Share Email Print

Proceedings Paper

Automatic panoramic image stitching and free exploration in virtual scenery
Author(s): Qiang Wang; Cailin Li; Peihuan Ji; Hualiang Hu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper presented an automatic panorama generation and free roaming algorithm for the tedious previous approaches on panorama generation and limitations of single-viewpoint roaming. Firstly, it describes the single-viewpoint panorama generation method: detecting the image point features in SIFT operator, getting the robust homography estimation in RANSAC and stitching the panoramic images by multi-band blending. Secondly, we present the free roaming method. In this method the corresponding pixels in new-viewpoint image can be set from the original images matching points and the new-viewpoint image can be blended by corresponding TIN piece rendering at last. Experimental results show that it is practicable and meets the actual requirements.

Paper Details

Date Published: 30 October 2009
PDF: 7 pages
Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 74953G (30 October 2009); doi: 10.1117/12.839461
Show Author Affiliations
Qiang Wang, Wuhan Univ. (China)
Hunan City Univ. (China)
Cailin Li, Wuhan Univ. (China)
Peihuan Ji, China Three Gorges Project Corp. (China)
Hualiang Hu, Wuhan Univ. (China)

Published in SPIE Proceedings Vol. 7495:
MIPPR 2009: Automatic Target Recognition and Image Analysis
Tianxu Zhang; Bruce Hirsch; Zhiguo Cao; Hanqing Lu, Editor(s)

© SPIE. Terms of Use
Back to Top