...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Geoscience and Remote Sensing >An Improved Quantum-Behaved Particle Swarm Optimization for Endmember Extraction
【24h】

An Improved Quantum-Behaved Particle Swarm Optimization for Endmember Extraction

机译：端成员提取的改进的量子行为粒子群算法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Endmember extraction (EE) plays an important role in the quantitative analysis of hyperspectral images, as the main step in the decomposition of mixed pixels. At present, scholars have proposed many EE algorithms based on the linear spectral mixture model and the convex geometry principle, such as the pixel purity index (PPI) and the vertex component analysis (VCA). At the same time, many intelligent optimization algorithms, such as the particle swarm optimization (PSO) and the discrete PSO (DPSO), have been applied to EE, which can get promising results for real images. However, PSO and DPSO have theoretical limitations and cannot guarantee the global convergence. The problem of premature convergence will reduce the accuracy of the EE result. The quantum-behaved PSO (QPSO) can theoretically guarantee the convergence of the algorithm by combining the quantum mechanics into the PSO. In order to increase the accuracy of the algorithm, this paper proposes an improved QPSO (IQPSO) algorithm for EE. IQPSO has made innovations in population coding and initialization methods. Besides, the collaborative approach for updating the optimal positions of particles can help to solve the difficulties caused by high dimensions. The experimental results show that IQPSO can extract endmembers efficiently and effectively.
机译：作为混合像素分解的主要步骤，端元提取（EE）在高光谱图像的定量分析中起着重要作用。目前，学者们提出了许多基于线性谱混合模型和凸几何原理的EE算法，例如像素纯度指数（PPI）和顶点分量分析（VCA）。同时，许多智能优化算法，例如粒子群优化算法（PSO）和离散粒子优化算法（DPSO），已应用于EE，可以为真实图像获得有希望的结果。但是，PSO和DPSO具有理论上的局限性，不能保证全局收敛。过早收敛的问题将降低EE结果的准确性。通过将量子力学结合到PSO中，从理论上讲，量子行为PSO（QPSO）可以保证算法的收敛性。为了提高算法的准确性，本文提出了一种针对EE的改进的QPSO（IQPSO）算法。 IQPSO在种群编码和初始化方法方面进行了创新。此外，更新粒子最佳位置的协作方法可以帮助解决高维所带来的困难。实验结果表明，IQPSO可以高效地提取末端成员。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号