Land use classification based on chaos immune algorithm and remote sensing image

To improve the accuracy of land use classification based on remote sensing image, Chaos Immune Algorithm was proposed. Through the input samples the global optimization clustering center was found. And then the clustering center was employed to classify the view picture of remote sensing image. In this process, the ergodic property of chaos phenomenon was used to optimize the initial antibody population. Through the clone selection operator, mutation operator and recruited antibody, local optimums were avoided. Chaos Immune Algorithm was applied to classify land use in Huainan based on TM image. Based on confusion matrix, the landuse classification results of the Parallelepiped and Maximum likelihood methods were contrasted with Chaos Immune Algorithm. The results show that Chaos Immune Algorithm is superior to the two traditional algorithms, and its overall accuracy and Kappa coefficient reach 89.9% and 0.873, respectively. It is demonstrated that the ergodic property of chaos phenomenon can overcome data locality in samples and the immune algorithm can improve overall solution optimization.