• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文OA文献 >Multi-resolution analysis techniques and nonlinear PCA for hybrid pansharpening applications
【2h】

Multi-resolution analysis techniques and nonlinear PCA for hybrid pansharpening applications

机译：多分辨率分析技术和非线性pCa用于混合式捣固应用

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

t Hyperspectral images have a higher spectral resolution (i.e., a larger number of\udbands covering the electromagnetic spectrum), but a lower spatial resolution with respect\udto multispectral or panchromatic acquisitions. For increasing the capabilities of the data in\udterms of utilization and interpretation, hyperspectral images having both high spectral and\udspatial resolution are desired. This can be achieved by combining the hyperspectral image\udwith a high spatial resolution panchromatic image. These techniques are generally known\udas pansharpening and can be divided into component substitution (CS) and multi-resolution\udanalysis (MRA) based methods. In general, the CS methods result in fused images having\udhigh spatial quality but the fused images suffer from spectral distortions. On the other hand,\udimages obtained using MRA techniques are not as sharp as CS methods but they are spectrally\udconsistent. Both substitution and filtering approaches are considered adequate when applied\udto multispectral and PAN images, but have many drawbacks when the low-resolution image\udis a hyperspectral image. Thus, one of the main challenges in hyperspectral pansharpening is\udto improve the spatial resolution while preserving as much as possible of the original spectral\udinformation. An effective solution to these problems has been found in the use of hybrid\udapproaches, combining the better spatial information of CS and the more accurate spectral\udinformation of MRA techniques. In general, in a hybrid approach a CS technique is used to\udproject the original data into a low dimensionality space. Thus, the PAN image is fused with\udone or more features by means of MRA approach. Finally the inverse projection is used to\udobtain the enhanced image in the original data space. These methods, permit to effectively\udenhance the spatial resolution of the hyperspectral image without relevant spectral distortions\udand on the same time to reduce the computational load of the entire process. In particular,\udin this paper we focus our attention on the use of Nonlinear Principal Component Analysis\ud(NLPCA) for the projection of the image into a low dimensionality feature space. However,\udif on one hand the NLPCA has been proved to better represent the intrinsic informationof hyperspectral images in the feature space, on the other hand an analysis of the impact\udof different fusion techniques applied to the nonlinear principal components in order to\uddefine the optimal framework for the hybrid pansharpening has not been carried out yet.\udMore in particular, in this paper we analyze the overall impact of several widely used MRA\udpansharpening algorithms applied in the nonlinear feature space. The results obtained on both\udsynthetic and real data demonstrate that an accurate selection of the pansharpening method\udcan lead to an effective improvement of the enhanced hyperspectral image in terms of spectral\udquality and spatial consistency, as well as a strong reduction in the computational time.
机译：高光谱图像具有较高的光谱分辨率（即，覆盖电磁光谱的\ udband数量较大），但相对于多光谱或全色采集而言，其空间分辨率较低。为了提高在利用和解释方面的数据能力，期望具有高光谱和非空间分辨率的高光谱图像。这可以通过将高光谱图像与高空间分辨率全色图像相结合来实现。这些技术是众所周知的，可以分为基于组件替换（CS）和基于多分辨率\ udanalysis（MRA）的方法。通常，CS方法导致融合图像具有较高的空间质量，但是融合图像遭受光谱失真。另一方面，使用MRA技术获得的\ udimage图像不如CS方法清晰，但在光谱上\ ud一致性。当应用于多光谱和PAN图像时，替换和滤波方法都被认为是足够的，但是当低分辨率图像应用于高光谱图像时，则具有许多缺点。因此，高光谱全景锐化中的主要挑战之一是在提高空间分辨率的同时保留尽可能多的原始光谱信息。通过使用混合\ udapproaches，将CS更好的空间信息与MRA技术的更准确的光谱\ udinformation相结合，已经找到了解决这些问题的有效方法。通常，在混合方法中，使用CS技术将原始数据\ ud投影到低维空间中。因此，借助MRA方法将PAN图像与\ udone或更多特征融合在一起。最后，反投影用于\获得原始数据空间中的增强图像。这些方法允许有效地提高高光谱图像的空间分辨率而没有相关的光谱失真，同时减少了整个过程的计算量。特别是，\ udin本文将注意力集中在使用非线性主成分分析\ ud（NLPCA）将图像投影到低维特征空间中。然而，\ udif一方面被证明可以更好地表示特征空间中的高光谱图像的固有信息，另一方面分析了应用于非线性主成分的不同融合技术的影响\ ud \ ud更多，尤其是在本文中，我们分析了在非线性特征空间中应用的几种广泛使用的MRA \ udpansharpening算法的总体影响。在\综合和真实数据上获得的结果表明，精确选择全锐化方法\ ud可以在光谱\质量和空间一致性方面有效地增强增强的高光谱图像，并且可以大大减少计算时间。

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