indoor Localization Competition - IPSN 2015
SLIDE 9
Why Computer Vision ?
Microsoft Indoor Localization Competition - IPSN 2015 Problem ?? Accuracy
SLIDE 10
Why Not GPS ?
* works great outdoor Eample:
Dji Phantom hovering outdoor – windy day
/home/soliman/UbiquitousComputing/phantom-outdoor.mp4
SLIDE 11
Why Not GPS ?
** doesn't work indoor
There is no GPS signal
Eample:
Dji Phantom indoor
/home/soliman/UbiquitousComputing/phantom-indoor.mov
SLIDE 12
Motion Capture System
Indusry manufactoring: Vicon, OptiTrack, … Accuracy: millimeters Cost: Very ^ very ^ very High IR Spectrum → Only indoor Used usually in research labs
SLIDE 13
Motion Capture System
Very High FPS localiztion: 100 – 1000 FPS 6DOF
SLIDE 14
Motion Capture System
SLIDE 15
Motion Capture System
Example: Autonomous micro-quadcopter Flying indoor (lab) 100 FPS – why we need such a high FPS?
/home/soliman/UbiquitousComputing/ladybird-mute.mov /home/soliman/UbiquitousComputing/VCQ.mov /home/soliman/UbiquitousComputing/ladybird-neimanem.mp4
SLIDE 16
Triangulation
Triangulation is the process of determining 3D world coordinates for an object given 2D views from multiple cameras.
SLIDE 17
Triangulation
SLIDE 18
Prespective n Point
The aim of the Perspective-n-point problem is to determine the position and orientation of a camera given its intrinsic parameters and a set of n correspondences between 3D points 3D lines.
SLIDE 19
Prespective n Point
SLIDE 20
Prespective n Point
How we can estimate 6DOF from chessboard?!! 1)Chesboard corners detection (2D points) 2)Given 3D points – constant 3)Fiding corresponding between 2D and 3D 4)Solve PnP
SLIDE 21
Prespective n Point
Example: *AR Drone (as a camera) *Chessboard (known 3D points) AR Drone Parrot, flying automously and follow the chessboard. (About 10FPS “only“)
/home/soliman/UbiquitousComputing/ARDrone-PnP.mp4
SLIDE 22
3D Cameras
3D Cameras: Unlike normal 2D cameras, 3D cameras output an RGB-D matrix. RGB-D: besides a normal RGB output, depth info is also available.
SLIDE 23
3D Cameras
Microsoft Kinect 360: Patterns are projected (IR lights – different frequencies). Triangulation method applied with the IR camera to estimate depth. Why not using 2 cameras? Works indoor only – why?
SLIDE 24
RGBDSLAM
RGBDSLAM = RGBD + SLAM SLAM: Simultaneous Localization And Mapping
SLIDE 25
SLAM using Kinect
TurtleBot – robot with kinect Localizaion and Mapping using kinect
/home/soliman/UbiquitousComputing/turtlebot.mp4
SLIDE 26
Summary
Triangulation
PnP 3D cameras GPS Other sensors Accuracy Very High Med Very High (limited dist) High Low Cost $$$$ $$ $$ $ $ Time complexity Low Low+ Med Med Low Indoor/Outdoor Usually In Usua lly In In Out In/Out Usage complexity High Med Med Low Depends
SLIDE 27