Research on Anomaly Detection Based on MNF in Hyper Spectral Imagery

Guang Yang; Zhong Xiang Lei; He Nan Wu; Qiang Qiang Meng; Gao Pan He

doi:10.4028/www.scientific.net/AMM.644-650.1085

Paper Titles

Image Texture-Based Vehicle Cast Shadow Elimination Approach
p.1066

An Optimized Fabric Self Collision Detection Method
p.1070

Design of Wireless Monitoring System for Electric Equipment Based on CC2530
p.1074

Implementation of a Design for Oxygen Saturation Measurement System
p.1079

Research on Anomaly Detection Based on MNF in Hyper Spectral Imagery
p.1085

An Analysis of the Existing Problems of China's Coal Mine Safety Monitoring and Control System
p.1089

Abnormal Network Traffic Detection Based on Conditional Event Algebra
p.1093

Seeds Microscopic Image Edge Detection Based on the Clustering Method and Applied in Andriod Platform
p.1100

Shape Features Detection Based on Hough Transform in Images
p.1104

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 644-650Research on Anomaly Detection Based on MNF in...

Research on Anomaly Detection Based on MNF in Hyper Spectral Imagery

Abstract:

A novel method was proposed to solve the problem which was caused by high dimensions. Minimum Noise Fraction was used for dimension reduction. And then the RX algorithm and KRX algorithm was used to detect the data after dimensional reduction. The method proposed was better by comparing the ROC of four detection results.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 644-650)

Pages:

1085-1088

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.644-650.1085

Citation:

Cite this paper

Online since:

September 2014

Authors:

Guang Yang*, Zhong Xiang Lei, He Nan Wu, Qiang Qiang Meng, Gao Pan He

Keywords:

Anomaly Detection, Hyper Spectral Data, Minimum Noise Fraction

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

* - Corresponding Author

References

[1] Vidal M, Amigo J M. Pre-processing of Hyper spectral Images[J]. Chemometrics and Intelligent Laboratory Systems, 2012, 34(2): 274-286.

Google Scholar

[2] Benediktsson JA, Swain P H. Consensus Theoretic Classification Methods. IEEE Transactions on System Man and Cybernetics, 1992, 22(4): 688-704.

DOI: 10.1109/21.156582

Google Scholar

[3] Chen J Y, Reed I S. A Detection Algorithm for Opital Targets in Clutter[J]. IEEE Transactions on Aerospace and Electronic Systems, 1987, 23(1): 46-59.

DOI: 10.1109/taes.1987.313335

Google Scholar

[4] Reed I S, Yu X L. Adaptive Multiple-Band CFAR Detection of An Optical Pattern with Unknown Spectral Distribution. IEEE Transactions on Acoustics, Speech and Signal Processing[J], 1990, 38(10): 1760-1770.

DOI: 10.1109/29.60107

Google Scholar

[5] Chang C I. Hyper spectral Imaging: Techniques for Spectral Detection and Classification[M]. New York: Kluwer Academic, (2003).

Google Scholar

[6] Richards J A., Jia X. Remote Sensing Digital Image Processing[M]. New York: Springer-Verlag, (1993).

Google Scholar

[7] Harsanyi, Charles J. Detection and Classification of Subpixel Spectral Signatures in Hyper spectral Image Sequences[D]. USA: University of Maryland Baltimore County, 1993: 56-100.

Google Scholar

[8] Hsueh M, Chang C I. Adaptive Causal Anomaly Detection for Hyper spectral Imagery[C]. IEEE International on Geoscience and Remote Sensing Symposium, 2004, 5: 3222-3224.

DOI: 10.1109/igarss.2004.1370387

Google Scholar

[9] Hsuan R. Weighted Anomaly Detection for Hyper spectral Remotely Sensed Images[J]. SPIE, 2005, 5995(1): 20-27.

Google Scholar

[10] Manolakis D, Siracusa C, Mardcn D. Hyper spectral Adaptive Matched Filter Detectors: Practical Performance Comparison[J]. SPIE, 2001, 4831: 18-33, 40-42.

Google Scholar