4464

Parallel Processing for Normal Mixture Models of Hyperspectral Data Using a Graphics Processor

Yuliya Tarabalka, Trym Vegard Haavardsholm, Ingebjorg Kasen, Torbjorn Skauli
Norwegian Defence Res. Establ. (FFI), Kjeller
IEEE International Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008

@inproceedings{tarabalka2008parallel,

   title={Parallel Processing for Normal Mixture Models of Hyperspectral Data Using a Graphics Processor},

   author={Tarabalka, Y. and Haavardsholm, T.V. and Kasen, I. and Skauli, T.},

   booktitle={Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International},

   volume={2},

   pages={II–990},

   organization={IEEE},

   year={2008}

}

Download Download (PDF)   View View   Source Source   

672

views

Multivariate normal mixture models, where a complex statistical distribution is represented by a weighted sum of several multivariate normal probability distributions, have many potential applications including anomaly detection (AD) in hyperspectral (HS) images. The high computational cost of mixture models requires hardware and/or algorithmic acceleration to make AD run in real time. In this paper we describe the concurrency present in the AD algorithm that includes a normal mixture estimation task. We explore the use of graphics processing units (GPUs) for parallel implementation of the algorithm. The GPU implementations provide a significant speedup compared to multi-core central processing unit (CPU) implementations, and enable the algorithm to execute in real time.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: