Multi-view object co-segmentation based on the mixture of links model

Dongting Hu; Yugang Li; Xiabi Liu

doi:10.1117/12.2197637

6 July 2015 Multi-view object co-segmentation based on the mixture of links model

Dongting Hu, Yugang Li, Xiabi Liu

Proceedings Volume 9631, Seventh International Conference on Digital Image Processing (ICDIP 2015); 96310S (2015) https://doi.org/10.1117/12.2197637
Event: Seventh International Conference on Digital Image Processing (ICDIP15), 2015, Los Angeles, United States

Abstract

We present a novel mixture of links model to segment an object observed from multiple viewpoints. Each component in this mixture represents a temporal linkage between superpixels from all the viewpoints, hence expressing the inter-view consistency. The principle goal is to find the maximum a posterior estimate of appearance models and the exact bounding-box of object in each view. To this end, the segmentation is casted as finding more comprehensive and accurate samples using the mixture of links model. In contrast to most existing multi-view co-segmentation methods that rely on time-consuming 3D information, our method only uses 2D cues to achieve faster speed without decreasing the accuracy. The experimental results confirm the effectiveness of our approach.

Citation Download Citation

Dongting Hu, Yugang Li, and Xiabi Liu "Multi-view object co-segmentation based on the mixture of links model", Proc. SPIE 9631, Seventh International Conference on Digital Image Processing (ICDIP 2015), 96310S (6 July 2015); https://doi.org/10.1117/12.2197637

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