摘要
以黑龙江凉水自然保护区为研究对象,采用GF-1卫星遥感影像为数据源,提取遥感影像在不同窗口大小下的纹理特征信息,与遥感影像自身的光谱信息相结合;利用随机森林算法,结合地面蓄积量采样点数据,建立凉水自然保护区蓄积量反演模型。结果表明:只基于卫星光谱的反演模型的相关系数为0.59,基于卫星光谱与纹理特征的蓄积量反演模型的相关系数为0.65;当窗口大小为3×3时,森林蓄积量反演效果最好。研究表明,基于卫星光谱信息和纹理特征信息,利用随机森林算法进行森林蓄积量反演在森林资源调查方面具有良好的应用前景。
This research taking Liangshui Nature Reserve in Heilongjiang as study area, using GF-1 satellite image as data source, textural features under different window sizes and spectral feature were extracted from GF-! image. Forest stock volume inversion model were constructed using random forest algorithm and Liangshui forest vol- ume data obtained by field investigation. Experimental results showed the coefficient of determination R2 was 0.59 for the spectrally based volume estimation model, and the coefficient of determination R2 was 0. 65 for the spectral and textural feature combining model. When window size is set to 3 × 3, the forest stock volume inversion model a- chieves the best result. The result indicate that forest stock volume estimation based on spectral and textural feature from satellite image using random forests has potential application in forest inventory. Key words： stock volume, inversion, random forest, nature reserve, GF-1 satellite, remote sensing image, textural feature
出处
《西南林业大学学报（自然科学）》
CAS
北大核心
2016年第5期125-129,157,共6页
Journal of Southwest Forestry University：Natural Sciences
基金
高分辨率对地观测系统重大专项(民用部分)应用示范系统项目(21-Y30B05-9001-13/15-7)资助
国家自然科学基金项目(51409204
41401496)资助
陕西省自然科学基础研究计划(2015JQ4105)资助
江西省数字国土重点实验开放基金项目(DLLJ2015604)资助
2016年陕西省大学生创新创业训练计划项目(1402)资助
陕西省教育厅科研计划项目(16JK1496)资助
关键词
蓄积量
反演
随机森林
保护区
高分一号卫星
遥感影像
纹理特征
stock volume, inversion, random forest, nature reserve, GF-1 satellite, remote sensing image,textural feature
