Gravitation-based edge detection for hyperspectral images

Genyun Sun, Aizhu Zhang, Jinchang Ren, Jingsheng Ma, Peng Wang, Yuanzhi Zhang, Xiuping Jia

Research output: Contribution to journalArticle

  • 3 Citations

Abstract

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.
LanguageEnglish
Article number592
Number of pages23
JournalRemote Sensing
Volume9
DOIs
StatePublished - 11 Jun 2017

Fingerprint

pixel
detection method
computer vision
multispectral image
potential energy
image analysis
detection
remote sensing
method
state of the art
travel

Keywords

  • edge detection
  • hyperspectral images
  • gravitation
  • remote sensing
  • feature space
  • image analysis

Cite this

Sun, G., Zhang, A., Ren, J., Ma, J., Wang, P., Zhang, Y., & Jia, X. (2017). Gravitation-based edge detection for hyperspectral images. Remote Sensing, 9, [592]. DOI: 10.3390/rs9060592
Sun, Genyun ; Zhang, Aizhu ; Ren, Jinchang ; Ma, Jingsheng ; Wang, Peng ; Zhang, Yuanzhi ; Jia, Xiuping. / Gravitation-based edge detection for hyperspectral images. In: Remote Sensing. 2017 ; Vol. 9.
@article{e3a14d5bfa134750bb9f9c955865da7e,
title = "Gravitation-based edge detection for hyperspectral images",
abstract = "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.",
keywords = "edge detection, hyperspectral images, gravitation, remote sensing, feature space, image analysis",
author = "Genyun Sun and Aizhu Zhang and Jinchang Ren and Jingsheng Ma and Peng Wang and Yuanzhi Zhang and Xiuping Jia",
year = "2017",
month = "6",
day = "11",
doi = "10.3390/rs9060592",
language = "English",
volume = "9",
journal = "Remote Sensing",
issn = "2072-4292",

}

Sun, G, Zhang, A, Ren, J, Ma, J, Wang, P, Zhang, Y & Jia, X 2017, 'Gravitation-based edge detection for hyperspectral images' Remote Sensing, vol. 9, 592. DOI: 10.3390/rs9060592

Gravitation-based edge detection for hyperspectral images. / Sun, Genyun; Zhang, Aizhu; Ren, Jinchang; Ma, Jingsheng ; Wang, Peng; Zhang, Yuanzhi; Jia, Xiuping.

In: Remote Sensing, Vol. 9, 592, 11.06.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Gravitation-based edge detection for hyperspectral images

AU - Sun,Genyun

AU - Zhang,Aizhu

AU - Ren,Jinchang

AU - Ma,Jingsheng

AU - Wang,Peng

AU - Zhang,Yuanzhi

AU - Jia,Xiuping

PY - 2017/6/11

Y1 - 2017/6/11

N2 - 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.

AB - 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.

KW - edge detection

KW - hyperspectral images

KW - gravitation

KW - remote sensing

KW - feature space

KW - image analysis

U2 - 10.3390/rs9060592

DO - 10.3390/rs9060592

M3 - Article

VL - 9

JO - Remote Sensing

T2 - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

M1 - 592

ER -

Sun G, Zhang A, Ren J, Ma J, Wang P, Zhang Y et al. Gravitation-based edge detection for hyperspectral images. Remote Sensing. 2017 Jun 11;9. 592. Available from, DOI: 10.3390/rs9060592