面向对象的遥感震害信息提取方法——以汶川地震为例被引量：13

Object-oriented Method for Extracting Seismic Disaster Information Using Remote Sensing Images --A Case Study of Wenchuan Earthquake

在线阅读下载PDF

导出

摘要本文总结了近年来利用遥感影像进行震害信息提取的方法和研究趋势，随着遥感影像分辨率的提高，震害信息提取逐渐从传统的基于像元方法向基于对象的方法转变。文中以汶川地震为例，利用面向对象的分类方法提取了典型震害信息，并提出了面向对象的变化检测方法的工作流程。对震害建筑物破坏情况，分别用最小距离分类、马氏距离分类、支撑向量机分类和面向对象分类进行了实验研究，并对这几种不同分类方法的实验结果进行了对比分析。实验结果表明，面向对象的震害信息提取方法克服了传统的基于像元的分类方法的缺点，提高了建筑物识别的精度，在建筑物震害和地震次生灾害的信息提取中取得了较好的效果。 This paper summarizes the method and research trends on extracting seismic disaster information using remote sensing images in recent years. With the increase of remote sensing images＇ resolution, the extraction of seismic disaster information changes gradually from pixel-based method to object-based method. In a case study of the Wenchuan earthquake, this paper utilizes object-oriented classification method in extracting typical seismic disaster information, and presents the workflow of object-oriented change detection method. Experiments on seismic disaster building damage were conducted using minimum distance classification, Mahalanobis distance classification, SVM classification, object-oriented classification methods. Comparative analysis was carried out on the corresponding results of different classification method. The experimental results show that object-oriented seismic disaster information extraction method can overcome the disadvantage of conventional pixel-oriented method, improve the building identification precision, and get good effects in extracting building seismic disaster and secondary seismic disaster information.

作者赵福军张磊

机构地区中国地震局工程力学研究所黑龙江科技学院天津市地震局

出处《地震》 CSCD 北大核心 2009年第B10期130-138,共9页 Earthquake

基金 “十一五”同家科技支撑计划（2006BAC13B03-0102）

关键词多尺度分割面向对象变化检测遥感震害信息提取 Object-oriented change detection Multi-resolution segmentation Remote sensing Seismic disaster information extraction

分类号 P315.7 [天文地球—地震学]

作者简介赵福军（1974-），男，黑龙江讷河人，2005年博士研究生，主要从事震害识别、遥感与GIS应用等研究。

引文网络
相关文献

参考文献7

1Hajime Mitomi, Fumio Yamazaki, Masashi Matsuoka. Automated detection of building damage due to recent earthquakes using aerial television images[A]. Proceedings of the 21st Asian Conference on Remote Sensing[C]. Asian Conference on Remote Sensing, Taiwan:Taipei. 2000. 1-7.
2Miguel Estrada, Fumio Yamazaki. Use of Landsat Images for the Identification of Damage Due to the 1999 Kocaeli, Turkey Earthquake[A]. Proceedings of the 21st Asian Conference on Remote Sensing[C], Asian Conference on Remote Sensing, Taiwan: Taipei. 2000:1-11.
3Mitomi H, Yamazaki F, Matsuoka M. Development of automated extraction method for building damage area based on maximum likelihood classifier[A]. Proceedings of 8th International Conference on Structural Safety and Reliability[C]. Structural Safety and Reliability, California: New Beech. 2001. 2430-442.
4Turker M, San B T. Detection of collapsed buildings caused by the 1999 Izmit. Turkey earthquake through digital analysis of post-event aerial photographs[J].International Journal of Remote Sens ing, 200,1, 25 (21) : 4701-4714.
5Rathje E M, Kyu-Seok Woo, Crawford M, et al. Earthquake damage identification using multi-temporal high-resolution optical satellite imagery[A]. IEEE International Geoscience and Remote Sensing Symposium[C]. 2005. 5045-5048.
6张磊.遥感震害快速评估关键技术研究[D].北京:中国地震局地壳应力研究所,2008.
7周春艳,王萍,张振勇,齐成涛.基于面向对象信息提取技术的城市用地分类[J].遥感技术与应用,2008,23(1):31-35. 被引量：85

二级参考文献6

1宫鹏,黎夏,徐冰.高分辨率影像解译理论与应用方法中的一些研究问题[J].遥感学报,2006,10(1):1-5. 被引量：138
2Herold M, Mueller A,Guente S,et al. Object-oriented Mapping and Analysis of Urban Land Use/Cover Using IKONOS Data[A]. Proceedings of the 22nd EARSEL Symposium[C]. Prague,Czech Republic, June,2002.
3Baatz M, Schape A. Multi-resolution Segmentation:An Optimization Approach for High Quality Multi-scale Image Segmentation[A]. Strobl J, Blaschke T, Griesebner G, et al. Angewandte Geographische Informations Verarbeitung Ⅻ[C]. Heidelberg, 2000.
4Baatz M, Heynen M, Hofmann P, et al. eCognition User Guide [S]. Munchen,Definiens AG,2000.
5Caprioli M, Tarantino E. Urban Features Recognition from VHR Satellite Data with an Object-oriented Approach [A]. Proceedings of Commission Ⅳ Joint Workshop, Challenges in Geospatial Analysis,Integration and Visualization Ⅱ, Stuttgart [C]. Germany, September 8-9,2003.
6黄慧萍.面向对象影像分析中的尺度问题研究[M].北京:中国科学院遥感应用研究所,2003.