A suite of parallel algorithms for efficient band selection from hyperspectral images
- 56 Downloads
The analysis of hyperspectral images is usually very heavy from the computational point-of-view, due to their high dimensionality. In order to avoid this problem, band selection (BS) has been widely used to reduce the dimensionality before the analysis. The aim is to extract a subset of the original bands of the hyperspectral image, preserving most of the information contained in the original data. The BS technique can be performed by prioritizing the bands on the basis of a score, assigned by specific criteria; in this case, BS turns out in the so-called band prioritization (BP). This paper focuses on BP algorithms based on the following parameters: signal-to-noise ratio, kurtosis, entropy, information divergence, variance and linearly constrained minimum variance. In particular, an optimized C serial version has been developed for each algorithm from which two parallel versions have been derived using OpenMP and NVIDIA’s compute unified device architecture. The former is designed for a multi-core CPU, while the latter is designed for a many-core graphics processing unit. For each version of these algorithms, several tests have been performed on a large database containing both synthetic and real hyperspectral images. In this way, scientists can integrate the proposed suite of efficient BP algorithms into existing frameworks, choosing the most suitable technique for their specific applications.
KeywordsHyperspectral imaging Band selection (BS) Band prioritization (BP) Real-time processing Central processing unit (CPU) Graphics processing unit (GPU)
The authors gratefully thank NVIDIA Corporation for the donation of the GPU Tesla K40 used for this research.
- 2.Mausel, P.W., Kramber, W.J., Lee, J.K.: Optimum band selection for supervised classification of multispectral data. Photogramm. Eng. Remote Sens. 56(1), 55–60 (1990)Google Scholar
- 3.Stearns, S.D., Wilson, B.E., Peterson, J.R.: Dimensionality reduction by optimal band selection for pixel classification of hyperspectral imagery. In: Applications of Digital Image Processing XVI, SPIE, vol. 2028, pp. 118–127 (1993)Google Scholar
- 8.Wang, S., Chang, C.-I.: Band prioritization for hyperspectral imagery. In: Proceedings of SPIE 6302, Imaging Spectrometry XI, 63020I, https://doi.org/10.1117/12.681658 (2006)
- 15.NVIDIA Corp.: NVIDIA Kepler GK110 architecture whitepaper. https://www.nvidia.com/content/PDF/kepler/NVIDIA-Kepler-GK110-Architecture-Whitepaper.pdf. Accessed Feb 2017
- 16.Nascimento, J.M.P., Bioucas-Dias, J.M.: Hyperspectral subspace identification. IEEE Trans. Geosci. Remote Sens. 46(8), 1445–2435 (2008)Google Scholar
- 21.Green, R.O., Eastwood, M.L., Sarture, C.M., Chrien, T.G., Aronsson, M., Chippendale, B.J., Faust, J.A., Pavri, B.E., Chovit, C.J., Solis, M., Olah, M.R., Williams, O.: Imaging spectroscopy and the airborne visible/infrared imaging spectrometer. Remote Sens. Environ. 65(3), 227–248 (1998)CrossRefGoogle Scholar
- 22.Yang, H., Du, Q.: Fast band selection for hyperspectral imagery. In: 2011 IEEE 17th international conference on parallel and distributed systems, Tainan, pp. 1048–1051 (2011)Google Scholar
- 23.Zheng, J., Zhao, L., Li, X., Zhou, X., Li, J.: GPU-based acceleration of the hyperspectral band selection by SNR estimation using wavelet transform. In: Proceedings of SPIE 9263, multispectral, hyperspectral, and ultraspectral remote sensing technology, techniques and applications V (2014)Google Scholar
- 26.Chang, Y.L., Fang, J.P., Benediktsson, J.A., Chang, L., Ren, H., Chen, K.S.: Band selection for hyperspectral images based on parallel particle swarm optimization schemes. In: 2009 IEEE international geoscience and remote sensing symposium, Cape Town, pp. V-84–V-87 (2009)Google Scholar