Theses and Dissertations
Issuing Body
Mississippi State University
Advisor
Du, Q. Jenny
Committee Member
Banicescu, Ioana
Committee Member
Younan, H. Nicholas
Committee Member
Moorhead II, J. Robert
Date of Degree
4-30-2011
Document Type
Dissertation - Open Access
Major
Electrical Engineering
Degree Name
Doctor of Philosophy (Ph.D)
College
James Worth Bagley College of Engineering
Department
Department of Electrical and Computer Engineering
Abstract
In this dissertation, dimensionality reduction for hyperspectral remote sensing imagery is investigated to alleviate practical application difficulties caused by high data dimension. Band selection and band clustering are applied for this purpose. Based on availability of object prior information, supervised, semi-supervised, and unsupervised techniques are proposed. To take advantage of modern computational architecture, parallel implementations on cluster and graphics processing units (GPU) are developed. The impact of dimensionality reduction on the following data analysis is also evaluated. Specific contributions are as below. 1. A similarity-based unsupervised band selection algorithm is developed to select distinctive and informative bands, which outperforms other existing unsupervised band selection approaches in the literature. 2. An efficient supervised band selection method based on minimum estimated abundance covariance is developed, which outperforms other frequently-used metrics. This new method does not need to conduct classification during band selection process or examine original bands/band combinations as do traditional approaches. 3. An efficient semi-supervised band clustering method is proposed, which uses class signatures to conduct band partition. Compared to traditional unsupervised clustering, computational complexity is significantly reduced. 4. Parallel GPU implementations with computational cost saving strategies for the developed algorithms are designed to facilitate onboard processing. 5. As an application example, band selection results are used for urban land cover classification. With a few selected bands, classification accuracy can be greatly improved, compared to the one using all the original bands or those from other frequently-used dimensionality reduction methods.
URI
https://hdl.handle.net/11668/15049
Recommended Citation
Yang, He, "Dimensionality reduction for hyperspectral imagery" (2011). Theses and Dissertations. 1510.
https://scholarsjunction.msstate.edu/td/1510
Comments
In this dissertation, dimensionality reduction for hyperspectral remote sensing imagery is investigated to alleviate practical application difficulties caused by high data dimension. Band selection and band clustering are applied for this purpose. Based on availability of object prior information, supervised, semi-supervised, and unsupervised techniques are proposed. To take advantage of modern computational architecture, parallel implementations on cluster and graphics processing units (GPU) are developed. The impact of dimensionality reduction on the following data analysis is also evaluated. Specific contributions are as below. 1. A similarity-based unsupervised band selection algorithm is developed to select distinctive and informative bands, which outperforms other existing unsupervised band selection approaches in the literature. 2.An efficient supervised band selection method based on minimum estimated abundance covariance is developed, which outperforms other frequently-used metrics. This new method does not need to conduct classification during band selection process or examine original bands/band combinations as do traditional approaches. 3.An efficient semi-supervised band clustering method is proposed, which uses class signatures to conduct band partition. Compared to traditional unsupervised clustering, computational complexity is significantly reduced. 4.Parallel GPU implementations with computational cost saving strategies for the developed algorithms are designed to facilitate onboard processing. 5.As an application example, band selection results are used for urban land cover classification. With a few selected bands, classification accuracy can be greatly improved, compared to the one using all the original bands or those from other frequently-used dimensionality reduction methods.