Research Papers

Fast hyperspectral anomaly detection for environmental applications

[+] Author Affiliations
Mohsen Zare-Baghbidi

University of Isfahan, College of Engineering, Department of Computer Engineering, Isfahan, Iran

Saeid Homayouni

University of Ottawa, Department of Geography, Ottawa, Canada

J. Appl. Remote Sens. 7(1), 073489 (Oct 31, 2013). doi:10.1117/1.JRS.7.073489
History: Received February 22, 2013; Revised July 23, 2013; Accepted October 15, 2013
Text Size: A A A

Abstract.  Anomaly detection (AD) is a particular case of target detection applications that aim to find the objects in the image scene which are anomalous in comparison to their surrounding background. In many applications, like real-time detection of environmental pollution, not only the accuracy of the algorithm, but also its runtime is important. Because AD algorithms run on high-dimensional data cubes, their runtimes are normally not optimal. This paper presents two high-speed AD algorithms: the first method is based on the maximum and minimum values of the spectral signature of hyperspectral data pixels; the other employs simple statistical and mathematical tools to calculate the abnormality of image pixels. The proposed methods have been compared with the Kernel-RX detector which is a well known, high performance AD. The AD methods have been applied to four hyperspectral datasets acquired by Airborne Visible/Infrared Imaging Spectrometer, Hyperspectral Mapper, and SpecTIR sensors. The evaluation of the algorithms has been done using receiver operation characteristic (ROC) curve, visual investigation, and runtime of the algorithms. Experimental results show that the detection performance of the proposed methods is almost equal to Kernel-RX detector. In addition, the proposed AD methods have a much better runtime than Kernel-RX detector and are fast enough to be implemented in real-time environmental applications.

Figures in this Article
© 2013 Society of Photo-Optical Instrumentation Engineers

Topics

Sensors ; Algorithms

Citation

Mohsen Zare-Baghbidi and Saeid Homayouni
"Fast hyperspectral anomaly detection for environmental applications", J. Appl. Remote Sens. 7(1), 073489 (Oct 31, 2013). ; http://dx.doi.org/10.1117/1.JRS.7.073489


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.