• 主题
高级搜索  >
历史搜索 清空历史
首页> 美国卫生研究院文献>Sensors (Basel Switzerland) >Fusion of Unmanned Aerial Vehicle Panchromatic and Hyperspectral Images Combining Joint Skewness-Kurtosis Figures and a Non-Subsampled Contourlet Transform
【2h】

Fusion of Unmanned Aerial Vehicle Panchromatic and Hyperspectral Images Combining Joint Skewness-Kurtosis Figures and a Non-Subsampled Contourlet Transform

机译：结合关节偏度-峰度图和非下采样Contourlet变换的无人机全色和高光谱图像的融合

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务，本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文，但由于OA文献来源多样且变更频繁，仍可能出现获取不到、文献不完整或与标题不符等情况，如果获取不到我们将提供退款服务。请知悉。
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

To obtain fine and potential features, a highly informative fused image created by merging multiple images is usually required. In our study, a novel fusion algorithm called JSKF-NSCT is proposed for fusing panchromatic (PAN) and hyperspectral (HS) images by combining the joint skewness-kurtosis figure (JSKF) and the non-subsampled contourlet transform (NSCT). The JSKF model is used first to derive the three most sensitive bands from the original HS image according to the product of the skewness and the kurtosis coefficients of each band. Afterwards, an intensity-hue-saturation (IHS) transform is used to obtain the luminance component I of the produced false-colour image consisting of the above three bands. Then the NSCT method is used to decompose component I of the false-colour image and the PAN image. The weight-selection rule based on the regional energy is adopted to acquire the low-frequency coefficients and the correlation between the central pixel and its surrounding pixels is used to select the high-frequency coefficients. Finally, the fused image is obtained by applying an IHS inverse transform and an inverse NSCT transform. The unmanned aerial vehicle (UAV) HS and PAN images under low- and high-vegetation coverage of wheat at the flag leaf stage (Stage I) and the grain filling stage (Stage II) are used as the sample data sources. The fusion results are comparatively validated using spatial (entropy, standard deviation, average gradient and mean) and spectral (normalised difference vegetation, NDVI, and leaf area index, LAI) assessments. Additional comparative studies using anomaly detection and pixel clustering also demonstrate that the proposed method outperforms other methods. They show that the algorithm reported herein can better preserve the original spatial and spectral characteristics of the two types of images to be fused and is more stable than IHS, principal components analysis (PCA), non-negative matrix factorization (NMF) and Gram-Schmidt (GS).
机译：为了获得精细和潜在的特征，通常需要通过合并多个图像而创建的高度信息化的融合图像。在我们的研究中，提出了一种新颖的融合算法，称为JSKF-NSCT，它通过结合联合偏斜度峰度图（JSKF）和非下采样轮廓波变换（NSCT）来融合全色（PAN）和高光谱（HS）图像。首先使用JSKF模型根据每个波段的偏度和峰度系数的乘积从原始HS图像中得出三个最敏感的波段。之后，使用强度-色相-饱和度（IHS）变换来获得所产生的由上述三个波段组成的假彩色图像的亮度分量I。然后使用NSCT方法分解假彩色图像和PAN图像的分量I。采用基于区域能量的权重选择规则来获取低频系数，并使用中心像素与其周围像素之间的相关性来选择高频系数。最后，通过应用IHS逆变换和NSCT逆变换获得融合图像。在旗叶期（第一阶段）和籽粒充实阶段（第二阶段）的小麦低，高植被覆盖下的无人飞行器（UAV）HS和PAN​​图像用作样本数据源。使用空间（熵，标准差，平均梯度和均值）和光谱（归一化差异植被，NDVI和叶面积指数，LAI）评估对融合结果进行了比较验证。使用异常检测和像素聚类的其他比较研究也表明，所提出的方法优于其他方法。他们表明，本文报告的算法可以更好地保留要融合的两种类型图像的原始空间和光谱特征，并且比IHS，主成分分析（PCA），非负矩阵分解（NMF）和Gram-施密特（GS）。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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