Real-time salient object detection with a minimum spanning tree

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 ima...

Full description

Saved in:
Bibliographic Details
Main Authors: TU, Wei-Chih, HE, Shengfeng, YANG, Qingxiong, CHIEN, Shao-Yi
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2016
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8431
https://ink.library.smu.edu.sg/context/sis_research/article/9434/viewcontent/Real_Time_Salient_Object_Detection_With_a_Minimum_Spanning_Tree.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9434
record_format dspace
spelling sg-smu-ink.sis_research-94342024-01-04T10:06:34Z Real-time salient object detection with a minimum spanning tree TU, Wei-Chih HE, Shengfeng YANG, Qingxiong CHIEN, Shao-Yi 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. 2016-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8431 info:doi/10.1109/CVPR.2016.256 https://ink.library.smu.edu.sg/context/sis_research/article/9434/viewcontent/Real_Time_Salient_Object_Detection_With_a_Minimum_Spanning_Tree.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Background region Dissimilarity measures Distance transform algorithms Distance transforms Minimum spanning trees Object geometries Salient object detection State-of-the-art methods Databases and Information Systems Theory and Algorithms
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Background region
Dissimilarity measures
Distance transform algorithms
Distance transforms
Minimum spanning trees
Object geometries
Salient object detection
State-of-the-art methods
Databases and Information Systems
Theory and Algorithms
spellingShingle Background region
Dissimilarity measures
Distance transform algorithms
Distance transforms
Minimum spanning trees
Object geometries
Salient object detection
State-of-the-art methods
Databases and Information Systems
Theory and Algorithms
TU, Wei-Chih
HE, Shengfeng
YANG, Qingxiong
CHIEN, Shao-Yi
Real-time salient object detection with a minimum spanning tree
description 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.
format text
author TU, Wei-Chih
HE, Shengfeng
YANG, Qingxiong
CHIEN, Shao-Yi
author_facet TU, Wei-Chih
HE, Shengfeng
YANG, Qingxiong
CHIEN, Shao-Yi
author_sort TU, Wei-Chih
title Real-time salient object detection with a minimum spanning tree
title_short Real-time salient object detection with a minimum spanning tree
title_full Real-time salient object detection with a minimum spanning tree
title_fullStr Real-time salient object detection with a minimum spanning tree
title_full_unstemmed Real-time salient object detection with a minimum spanning tree
title_sort real-time salient object detection with a minimum spanning tree
publisher Institutional Knowledge at Singapore Management University
publishDate 2016
url https://ink.library.smu.edu.sg/sis_research/8431
https://ink.library.smu.edu.sg/context/sis_research/article/9434/viewcontent/Real_Time_Salient_Object_Detection_With_a_Minimum_Spanning_Tree.pdf
_version_ 1787590748323971072