Region of interests extraction based on visual saliency for remote sensing image

Long Ma; Bin Xu; Fukun Bi; He Chen; Ying Yu

Region of interests extraction based on visual saliency for remote sensing image

Long Ma
, Bin Xu^*
, Fukun Bi
, He Chen
, Ying Yu

^*此作品的通讯作者

信息与电子学院

Beijing Institute of Technology
Beijing Institute of Remote Sensing Information
North China University of Technology
Yunnan University

科研成果: 会议稿件 › 论文 › 同行评审

摘要

This paper proposes a novel region of interests extraction method for remote sensing image based on visual saliency analysis as well as the multi-scale saliency fusion mechanism. Firstly, under the theory of multi-scale and multiresolution analysis, the gaussian pyramid representation is generated. Then, various spatial features are exploited to compute saliency maps under different scales. Finally the saliency map could be calculated by the corresponding level fusing as well as the across-scale combination. The comparative experiments validate the effectiveness of the proposed model.

源语言	英语
出版状态	已出版 - 2015
活动	IET International Radar Conference 2015 - Hangzhou, 中国期限: 14 10月 2015 → 16 10月 2015

会议

会议	IET International Radar Conference 2015
国家/地区	中国
市	Hangzhou
时期	14/10/15 → 16/10/15

其它文件与链接

链接到 Scopus 的出版物

引用此

@conference{90dddeb551d246e79684d4aa3bf0f9a9,

title = "Region of interests extraction based on visual saliency for remote sensing image",

abstract = "This paper proposes a novel region of interests extraction method for remote sensing image based on visual saliency analysis as well as the multi-scale saliency fusion mechanism. Firstly, under the theory of multi-scale and multiresolution analysis, the gaussian pyramid representation is generated. Then, various spatial features are exploited to compute saliency maps under different scales. Finally the saliency map could be calculated by the corresponding level fusing as well as the across-scale combination. The comparative experiments validate the effectiveness of the proposed model.",

keywords = "Multi-scale analysis, Region of interests, Remote sensing image processing, Saliency fusion, Visual saliency",

author = "Long Ma and Bin Xu and Fukun Bi and He Chen and Ying Yu",

year = "2015",

language = "English",

note = "IET International Radar Conference 2015 ; Conference date: 14-10-2015 Through 16-10-2015",

}

TY - CONF

T1 - Region of interests extraction based on visual saliency for remote sensing image

AU - Ma, Long

AU - Xu, Bin

AU - Bi, Fukun

AU - Chen, He

AU - Yu, Ying

PY - 2015

Y1 - 2015

N2 - This paper proposes a novel region of interests extraction method for remote sensing image based on visual saliency analysis as well as the multi-scale saliency fusion mechanism. Firstly, under the theory of multi-scale and multiresolution analysis, the gaussian pyramid representation is generated. Then, various spatial features are exploited to compute saliency maps under different scales. Finally the saliency map could be calculated by the corresponding level fusing as well as the across-scale combination. The comparative experiments validate the effectiveness of the proposed model.

AB - This paper proposes a novel region of interests extraction method for remote sensing image based on visual saliency analysis as well as the multi-scale saliency fusion mechanism. Firstly, under the theory of multi-scale and multiresolution analysis, the gaussian pyramid representation is generated. Then, various spatial features are exploited to compute saliency maps under different scales. Finally the saliency map could be calculated by the corresponding level fusing as well as the across-scale combination. The comparative experiments validate the effectiveness of the proposed model.

KW - Multi-scale analysis

KW - Region of interests

KW - Remote sensing image processing

KW - Saliency fusion

KW - Visual saliency

UR - https://www.scopus.com/pages/publications/84973541065

M3 - Paper

AN - SCOPUS:84973541065

T2 - IET International Radar Conference 2015

Y2 - 14 October 2015 through 16 October 2015

ER -

Region of interests extraction based on visual saliency for remote sensing image

摘要

会议

其它文件与链接

学术指纹

引用此