一個對於高光譜影像的二維模擬退火波段選擇方法

A two-dimension simulated annealing band selection approach for hyperspectral imagery

林鈞傑(Chun-Chieh Lin)

指導教授 ： 方志鵬 ； 張陽郎

國立臺北科技大學/電資學院/電機工程系研究所/碩士(2007年)

https://doi.org/10.6841/NTUT.2007.00247

摘要

就高光譜影像而言，貪婪模組特徵空間（GME）利用貪婪演算法為基礎群集高度相關的高光譜波段成一個較小的波段子集合。在本論文中，我們採用模擬退火法取代高光譜影像處理中被採用的GME方法，模擬退火法在最佳化方法中通常是一種更有效的探索方法。這篇論文提出一個「二維模擬退火波段選取（2DSABS）」方法，這個方法能有效地進行高光譜特徵抽取。「二維模擬退火波段選取」以模擬退火演算法為基礎，針對高光譜影像選擇一組非相關的高光譜波段，同時利用在高光譜影像中不同種類的分離度來降低維度，並且進一步有效地產生一個唯一群集的特徵空間（CE）。本論文所提出的二維模擬退火波段選取特色有(1)避免轉換資訊成波段的線性組合的偏差值問題，這是採用傳統的主成份分析方式常見的問題；(2)利用一個簡單的邏輯運算，稱為「CE特徵維度齊一化轉換」，將不同種類的資訊混合，形成具有共通特徵波段的群集子集合；(3)提供一個快速的程序，使能同時地選取最有意義的特徵，並顯著地改善特徵分解計算的複雜性。實驗結果顯示，本論文提出的二維模擬退火波段選取方法有不錯的效率，並且能夠作為現今特徵抽取演算法中的另一種選擇。

關鍵字

高光譜 ； 特徵萃取 ； 貪婪模組特徵空間(GME) ； 模擬退火波段選取(SABS) ； 群聚特徵模組 / 特徵維度一致化轉換(CE/FSUT) ； 主成分分析 (PCA)

並列摘要

For hyperspectral imagery, greedy modular eigenspaces (GME) has been developed by clustering highly correlated hyperspectral bands into a smaller subset of band modular based on greedy algorithm. In this paper, we introduce a simulated annealing mechanism, which is a typical heuristic method in the optimization process, in place of greedy paradigm as adopted in GME approach for hyperspectral imagery. This paper proposes a new method called the two-dimension simulated annealing band selection (2DSABS) for hyperspectral feature extraction. The 2DSABS selects the sets of non-correlated hyperspectral bands for hyperspectral images based on simulated annealing (SA) algorithm while utilizing the inherent separability of different classes in hyperspectral images to reduce dimensionality and further to effectively generate a unique clustered eigenspace (CE) feature. The proposed 2DSABS features can (1) avoid the bias problems of transforming the information into linear combinations of bands as does the traditional principal components analysis (PCA); (2) select each band by a simple logical operation, called CE feature scale uniformity transformation (CE/FSUT), to include different classes into the most common feature clustered subset of bands; (3) provide a fast procedure to simultaneously select the most significant features, and therefore dramatically improve the eigen-decomposition computational complexity. The experimental results show that the proposed 2DSABS approach is effective and can be used as an alternative to the existing feature extraction algorithms.

並列關鍵字

hyperspectral ； feature extraction ； greedy modular eigenspaces (GME) ； simulated annealing band selection (SABS) ； clustered eigenspace / feature scale uniformity transformation (CE/FSUT) ； principal component analysis (PCA)

參考文獻

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

[3] J. Harsanyi and C.-I. Chang, “Hyperspectral image classification and dimensionality reduction: anorthogonal subspace projection approach,” IEEE Trans. Geosci. Remote Sensing 32, no. 4, 1994, pp. 779–785.

[4] C. Lee and D. A. Landgrebe, “Analyzing high-dimensional multispectral data,” IEEE Trans. Geosci. Remote Sensing 31, no. 4, 1993, pp. 792–800.

[5] Rudy Setiono and Huan Liu, “Neural-Network Feature Selector”, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 8, NO. 3, MAY 1997

[6] Yang-Lang Chang, Chin-Chuan Han, Kuo-Chin Fan, K.S. Chen, Chia-Tang Chen and Jeng-Horng Chang, "Greedy Modular Eigenspaces and Positive Boolean Function for Supervised Hyperspectral Image Classification," Optical Engineering, Vol. 42, Issue 9, pp. 2576-2587, September 2003 (SCI, EI).