摘要
回顾了粒子群算法的基本原理,分析了端元提取算法的两种技术途径。利用粒子群优化的原理,结合凸面几何学理论和线性光谱混合模型,设计了一种粒子群优化端元提取算法,并设计了算法的快速实现方法。该算法不需要假设影像中存在纯像元,同时保持了端元光谱的形状。利用模拟数据和AVIRIS影像对该算法、SGA算法和NMF算法进行实验对比分析,实验结果证明该算法的端元提取精度优于其他二者。
The theory of particle swarm optimization is reviewed, and two technical ways of endmembers extraction are analyzed. A particle swarm optimization-based endmembers extraction algorithms for hyperspectral imagery is proposed, which is based on the theo- ries of particle swarm optimization, convex geometry and the linear spectral mixture model. The fast implementation method of this al- gorithm is designed. This algorithm needn＇t suppose that there are pure pixels in hyperspectral images, as well as this algorithm can pre- serve the shape of the endmembers＇ spectrums. It carries out the experiments by simulative and AVIRIS hyperspectral image, and the results among the PSO-based algorithm, SGA and NMF are compared and analyzed. The results of experiments prove the PSO-based al- gorithm is more accurate than SGA and NMF.
出处
《计算机工程与应用》
CSCD
2012年第8期189-193,共5页
Computer Engineering and Applications
关键词
高光谱影像
粒子群优化
线性混合模型
端元提取
hyperspectral imagery
particle swarm optimization
linear mixture model
endmembers extraction
