New real-time algorithm for multiview disparity-based 3D-object segmentation

Yuecheng Zhang; Yun He

doi:10.1117/12.411850

29 December 2000 New real-time algorithm for multiview disparity-based 3D-object segmentation

Yuecheng Zhang, Yun He

Proceedings Volume 4310, Visual Communications and Image Processing 2001; (2000) https://doi.org/10.1117/12.411850
Event: Photonics West 2001 - Electronic Imaging, 2001, San Jose, CA, United States

Abstract

With the development of video communication system, more and more attention has been put on the implementation of varieties of functionality associated with content. Thus, the object segmentation algorithms features both semantic and automatic are tremendous necessary. In this paper a new real-time algorithm for 3D-object segmentation algorithm based on disparity is proposed. Its kernel disparity matching methodology is developed on base of a general pixel-based segmentation algorithm known a Dynamic Programming on Disparity Space Image. With the introduction of weighted feature span, the computational complexity is reduced apparently. The proposed algorithm is tested on both real captured stereo sequence and synthetic multiview sequence, and gets satisfying result in generality, quality and complexity.

Citation Download Citation

Yuecheng Zhang and Yun He "New real-time algorithm for multiview disparity-based 3D-object segmentation", Proc. SPIE 4310, Visual Communications and Image Processing 2001, (29 December 2000); https://doi.org/10.1117/12.411850

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available