CAJ | 학술논문

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.
고분변요감영상적신식제취대광산적감측유착중요의의，영상분할시고분변솔요감영상신식제취관건적일보.문중이공주희토광산적고분변솔요감영상위원수거，채용분형망락연화다척도분할산법대고분변솔요감영상진행분할，통과Robert산자적변연제취결과계산분할삼수획취분할척도，병재차기출상설치불동분할척도대영상진행분할，대비분석분할결과표명，침정지적최우분할척도위35.최후이용분할질량치대분할결과진행평개분석，험증료시험결과적정학성.
It has important significance for high resolution remote sensing image information extraction to monitor rare earth mine. 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 by segmentation quality value, it verifies the accuracy of experimental result.