基于线性光谱分解方法的森林选择性砍伐与再生监测研究——以巴西亚马逊森林为例  

Monitoring Selective Logging and Forest Regeneration Based on Linear Spectral Mixture Method: a Case Study of the Brazilian Amazon

作　　者：祝善友[1] 陈亭[1] 曹云[1] 张海龙[1] 张桂欣[1] 

机构地区：[1]南京信息工程大学地理与遥感学院,南京210044

出　　处：《科学技术与工程》2015年第20期78-83,共6页Science Technology and Engineering

基　　金：国家重点基础研究发展计划(2010CB950701);国家自然科学基金项目(41001289;41201369);江苏高校优势学科建设工程资助项目资助

摘　　要：以巴西亚马逊热带森林为例,在Landsat TM、ETM+影像提取光合植被(PV)、非光合植被(NPV)、土壤(soil)端元光谱的基础上,利用线性光谱分解模型得到端元地物丰度,进而设计合理的检测规则实现了选择性森林砍伐与森林再生所产生的森林变化监测。结果表明,基于线性光谱分解的方法能够以较高精度准确检测出选择性砍伐与森林再生,是森林变化宏观监测的有效手段之一。Taking Amazon rain forest in Brazil as an example, the endmember spectrum of photosynthetic vege- tation （PV）, non-photosynthetic vegetation （NPV）, the soil from TM/ETM ＋ images were selected, and used lin- ear spectral mixture model to retrieve the fractional cover of PV, NPV and soil. In addition, the detection rules used to detect the selective logging and forest regeneration were discussed. Results show that there is a higher preci- sion for detecting selective logging and forest regeneration based on the linear spectral unmixing method, which can be effectively used to monitor the macro-scale forest change.

关 键 词：线性光谱分解模型 选择性砍伐 混合像元 森林再生 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]