The correlation analysis of NDVI products based on sparse representation

In remote sensing applications, we often encounter data loss issue. When calculating NDVI of some regions, remote sensing data set from Landsat should be used. However, the data set is maybe incomplete. Our empirical method to deal with this problem is to use data set from HJ-1 instead. Naturally, we surmise that the data set obtained by HJ-1 must correlate with the data set obtained by Landsat on condition that the data sets from two satellites have been registered. In this work, We first learned a dictionary and defined a metric under this dictionary to measure NDVI of data set in sparse domain. Through the experiments we can draw the conclusion that NDVI also can be calculated in sparse domain by our method and there is a high correlation between NDVI and NDVI calculated in sparse domains denoted as S NDVI. Based on this, we use the difference of S NDVIs of two data sets to measure the correlation of them in sparse domain which has a linear relationship with the correlation of NDVIs of two data sets.