Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (32): 144-147.

• 数据库、信号与信息处理 • Previous Articles     Next Articles

Research of change detection using state transition matrix

LI Xue1,SHU Ning2,WANG Yan2,LI Liang2   

  1. 1.Institute of Seismology,China Earthquake Administration,Wuhan 430071,China
    2.School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-11-11 Published:2011-11-11

基于状态转移矩阵的变化检测方法

李 雪1,舒 宁2,王 琰2,李 亮2   

  1. 1.中国地震局 地震研究所,武汉 430071
    2.武汉大学 遥感信息工程学院,武汉 430079

Abstract: Land-use has been the focus of the study in the remote sensing image change detection.This paper proposes a change detection method based on the State Transition Matrix(STM).It uses segments as the unit to analyse the images.After the samples selection and update,the STM,obtained from the auxiliary data,is used to amend the result of the change detection.The experiment shows the effectiveness of the method.

Key words: change detection, auxiliary data, state transition matrix, Markov chain

摘要: 土地利用变化检测一直是遥感影像变化检测研究的重点。在分析已有变化检测方法的基础上提出了一种基于状态转移矩阵(State Transition Matrix,STM)的变化检测方法。以像斑为分析单位,通过样本像斑的选择与更新对变化检测区域进行分析,利用辅助数据生成的地物变化状态转移矩阵对变化检测结果进行修正。实验证明了该方法的有效性。

关键词: 变化检测, 辅助数据, 状态转移矩阵, 马尔科夫链