多源遥感影像提取火烧迹地面积不确定性研究  

Uncertainty study of fire scar area extraction with different image sources

作　　者：易维[1] 曾湧[1] 王凤阁[2] 原征[1] Yi Wei;Zeng Yong;Wang Fengge;Yuan Zheng(China Centra For Resources Satellite Data and Application, Beijing 100094, China;Information Center of Forest Prediction and Monitoring, State Forestry Administration,Beijing 100714, China)

机构地区：[1]中国资源卫星应用中心,北京100094 [2]国家林业局森林防火预警监测信息中心,北京100714

出　　处：《电子测量技术》2018年第9期91-94,共4页Electronic Measurement Technology

摘　　要：利用遥感影像计算火烧迹地面积是火灾评估的常用方法,为了论证不同影像提取火烧迹地面积的差异,以4种国产卫星影像作为数据源,提出区分指数和确定度指数分析火烧迹地与林地在不同影像中的区分程度,并利用NDVI多阈值和混合像元分解方法分别提取火烧迹地面积。研究结果表明：高分辨率遥感影像对火烧迹地和林地的区分性较好,并且采用NDVI指数的区分程度高于近红外波段,NDVI多阈值提取随着阈值变化在不同影像中结果差异较大,而混合像元分解提取结果一致性较好。Calculating the fire scar area with remote sensing images is a commonly used method of fire risk assessment.In order to demonstrate the differences of fire scar area extraction with difference images,we use the discrimination index and uncertainty index of fire scar and unburned forest to analyze distinguishing degree in different images,multi thresholds of NDVI and mixed pixel decomposition method to extract fire scar area respectively.The results show that the distinction between fire scar and unburned forest is better in high resolution remote sensing image,and the distinction using NDVI index was higher than that using the near infrared band.The extraction results with NDVI vary with threshold changes while mixed pixel decomposition extraction results perform in good agreement.

关 键 词：多源遥感影像 火烧迹地 多阈值 混合像元分解 

分 类 号：TN29[电子电信—物理电子学]