An Automatic Relative Radiometric Correction Method Based on Slow Feature Analysis

Radiometric correction is very important for temporal remote sensing images analysis. The key of relative radiometric correction is to accurately select pseudo-invariant features (PIFs). This process should be automatic. Slow feature analysis is a new learning algorithm to extract invariant feature from input signals. It is appreciate to separate the unchanged pixels. We apply iteration process to assign high weights to unchanged pixels. After convergence, the linear function is calculated directly with all the pixels and their weights. The experiment demonstrates that our automatic relative radiometric correction method can get a good performance.