高分辨率影像城市绿地快速提取技术与应用

Detecting Urban Vegetation Efficiently with High Resolution Remote Sensing Data

高分辨率遥感影像是城市绿地信息快速提取的主要数据源 ,文中以多尺度影像分割与面向对象影像分析方法为主要技术 ,利用样本多边形对象的成员函数建立训练区 ,自动提取大庆市城市绿地覆盖信息 ,达到清查城市绿地的目的。该方法信息获取周期短、精度高、成本低 ,实现了城市绿地信息精确获取与快速更新。

Monitoring urban vegetation is one of the major environmental applications in remote sensing today.As the main data sources for urban vegetation high resolution imagery provides a good basis for recognizing and monitoring small scale structure changes. Going far beyond the methodical limits of pixel based and manual interpretation approaches,multi resolution image segmentation and object oriented image analysis approaches are used for extracting information from airborne remote sensing data.This paper presents a snapshot of work to detect vegetation information in Daqing city using this new patented technique. It allows the segmentation of an image into highly homogeneous image objects in any chosen resolution and the generation of a network of image objects. The process does not classify single pixel but rather image object.Not only spectral information but also spatial, physical and contextual characteristics of image objects are used for classification.Classification is conducted by fuzzy logic,and image objects are evaluated using membership function classifiers.Membership functions are used to produce class description, which consists of a set of fuzzy expressions from appropriate sample objects.The result of vegetation information extraction is promising and the precision of classification is higher than other conventional processes.It is obvious that this new image analysis approach offers a satisfying solution to extract information quickly and efficiently.