Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2016

Abstract

In this paper, we present a real-time salient object detection system based on the minimum spanning tree. Due to the fact that background regions are typically connected to the image boundaries, salient objects can be extracted by computing the distances to the boundaries. However, measuring the image boundary connectivity efficiently is a challenging problem. Existing methods either rely on superpixel representation to reduce the processing units or approximate the distance transform. Instead, we propose an exact and iteration free solution on a minimum spanning tree. The minimum spanning tree representation of an image inherently reveals the object geometry information in a scene. Meanwhile, it largely reduces the search space of shortest paths, resulting an efficient and high quality distance transform algorithm. We further introduce a boundary dissimilarity measure to compliment the shortage of distance transform for salient object detection. Extensive evaluations show that the proposed algorithm achieves the leading performance compared to the state-of-the-art methods in terms of efficiency and accuracy.

Keywords

Background region, Dissimilarity measures, Distance transform algorithms, Distance transforms, Minimum spanning trees, Object geometries, Salient object detection, State-of-the-art methods

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Information Systems and Management

Publication

Proceedings of the 29th IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016 June 26 - July 1

Volume

2016-January

First Page

2334

Last Page

2342

ISBN

9781467388504

Identifier

10.1109/CVPR.2016.256

Publisher

IEEE

City or Country

New Jersey

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2016.256

Download

Share

COinS