Automatic Radiometric Normalization for Multitemporal Remote Sensing Imagery With Iterative Slow Feature Analysis

Multitemporal imagery analysis has attracted widespread interest in recent years due to the large number of applications. Multitemporal remote sensing imagery analysis is very important for Earth observation, in order to allow an understanding of the relationships and interactions between human and natural phenomena. Radiometric variance of the same targets due to differences in environmental conditions is one of the most important issues. In this paper, we propose an automatic radiometric normalization method with iterative slow feature analysis (ISFA) to reduce the radiometric variance. Slow feature analysis extracts invariant features from the quickly varying input signals. It is first reformulated for the multitemporal imagery problem and then improved to an iterative version. In the iteration, high weights are assigned to unchanged pixels. After convergence, the linear function of the radiometric normalization is directly obtained with all the pixels and their weights. If the ISFA is negatively affected by the changed pixels in some special cases and cannot find the correct regression line, initial seeds are selected as the initial weights in the iteration, to improve the performance, which is called S-ISFA. Two pairs of multitemporal ETM images from different seasons and years were used to test the effectiveness of our proposed method. The quantitative evaluation showed that our proposed method performs better, with smaller differences in the statistical distributions and radiometric values than the other state-of-the-art methods. The robustness with regard to the selection of initial seeds was also proved in the experiment.