电子测量与仪器学报

王超,申祎,仇星,行鸿彦,张艳,卞长林.基于优化视觉词典的震后高分遥感影像震害建筑物检测[J].电子测量与仪器学报,2020,34(10):208-218

基于优化视觉词典的震后高分遥感影像震害建筑物检测

Damaged building detection based on optimized visual dictionary from post-earthquake high-resolution remote sensing images

DOI：

中文关键词: 震后高分遥感影像视觉词典震害建筑物检测

英文关键词:post-earthquake high-resolution remote sensing image visual dictionary earthquake damaged building detection

基金项目:江苏省“六大人才高峰”高层次人才项目(XYDXX-135)资助

作者	单位
王超	1. 南京信息工程大学电子与信息工程学院
申祎	2. 商丘工学院
仇星	1. 南京信息工程大学电子与信息工程学院
行鸿彦	1. 南京信息工程大学电子与信息工程学院
张艳	1. 南京信息工程大学电子与信息工程学院
卞长林	1. 南京信息工程大学电子与信息工程学院

Author	Institution
Wang Chao	1. School of Electronic and Information Engineering, Nanjing University of Information Science and Technology
Shen Yi	2. Shangqiu Institute of Technology
Qiu Xing	1. School of Electronic and Information Engineering, Nanjing University of Information Science and Technology
Xing Hongyan	1. School of Electronic and Information Engineering, Nanjing University of Information Science and Technology
Zhang Yan	1. School of Electronic and Information Engineering, Nanjing University of Information Science and Technology
Bian Changlin	1. School of Electronic and Information Engineering, Nanjing University of Information Science and Technology

摘要点击次数: 366

全文下载次数: 339

中文摘要:

在缺少震前参考信息前提下,提出了一种基于优化视觉词典的震后高分遥感影像震害建筑物检测方法。首先通过 WJSEG(wavelet-JSEG)分割以及一组非建筑物筛选规则提取潜在建筑物集合;其次利用光谱、纹理及几何形态学特征构建了一种震害视觉词典模型,跨越了从像素到震害特征间的“语义鸿沟”;在此基础上设计了一种基于类内和类间惩罚因子的视觉词典优化策略,减少了信息冗余及证据冲突;最后通过随机森林分类器将建筑物进一步划分为完好建筑物、部分震害建筑物及废墟。在两组实验中,该方法的总体精度均达到 85%以上,从而可为震后应急响应救援及灾后重建提供关键的决策支持信息。

英文摘要:

Being lack of the pre-earthquake reference information, a new method of damaged building detection of high-resolution remote sensing image based on optimized visual dictionary is proposed. Firstly, wavelet-JSEG (WJSEG) segmentation and a set of non-building screening rules are applied to extract the potential building set. Secondly, a visual dictionary model of earthquake damage is constructed by introducing spectral, texture and geometric morphological features to across the semantic gap between pixels and earthquake damage features. On this basis, a visual dictionary optimization strategy based on intra-class and inter-class penalty indexes is designed to further reduce redundant information and evidence conflict. Finally, the buildings are further classified into intact buildings, partially damaged buildings and ruins by random forest classifier. In two experiments, the overall accuracy of the proposed method reached more than 85%, which can provide key decision support information for post-earthquake emergency response and reconstruction.

查看全文查看/发表评论下载PDF阅读器