The document discusses the evolution and various types of augmented reality (AR) interfaces, highlighting their definitions, characteristics, and interaction methods. It explores mobile, web-based, and tangible interfaces, emphasizing the integration of natural interactions, gesture recognition, and multimodal input. The potential for intelligent interfaces and future research opportunities in AR technology is also presented.

1. Natural Interfaces for
Augmented Reality
Mark Billinghurst
HIT Lab NZ
University of Canterbury

3. Augmented Reality Definition
 Defining Characteristics [Azuma 97]
 Combines Real and Virtual Images
- Both can be seen at the same time
 Interactive in real-time
- The virtual content can be interacted with
 Registered in 3D
- Virtual objects appear fixed in space

4. AR Today
 Most widely used AR is mobile or web based
 Mobile AR
 Outdoor AR (GPS + compass)
- Layar (10 million+ users), Junaio, etc
 Indoor AR (image based tracking)
- QCAR, String etc
 Web based (Flash)
 Flartoolkit marker tracking
 Markerless tracking

5. AR Interaction
 You can see spatially registered AR..
how can you interact with it?

6. AR Interaction Today
 Mostly simple interaction
 Mobile
 Outdoor (Junaio, Layar, Wikitude, etc)
- Viewing information in place, touch virtual tags
 Indoor (Invizimals, Qualcomm demos)
- Change viewpoint, screen based (touch screen)
 Web based
 Change viewpoint, screen interaction (mouse)

7. History of AR Interaction

8. 1. AR Information Viewing
 Information is registered to
real-world context
 Hand held AR displays
 Interaction
 Manipulation of a window
into information space
 2D/3D virtual viewpoint control
 Applications
 Context-aware information displays
 Examples NaviCam Rekimoto, et al. 1997
 NaviCam, Cameleon, etc

9. Current AR Information Browsers
 Mobile AR
 GPS + compass
 Many Applications
 Layar
 Wikitude
 Acrossair
 PressLite
 Yelp
 AR Car Finder
 …

10. 2. 3D AR Interfaces
 Virtual objects displayed in 3D
physical space and manipulated
 HMDs and 6DOF head-tracking
 6DOF hand trackers for input
 Interaction
 Viewpoint control
 Traditional 3D UI interaction:
Kiyokawa, et al. 2000
manipulation, selection, etc.
 Requires custom input devices

11. VLEGO - AR 3D Interaction

12. 3. Augmented Surfaces and
Tangible Interfaces
 Basic principles
 Virtual objects are projected
on a surface
 Physical objects are used as
controls for virtual objects
 Support for collaboration

13. Augmented Surfaces
 Rekimoto, et al. 1998
 Front projection
 Marker-based tracking
 Multiple projection surfaces

15. Tangible User Interfaces (Ishii 97)
 Create digital shadows
for physical objects
 Foreground
 graspable UI
 Background
 ambient interfaces

16. Tangible Interface: ARgroove
 Collaborative Instrument
 Exploring Physically Based Interaction
 Move and track physical record
 Map physical actions to Midi output
- Translation, rotation
- Tilt, shake
 Limitation
 AR output shown on screen
 Separation between input and output

18. Lessons from Tangible Interfaces
 Benefits
 Physical objects make us smart (affordances, constraints)
 Objects aid collaboration (shared meaning)
 Objects increase understanding (cognitive artifacts)
 Limitations
 Difficult to change object properties
 Limited display capabilities (project onto surface)
 Separation between object and display

19. 4: Tangible AR
 AR overcomes limitation of TUIs
 enhance display possibilities
 merge task/display space
 provide public and private views
 TUI + AR = Tangible AR
 Apply TUI methods to AR interface design

20. Example Tangible AR Applications
 Use of natural physical object manipulations to
control virtual objects
 LevelHead (Oliver)
 Physical cubes become rooms
 VOMAR (Kato 2000)
 Furniture catalog book:
- Turn over the page to see new models
 Paddle interaction:
- Push, shake, incline, hit, scoop

21. VOMAR Interface

22. Evolution of AR Interaction
1. Information Viewing Interfaces
 simple (conceptually!), unobtrusive
§ 3D AR Interfaces
 expressive, creative, require attention
§ Tangible Interfaces
 Embedded into conventional environments
4. Tangible AR
 Combines TUI input + AR display

23. Limitations
 Typical limitations
 Simple/No interaction (viewpoint control)
 Require custom devices
 Single mode interaction
 2D input for 3D (screen based interaction)
 No understanding of real world
 Explicit vs. implicit interaction
 Unintelligent interfaces (no learning)

24. Natural Interaction

25. The Vision of AR

26. To Make the Vision Real..
 Hardware/software requirements
 Contact lens displays
 Free space hand/body tracking
 Environment recognition
 Speech/gesture recognition
 Etc..

27. Natural Interaction
 Automatically detecting real environment
 Environmental awareness
 Physically based interaction
 Gesture Input
 Free-hand interaction
 Multimodal Input
 Speech and gesture interaction
 Implicit rather than Explicit interaction

28. Environmental Awareness

29. AR MicroMachines
 AR experience with environment awareness
and physically-based interaction
 Based on MS Kinect RGB-D sensor
 Augmented environment supports
 occlusion, shadows
 physically-based interaction between real and
virtual objects

30. Operating Environment

31. Architecture
 Our framework uses five libraries:
 OpenNI
 OpenCV
 OPIRA
 Bullet Physics
 OpenSceneGraph

32. System Flow
 The system flow consists of three sections:
 Image Processing and Marker Tracking
 Physics Simulation
 Rendering

33. Physics Simulation
 Create virtual mesh over real world
 Update at 10 fps – can move real objects
 Use by physics engine for collision detection (virtual/real)
 Use by OpenScenegraph for occlusion and shadows

34. Rendering
Occlusion Shadows

35. Natural Gesture Interaction
HIT Lab NZ AR Gesture Library

36. Motivation
AR MicroMachines and PhobiAR
• Treated the environment as
static – no tracking
• Tracked objects in 2D
More realistic interaction requires 3D gesture tracking

37. Motivation
Occlusion Issues
AR MicroMachines only achieved realistic occlusion because the user’s viewpoint matched the Kinect’s
Proper occlusion requires a more complete model of scene objects

38. HITLabNZ’s Gesture Library
Architecture

39. HITLabNZ’s Gesture Library
Architecture
o Supports PCL, OpenNI, OpenCV, and Kinect SDK.
o Provides access to depth, RGB, XYZRGB.
o Usage: Capturing color image, depth image and
concatenated point clouds from a single or multiple cameras
o For example:
Kinect for Xbox 360
Kinect for Windows
Asus Xtion Pro Live

40. HITLabNZ’s Gesture Library
Architecture
o Segment images and point clouds based on color, depth and
space.
o Usage: Segmenting images or point clouds using color
models, depth, or spatial properties such as location, shape
and size.
o For example:
Skin color segmentation
Depth threshold

41. HITLabNZ’s Gesture Library
Architecture
o Identify and track objects between frames based on
XYZRGB.
o Usage: Identifying current position/orientation of the
tracked object in space.
o For example:
Training set of hand
poses, colors
represent unique
regions of the hand.
Raw output (without-
cleaning) classified
on real hand input
(depth image).

42. HITLabNZ’s Gesture Library
Architecture
o Hand Recognition/Modeling
 Skeleton based (for low resolution
approximation)
 Model based (for more accurate
representation)
o Object Modeling (identification and tracking rigid-
body objects)
o Physical Modeling (physical interaction)
 Sphere Proxy
 Model based
 Mesh based
o Usage: For general spatial interaction in AR/VR
environment

43. Method
Represent models as collections of spheres moving with
the models in the Bullet physics engine

44. Method
Render AR scene with OpenSceneGraph, using depth map
for occlusion
Shadows yet to be implemented

45. Results

46. HITLabNZ’s Gesture Library
Architecture
o Static (hand pose recognition)
o Dynamic (meaningful movement recognition)
o Context-based gesture recognition (gestures with context,
e.g. pointing)
o Usage: Issuing commands/anticipating user intention and
high level interaction.

47. Multimodal Interaction

48. Multimodal Interaction
 Combined speech input
 Gesture and Speech complimentary
 Speech
- modal commands, quantities
 Gesture
- selection, motion, qualities
 Previous work found multimodal interfaces
intuitive for 2D/3D graphics interaction

49. 1. Marker Based Multimodal Interface
 Add speech recognition to VOMAR
 Paddle + speech commands

51. Commands Recognized
 Create Command "Make a blue chair": to create a virtual
object and place it on the paddle.
 Duplicate Command "Copy this": to duplicate a virtual object
and place it on the paddle.
 Grab Command "Grab table": to select a virtual object and
place it on the paddle.
 Place Command "Place here": to place the attached object in
the workspace.
 Move Command "Move the couch": to attach a virtual object
in the workspace to the paddle so that it follows the paddle
movement.

52. System Architecture

53. Object Relationships
"Put chair behind the table”
Where is behind?
View specific regions

54. User Evaluation
 Performance time
 Speech + static paddle significantly faster
 Gesture-only condition less accurate for position/orientation
 Users preferred speech + paddle input

55. Subjective Surveys

56. 2. Free Hand Multimodal Input
 Use free hand to interact with AR content
 Recognize simple gestures
 No marker tracking
Point Move Pick/Drop

57. Multimodal Architecture

58. Multimodal Fusion

59. Hand Occlusion

60. User Evaluation
 Change object shape, colour and position
 Conditions
 Speech only, gesture only, multimodal
 Measure
 performance time, error, subjective survey

61. Experimental Setup
Change object shape
and colour

62. Results
 Average performance time (MMI, speech fastest)
 Gesture: 15.44s
 Speech: 12.38s
 Multimodal: 11.78s
 No difference in user errors
 User subjective survey
 Q1: How natural was it to manipulate the object?
- MMI, speech significantly better
 70% preferred MMI, 25% speech only, 5% gesture only

63. Future Directions

64. Future Research
 Mobile real world capture
 Mobile gesture input
 Intelligent interfaces
 Virtual characters

65. Natural Gesture Interaction on Mobile
 Use mobile camera for hand tracking
 Fingertip detection

66. Evaluation
 Gesture input more than twice as slow as touch
 No difference in naturalness

67. Intelligent Interfaces
 Most AR systems stupid
 Don’t recognize user behaviour
 Don’t provide feedback
 Don’t adapt to user
 Especially important for training
 Scaffolded learning
 Moving beyond check-lists of actions

68. Intelligent Interfaces
 AR interface + intelligent tutoring system
 ASPIRE constraint based system (from UC)
 Constraints
- relevance cond., satisfaction cond., feedback

69. Domain Ontology

70. Intelligent Feedback
 Actively monitors user behaviour
 Implicit vs. explicit interaction
 Provides corrective feedback

72. Evaluation Results
 16 subjects, with and without ITS
 Improved task completion
 Improved learning

73. Intelligent Agents
 AR characters
 Virtual embodiment of system
 Multimodal input/output
 Examples
 AR Lego, Welbo, etc
 Mr Virtuoso
- AR character more real, more fun
- On-screen 3D and AR similar in usefulness

74. Conclusions

75. Conclusions
 AR traditionally involves tangible interaction
 New technologies support natural interaction
 Environment capture
 Natural gestures
 Multimodal interaction
 Opportunities for future research
 Mobile, intelligent systems, characters

76. More Information
• Mark Billinghurst
– mark.billinghurst@hitlabnz.org
• Website
– http://www.hitlabnz.org/