• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Cloud Computing and Security >Detection in SAR Images Based on Histogram and Improved Elitist Genetic Fuzzy Clustering
【24h】

Detection in SAR Images Based on Histogram and Improved Elitist Genetic Fuzzy Clustering

机译：基于直方图和改进的精英遗传模糊聚类的SAR图像检测

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Change detection in Synthetic Aperture Radar Images has been an important technique for Synthetic Aperture Radar Images. In this paper, a novel unsupervised change detection algorithm based on histogram and improved elitist genetic fuzzy clustering is proposed. First, a difference image is generated by multiplying transform fusion. Second, we use the characteristics of the histogram to deal with the difference image. Then, the new algorithm is proposed to partition these characteristics into changed and unchanged regions. The proposed algorithm has the following merits: 1. FCM is employed to initialize the population and to calculate the fitness function of the genetic algorithm. 2. The optimal solution is selected by an elitist selection strategy based on population concentration and the optimal solution will be the initial clustering center of FCM, which significandy increases the convergence speed. 3. The histogram is utilized to reduce the sample points of images. Compared with the state-of-the-art algorithms, the experimental results demonstrate the effectiveness in processing of change detection in SAR images.
机译：合成孔径雷达图像中的变化检测已成为合成孔径雷达图像中的一项重要技术。提出了一种基于直方图和改进的精英遗传模糊聚类的无监督变化检测算法。首先，通过相乘变换融合来生成差分图像。其次，我们使用直方图的特征来处理差异图像。然后，提出了一种新的算法将这些特征划分为变化和不变的区域。所提出的算法具有以下优点：1.采用FCM初始化种群并计算遗传算法的适应度函数。 2.最佳解决方案是基于人群集中的精英选择策略选择的，而最佳解决方案将是FCM的初始聚类中心，这显着提高了收敛速度。 3.直方图用于减少图像的采样点。与最新算法相比，实验结果证明了在SAR图像变化检测处理中的有效性。

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