基于CBERS-02B高分辨率遥感影像分割的最优尺度选取  

Optimal scale selection base on CBERS-02B high-resolution remote sensing images

作　　者：况润元[1] 袁秀华[1] 罗卫[1] 张萌[1] 王聪颖[1] 

机构地区：[1]江西理工大学建筑与测绘工程学院,江西赣州341000

出　　处：《江西理工大学学报》2013年第5期29-33,共5页Journal of Jiangxi University of Science and Technology

基　　金：国家自然科学基金资助项目(41101322);江西省科技厅项目(20114BAB213022);江西省教育厅科技项目(GJJ13424)

摘　　要：高分辨遥感影像的信息提取对矿山的监测有着重要意义,影像分割是高分辨率遥感影像信息提取关键的一步.文中以赣州稀土矿山的高分辨率遥感影像为源数据,采用分形网络演化多尺度分割算法对高分辨率遥感影像进行分割,通过Robert算子的边缘提取结果计算分割参数获取分割尺度,并在此基础上设置不同分割尺度对影像进行分割,对比分析分割结果表明,沉淀池的最优分割尺度为35.最后利用分割质量值对分割结果进行评价分析,验证了试验结果的正确性.It has important monitor rare earth mine. significance for high resolution remote sensing image information extraction to Image segmentation is a key step in the high resolution remote sensing image information extraction. In order to obtain the optimal segmentation results, this paper chooses high-resolution remote sensing image of Ganzhou rare earth mines, uses Fractal Net Evolution Approach algorithm to segment high resolution remote sensing image, and computes segmentation parameter to obtain segmentation scale by edge extraction results of Robert operator, and sets different segmentation scale to segment image base on it, after comparing and analyzing segmentation results, it shows that optimal segmentation scale of sedimentation tank was 35. At last Segmentation results were evaluated of experimental result.

关 键 词：高分辨率遥感影像 矿山 面向对象 多尺度分割 最优尺度 评价分析 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]