插值法在去除MODIS遥感影像条带噪声中的应用

APPLICATION OF INTERPOLATION METHOD IN DESTRIPING MODIS IMAGES

采用多元并扫方式(1 km分辨率10元并扫,500 m分辨率20元并扫,250 m分辨率40元并扫)的MODIS传感器,由于各探测单元在轨响应差异而引起的条带噪声对MODIS定量产品的反演计算精度造成一定影响。为了尽可能减少这种影响,提高MODIS定量产品反演精度,本文提出了应用插值法剔除MODIS数据条带噪声。研究首先分析了传统去条带噪声方法的弊端,根据条带噪声在MODIS影像中的分布规律,以及如何准确判断条带噪声所在的行,然后应用插值法去除了MODIS波段5和波段30影像的条带噪声,取得了满意的效果,最后对图像的去除效果与传统的矩匹配法和傅立叶变换法进行了比较,并用两种评价指标做出评价。结果表明,两种评价指标得出的结果一致,也正说明了插值法是一种很好的去除MODIS数据条带噪声的方法,同时用这种方法处理后的图像还能保留原有的大部分信息。

MODIS method is a sensor to get the data by multi-detector observation, 1 km resolution wave band needs 10 detectors to scan at the same time,500 m resolution wave band needs 20 detectors,and 250 m resolution wave band needs 40 detectors. The adoption of this technology has a problem of the consistency between so many detectors, therefore, the response discrepancy between these detectors will cause the certain stripe noises in MODIS sensor. In order to reduce the influence of MODIS stripe on the manage- ment of data and improve the retrieving precision of remote sensing quantified products as soon as possible, an interpolation method to destripe MODIS image is presented. In this paper,firstly,the limitations of the classical destriping methods are analyzed~ secondly,the stripe noises at channel 5 and channel 30 are removed respectively by using the interpolation method on the basis of the regularities of stripe noises distribution and the position of noises lines occurrence in remote sensing image; finally,the obtained results are compared with the ones of destriping by using the moment matching method and the Fourier transform method. The results show that the interpolation method is superior to the other two methods in destriping image,and the destripped image can reserve most of original information content of MODIS image.