Gravitation-Based Edge Detection in Hyperspectral Images

Edge detection is one of the key issues in the field of computer vision and remote sensing image analysis. Although many different edge-detection methods have been proposed for gray-scale, color, and multispectral images, they still face difficulties when extracting edge features from hyperspectral...

Full description

Bibliographic Details
Main Authors: Genyun Sun, Aizhu Zhang, Jinchang Ren, Jingsheng Ma, Peng Wang, Yuanzhi Zhang, Xiuping Jia
Format: Article
Language:English
Published: MDPI AG 2017-06-01
Series:Remote Sensing
Subjects:
Online Access:http://www.mdpi.com/2072-4292/9/6/592
id doaj-a6969859385143c9bc9adb78f045ca7b
record_format Article
spelling doaj-a6969859385143c9bc9adb78f045ca7b2020-11-24T21:01:40ZengMDPI AGRemote Sensing2072-42922017-06-019659210.3390/rs9060592rs9060592Gravitation-Based Edge Detection in Hyperspectral ImagesGenyun Sun0Aizhu Zhang1Jinchang Ren2Jingsheng Ma3Peng Wang4Yuanzhi Zhang5Xiuping Jia6School of Geosciences, China University of Petroleum (East China), Qingdao 266580, ChinaSchool of Geosciences, China University of Petroleum (East China), Qingdao 266580, ChinaDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1XQ, UKInstitute of Petroleum, Heriot-Watt University, Edinburgh EH14 4AS, UKSchool of Geosciences, China University of Petroleum (East China), Qingdao 266580, ChinaKey Lab of Lunar Science and Deep-Exploration, Chinese Academy of Sciences, Beijing 100012, ChinaSchool of Engineering and Information Technology, The University of New South Wales at Canberra, Canberra ACT 2600, AustraliaEdge detection is one of the key issues in the field of computer vision and remote sensing image analysis. Although many different edge-detection methods have been proposed for gray-scale, color, and multispectral images, they still face difficulties when extracting edge features from hyperspectral images (HSIs) that contain a large number of bands with very narrow gap in the spectral domain. Inspired by the clustering characteristic of the gravitational theory, a novel edge-detection algorithm for HSIs is presented in this paper. In the proposed method, we first construct a joint feature space by combining the spatial and spectral features. Each pixel of HSI is assumed to be a celestial object in the joint feature space, which exerts gravitational force to each of its neighboring pixel. Accordingly, each object travels in the joint feature space until it reaches a stable equilibrium. At the equilibrium, the image is smoothed and the edges are enhanced, where the edge pixels can be easily distinguished by calculating the gravitational potential energy. The proposed edge-detection method is tested on several benchmark HSIs and the obtained results were compared with those of four state-of-the-art approaches. The experimental results confirm the efficacy of the proposed method.http://www.mdpi.com/2072-4292/9/6/592edge detectionhyperspectral imagegravitationremote sensingfeature space
collection DOAJ
language English
format Article
sources DOAJ
author Genyun Sun
Aizhu Zhang
Jinchang Ren
Jingsheng Ma
Peng Wang
Yuanzhi Zhang
Xiuping Jia
spellingShingle Genyun Sun
Aizhu Zhang
Jinchang Ren
Jingsheng Ma
Peng Wang
Yuanzhi Zhang
Xiuping Jia
Gravitation-Based Edge Detection in Hyperspectral Images
Remote Sensing
edge detection
hyperspectral image
gravitation
remote sensing
feature space
author_facet Genyun Sun
Aizhu Zhang
Jinchang Ren
Jingsheng Ma
Peng Wang
Yuanzhi Zhang
Xiuping Jia
author_sort Genyun Sun
title Gravitation-Based Edge Detection in Hyperspectral Images
title_short Gravitation-Based Edge Detection in Hyperspectral Images
title_full Gravitation-Based Edge Detection in Hyperspectral Images
title_fullStr Gravitation-Based Edge Detection in Hyperspectral Images
title_full_unstemmed Gravitation-Based Edge Detection in Hyperspectral Images
title_sort gravitation-based edge detection in hyperspectral images
publisher MDPI AG
series Remote Sensing
issn 2072-4292
publishDate 2017-06-01
description Edge detection is one of the key issues in the field of computer vision and remote sensing image analysis. Although many different edge-detection methods have been proposed for gray-scale, color, and multispectral images, they still face difficulties when extracting edge features from hyperspectral images (HSIs) that contain a large number of bands with very narrow gap in the spectral domain. Inspired by the clustering characteristic of the gravitational theory, a novel edge-detection algorithm for HSIs is presented in this paper. In the proposed method, we first construct a joint feature space by combining the spatial and spectral features. Each pixel of HSI is assumed to be a celestial object in the joint feature space, which exerts gravitational force to each of its neighboring pixel. Accordingly, each object travels in the joint feature space until it reaches a stable equilibrium. At the equilibrium, the image is smoothed and the edges are enhanced, where the edge pixels can be easily distinguished by calculating the gravitational potential energy. The proposed edge-detection method is tested on several benchmark HSIs and the obtained results were compared with those of four state-of-the-art approaches. The experimental results confirm the efficacy of the proposed method.
topic edge detection
hyperspectral image
gravitation
remote sensing
feature space
url http://www.mdpi.com/2072-4292/9/6/592
work_keys_str_mv AT genyunsun gravitationbasededgedetectioninhyperspectralimages
AT aizhuzhang gravitationbasededgedetectioninhyperspectralimages
AT jinchangren gravitationbasededgedetectioninhyperspectralimages
AT jingshengma gravitationbasededgedetectioninhyperspectralimages
AT pengwang gravitationbasededgedetectioninhyperspectralimages
AT yuanzhizhang gravitationbasededgedetectioninhyperspectralimages
AT xiupingjia gravitationbasededgedetectioninhyperspectralimages
_version_ 1716777312445267968