Unsupervised Salient Object Detection by Aggregating Multi-Level Cues

In this paper, we present a novel method to detect salient object based on multi-level cues. First, a proposal processing scheme is developed by various object-level saliency cues to generate an initial saliency map. For the sake of more accurate object boundaries, a two-stage optimization mechanism...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenxing Xia, Hanling Zhang
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8534342/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850109493641216000
author Chenxing Xia
Hanling Zhang
author_facet Chenxing Xia
Hanling Zhang
author_sort Chenxing Xia
collection DOAJ
description In this paper, we present a novel method to detect salient object based on multi-level cues. First, a proposal processing scheme is developed by various object-level saliency cues to generate an initial saliency map. For the sake of more accurate object boundaries, a two-stage optimization mechanism is then proposed upon superpixel-level. Finally, the superpixel-level saliency map is further improved to construct the final saliency map by applying superpixel-to-pixel mapping. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-art saliency detection methods in terms of different evaluation metrics on several benchmark datasets.
format Article
id doaj-art-0e3af6eb5a7e41709f4aeef2ef4c8ec5
institution OA Journals
issn 1943-0655
language English
publishDate 2018-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-0e3af6eb5a7e41709f4aeef2ef4c8ec52025-08-20T02:38:03ZengIEEEIEEE Photonics Journal1943-06552018-01-0110611110.1109/JPHOT.2018.28812718534342Unsupervised Salient Object Detection by Aggregating Multi-Level CuesChenxing Xia0Hanling Zhang1https://orcid.org/0000-0001-5954-1424College of Computer Science and Electronic Engineering, Hunan University, Changsha, ChinaCollege of Computer Science and Electronic Engineering, Hunan University, Changsha, ChinaIn this paper, we present a novel method to detect salient object based on multi-level cues. First, a proposal processing scheme is developed by various object-level saliency cues to generate an initial saliency map. For the sake of more accurate object boundaries, a two-stage optimization mechanism is then proposed upon superpixel-level. Finally, the superpixel-level saliency map is further improved to construct the final saliency map by applying superpixel-to-pixel mapping. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-art saliency detection methods in terms of different evaluation metrics on several benchmark datasets.https://ieeexplore.ieee.org/document/8534342/Saliency detectionmulti-level cuesobject proposals.
spellingShingle Chenxing Xia
Hanling Zhang
Unsupervised Salient Object Detection by Aggregating Multi-Level Cues
IEEE Photonics Journal
Saliency detection
multi-level cues
object proposals.
title Unsupervised Salient Object Detection by Aggregating Multi-Level Cues
title_full Unsupervised Salient Object Detection by Aggregating Multi-Level Cues
title_fullStr Unsupervised Salient Object Detection by Aggregating Multi-Level Cues
title_full_unstemmed Unsupervised Salient Object Detection by Aggregating Multi-Level Cues
title_short Unsupervised Salient Object Detection by Aggregating Multi-Level Cues
title_sort unsupervised salient object detection by aggregating multi level cues
topic Saliency detection
multi-level cues
object proposals.
url https://ieeexplore.ieee.org/document/8534342/
work_keys_str_mv AT chenxingxia unsupervisedsalientobjectdetectionbyaggregatingmultilevelcues
AT hanlingzhang unsupervisedsalientobjectdetectionbyaggregatingmultilevelcues