A PROSAIL-based spectral unmixing algorithm for solving vegetation spectral variability problem

The spectral signature of vegetation in the image is easily affected by background soil reflectance and spectral variability of vegetation reflectance, spectral variability is one of the major error sources of unmixing. The traditional algorithms do not solve spectral variability problem from the mechanism. In this paper, we take advantage of radiative transfer model, in order to describe the spectral variability of endmember. As a result, the spectral variability can be quantitatively described. The experimental results show that the PROSAIL Model Spectral Unmixing (PMSU) algorithm has higher unmixing precision than the other algorithms.

[1]  Martin Brown,et al.  Linear spectral mixture models and support vector machines for remote sensing , 2000, IEEE Trans. Geosci. Remote. Sens..

[2]  Jean-Yves Tourneret,et al.  Bayesian Estimation of Linear Mixtures Using the Normal Compositional Model. Application to Hyperspectral Imagery , 2010, IEEE Transactions on Image Processing.

[3]  Guillermo Sapiro,et al.  Learning Discriminative Sparse Representations for Modeling, Source Separation, and Mapping of Hyperspectral Imagery , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Antonio J. Plaza,et al.  Automated Extraction of Image-Based Endmember Bundles for Improved Spectral Unmixing , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[5]  Margaret E. Gardner,et al.  Mapping Chaparral in the Santa Monica Mountains Using Multiple Endmember Spectral Mixture Models , 1998 .

[6]  Ye Zhang,et al.  SVM-Based Unmixing-to-Classification Conversion for Hyperspectral Abundance Quantification , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[7]  John F. Mustard,et al.  Spectral unmixing , 2002, IEEE Signal Process. Mag..

[8]  Paul D. Gader,et al.  Spatial and Spectral Unmixing Using the Beta Compositional Model , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  K. C. Ho,et al.  Endmember Variability in Hyperspectral Analysis: Addressing Spectral Variability During Spectral Unmixing , 2014, IEEE Signal Processing Magazine.

[10]  W. Verhoef,et al.  PROSPECT+SAIL models: A review of use for vegetation characterization , 2009 .

[11]  Pol Coppin,et al.  Endmember variability in Spectral Mixture Analysis: A review , 2011 .

[12]  Roberta E. Martin,et al.  PROSPECT-4 and 5: Advances in the leaf optical properties model separating photosynthetic pigments , 2008 .

[13]  Guo-mo Zhou,et al.  [Retrieval of leaf area index of moso bamboo forest with Landsat Thematic Mapper image based on PROSAIL canopy radiative transfer model]. , 2013, Ying yong sheng tai xue bao = The journal of applied ecology.

[14]  Vinay Kumar Sehgal,et al.  Inversion of PROSAIL Model for Retrieval of Plant Biophysical Parameters , 2012, Journal of the Indian Society of Remote Sensing.