Scalable 3D representation for 3D video in a large-scale space

Authors:
Itaru Kitahara;Yuichi Ohta
Affiliations:
ATR Intelligent Robotics and Communication Laboratories, Hikaridar 2-2, Keihanna Science City, Kyoto, 619-0288, Japan;Institute of Engineering Mechanics and Systems, University of Tsukuba, Tennoudai 1-1-1, Tsukuba, Ibaraki, 305-8573, Japan
Venue:
Presence: Teleoperators and Virtual Environments - Special issue: IEEE VR 2003
Year:
2004

Citing 10
Cited 2

Rapid octree construction from image sequences

CVGIP: Image Understanding
Image-based visual hulls

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Virtualized Reality: Constructing Virtual Worlds from Real Scenes

IEEE MultiMedia
The Visual Hull Concept for Silhouette-Based Image Understanding

IEEE Transactions on Pattern Analysis and Machine Intelligence
Homography Based Parallel Volume Intersection: Toward Real-Time Volume Reconstruction using Active Cameras

CAMP '00 Proceedings of the Fifth IEEE International Workshop on Computer Architectures for Machine Perception (CAMP'00)
Photorealistic Scene Reconstruction by Voxel Coloring

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A Space-Sweep Approach to True Multi-Image Matching

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
3D Image Display with Motion Parallax by Camera Matrix Stereo

ICMCS '96 Proceedings of the 1996 International Conference on Multimedia Computing and Systems
An Emerging Medium: Interactive Three Dimensional Digital Video

ICMCS '96 Proceedings of the 1996 International Conference on Multimedia Computing and Systems
From 2D Images to 2.5D Sprites: A Layered Approach to Modeling 3D Scenes

ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2

The Great Buddha Project: Digitally Archiving, Restoring, and Analyzing Cultural Heritage Objects

International Journal of Computer Vision
Applicability of Camera Works to Free Viewpoint Videos with Annotation and Planning

IEICE - Transactions on Information and Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce our research aimed at realizing a 3D video system in a very large-scale space such as a soccer stadium or concert hall. We propose a method for describing the shape of a 3D object with a set of planes in order to effectvely synthesize a novel view of the object. The most effective layout of the planes can be determined based on the relative locations of the observer's viewing position, multiple cameras, and 3D obiects, We describe a method for controlling the LOD of the 3D representation by adjusting the planes' orientation, interval, and resolution. The data size of the 3D model and the processing time can be reduced drastically. The effectiveness of the proposed method is demonstrated by our experimental results.