基于SVM的矸石山分布信息提取方法  

Extracting Method of Coal Refuse Heap Distribution Information Based on SVM

作　　者：范忻[1] 张书建[1] 

机构地区：[1]中国矿业大学,江苏徐州221008

出　　处：《地矿测绘》2011年第3期15-18,共4页Surveying and Mapping of Geology and Mineral Resources

摘　　要：以钱营孜矿区工业广场附近矸石山为例,采用EROS-B高分辨率遥感影像与日本ALOS多光谱影像融合后的影像作为数据源,利用MNF变换和小波变换对图像进行去噪,然后运用SVM方法对实验区内的矸石山信息进行提取。实验结果表明,采用径向基函数的SVM模型能快速准确地提取矿区矸石山分布信息,提取精度达到了80.59%,提取的信息可广泛应用于煤炭资源开发状况和矿区环境监测的研究。This paper, for example of Qianyingzi mining area, used EROS-B high resolution remote sensing image and ALOS multispectral images with Japan after fusion image as data sources, used wavelet transform and MNF of image denoising of SVM, and then used the coal refuse heap experimental zone information extraction. Experimental results show the radial basis function of the SVM model can rapidly and accurately extract mining coal refuse heap distribution information, accuracy reached 80.59%, can be widely used in coal resources development status and the mining area environment monitoring research.

关 键 词：SVM 矸石山 MNF变换 影像 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置] P237[自动化与计算机技术—控制科学与工程]