User Interface Engineering HS 2013

Size: px

Start display at page:

Download "User Interface Engineering HS 2013"

Adrian Roberts
6 years ago
Views:

1 User Interface Engineering HS 2013 Augmented Reality Part I Introduction, Definitions, Application Areas ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

2 Outline Introduction to Augmented Reality Definition and brief history of AR and VR Mobile Augmented Reality Camera and object tracking Marker based Natural feature tracking Visual SLAM Dense Reconstruction ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

3 What is Augmented Reality? ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

5 Augmented Reality Definition Defining Characteristics [Azuma 97] Combines Real and Virtual Information Both can be perceived at the same time Interactive in real-time The virtual content can be interacted with Registered in 3D Virtual objects appear fixed in space ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

6 Milgram s Reality-Virtuality continuum Mixed Reality Real Environment Augmented Reality (AR) Augmented Virtuality (AV) Virtual Environment Reality - Virtuality (RV) Continuum ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

7 A Brief History of AR and VR ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

the existence of matter. A chair displayed in such a room would be good enough to sit in.

8 The Sword of Damocles. Ivan Sutherland The ultimate display would, of course, be a room within which the computer can control the existence of matter. A chair displayed in such a room would be good enough to sit in. Handcuffs displayed in such a room would be confining, and a bullet displayed in such a room would kill. - The Ultimate Display. Ivan Sutherland

9 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

10 Virtual Reality Immersive VR Head mounted display, gloves Separation from the real world ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

11 VR Today $3-5 Billion VR business (+ > $150 Billion Graphics Industry) Visualization, simulation, gaming, CAD/CAE, multimedia, graphics arts ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

12 AR vs VR Virtual Reality: Replaces Reality Scene Generation: requires realistic images Display Device: fully immersive, wide FOV Tracking and Sensing: low accuracy is okay Augmented Reality: Enhances Reality Scene Generation: minimal rendering okay Display Device: non-immersive, small FOV Tracking and Sensing: high accuracy needed ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

13 A Brief History of AR (1) s: US Air Force Super Cockpit (T. Furness) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

14 A Brief History of AR (2) Early 1990 s: Boeing coined the term AR. Wire harness assembly application begun (T. Caudell, D. Mizell). ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

UNC hybrid magnetic-vision tracker ETH Zürich Departement Computer

15 A Brief History of AR (3) 1994: Motion stabilized display [Azuma] 1995: Fiducial tracking in video see-through [Bajura / Neumann] 1996: UNC hybrid magnetic-vision tracker ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

interaction Late 90 s: Augmented sports broadcasts ETH Zürich Departement

16 A Brief History of AR (4) 1996: MIT Wearable Computing efforts 1998: Dedicated conferences begin Late 90 s: Collaboration, outdoor, interaction Late 90 s: Augmented sports broadcasts ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

17 Spatial Augmented Reality: Merging Real and Virtual Worlds. O. Bimber, R. Raskar Augmented Reality - Technologies ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

18 Mobile Augmented Reality ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Applications Context-aware information displays ETH Zürich Departement

19 NaviCam (Rekimoto, 1995) Information is registered to real-world context Hand held AR displays Interaction Manipulation of a window into information space Applications Context-aware information displays ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

20 Backpack/Wearable AR 1997 Backpack AR Feiner s Touring Machine AR Quake (Thomas) Tinmith (Piekarski) MCAR (Reitmayr) Bulky, HMD based

Mobile AR: Touring Machine (1997) University of Columbia Feiner, MacIntyre, Höllerer, Webster Combines See through head mounted display GPS tracking

21 Mobile AR: Touring Machine (1997) University of Columbia Feiner, MacIntyre, Höllerer, Webster Combines See through head mounted display GPS tracking Orientation sensor Backpack PC (custom) Tablet input ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

22 MARS View Virtual tags overlaid on the real world Information in place ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

23 1997 Philip Kahn invents camera phone 1999 First commercial camera phone Sharp J-SH04 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

24 Millions of Camera Phones DSC Phone ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Mobile AR by Weight 1996 2003 2007 Backpack+HMD:

25 Mobile AR by Weight Backpack+HMD: 5-8kg Scale it down: Vesp R [Kruijff ISMAR07]: Sony UMPC 1.1GHz 1.5kg still >$5K Scale it down more: Smartphone $500 All-in-one 0.1kg billions of units ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Hardware Sensors Camera (8MP, 30 fps @1080p) Maker based/markerless tracking Video overlap GPS (1-10m, 1-2Hz) Outdoor location Compass Indoor/outdoor

26 Hardware Sensors Camera (8MP, 30 Maker based/markerless tracking Video overlap GPS (1-10m, 1-2Hz) Outdoor location Compass Indoor/outdoor orientation Accelerometer Motion sensing, relative tilt ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

27 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

28 Augmented Reality Main Challenges Tracking Visual Coherency Scene Reconstruction ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

29 Tracking: Pose estimation & Object Recognition ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Tracking is Estimating the device s pose (position and orientation) Strictly in real time (30Hz) With high spatial precision (1cm, 1 degree) Robustly for operation by human user No unrealistic

30 Tracking is Estimating the device s pose (position and orientation) Strictly in real time (30Hz) With high spatial precision (1cm, 1 degree) Robustly for operation by human user No unrealistic assumptions about HW Leaving enough power to other tasks (interaction, graphics) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

ARToolKit Tracking (Kato) ARToolKit - Computer vision based marker tracking libraries http://artoolkit.sourceforge.

31 ARToolKit Tracking (Kato) ARToolKit - Computer vision based marker tracking libraries ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

32 Marker Tracking Overview Camera Image Fiducial Detection Contours Rectangle Fitting Lens Undistortion Identified Markers Pattern Checking Rectangles Undistorted Corners Pose Estimation Estimated Poses ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

border Check for size reject candidates early that are too small (or too large) ETH Zürich

33 Marker Tracking Fiducial Detection Threshold the whole image to black and white Search scanline by scanline for edges (white to black) Follow edge until either back to starting pixel image border Check for size reject candidates early that are too small (or too large) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

34 Marker Tracking Rectangle Fitting Start with an arbitrary point x on the contour The point with maximum distance must be a corner c 0 Draw line through c 0 and the center Find points c 1 & c 2 with maximum distance left and right of diag. New diagonal from c 1 to c 2 Find point c 3 right of diagonal with maximum distance ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

model) Extract pattern by sampling Check pattern Id (implicit encoding) Template (normalized cross

35 Marker Tracking Pattern checking Calculate homography using the 4 corner points Direct Linear Transform algorithm Maps normalized coordinates to marker coordinates (simple perspective projection, no camera model) Extract pattern by sampling Check pattern Id (implicit encoding) Template (normalized cross correlation) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

36 Marker tracking Pose estimation Calculates marker position and rotation relative to the camera Initial estimation directly from homography Very fast, but coarse Jitters a lot Refinement via Gauss-Newton iteration or Levenberg-Marquardt 6 parameters (3 for position, 3 for rotation) to refine At each iteration Calculate re-projection error ε Calculate Jacobian matrix J (matrix of all first-order partial derivatives) Solve the equation (J T J + λd)δ = J T ε for Δ (e.g. using Cholesky factorization) Add Δ to pose Quit if accurate enough or if max. steps reached ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

http://handheldar.icg.tugraz.at/artoolkitplus.

37 Marker Tracking Pipeline Goal: Do all this in less than 20 milliseconds on a mobile phone ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

39 Natural Feature Tracking ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

40 Markerless Tracking ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

41 Natural feature tracking Tracking from features of the surrounding environment Corners, edges, blobs,... Generally more difficult than marker tracking Markers are designed for their purpose The natural environment is not Less well-established methods Every year new ideas are proposed Usually much slower than marker tracking ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

42 Tracking by detection This is what most trackers do Targets are detected every frame Popular because tracking and detection are solved simultaneously Recognition Camera Image Keypoint detection Descriptor creation and matching Outlier Removal Pose estimation and refinement Pose ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

43 Natural feature tracking What is a keypoint? It depends on the detector you use! For high performance use the FAST corner detector Apply FAST to all pixels of your image Obtain a set of keypoints for your image Reduce the amount of corners using non-maximum suppression Describe the keypoints E. Rosten and T. Drummond (May 2006). "Machine learning for high-speed corner detection". ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

44 FAST Corner detector ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Natural feature tracking Descriptors Again depends on

Can use SIFT Estimate the dominant keypoint orientation

Describe the keypoints in terms of the gradients

45 Natural feature tracking Descriptors Again depends on your choice of a descriptor! Can use SIFT Estimate the dominant keypoint orientation using gradients Compensate for detected orientation Describe the keypoints in terms of the gradients surrounding it Wagner D., Reitmayr G., Mulloni A., Drummond T., Schmalstieg D., Real-Time Detection and Tracking for Augmented Reality on Mobile Phones. IEEE Transactions on Visualization and Computer Graphics, May/June, 2010 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

will be from our image Build a database file with all descriptors and their position on the original image

46 NFT Database creation Offline step Searching for corners in a static image For robustness look at corners on multiple scales Some corners are more descriptive at larger or smaller scales We don t know how far users will be from our image Build a database file with all descriptors and their position on the original image ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

47 NFT Real-time tracking Search for keypoints in the video image Create the descriptors Match the descriptors from the live video against those in the database Remove the keypoints that are outliers Use the remaining keypoints to calculate the pose of the camera Recognition Camera Image Keypoint detection Descriptor creation and matching Outlier Removal Pose estimation and refinement Pose ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

48 NFT Results Wagner D., Reitmayr G., Mulloni A., Drummond T., Schmalstieg D., Real-Time Detection and Tracking for Augmented Reality on Mobile Phones. IEEE Transactions on Visualization and Computer Graphics, May/June, 2010 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

49 15 Minute Break ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

50 User Interface Engineering HS 2013 Augmented Reality Part II Modern Approaches to Augmented Reality ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

51 Outline Introduction to Augmented Reality Definition and brief history Mobile Augmented Reality Camera and object tracking Marker based Natural feature tracking Visual SLAM Dense Reconstruction ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

52 Informed vs. uninformed tracking Informed tracking Requires knowing the environment Requires storing a large database of information Users can point the phone at anything described in the database Allows for adding semantic information to the database E.g., where is the ground plane? Uninformed tracking Works also for unknown environments Requires creating a database of keypoints on the fly Prone to drift Prone to corruption of the database User must move smoothly to build the database incrementally ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

NFT in unknown environments We can also build a 3D database of keypoints Georg Klein and David Murray Parallel Tracking and Mapping for Small AR Workspaces In Proc.

53 NFT in unknown environments We can also build a 3D database of keypoints Georg Klein and David Murray Parallel Tracking and Mapping for Small AR Workspaces In Proc. International Symposium on Mixed and Augmented Reality (ISMAR'07) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

54 Frame by Frame SLAM Why is SLAM fundamentally hard? Time One frame Find features Update camera pose and entire map Many DOF Draw graphics ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

55 Frame by Frame SLAM SLAM Updating entire map every frame is expensive!!! Needs sparse map of high-quality features - A. Davison Proposed approach Use dense map (of low quality features) Don t update the map every frame: Keyframes Split the tracking and mapping into two threads ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

56 Parallel Tracking and Mapping Time Thread #2 Mapping Update map One frame Thread #1 Tracking Find features Update camera pose only Fast & Robust Draw graphics ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

57 Parallel Tracking and Mapping Tracking Thread: Responsible estimation of camera pose and rendering augmented graphics Must run at 30 Hz Make as robust and accurate as possible Mapping thread: Responsible for providing the map Can take lots of time per key frame Make as rich and accurate as possible ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

58 Tracking thread Pre-process frame Map Project points Project points Match points Match points Update Camera Pose Coarse stage Update Camera Pose Fine stage Draw Graphics ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

59 Pre-process frame Image pyramid with four levels Coarse to fine 640x x x120 80x60 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

60 Pre-process frame Image pyramid with four levels Coarse to fine Detect FAST corners E. Rosten et al (ECCV 2006) 640x x x120 80x60 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

61 Project Points Use motion model to update camera pose Constant velocity model Estimated current Pt + 1 Previous pos Pt Previous pos Pt 1 t t Vt = (Pt Pt 1)/ t Pt + 1 = Pt + t (Vt) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Project Points Choose subset to measure ~ 50

62 Project Points Choose subset to measure ~ 50 features for coarse stages (highest score) 1000 randomly selected for fine stage 1000 ~50 640x x x120 80x60 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Match Points Generate 8x8 matching template (warped from source key-frame map) Search a fixed radius around projected position Use Zero-mean SSD

63 Match Points Generate 8x8 matching template (warped from source key-frame map) Search a fixed radius around projected position Use Zero-mean SSD Only search at FAST corner points ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

64 Update camera pose 6-DOF problem Obtain by SFM (Three-point algorithm)? ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

65 Draw graphics What can we draw in an unknown scene? Assume single plane visible at start Run VR simulation on the plane ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

66 Mapping thread Stereo Initialization Wait for new key frame Add new map points Tracker Optimize map Map maintenance ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

67 Stereo Initialization Use five-point-pose algorithm D. Nister et. al Requires a pair of frames and feature correspondences Provides initial map User input required: Two clicks for two key-frames Smooth motion for feature correspondence ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

68 Wait for new key frame Key frames are only added if: There is a sufficient baseline to the other key frame Tracking quality is good When a key frame is added: The mapping thread stops whatever it is doing All points in the map are measured in the key frame New map points are found and added to the map ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

69 Add new map points Want as many map points as possible Check all FAST corners in the key frame: Check score Check if already in map Epipolar search in a neighboring key frame Triangulate matches and add to map Repeat in four image pyramid levels ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

70 Optimize map Use batch SFM method: Bundle Adjustment Adjusts map point positions and key frame poses Minimize reprojection error of all points in all keyframes (or use only last N key frames) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

71 Map maintenance When camera is not exploring, mapping thread has idle time Data association in bundle adjustment is reversible Re-attempt outlier measurements Try measure new map features in all old key frames ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

72 Mapping Thread Summary ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

73 Examples & Limitations ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

74 [Izadi, Kim, Hilliges, Molyneaux, Newcombe, Kohli, Shotton, Hodges, Freeman, Davison, Fitzgibbon. UIST 11] [Newcombe, Izadi, Hilliges, Molyneaux, Kim, Davison, Kohli, Shotton, Hodges, Fitzgibbon. ISMAR 11 (Best Paper Award)]

75 Core Components ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Correspondences along ray Euclidean and normal compatibility Minimise point-plane error metric arg min Σ (T v k (x,y) - v k 1 (x,y)) n

76 ICP for pose estimation (V k, N k ) At time K Find single 6DOF transform T to align points (V k ) and normals (N k ) with previous frame (V k-1, N k-1 ) Projective data association Project current oriented points (V k, N k ) using global transform T k-1 Correspondences along ray Euclidean and normal compatibility Minimise point-plane error metric arg min Σ (T v k (x,y) - v k 1 (x,y)) n k 1 (x,y) 2 x,y (V k-1, N k-1 ) (T) ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

77 Tracking from the dense model ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

GPU Volumetric representation Voxel grid Truncated signed distance measurements (Curless & Levoy, SIGGRAPH 96) Uncertainty of range data Projective update Voxel converted: global point p project(t k

78 GPU Volumetric representation Voxel grid Truncated signed distance measurements (Curless & Levoy, SIGGRAPH 96) Uncertainty of range data Projective update Voxel converted: global point p project(t k -1 p) TSDF = CameraCenter p depth Weighted average Raycast extracts implicit surface ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

79 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

-0.9-0.4-0.1 0.2 0.9 1 1 1 1 1-1 -0.9-0.2 0.1 0.5 0.9 1 1 1 1-1 -0.9-0.3 0.2 0.2 0.8 1 1 1 1-1 -0.9-0.4 0.

9-0.7-0.5 0.0 0.4 0.9 1 1 1 1-0.1-0.0-0.0 0.1 0.

80 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

81 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

83 Geometry-aware AR

84 Occlusion handling

86 ProjectorFusion [Augmented Projectors. Pervasive 12.] ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

87 ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

88 Next Week Lecture Recap and Latest Research Highlights (20 minutes max) Final project presentation and demo 10 minutes for each group (use full time allotment) Present your final project including Technical detail on implementation Difficulties encountered (and overcome) Assignment of tasks to group members Live demos in the exercise slot ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

89 Reading Suggestions R. Azuma, "SIGGRAPH95 Course Notes: A Survey of Augmented Reality", ACM Siggraph, Kato, H., Billinghurst, M. Marker Tracking and HMD Calibration for a video-based Augmented Reality Conferencing System. In Proceedings of the 2nd International Workshop on Augmented Reality (IWAR 99). Wagner D., Reitmayr G., Mulloni A., Drummond T., Schmalstieg D., Real-Time Detection and Tracking for Augmented Reality on Mobile Phones. IEEE Transactions on Visualization and Computer Graphics G. Klein and D. Murray. Parallel Tracking and Mapping for Small AR Workspaces. In Proc. International Symposium on Mixed and Augmented Reality (ISMAR'07) S. Izadi, D. Kim, O. Hilliges, et al. KinectFusion: Real-time 3D Reconstruction And Interaction Using A Moving Depth Camera. In ACM UIST 11. ETH Zürich Departement Computer Science User Interface Engineering HS 2013 Prof. Dr. Otmar Hilliges

Augmented Reality, Advanced SLAM, Applications

Augmented Reality, Advanced SLAM, Applications Prof. Didier Stricker & Dr. Alain Pagani alain.pagani@dfki.de Lecture 3D Computer Vision AR, SLAM, Applications 1 Introduction Previous lectures: Basics (camera,