Advertisement

Joint Kurtosis–Skewness-Based Background Smoothing for Local Hyperspectral Anomaly Detection

  • Yulei Wang
  • Yiming ZhaoEmail author
  • Yun Xia
  • Chein-I Chang
  • Meiping Song
  • Chunyan Yu
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

Anomaly detection becomes increasingly important in hyperspectral data exploitation due to the use of high spectral resolution to uncover many unknown substances which cannot be visualized or known a priori. The RX detector is one of the most commonly used anomaly detections algorithms, where both the global and local versions are studied. In the double window model of local RX detection, it is inevitable that there will be abnormal pixels in the outer window where the background information is estimated. These abnormal pixels will cause great interference to the detection result. Aiming at a better estimation of the local background, a joint kurtosis–skewness algorithm is proposed to smooth the background and get better detection results. The skewness and kurtosis are three and four order statistics respectively, which can express the non-Gaussian character of hyperspectral image and highlight the abnormal information of the target. The experimental results show that the proposed detection algorithm is more effective for both synthetic and real hyperspectral images.

Keywords

Hyperspectral image Local anomaly detection Background estimation Skewness Kurtosis 

References

  1. 1.
    Liu J. Hyperspectral imagery classification and anomaly detection based on sparse representation. Beijing: Beijing University of Chemical Technology; 2016. p. 43–54.Google Scholar
  2. 2.
    Wang Q, Yang G. Band selection based on local joint skewness and Kurtosis for hyperspectral image. Laser Optoelectron Prog. 2017;54(11):115–22.Google Scholar
  3. 3.
    Wang Y, Chen S-Y, Liu C, Chang C-I. Background suppression issues in anomaly detection for hyperspectral imagery. In: Conference on satellite data compression, communications, and processing X, Baltimore, MD, USA, 2014.Google Scholar
  4. 4.
    Zhu L, Wen G. Hyperspectral anomaly detection via background estimation and adaptive weighted sparse representation. Remote Sens. 2018;10(2).Google Scholar
  5. 5.
    Vafadar M, Ghassemian H. Anomaly detection of hyperspectral imagery using modified collaborative representation. IEEE Geosci Remote Sens Lett. 2018;1–5.Google Scholar
  6. 6.
    Zhao C, Wang Y, Qi B. Global and local real-time anomaly detectors for hyperspectral remote sensing imagery. Remote Sens. 2015;7(4):3966–85.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Yulei Wang
    • 1
    • 2
    • 3
  • Yiming Zhao
    • 1
    Email author
  • Yun Xia
    • 4
  • Chein-I Chang
    • 1
    • 5
  • Meiping Song
    • 1
    • 2
  • Chunyan Yu
    • 1
  1. 1.Dalian Maritime UniversityDalianChina
  2. 2.State Key Laboratory of Integrated Services NetworksXianChina
  3. 3.Key Laboratory of Spectral Imaging TechnologyChinese Academy of SciencesXianChina
  4. 4.Research and Development Center for China Academy of Launch Vehicle TechnologyBeijingChina
  5. 5.Department of Computer Science and Electrical EngineeringUniversity of Maryland, Baltimore CountyBaltimoreUSA

Personalised recommendations