Spectrally segmented principal component analysis of hyperspectral imagery for mapping invasive plant species

Principal component analysis (PCA) is one of the most commonly adopted feature reduction techniques in remote sensing image analysis. However, it may overlook subtle but useful information if applied directly to the analysis of hyperspectral data, especially for discriminating between different vegetation types. In order to accurately map an invasive plant species (horse tamarind, Leucaena leucocephala) in southern Taiwan using Hyperion hyperspectral imagery, this study developed a spectrally segmented PCA based on the spectral characteristics of vegetation over different wavelength regions. The developed algorithm can not only reduce the dimensionality of hyperspectral imagery but also extracts helpful information for differentiating more effectively the target plant species from other vegetation types. Experiments conducted in this study demonstrated that the developed algorithm performs better than correlation‐based segmented principal component transformation (SPCT) and conventional PCA (overall accuracy: 86%, 76%, 66%; kappa value: 0.81, 0.69, 0.57) in detecting the target plant species, as well as mapping other vegetation covers.

[1]  David A. Landgrebe,et al.  Analyzing high-dimensional multispectral data , 1993, IEEE Trans. Geosci. Remote. Sens..

[2]  C. McCormick.  Mapping Exotic Vegetation in the Everglades from Large-Scale Aerial Photographs , 1999 .

[3]  Lori M. Bruce,et al.  Why principal component analysis is not an appropriate feature extraction method for hyperspectral data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[4]  Marguerite Madden,et al.  Hyperspectral image data for mapping wetland vegetation , 2003, Wetlands.

[5]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[6]  R. Hall,et al.  Incorporating texture into classification of forest species composition from airborne multispectral images , 2000 .

[7]  John Shepanski,et al.  Hyperion, a space-based imaging spectrometer , 2003, IEEE Trans. Geosci. Remote. Sens..

[8]  Tiranee Achalakul,et al.  A concurrent spectral-screening PCT algorithm for remote sensing applications , 2000, Inf. Fusion.

[9]  Tim R. McVicar,et al.  Preprocessing EO-1 Hyperion hyperspectral data to support the application of agricultural indexes , 2003, IEEE Trans. Geosci. Remote. Sens..

[10]  P. Switzer,et al.  A transformation for ordering multispectral data in terms of image quality with implications for noise removal , 1988 .

[11]  Kadi Bouatouch,et al.  Nested radiosity for plant canopies , 1998, The Visual Computer.

[12]  Stephen G. Ungar,et al.  Overview of the Earth Observing One (EO-1) mission , 2003, IEEE Trans. Geosci. Remote. Sens..

[13]  René Vidal,et al.  A new GPCA algorithm for clustering subspaces by fitting, differentiating and dividing polynomials , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[14]  S. Ustin,et al.  Using AVIRIS data and multiple-masking techniques to map urban forest tree species , 2004 .

[15]  K. Staenz.  Classification of a Hyperspectral Agricultural Data Set Using Band Moments for Reduction of the Spectral Dimensionality , 1996 .

[16]  F. Baret,et al.  PROSPECT: A model of leaf optical properties spectra , 1990 .

[17]  S. Shankar Sastry,et al.  Generalized principal component analysis (GPCA) , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Gladimir V. G. Baranoski,et al.  Reducing the dimensionality of plant spectral databases , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[19]  Jiang Li,et al.  Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction , 2002, IEEE Trans. Geosci. Remote. Sens..

[20]  J. Woolley.  Reflectance and transmittance of light by leaves. , 1971, Plant physiology.

[21]  J. C. Price,et al.  Spectral band selection for visible-near infrared remote sensing: spectral-spatial resolution tradeoffs , 1997, IEEE Trans. Geosci. Remote. Sens..

[22]  Pablo J. Zarco-Tejada,et al.  ESTIMATION OF CHLOROPHYLL FLUORESCENCE UNDER NATURAL ILLUMINATION FROM HYPERSPECTRAL DATA , 2001 .

[23]  C. Tucker,et al.  Leaf optical system modeled as a stochastic process. , 1977, Applied optics.

[24]  David A. Landgrebe,et al.  Analyzing High Dimensional Data , 1992, [Proceedings] IGARSS '92 International Geoscience and Remote Sensing Symposium.

[25]  S. Ustin,et al.  Mapping nonnative plants using hyperspectral imagery , 2003 .

[26]  Marco Diani,et al.  An unsupervised algorithm for the selection of endmembers in hyperspectral images , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[27]  William Philpot,et al.  A derivative-aided hyperspectral image analysis system for land-cover classification , 2002, IEEE Trans. Geosci. Remote. Sens..

[28]  Masato Katoh,et al.  Classifying tree species in a northern mixed forest using high-resolution IKONOS data , 2004, Journal of Forest Research.

[29]  Milo E. Richmond,et al.  Field Determination of Optimal Dates for the Discrimination of Invasive Wetland Plant Species Using Derivative Spectral Analysis , 2005 .

[30]  T. S. Prasad,et al.  New hyperspectral vegetation characterization parameters , 2001 .

[31]  John A. Richards,et al.  Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[32]  Fuan Tsai,et al.  Derivative analysis of hyperspectral data , 1996, Remote Sensing.

[33]  M. Cochrane.  Using vegetation reflectance variability for species level classification of hyperspectral data , 2000 .