Share Email Print
cover

Proceedings Paper

Structure analysis of natural scenes using census transform and region competition
Author(s): Kunio Yamada; Tadashi Ichikawa; Takeshi Naemura; Kiyoharu Aizawa; Takahiro Saito
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper we propse an approach to generate a panorama depth map which is dense enough to be used as a template for cutting out a texture image by the depth, i.e. structuring the scene into layers to construct a shared 3-D image space. For depth estimation, we make use of census transform for robust determination of correspondence of a stereo pair. To interpolate unknown disparities, we introduced a process influenced by the K-means algorithm. For densification of the depth data, we make use of Region Competition. During the stitching, the confidence of the data is improved for the overlapped areas by multiple evaluation of the disparity data.

Paper Details

Date Published: 29 December 2000
PDF: 10 pages
Proc. SPIE 4310, Visual Communications and Image Processing 2001, (29 December 2000); doi: 10.1117/12.411800
Show Author Affiliations
Kunio Yamada, Telecommunications Advancement Organization of Japan (Japan)
Tadashi Ichikawa, Telecommunications Advancement Organization of Japan (Japan)
Takeshi Naemura, Telecommunications Advancement Organization of Japan and Univ. of Tokyo (United States)
Kiyoharu Aizawa, Telecommunications Advancement Organization of Japan and Univ. of Tokyo (Japan)
Takahiro Saito, Telecommunications Advancement Organization of Japan and Kanagawa Univ. (Japan)


Published in SPIE Proceedings Vol. 4310:
Visual Communications and Image Processing 2001
Bernd Girod; Charles A. Bouman; Eckehard G. Steinbach, Editor(s)

© SPIE. Terms of Use
Back to Top