A Parallel Change Detection Method for Spatiotemporally Multi-Temporal SAR Image Based On Enhance Learning and Wavelet

Abstract

To take the advantages of a variety of remote sensing data, the application of remote sensing image change detection is a very important choice. Remote sensing image change detection is large in computing capacity and time-consuming, and with the development of modern remote sensing technology, however, the amount of various remote sensing data obtained is getting larger and larger to find a change detection in the Synthetic Aperture Radar(SAR) images accurately for effective computing power. As a basis for parallelization which is a parallel change detection methods of multi- temporal SAR image based on wavelet transform is proposed. In the methods, platform based on parallel computing enhance learning. According to the statistical characteristics of SAR images and the semantics of Convolutional Neural Networks (CNN) analysis, an efficient Change detection methods based on Enhance Learning Semantic Analysis and wavelet transform is proposed to achieve precision of change detection, the probability and Statistics Characteristics of conjugate multi-distribution function which the pixel and task were pre-handled for parallel computing. Then, it's superior to traditional change detection results that is obtained Multi-sample training set. To establish Bellman equation model, and iterate the threshold-change area to calculate statistical characteristics. The experiments show that the improving methods and computing power on parallel change detection platform will achieve better results, and it is in remote sensing applications with enhance learning of behavior science methods to solve the image threshold area change detection in enhance learning for image processing for hybrid parallel computing.