A new parallel tool for classification of remotely sensed imagery

Authors:
Sergio Bernabé;Antonio Plaza;Prashanth Reddy Marpu;Jon Atli Benediktsson
Affiliations:
Hyperspectral Computing Laboratory, Department of Technology of Computers and Communications, University of Extremadura, Avda. de la Universdad s/n, E-10071 Cáceres, Spain;Hyperspectral Computing Laboratory, Department of Technology of Computers and Communications, University of Extremadura, Avda. de la Universdad s/n, E-10071 Cáceres, Spain;Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland;Faculty of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland
Venue:
Computers & Geosciences
Year:
2012

Citing 8
Cited 1

Hierarchy in Picture Segmentation: A Stepwise Optimization Approach

IEEE Transactions on Pattern Analysis and Machine Intelligence
Morphological Image Analysis: Principles and Applications

Morphological Image Analysis: Principles and Applications
Image Analysis and Mathematical Morphology

Image Analysis and Mathematical Morphology
Commodity cluster-based parallel processing of hyperspectral imagery

Journal of Parallel and Distributed Computing
Remote Sensing Digital Image Analysis: An Introduction

Remote Sensing Digital Image Analysis: An Introduction
High Performance Computing in Remote Sensing

High Performance Computing in Remote Sensing
Clusters Versus FPGA for Parallel Processing of Hyperspectral Imagery

International Journal of High Performance Computing Applications
GPU for Parallel On-Board Hyperspectral Image Processing

International Journal of High Performance Computing Applications

Accelerating satellite image based large-scale settlement detection with GPU

Proceedings of the 1st ACM SIGSPATIAL International Workshop on Analytics for Big Geospatial Data

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe a new tool for classification of remotely sensed images. Our processing chain is based on three main parts: (1) pre-processing, performed using morphological profiles which model both the spatial (high resolution) and the spectral (color) information available from the scenes; (2) classification, which can be performed in unsupervised fashion using two well-known clustering techniques (ISODATA and k-means) or in supervised fashion, using a maximum likelihood classifier; and (3) post-processing, using a spatial-based technique based on a moving a window which defines a neighborhood around each pixel which is used to refine the initial classification by majority voting, taking in mind the spatial context around the classified pixel. The processing chain has been integrated into a desktop application which allows processing of satellite images available from Google Maps(TM) engine and developed using Java and the SwingX-WS library. A general framework for parallel implementation of the processing chain has also been developed and specifically tested on graphics processing units (GPUs), achieving speedups in the order of 30xwith regard to the serial version of same chain implemented in C language.