Title :
Intermediate view generation of soccer scene from multiple videos
Author :
Inamoto, Naho ; Saito, Hideo
Author_Institution :
Dept. of Inf. & Comput. Sci., Keio Univ., Yokohama, Japan
Abstract :
This paper introduces a novel method for generating an intermediate view of soccer scenes taken by multiple video cameras. In the proposed method, a soccer scene is classified into dynamic regions, a field region, and a background region. Using an epipolar geometry in the first region and homography in the second, dense correspondence is obtained to interpolate views. For the third region, partial area images are extracted from the panoramic image compounded from the background of multiple views. Finally synthesizing them completes intermediate view images of the whole object. Applying this method to actual scenes of a soccer match captured at the stadium, we succeeded in generating natural intermediate view videos.
Keywords :
feature extraction; image classification; image segmentation; natural scenes; sport; video signal processing; background region; dense correspondence; dynamic regions; epipolar geometry; field region; homography; intermediate view generation; intermediate view images; multiple videos; multiple view background; natural intermediate view videos; panoramic image; partial area image extraction; soccer scene; soccer scene classification; Cameras; Computer science; Image generation; Image reconstruction; Layout; Shape; Videos;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1048401