Decomposition of the Mixed Pixels of SAR Remote Sensing Images Based on the Partheno‐Genetic Algorithm

Abstract The existing theories and methods used for remote sensing images' mixed pixel decomposition all require that the number of image channels should be more than the number of ground kinds, but the characteristics of the Synthetic Aperture Radar (SAR) determine that SAR image can not have excessive numbers of channels. To solve the problem of the SAR images' mixed pixel decomposition in the circumstance of ground kinds being more than channels number, we propose a new method for mixed pixels' decomposition based on the Partheno‐Genetic algorithm. In our algorithm, we establish a new chromosome coding method and an evolution iterative method. The new algorithm can realize the ideal mixed pixel decomposition and decompose more ground kinds than the number of channels for the observation data. We choose the area of the Tiananmen vicinity from the Beijing ENVISAT‐ASAR image as our experiment data source. The result of experiment shows that our algorithm is correct and effective.