基于影像融合和面向对象技术的植被信息提取研究  

Study on Vegetation Information Extraction based on Object-oriented Image Analysis

作　　者：别强[1] 何磊[1] 赵传燕[2] 

机构地区：[1]兰州大学资源环境学院,甘肃兰州730000 [2]兰州大学草地农业系统国家重点实验室,甘肃兰州730000

出　　处：《遥感技术与应用》2014年第1期164-171,共8页Remote Sensing Technology and Application

基　　金：国家自然科学基金项目(91025015;No.30770387);环境保护公益性行业科研专项(NEPCP 200809098)

摘　　要：高分辨率影像具有丰富的光谱信息和空间信息。采用不同的图像融合技术融合GeoEye影像全色波段和多光谱波段,用建立的参考多边形和对应多边形残差法评价分割质量,以确定研究区各地物类型的最优分割参数组合,选择目标地物分类特征,建立分类规则,在此基础上实现研究区内不同地物类型的面向对象信息提取。结果表明:Gram-Schmidt(GS)融合法具有最优的融合效果,所选特征能够很好地实现目标地物信息提取,并且具有明确的地学意义,面向对象信息提取总体精度达到90.3%,Kappa系数为0.86,该研究为高精度植被信息的提取提供了有效的方法。Vegetation is an important part in ecological system and indicating certain landscapes, It is a meaningful work to obtain detailed information of vegetation using GeoEye image with its abundant spatial and spectral infor- mation. This study fused the panchromatic band and multispectral bands with four image fusion methods, Image segmentation is the first and critical procedure in the workflow of object-oriented image analysis, discrepancy be- tween reference polygons and corresponding segment is used to assess segmentation quality in this study. We ex- tracted the vegetation information using classification feature which is selected from the perspective of remote sens- ing image cognition and geographical understanding. The results showed that Gram-Schmidt （GS）method is the most effective in fusing panchromatic bands and multispectral bands,And object-oriented classification is effective in high resolution remote sensing information extraction,the overall accuracy is up to 90.3%. this research provided an effective method for vegetation information extraction.

关 键 词：遥感 图像融合 影像分割 面向对象 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]