New Measure Based Manifold Algorithm and Application in Anomaly Detection of Hyperspectral Imagery

Abstract:

Hyperspectral data is endowed with characteristics of intrinsic nonlinear structure and high dimension. In this paper, a nonlinear manifold learning algorithm - ISOMAP is applied to anomaly detection. Then an improved ISOMAP algorithm is developed based on the analysis of the inherent characteristics of hyperspectral imagery. The improved ISOMAP algorithm selects neighborhood according to a novel measure of combination of spectral gradient and spectral angle in order to make the algorithm more robust to the changes of light and terrain. Experimental results prove the effectiveness of the algorithm in improving the detection performance.

• Periodical: Applied Mechanics and Materials (Volumes 80-81)
• Pages: 797-803
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.80-81.797
• Online since: July 2011
• Authors: Liang Liang Wang, Zhi Yong Li, Ji Xiang Sun, Chun Du
• Keywords: Anomaly Detection, Isomap, Manifold Learning, Remote Sensing, Spectral Gradient

References

[1] Qingxi Tong, Bing Zhang, Lanfen Zhen, Hyperspectral remote sensing - principle, technique and application, Higher Education Press, (2006).

[2] Tian Han, Goodenough, D. G, Nonlinear feature extraction of hyperspectral data based on locally linear embedding,  Geoscience and Remote Sensing Symposium, 25(2005) 1237 - 1240.

DOI: 10.1109/igarss.2005.1525342

[3] Ma, L., Crawford, M.M., Tian, J. W, Anomaly detection for hyperspectral images based on robust locally linear embedding, Infrared Millimeter Terahertz Waves 31(2010) 753–762.

DOI: 10.1007/s10762-010-9630-3

[4] A. N. Gorban, A. Zinovyev, Principal manifolds and graphs in practice: from molecular biology to dynamical systems, International Journal of Neural Systems, 20 (2010) 219-232.

DOI: 10.1142/s0129065710002383

[5] Gabriel Peyré, Manifold models for signals and images, Computer Vision and Image Understanding, 113(2009) 249-260.

DOI: 10.1016/j.cviu.2008.09.003

[6] Tenenbaum, J., V. Silva, et al., A global geometric framework for nonlinear dimensionality reduction, science, 290 (2000) 2319-2323.

DOI: 10.1126/science.290.5500.2319

[7] Roweis, S. and L. Saul, Nonlinear dimensionality reduction by locally linear embedding, science, 290 (2000) 2323-2326.

DOI: 10.1126/science.290.5500.2323

[8] Sohn, Y., E. Moran, and F. Gurri, Deforestation in north-central Yucatan (1985-1995): Mapping secondary succession of forest and agricultural land use in Sotuta using the cosine of the angle concept, Photogrammetric Engineering and Remote Sensing, 65 (1999).

[9] Bachmann, C., T. Ainsworth, et al., Exploiting manifold geometry in hyperspectral imagery , IEEE Transactions on Geoscience and Remote Sensing, 43(2005) 441-454.

DOI: 10.1109/tgrs.2004.842292

[10] R. A. Schowengerdt, Remote Sensing: Models and Methods for Image Processing, 2nd ed., Academic Press, San Diego, (1997).

[11] Angelopoulou E, Lee S W, Bajcsy R. Spectral gradient: A material descriptor invariant to geometry and incident illumination, Proceedings of International Conference on Computer Vision, (1999) 861-867.

DOI: 10.1109/iccv.1999.790312

[12] Reed, I. and X. Yu, Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution, IEEE Transactions on Acoustics, Speech and Signal Processing, 38 (1990) 1760-1770.

DOI: 10.1109/29.60107