Abstract:
In this paper we presents a silhouette-based method for 3D human body reconstruction from multiple views. The silhouettes are extracted automatically from the captured frames using a background-learning approach. The multiple views are integrated using the epipolar geometry relating the pair of synchronized video streams. The 3D model of the human body is derived from the integration of the median axis of the silhouettes along with a Generalized Cylinders description of the 3D shape. The proposed approach is validated by a set of experiments capturing various human postures. 1.
Citations
|
778
|
Pfinder: Real-Time Tracking of the Human Body
– Wren, Azarbayejani, et al.
- 1997
|
|
395
|
A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry
– Zhang, Deriche, et al.
- 1995
|
|
178
|
Model-Based Vision: A Program to See a Walking Person
– Hogg
- 1983
|
|
113
|
Model-based image analysis of human motion using constraint propagation
– O'Rourke, Badler
- 1980
|
|
112
|
3D human body model acquisition from multiple views
– Kakadiaris, Metaxas
- 1995
|
|
94
|
Constructing virtual worlds using dense stereo
– Narayanan, Rander, et al.
- 1998
|
|
92
|
Artificial Reality
– Krueger
- 1985
|
|
81
|
Volumetric descriptions of objects from multiple views
– Martin, Aggarwal
- 1983
|
|
63
|
View-based interpretation of real-time optical flow for gesture recognition
– Cutler, Turk
- 1998
|
|
44
|
action: The role of knowledge in the perception of motion
– Movement
- 1997
|
|
40
|
Perceptual user interfaces
– Turk, Robertson
- 2000
|
|
35
|
The 3D Room: Digitizing Time-varying 3D Events by Synchronized Multiple Video Streams
– Kanade, Saito, et al.
- 1998
|
|
31
|
Structure from motion of rigid and jointed objects
– Webb, Aggarwal
- 1982
|
|
29
|
Volumetric Scene Reconstruction from Multiple Views
– Dyer
- 2001
|
|
29
|
Towards a system for the interpretation of Moving Light Displays
– Rashid
- 1980
|
|
22
|
Human body motion segmentation in a complex scene
– Leung, Yang
- 1987
|
|
21
|
Visual interaction with lifelike characters
– Turk
- 1996
|
|
20
|
Tracking self-occluding articulated objects in dense disparity maps
– Jojic, Turk, et al.
- 1999
|
|
19
|
A virtual mirror interface using real-time robust face tracking
– Darrell, Gordon, et al.
- 1998
|
|
14
|
Real-time 3d motion capture
– Horprasert, Haritaoglu, et al.
- 1998
|
|
13
|
3-D model-based tracking of human upper body movement: a multi-view approach
– Gavrila, Davis
- 1995
|
|
13
|
From an intensity image to 3-D segmented descriptions
– Zerroug, Nevatia
- 1994
|
|
12
|
The interpretation of visual motion: Recognizing moving light displays
– Goddard
- 1989
|
|
5
|
Globeall: Panoramic video for an intelligent room
– Nicolescu, Medioni
- 2000
|
|
2
|
Human body postures from trinocular camera images
– Iwassawa, Ohya, et al.
- 2000
|
