Fast salient object detection through efficient subwindow search

Mei Chen Yeh, Chih Fan Hsu, Chia Ju Lu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Salient object detection techniques have a variety of applications of broad interest. However, the detection must be fast to facilitate these processes. In this paper, we address the computational problems in salient object detection. Several approaches to resolving the salient object detection problem consist of two steps: saliency map extraction and salient object localization. To achieve accurate detection, multiple features are typically combined for computing a saliency map, and a dense-sampling approach that examines numerous regions is widely used (both processes are computationally demanding). We integrated salient feature computation into the search process and accelerated state-of-the-art approaches by using an efficient subwindow search framework. We developed a fast and accurate salient object detection system. The experimental results using the MSRA salient object database validated the effectiveness and the computational efficiency of the proposed approach.

Original languageEnglish
Pages (from-to)60-66
Number of pages7
JournalPattern Recognition Letters
Volume46
DOIs
Publication statusPublished - 2014 Sep 1

Fingerprint

Computational efficiency
Sampling
Object detection
Object-oriented databases

Keywords

  • Computational efficiency
  • Object detection
  • Saliency

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Fast salient object detection through efficient subwindow search. / Yeh, Mei Chen; Hsu, Chih Fan; Lu, Chia Ju.

In: Pattern Recognition Letters, Vol. 46, 01.09.2014, p. 60-66.

Research output: Contribution to journalArticle

@article{169bc46b985b40afbdad6191fd17f079,
title = "Fast salient object detection through efficient subwindow search",
abstract = "Salient object detection techniques have a variety of applications of broad interest. However, the detection must be fast to facilitate these processes. In this paper, we address the computational problems in salient object detection. Several approaches to resolving the salient object detection problem consist of two steps: saliency map extraction and salient object localization. To achieve accurate detection, multiple features are typically combined for computing a saliency map, and a dense-sampling approach that examines numerous regions is widely used (both processes are computationally demanding). We integrated salient feature computation into the search process and accelerated state-of-the-art approaches by using an efficient subwindow search framework. We developed a fast and accurate salient object detection system. The experimental results using the MSRA salient object database validated the effectiveness and the computational efficiency of the proposed approach.",
keywords = "Computational efficiency, Object detection, Saliency",
author = "Yeh, {Mei Chen} and Hsu, {Chih Fan} and Lu, {Chia Ju}",
year = "2014",
month = "9",
day = "1",
doi = "10.1016/j.patrec.2014.05.006",
language = "English",
volume = "46",
pages = "60--66",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - Fast salient object detection through efficient subwindow search

AU - Yeh, Mei Chen

AU - Hsu, Chih Fan

AU - Lu, Chia Ju

PY - 2014/9/1

Y1 - 2014/9/1

N2 - Salient object detection techniques have a variety of applications of broad interest. However, the detection must be fast to facilitate these processes. In this paper, we address the computational problems in salient object detection. Several approaches to resolving the salient object detection problem consist of two steps: saliency map extraction and salient object localization. To achieve accurate detection, multiple features are typically combined for computing a saliency map, and a dense-sampling approach that examines numerous regions is widely used (both processes are computationally demanding). We integrated salient feature computation into the search process and accelerated state-of-the-art approaches by using an efficient subwindow search framework. We developed a fast and accurate salient object detection system. The experimental results using the MSRA salient object database validated the effectiveness and the computational efficiency of the proposed approach.

AB - Salient object detection techniques have a variety of applications of broad interest. However, the detection must be fast to facilitate these processes. In this paper, we address the computational problems in salient object detection. Several approaches to resolving the salient object detection problem consist of two steps: saliency map extraction and salient object localization. To achieve accurate detection, multiple features are typically combined for computing a saliency map, and a dense-sampling approach that examines numerous regions is widely used (both processes are computationally demanding). We integrated salient feature computation into the search process and accelerated state-of-the-art approaches by using an efficient subwindow search framework. We developed a fast and accurate salient object detection system. The experimental results using the MSRA salient object database validated the effectiveness and the computational efficiency of the proposed approach.

KW - Computational efficiency

KW - Object detection

KW - Saliency

UR - http://www.scopus.com/inward/record.url?scp=84902669915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902669915&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2014.05.006

DO - 10.1016/j.patrec.2014.05.006

M3 - Article

AN - SCOPUS:84902669915

VL - 46

SP - 60

EP - 66

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -