基於平行粒子群優非純度波段優先權法應用於高光譜影像波段選取

近年來光譜感測器的卓越發展，高光譜影像的資訊越趨豐富，資料量也越來越龐大，相對的其計算複雜度也越來越高，因此如何快速且有效率的挑選出有利於辨識的波段是一大課題。本論文提出一套波段選取的方法，其中包含了「粒子群優法 (Particle Swarm Optimization, PSO)」及「非純度波段優先權法(Impurity Function Band Prioritization, IFBP)」，首先將光譜資料經由PSO粗略的將相似度高的波段群聚在一起，接著透過IFBP方法精細的從群聚的波段中，挑選出最具代表性的波段，以降低光譜資料的複雜度。然而，當光譜資料越趨龐大時，PSO演算法依然需要耗費大量時間，因此本論文應用CUDA (Compute Unified Device Architecture)技術實現平行粒子群優法(PPSO)，利用圖形處理單元(Graphics Processing Unit, GPU)提升整體運算速度。本論文採用鰲鼓溼地的 MASTER 遙測影像以及 Northwest Tippecanoe County 的AVIRIS 遙測影像為實驗圖資。由實驗結果可以得知，本論文所提出的平行粒子群優非純度波段優先權法能夠迅速、有效地挑選出有價值且具代表性的波段，並透過最近鄰分類器(K-nearest neighbor, kNN)得到良好的分類效果。

關鍵字

相關係數矩陣；降維；圖形處理單元；非純度波段優先權法；粒子群優波段選取

並列摘要

In recent years, satellite imaging technologies have resulted in an increased number of bands acquired by hyperspectral sensors, greatly advancing the field of remote sensing. Accordingly, owing to the increasing number of bands, band selection in hyperspectral imagery for dimension reduction is important. This paper presents a framework for band selection in hyperspectral imagery that uses two techniques, referred to as particle swarm optimization (PSO) band selection and the impurity function band prioritization (IFBP) method. With the PSO band selection algorithm, highly correlated bands of hyperspectral imagery can first be grouped into modules to coarsely reduce high-dimensional datasets. Then, these highly correlated band modules are analyzed with the IFBP method to finely select the most important feature bands from the hyperspectral imagery dataset. However, PSO band selection is a time-consuming procedure when the number of hyperspectral bands is very large. Hence, this paper proposes a parallel computing version of PSO, namely parallel PSO (PPSO), using a modern graphics processing unit (GPU) architecture with NVIDIA’s compute unified device architecture (CUDA) technology to improve the computational speed of PSO processes. The natural parallelism of the proposed PPSO lies in the fact that each particle can be regarded as an independent agent. Parallel computation benefits the algorithm by providing each agent with a parallel processor. The intrinsic parallel characteristics embedded in PPSO are, therefore, suitable for parallel computation. The effectiveness of the proposed PPSO is evaluated through the use of Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) hyperspectral images. The performance of PPSO is validated using the supervised K-nearest neighbor classifier. The experimental results demonstrate that the proposed PPSO/IFBP band selection method can not only improve computational speed, but also offer a satisfactory classification performance.

並列關鍵字

Correlation Coefficient Matrix ； Dimension Reduction ； Graphics Processing Unit ； Impurity Function Band Prioritization ； Particle Swarm Optimization Band Selection

參考文獻

[26] 徐斌峰，一個維度優先權方法應用於粒子群優法在高維度影像特徵抽取，碩士論文，國立台北科技大學電機工程研究所，台北，2011。

[35] Yang-Lang Chang, Jyh-Perng Fang, Hsuan Ren, Wen-Yew Liang, and Jin-Nan Liu, "A Simulated Annealing Feature Extraction Approach for Hyperspectral Images," Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, IGARSS '07, Barcelona, Spain ,July 23-27,2007, NSC 95-2221-E-027-037, (EI).

[1] R. Duda and P. Hart, Pattern Classification and Scene Analysis, New York: John Wiley & Sons, 1973.

[2] A. Ambikapathi, T.-H. Chan, W.-K. Ma and C.-Y. Chi, "Chance constrained robust minimum volume enclosing simplex algorithm for hyperspectral unmixing," IEEE Trans. Geoscience and Remote Sensing, vol. 49, no. 11, Nov. 2011, pp. 4194-4209.

[3] G. F. Hughes, "On the mean accuracy of statistical pattern recognizers, " IEEE Transactions on Information Theory, vol. 14 no. 1, 1968, pp. 55–63.2.

國際替代計量

基於平行粒子群優非純度波段優先權法應用於高光譜影像波段選取

全文下載

主題瀏覽