帮助 关于我们

返回检索结果

基于对象的遥感案例推理方法检测岩溶地面塌陷
Object-based and Case-based Reasoning Method for Ground Collapses Detection

查看参考文献20篇

窦杰 1   钱峻屏 2   陈水森 2   郑小战 3   刘瑞华 2   朱俊凤 2   夏换 4  
文摘 岩溶地面塌陷是一种典型的城市地质灾害,岩溶地面塌陷的检测在城市防灾减灾中具有重要的意义. 目前常用的塌陷检测多基于野外调查或者遥感目视解译,检测效率低. 采用人工智能方法对遥感影像中的岩溶地面塌陷检测及分类的研究值得尝试. 采用0.2m分辨率的高分辨率航空影像,以多尺度分割后的影像对象为基本单元,提取影像对象的特征属性. 在利用遗传算法对检测因子进行优化后,在Matlab平台下建立案例推理(CBR)程序,实现基于影像对象的塌陷识别与分类. 最后结合ArcGIS软件完成对岩溶地面塌陷的快速检测结果的精度评价和方法的适宜性分析. 研究结果发现,案例推理方法适合于高分辨率影像中的岩溶地面塌陷快速自动检测. 利用野外调查数据对自动检测结果的精度验证表明,对成熟岩溶地面塌陷的检测精度达到88.9%,总精度为88.1%,卡帕系数为79.1%;利用同一方法和案例库对不同试验区的岩溶地面塌陷检测结果进行了对比检测,总精度为 82.2%,表明该方法和案例库有很好的可重用性. 对比CBR方法和传统监督分类方法发现,基于对象的监督分类方法检测精度(总分类精度是68%,卡帕系数只有47.9%)仍低于CBR方法,说明CBR方法更适合于解决复杂环境下的分类及检测伪命题. 提出的案例推理方法检测速度快、精度较高,是实现岩溶地面塌陷自动检测的一种有效手段
其他语种文摘 Ground collapse was a typical geological disaster in karstic area. Comparing to other geological disaster, ground collapses were considerably small in scale and dispersive in distribution. This made detecting and identification of ground collapse in urban areas quite a challenging work. In this paper, an object-based image analysis method was used to detect the ground collapse sites using remote sensing images. Firstly, multi-scale image segmentation was performed on the 0.2 meter aerial image of study area and over tens of spatial, spectral, shape and texture features were extracted based on the segmented image objects. Then eight optimized features for ground collapse classification was selected using generic algorithm (GA), which obtains the best fitness value in ground collapse classification. After that, some on the spot ground collapses were used as cases sites and cased-based-reasoning( CBR) classification was applied on all the segmented image objects, from large scale to small scale. In the end, classification accuracy was evaluated over the whole study area. The overall object-based CBR classification of ground collapse area is about 0.881 and the kappa coefficient is 0.791. Higher accuracy(0.889) is achieved for the ripe ground collapses detection. The same case library was also applied to another trial area for reusability testing and achieved satisfactory results. In conclusion, CBR method could be successfully applied to ground collapses detection using high resolution images. CBR method proposed in this paper could achieve betters classification accuracy than traditional supervised classification methods
来源 中国图象图形学报 ,2010,15(6):900-909 【核心库】
关键词 面向对象 ; 多尺度分割 ; 遗传算法(GA) ; 案例推理(CBR) ; 岩溶地面塌陷
地址

1. 中国科学院广州地球化学研究所, 广东省遥感与GIS重点实验室, 广州, 510640  

2. 广州地理研究所, 广东省遥感与GIS重点实验室, 广州, 510070  

3. 广州地质调查院, 广州, 510500  

4. 中国科学院广州地球化学研究所, 广州, 510640

语种 中文
文献类型 研究性论文
ISSN 1006-8961
学科 自动化技术、计算机技术
基金 广州城市地质调查
文献收藏号 CSCD:3962399

参考文献 共 20 共1页

1.  杜培军. GIS支持下遥感图像中采矿塌陷地提取方法研究. 中国图象图形学报,2003,8(2):231-235 被引 3 次    
2.  Qiao Yanxiao. The approach and application effect of remote sensing technique in regional geo-logical hazard investigation in northern west Hebe-takes Zhangjiakou City as an example. The Chinese Journal of Geological Hazard and Control,2002,12(4):91-93 被引 1 次    
3.  张振德. 遥感技术在长江三峡库区大型地质灾害调查中的应用. 国土资源遥感,2003(2):11-26 被引 5 次    
4.  Benson R C. Assessment and long term monitoring of localized subsidence using ground penetrating radar. Proceedings of the 2nd Multidisciplinary Conference on Sinkholes and the Environmental Impacts of Karsts,1987:161-169 被引 1 次    
5.  Yamazaki F. Visual damage interpretation of buildings in bam city using quickbird images. Earthquake Spectra,2005,21(S1):S329-S336 被引 7 次    
6.  Schweier C. Classification of collapsed buildings for fast damage and loss assessment. Bulletin of Earthquake Engineering,2006,4(2):177-192 被引 5 次    
7.  吴泉源. 人工智能与专家系统,1995 被引 100 次    
8.  Watson I. Applying Case-Based Reasoning: Techniques for Enterprise Systems,1997:245-252 被引 2 次    
9.  Holt A. Applying case-based reasoning techniques in GIS. International Journal of Geographical Information Science,1999,13(1):9-25 被引 16 次    
10.  Branting K L. An empirical evaluation of modelbased case matching and adaptation. Proceedings of Casebased Reasoning Workshop-Seattle,1994:72-78 被引 1 次    
11.  杜云艳. 地理案例推理及其应用. 地理学报,2002,57(2):151-158 被引 12 次    
12.  钱峻屏. 时间序列案例推理检测土地利用短期快速变化. 自然资源学报,2007,22(5):735-746 被引 2 次    
13.  . eCognition, User Guide. Definiens Imaging GmbH, Munich,2002 被引 1 次    
14.  陈云浩. 基于面向对象和规则的遥感影像分类研究. 武汉大学学报(信息科学版),2006,31(4):316-320 被引 133 次    
15.  史忠植. 知识发现,2002:265-266 被引 3 次    
16.  Watson. Case-based reasoning is a methodology not technology. Knowledge-based Systems,1999,12(5):303-308 被引 2 次    
17.  Schmidt G. Case-based reasoning for production scheduling. International Journal of Production Economics,1998,56/57(1):537-546 被引 4 次    
18.  Yan N J. Applying case-based reasoning technique to retaining wall selection. Automation in Construction,1998,18(7):271-283 被引 1 次    
19.  De Mantaras R L. Case-based reasoning. Lecture Notes in Computer Science,2001,16(8):127-145 被引 1 次    
20.  Guardati S. RBCShel 1: A tool for the construction of systems with case-based reasoning. Export Systems with Applications,1998,14(1):63-70 被引 1 次    
引证文献 1 篇

1 窦杰 机器学习在滑坡智能防灾减灾中的应用与发展趋势 地球科学,2023,48(5):1657-1674
被引 4 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号