Download:
by Jane Mulligan, Volkan Isler, Kostas Daniilidis
International Journal of Computer Vision
http://www.cs.colorado.edu/~janem/pdf/ijcv.pdf
Add To MetaCart
Abstract:
In telepresence applications each user is immersed in a rendered 3D-world composed from representations transmitted from remote sites. The challenge is to compute dense range data at high frame rates, since participants cannot easily communicate if the processing cycle or network latencies are long. Moreover, errors in new stereoscopic views of the remote 3D-world should be hardly perceptible. To achieve the required speed and accuracy, we use trinocular stereo, a matching algorithm based on the sum of modified normalized cross-correlations, and subpixel disparity interpolation. To increase speed we use Intel IPL functions in the pre-processing steps of background subtraction and image rectification as well as a four-processor parallelization. To evaluate our system we have developed a testbed which provides a set of registered dense “ground-truth” laser data and image data from multiple views. 1
Citations
|
1021
|
Three Dimensional Computer Vision: A Geometric Viewpoint
– Faugeras
- 1993
|
|
686
|
Performance of optical flow techniques
– Barron, Fleet, et al.
- 1994
|
|
365
|
A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
– Scharstein, Szeliski
- 2002
|
|
280
|
A theory of shape by space carving
– Kutulakos, Seitz
- 2000
|
|
260
|
Photorealistic scene reconstruction by voxel coloring
– Seitz, Dyer
- 1999
|
|
196
|
A multiple-baseline stereo
– Okutomi, Kanade
- 1993
|
|
185
|
The office of the future: A unified approach to image-based modeling and spatially immersive displays
– Raskar, Welch, et al.
- 1998
|
|
161
|
Structure from Stereo – A Review
– Dhond, Aggarwal
- 1989
|
|
113
|
Stereo Vision for Planetary Rovers: Stochastic Modeling to Near RealTime Implementation
– Matthies
- 1992
|
|
91
|
Constructing Virtual Worlds Using Dense Stereo
– Narayanan, Rander, et al.
- 1998
|
|
77
|
A Bayesian approach to binocular stereopsis
– Belhumeur
- 1996
|
|
74
|
Artificial Vision for Mobile Robots: Stereo Vision and Multisensory Perception
– Ayache
- 1991
|
|
69
|
A real time system for robust 3d voxel reconstruction of human motions
– Cheung, Kanade, et al.
- 2000
|
|
39
|
Exact voxel occupancy with graph cuts
– Snow, Viola, et al.
- 2000
|
|
32
|
An experimental comparison of stereo algorithms
– Szeliski, Zabih
- 1999
|
|
29
|
Prediction error as a quality metric for motion and stereo
– Szeliski
- 1999
|
|
15
|
View-independent scene acquisition for tele-presence
– Mulligan, Daniilidis
- 2000
|
|
12
|
Performance Evaluation of Stereo for Tele-presence
– Mulligan, Isler, et al.
- 2001
|
|
12
|
Stereo without Search
– Tomasi, Manduchi
- 1996
|
|
10
|
Three-dimensional Computer Vision. MIT-Press
– Faugeras
- 1993
|
|
10
|
Improving depth map by right-angled trinocular stereo
– Ohta, Watanabe, et al.
- 1986
|
|
9
|
Measuring the self-consistency of stereo algorithms
– Leclerc, Luong, et al.
- 2000
|
|
8
|
Virtually there
– Lanier
- 2001
|
|
7
|
Quantitative evaluation of matching methods and validity measures for stereo vision
– Banks, Corke
- 2001
|
|
3
|
Predicting disparity windows for real-time stereo
– Mulligan, Daniilidis
- 2000
|
|
2
|
Vareck Bostrom, and Rajeeb Hazra. Implementation of a realtime foreground/background segmentation system on the intel architecture
– Martins, Nickerson
- 1999
|
|
1
|
Virtual view generation from 3d digital video
– Gerard
- 1997
|
