FPGA Implementation of the HySime Algorithm for the Determination of the Number of Endmembers in Hyperspectral Data

Abstract

Spectral unmixing is an important task for remotely sensed hyperspectral data exploitation. It amounts the identification of pure spectral signatures (endmembers) in the data, and the estimation of the abundance of each endmember in each (possibly mixed) pixel. A challenging problem in spectral unmixing is how to determine the number of endmembers in a given scene. One of the most popular and widely used techniques for this purpose is the HySime algorithm but, due to the complexity and high dimensionality of hyperspectral scenes, this technique is computational expensive. Reconfigurable field-programmable gate arrays (FPGAs) are promising platforms that allow hardware/software codesign and the potential to provide powerful onboard computing capabilities and flexibility at the same time. In this paper, we present the first FPGA design for the HySime algorithm. Our system includes a direct memory access (DMA) module and implements a prefetching technique to hide the latency of the input/output communications. The proposed method has been implemented on a Virtex-7 XC7VX690T FPGA and tested using real hyperspectral data collected by NASAs airborne visible infrared imaging spectrometer (AVIRIS) over the Cuprite mining district in Nevada and the World trade center (WTC) in New York.Experimental results demonstrate that our hardware version of the HySime algorithm can significantly outperform a software version, which makes our reconfigurable system appealing for onboard hyperspectral data processing.Index Terms-Field-programmable gate arrays (FPGAs), hyperspectral imaging, HySime, number of endmembers estimation, reconfigurable hardware.

Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art

“…This device can be used to implement any circuit (provided there are a sufficient number of logic blocks). FPGAs have been widely used to accelerate hyperspectral imaging algorithms for onboard processing [321][322][323].…”

Porting a PCA-based hyperspectral image dimensionality reduction algorithm for brain cancer detection on a manycore architecture

“…González et al provide an extensive description of this method in [21], including the mathematical basis.…”

“…Among all the existing variations, the cyclic Jacobi [21] has finally been implemented. As described in Section II, the main variation of this method is that, instead of choosing the elements to be zeroed by finding the largest off-diagonal element, it chooses the next element in a given order, e. g., row by row.…”

Parallel implementation of a hyperspectral data geometry-based estimation of number of endmembers algorithm

“…The acceleration of both methods on different architectures has been extensively studied by previous work. [6][7][8] The geometry-based estimation of number of endmembers algorithm (GENE) 1 has been recently proposed as a promising alternative to VD and HySime. However, to the best of the authors' knowledge, its parallel implementation has not been studied yet.…”