Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2020, Vol. 56 ›› Issue (1): 143-154.DOI: 10.13209/j.0479-8023.2019.110

Previous Articles     Next Articles

Random Forest Model for the Estimation of Fractional Vegetation Coverage Based on a UAV-Ground Co-Sampling Strategy

CHENG Junyi, ZHANG Xianfeng, SUN Min, LUO Peng, YANG Wanting   

  1. Institute of Remote Sensing and GIS, Peking University, Beijing 100871
  • Received:2019-01-24 Revised:2019-05-21 Online:2020-01-20 Published:2020-01-20
  • Contact: ZHANG Xianfeng, E-mail: xfzhang(at)pku.edu.cn

基于空地协同采样的植被覆盖度随机森林估算方法

程俊毅, 张显峰, 孙敏, 罗鹏, 杨婉婷   

  1. 北京大学遥感与地理信息系统研究所, 北京 100871
  • 通讯作者: 张显峰, E-mail: xfzhang(at)pku.edu.cn
  • 基金资助:
    内蒙古自治区科技厅重大专项(数字化矿区资源管理与矿区生态环境监测技术与应用, 2015—2018)和国家重点研发计划(2017YFC1500902)资助

Abstract:

A nonparametric regression — random forest model for the estimation of fractional vegetation coverage (FVC) in a complex topographic area is presented based on low-altitude unmanned aerial vehicle (UAV) hyperspectral imagery. In order to collect a large number of sufficient training samples required for random forest algorithm, the UAV equipped with an optical camera was used to vertically capture the images of land covers in several inaccessible areas such as high mountains, water body and densely forested areas, to increase the density of the ground sampling. The RGBVI (red-green-blue vegetation index) was calculated first and then the Otsu method was adopted to extract the FVC values of the samples from the UAV optical images and ground photos. After that, the hyperspectral images captured by the UAV GaiaSky-mini2 hyperspectral imaging system in the Youlougou Mining area, Chayouzhong County, Inner Mongolia on August 16?18, 2018 were used to extract feature variables, and this feature set was filtered by recursive feature elimination algorithm based on the importance of the variables. On the basis of the optimized feature set and extended training samples using the proposed UAV-ground cosampling approach, the random forest estimation model was constructed to estimate the FVC in the study area. Results indicated that the model achieved a determinant coefficient (R2) of 0.923 and a RMSE of 0.087 on the testing sample set and outperformed the commonly used Pixel Dichotomy method. It can be used in the fast and accurate monitoring of vegetation dynamics in mining areas.

Key words: fractional vegetation coverage, random forest, UAV-ground co-sampling, UAV hyperspectral remote sensing, mining area

摘要:

基于无人机高光谱影像, 建立地形复杂地区植被覆盖度的非参数随机森林回归估算模型。为获得构建随机森林模型所需的足够数量的训练样本, 利用低空无人机搭载的光学相机, 在从地面难以到达的山地、水域和植被茂密区, 通过垂直拍摄获得厘米分辨率的航拍影像, 作为对地面样方采样的补充。首先计算地面数码相机照片和无人机可见光影像的红绿蓝植被指数(red-green-blue vegetation index, RGBVI), 然后使用大津分割法提取样方的植被覆盖信息, 得到构建模型所需的训练样本。在此基础上, 基于2018年8月16—18日在内蒙古自治区察右中旗油娄沟矿区获取的GaiaSky-mini2无人机高光谱影像数据, 利用递归特征消除算法优选参与随机森林回归的特征变量集, 利用空地协同获取的训练样本构建植被覆盖度的随机森林回归估算模型。该模型在测试集上的确定系数R2为0.923, 均方根误差为0.087, 优于常用的像元二分模型, 可用于矿区植被动态信息的精细化监测。

关键词: 植被覆盖度, 随机森林, 空地协同采样, 无人机高光谱, 矿区