Parallel Multi-Temporal Remote Sensing Image Change Detection on GPU

Abstract

Change detection is an important technique in damage assessment area. As the amount of remote sensing images and the complexity of algorithms rise, the demand for processing power is increasing. In this paper, we propose PLog-FLCM, a parallel algorithm for change detection. It is implemented on AMD Accelerated Parallel Processing (APP) SDK v2 based on Open Computing Language. The parallel characteristics and implementation details of the proposed PLog-FLICM algorithm are presented. Experiments on several Synthetic Aperture Radar(SAR) images demonstrate that the proposed algorithm outperform other algorithms, and the designed parallel algorithm can greatly reduce the computational time of change detection algorithm. It has achieved speedups of between 63 and 145 times on AMD Radeon HD 6870 Graphics Processing Unit (GPU).