Parallel Morphological/Neural Classification of Remote Sensing Images Using Fully Heterogeneous and Homogeneous Commodity Clusters

The wealth spatial and spectral information available from last-generation Earth observation instruments has introduced extremely high computational requirements in many applications. Most currently available parallel techniques treat remotely sensed data not as images, but as unordered listings of spectral measurements with no spatial arrangement. In thematic classification applications, however, the integration of spatial and spectral information can be greatly beneficial. Although such integrated approaches can be efficiently mapped in homogeneous commodity clusters, low-cost heterogeneous networks of computers (HNOCs) have soon become a standard tool of choice in Earth and planetary missions. In this paper, we develop a new morphological/neural parallel algorithm for commodity cluster-based analysis of high-dimensional remotely sensed image data sets. The algorithms accuracy and parallel performance are tested (in the context of a real precision agriculture application) using two parallel platforms: a fully heterogeneous cluster made up of 16 workstations at University of Maryland, and a massively parallel Beowulf cluster at NASA's Goddard Space Flight Center

[1]  Alexey L. Lastovetsky,et al.  On performance analysis of heterogeneous parallel algorithms , 2004, Parallel Comput..

[2]  Alexey Lastovetsky Parallel Computing on Heterogeneous Networks: Lastrovetsky/Parallel Computing Networks , 2003 .

[3]  Massimo Cafaro,et al.  A dynamic earth observation system , 2003, Parallel Comput..

[4]  Alexey Lastovetsky Parallel computing on heterogeneous networks , 2003 .

[5]  Sundaram Suresh,et al.  Parallel implementation of back-propagation algorithm in networks of workstations , 2005, IEEE Transactions on Parallel and Distributed Systems.

[6]  Ping Wang,et al.  MODTRAN on supercomputers and parallel computers , 2002, Parallel Comput..

[7]  Sinthop Kaewpijit,et al.  Parallel and adaptive reduction of hyperspectral data to intrinsic dimensionality , 2001, Proceedings 42nd IEEE Symposium on Foundations of Computer Science.

[8]  Antonio J. Plaza,et al.  Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Jessica A. Faust,et al.  Imaging Spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) , 1998 .

[10]  M. Ancona,et al.  Cluster computing , 2003, Eleventh Euromicro Conference on Parallel, Distributed and Network-Based Processing, 2003. Proceedings..

[11]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[12]  Antonio J. Plaza,et al.  Commodity cluster-based parallel processing of hyperspectral imagery , 2006, J. Parallel Distributed Comput..

[13]  Peter Sussner,et al.  Morphological associative memories , 1998, IEEE Trans. Neural Networks.

[14]  Antonio J. Plaza,et al.  Automated generation of semi-labeled training samples for nonlinear neural network-based abundance estimation in hyperspectral data , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..