Hyperspectral Remote Sensing Classification Processing Parallel Computing Research Based on GPU

Abstract

Hyper spectral remote sensing has a great application in resources, environment, urban development and ecological balance and other aspects, one of the most important fields is for precise classification of features. Due to the hyper spectral remote sensing data has the characteristics of large data volume, the specific operation in the presence of long processing time problem. This paper focus on SAM algorithm and realize optimization based on the GPU parallel framework, and makes a system experiment on hyper spectral remote sensing images to prove the validity of this method.