A unified framework for correcting panoramic image distortions

Authors:
Frank Ekpar;Hiroyuki Hase;Masaaki Yoneda
Affiliations:
Department of Information Science, Faculty of Engineering, University of Fukui, Bunkyo, Fukui, Japan;Department of Information Science, Faculty of Engineering, University of Fukui, Bunkyo, Fukui, Japan;Department of Intellectual Information Systems, Faculty of Engineering, University of Toyama, Toyama, Japan
Venue:
ACOS'06 Proceedings of the 5th WSEAS international conference on Applied computer science
Year:
2006

Citing 4
Cited 0

The office of the future: a unified approach to image-based modeling and spatially immersive displays

Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Robust Video Mosaicing through Topology Inference and Local to Global Alignment

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Remote Reality Demonstration

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Video Mosaics for Virtual Environments

IEEE Computer Graphics and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a unified framework for the correction of non-linear distortions in panoramic images. Several techniques are combined to make the system robust, scalable and adaptable to real-time operation. Constructive neural networks are applied where appropriate to achieve robustness. Interactive curve sketching techniques based on polynomial interpolation are used in situations where quick, reliable and practical results are desired. The effectiveness of the system is demonstrated by applying it to the correction of non-linear distortions in the generation of perspective-corrected views from panoramic images acquired using catadioptric systems for use in virtual tours of remote locations.