地震地质 ›› 2019, Vol. 41 ›› Issue (5): 1273-1288.DOI: 10.3969/j.issn.0253-4967.2019.05.014

• 研究论文 • 上一篇    下一篇

基于马尔科夫随机场的单时相震害影像受损建筑物识别方法

张凌1, 谭璇2,3, 宋冬梅2, 王斌2, 李睿琳2,3   

  1. 1. 中国地震应急搜救中心, 北京 100049;
    2. 中国石油大学(华东), 海洋与空间信息学院, 青岛 266580;
    3. 中国石油大学(华东), 研究生院, 青岛 266580
  • 收稿日期:2018-08-31 修回日期:2019-01-09 出版日期:2019-10-20 发布日期:2019-12-07
  • 通讯作者: 王斌,男,讲师,E-mail:wangbin007@upc.edu.cn。
  • 作者简介:张凌,男,1961年生,高级工程师,主要从事遥感图像处理与分类方法研究,E-mail:zhanglingnerss@126.com。
  • 基金资助:
    国家自然科学基金(41701513,61371189,41772350)、中央高校基本科研业务费专项(16CX02026A)和大学生创新计划(201810425002)共同资助。

STUDY ON THE MRF-BASED METHOD FOR DAMAGED BUILDINGS EXTRACTION FROM THE SINGLE-PHASE SEISMIC IMAGE

ZHANG Ling1, TAN Xuan2,3, SONG Dong-mei2, WANG Bin2, LI Rui-lin2,3   

  1. 1. National Earthquake Response Support Service, Beijing 100049, China;
    2. College of Oceanography and Space Informatics, China University of Petroleum, Qingdao 266580, China;
    3. Graduate School, China University of Petroleum, Qingdao 266580, China
  • Received:2018-08-31 Revised:2019-01-09 Online:2019-10-20 Published:2019-12-07

摘要: 建筑物是地震中的主要承灾体,其受损情况可作为评估地震破坏等级的重要参考依据。因此,快速准确地对震后影像中的受损建筑物进行识别显得尤为重要,对震后救援和应急响应具有指导意义。现有的震害遥感信息提取方法的精度低、速度慢,无法满足快速应急响应的迫切要求。文中提出一种基于马尔科夫随机场(Markov Random Field,MRF)模型的建筑物受损程度检测方法,首先利用马尔科夫随机场对影像进行分割,再根据影像中不同程度受损建筑物所呈现的特征,利用支持向量机在分割后的影像中提取受损建筑物。实验表明,该方法性能良好,平均总体精度达93.02%。与传统方法相比,该方法操作简便,且提取精度和运行时间均有显著优势,能够精准、快速地识别震害单时相影像中的受损建筑物。

关键词: 地震灾害, 马尔科夫随机场, 受损建筑物检测, 图像分割

Abstract: Earthquake events are one of the most extraordinarily serious natural calamities, which not only cause heavy casualties and economic losses, but also various secondary disasters. Such events are devastating, and have far-reaching influences. As the main disaster bearing body in earthquake, buildings are often seriously damaged, thus it can be used as an important reference for earthquake damage assessment. Identifying damaged buildings from post-earthquake images quickly and accurately is of real importance, which has guidance meaning to rescue and emergency response. At present, the assessment of earthquake damage is mainly through artificial field investigation, which is time-consuming and cannot meet the urgent requirements of rapid emergency response. Markov Random Field(MRF)combines the neighborhood system of pixels with the prior distribution model to effectively describe the dependence between spatial pixels and pixels, so as to obtain more accurate segmentation results. The support vector machine(SVM)model is a simple and clear mathematical model which has a solid theoretical basis; in addition, it also has unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition problems. Thus, in this paper, a Markov random field-based method for damaged buildings extraction from the single-phase seismic image is proposed. The framework of the proposed method has three components. Firstly, Markov Random Field was used to segment the image; then, the spectral and texture features of the post-earthquake damaged building area are extracted. After that, Support Vector Machine was used to extract the damaged buildings according to the extracted features. In order to evaluate the proposed method, 5 areas in ADS40 earthquake remote sensing image were selected as experimental data, this image covers parts of Wenchuan City, Sichuan Province, where an earthquake had struck in 2008. And in order to verify the applicability of this method to different resolution images, an experimental area was selected from different resolution images obtained by the same equipment. The experimental results show that the proposed method has good performance and could effectively identify the damaged buildings after the earthquake. The average overall accuracy of the selected experimental areas is 93.02%. Compared with the result extracted by the widely used eCognition software, the proposed method is simpler in operation and can improve the extraction accuracy and running time significantly. Therefore, it has significant meaning for both emergency rescue work and accurate disaster information providing after earthquake.

Key words: seismic disaster, Markov Random Field, damaged buildings detection, image segmentation

中图分类号: