多源遥感数据在植被识别和提取中的应用

An Application of Multi-Source Remote Sensing Data in Identification and Extraction of Vegetation Information

不同类型的遥感数据有着自己独特的优势,如果综合应用,可以实现信息的互补,提高地物的识别精度。本文以福建省漳浦县为研究区域,利用SPOT5、ASTER和CBERS等多源遥感数据对植被的识别和提取方法进行研究,建立了基于多源遥感数据的专题信息提取流程。首先设计了基于不同植被专题信息自动提取的专家库,对单一遥感数据进行专题提取,然后基于专家知识进行决策级植被信息融合。多源遥感数据所提供的信息的优越性在于可以将不同传感器的光谱信息和时相特征进行互补,利用不同植被在不同遥感数据上的特征和专家知识,建立隶属度函数,判别每个像元的归属,完成研究区不同植被类型的专题提取。结果表明,与单一传感器数据的结果相比,综合利用多源遥感数据能较大程度地提高植被的提取精度。

The development of remote sensing technology and new types of sensor has made great progress in the field of observing the earth with remote sensing data. Different images have their unique advantages, and can be used synthetically. The synthetic use of remote sensing images plays an important role in vegetation management. However, it is difficult to obtain Multi-temporal remote sensing images through the same sensor under bad weather conditions, which limited the use of single-sensor remote with a land area of 582.5km^2 and abundant forest resources was selected as study area. SPOT5 ,ASTER and CBERS data were used to discuss the method of identification and extraction of vegetation information. The flow chart of special information Extraction was addressed in this paper. Firstly, the supervised classification method was adopted in SPOT5, ASTER and CBERS images respectively. Secondly, expert database was created for the extraction of vegetation information. Lastly, vegetation information fusion was carried out based on relevant expertise, and extraction was achieved. It is concluded that using Multi- source data can improve the accuracy of vegetation information extraction. At the same time, Vegetation Index and Principal Component Analysis could enhance the vegetation information. This method has great potential to be used in vegetation information extraction.