magic book: enhancing natural feature tracking with the user´s movement context

27
Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context Felix Loew Master Thesis (TU München) 21.01.200 5

Upload: stash

Post on 01-Feb-2016

31 views

Category:

Documents


0 download

DESCRIPTION

Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context. Felix Loew Master Thesis (TU München). 21.01.2005. Outline. Context-Awareness and Augmented Reality Vision Based Tracking: Natural Feature Tracking A „Magic Book“ User Study Software Architecture (DWARF ) - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Felix Loew

Master Thesis (TU München)

21.01.2005

Page 2: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Context-Awareness and Augmented Reality

• Vision Based Tracking: Natural Feature Tracking

• A „Magic Book“ User Study

• Software Architecture (DWARF )

• Expected results and conclusions

Outline

Page 3: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Context-Awareness and Augmented Reality

• A system has to adopt to the user´s behaviour!

• A system has to learn how it is used!

• New intuitive methods of interaction are required!

• The system has to disappear (Marc Weiser)!

Page 4: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

The „Magic Book“ in this context

• User has to „learn“ how it is used

• Very error-prone to movement– Movement of the handheld device is not

considered in the tracking routine– Vision based tracking loses orientation– User has to reinitialize the tracking (looking on

the marker again)– Immersion decreases!

Page 5: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

My Idea: Enhancing the Magic Book

Inertial Tracker: Intersense, Inertial Cube3 (~120FPS)

Vision Based Tracking: NFT (~20 FPS)

Movement

Page 6: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Context-Awareness and Augmented Reality

• Vision Based Tracking: Natural Feature Tracking

• A „Magic Book“ User Study

• Software Architecture (DWARF )

• Summary, Conclusions & Limitations

Outline

Page 7: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Basics: Natural Feature Tracking

Frame 1 Frame 2

Frame 3 Frame 4

Page 8: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• NFTARToolkit (Kato): 2D planar scenes• Estimation of feature position in next frame

– It is not realistic that no movement occurs– Linear estimation– Kalman Filter

• Within a window the “best match” with the template is searched (Template Matching)

• For every pixel within window the similarity with the template is calculated (Normalized Cross Correlation)

Basics: Natural Feature Tracking

Page 9: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Template Matching

Page 10: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Calculates similarity between template and area around search point– values [-1..1]

• Best match is considered as feature point in current frame (threshold ~0.7)!

• Computational expensive!– O (templateSize2 * searchSize2)

Normalized Cross Correlation

Page 11: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

My approach

• Consider movement as well!

• Use additional tracking device (Inertial Tracker / 3DOF)

• Naive approach:much movement large search window

low movement small search window

• Dynamic configuration during runtime

Page 12: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

What is much movement? Which movements actually occur?How does a user use such an application?

USER STUDY ON MAGIC BOOK

My approach

Page 13: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Context-Awareness and Augmented Reality

• Vision Based Tracking: Natural Feature Tracking

• A „Magic Book“ User Study

• Software Architecture (DWARF )

• Expected results and conclusions

Outline

Page 14: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Goals– Detecting specific movement patterns– Derive Movement model– Estimation of a correlation between changes in

orientation and feature points coordinates

User Study Setup

Orientation (Handheld, 3D)

Position (FP-Coords, 2D)

Page 15: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

User Study Setup

• Tracking Orientation and Position (6DOF)– Magnetic Tracker:

Flock of Birds

– Bird1: Magic Book

– Bird2: Handheld device

– Calibration to Magic Book coordinate system (Bird1)

Page 16: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Magnetic Tracker– Timestamp

– Position P = (px,py,pz)

– Orientation (quaternion) Q = (v,s)

• NFT– Timestamp

– 4 feature points per frame• Id

• Screen-Position S = (sx,sy)

Logging

Page 17: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Magnetic Tracker

pics\2_20_1.Case2.Flock.xls

• NFT

pics\2_20_1.Case2.Coords.xls

Logging

Page 18: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

User Tasks

• Comparable Tasks (Navigation Tasks)– User has to answer certain questions (Overview,

Focus and Search Tasks)• „What is the girls hair color?“

• „How many people do you see?“

• Free Tasks– User can use Magic Book freely

Page 19: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Evaluation

• Ideas for evaluation (Correlation)– Which angular offset (FOB) causes which

coordinate offset (NFT)?– Which angular velocities occur?– Which rotations occur?– Which changes of position occur?– Is there a common movement profile or are

there serious differences between different users?

Page 20: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Evaluation

• Find mapping between:

• Configure Software Architecture with this information

orientation search window

Page 21: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Context-Awareness and Augmented Reality

• Vision Based Tracking: Natural Feature Tracking

• A „Magic Book“ User Study

• Software Architecture (DWARF)

• Expected results and conclusions

Outline

Page 22: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Software Architecture (DWARF)

NFT ARToolkit

Page 23: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Dynamic Configuration

Page 24: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Context-Awareness and Augmented Reality

• Vision Based Tracking: Natural Feature Tracking

• A „Magic Book“ User Study

• Software Architecture (DWARF)

• Expected results and conclusions

Outline

Page 25: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Conclusions & Summary

• Hybrid Tracking approach to consider context information as well– Movement context– 2DO: What about user context?

• User Study on Magic Book (work in progress)– Expected conclusions on usage of Magic Book– Find correlation between movement and NFT properties– Process a configuration out of the study– Derive Movement model of the Magic Book– Limitation: Very task specific (features are not moving, only 2D)!

• Software Architecture

Page 26: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

• Heaps of work– I won’t cover everything I want to do

• Other “sensor-fusion” approaches might be more suited (Kalman-Filtering)

• Evaluation of User Study will be hard

• Is there an abstraction for NFT based applications?

Limitations & 2DO´s

Page 27: Magic Book: Enhancing Natural Feature Tracking with the User´s Movement Context

Thanks

• I would be glad if some of you want to join the study!