A multi-view camera system for the generation of real-time occlusion-free scene video

Authors:
Alparslan Yildiz;Yusuf Sinan Akgul
Affiliations:
GIT Vision Lab, Department of Computer Engineering, Gebze Institute of Technology, Gebze, Kocaeli, Turkey;GIT Vision Lab, Department of Computer Engineering, Gebze Institute of Technology, Gebze, Kocaeli, Turkey
Venue:
Proceedings of the 29th DAGM conference on Pattern recognition
Year:
2007

Citing 8
Cited 0

Dynamically reparameterized light fields

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Probabilistic Exclusion Principle for Tracking Multiple Objects

International Journal of Computer Vision
Efficient generation of the binary reflected gray code and its applications

Communications of the ACM
A Cooperative Algorithm for Stereo Matching and Occlusion Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Reconstructing Occluded Surfaces Using Synthetic Apertures: Stereo, Focus and Robust Measures

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
High-accuracy stereo depth maps using structured light

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Tracking appearances with occlusions

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel multi-view camera system that produces real-time single view scene video which sees through the static objects to observe the dynamic objects. The system employs a training phase to recover the correspondences and occlusions between the views to determine the image positions where seeing through would be necessary. During the runtime phase, each dynamic object is detected and automatically registered between the views. The registered objects are learned using an appearance based method and they are later used to superimpose the occluded dynamic objects on the desired view. The occlusion detection is done using a very efficient and effective method. The system is very practical and can be used in real life applications including video surveillance, communication, activity analysis, and entertainment. We validated the system by running various tests in office and outdoor environments.