| 基于无人机高光谱遥感的荒漠草原覆盖度提取方法研究 |
| |
| 引用本文： | 张燕斌,杜健民,毕玉革,王圆,朱相兵,高新超. 基于无人机高光谱遥感的荒漠草原覆盖度提取方法研究[J]. 光电子．激光, 2023, 34(8): 842-850 |
| |
| 作者姓名： | 张燕斌 杜健民 毕玉革 王圆 朱相兵 高新超 |
| |
| 作者单位： | 内蒙古农业大学 机电工程学院，内蒙古 呼和浩特 010010 ;内蒙古农业大学 职业技术学院，内蒙古 包头 014109,内蒙古农业大学 机电工程学院，内蒙古 呼和浩特 010010,内蒙古农业大学 机电工程学院，内蒙古 呼和浩特 010010,内蒙古农业大学 机电工程学院，内蒙古 呼和浩特 010010,内蒙古农业大学 机电工程学院，内蒙古 呼和浩特 010010,内蒙古农业大学 机电工程学院，内蒙古 呼和浩特 010010 |
| |
| 基金项目： | 国家自然科学基金项目(31660137)、内蒙古高等学校科学研究项目(NJZY21518)和内蒙古农业大学基本科研业务费专 项资金资助(BR220152)资助项目 |
| |
| 摘 要： | 植被覆盖度(fractional vegetation coverage, FVC)是草地退化评价的重要指标之一，实时、快速、准确地采集FVC是进行草地退化评价的基础。本文以无人机(unmanned aerial vehicle, UAV)高光谱遥感图像为数据源，提出了3D-ResNet18深度学习覆盖度提取方法，将此方法与回归模型法和ResNet18经典深度学习方法进行比较，并对提取精度进行验证。结果表明，提出的3D-ResNet18方法对荒漠草原FVC展现出较优的提取效果，总体估算精度达97.56%,相比较NDVI、SA-VI、G＿CR＿NDVI、G＿CR＿SAVI和ResNet18分别提高了8.32%、5.92%、2.20%、2.14%和1.87%,为荒漠草原FVC信息高精度和高效率的统计奠定基础。
|
| 关 键 词： | 无人机(UAV) 高光谱遥感 荒漠草原 深度学习 植被覆盖度(FVC) |
| 收稿时间： | 2022-10-24 |
| 修稿时间： | 2022-12-05 |
Extraction method of coverage in desert steppe based on UAV hyperspectral remote sensing |
| |
| ZHANG Yanbin,DU Jianmin,BI Yuge,WANG Yuan,ZHU Xiangbing and GAO Xinchao. Extraction method of coverage in desert steppe based on UAV hyperspectral remote sensing[J]. Journal of Optoelectronics·laser, 2023, 34(8): 842-850 |
| |
| Authors: | ZHANG Yanbin DU Jianmin BI Yuge WANG Yuan ZHU Xiangbing GAO Xinchao |
| |
| Affiliation: | College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot,Inner Mongolia 010010, China;Vocational and Technical College,Inner Mongolia Agricultural University, Baotou, Inner Mongolia 014109, China,College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot,Inner Mongolia 010010, China,College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot,Inner Mongolia 010010, China,College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot,Inner Mongolia 010010, China,College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot,Inner Mongolia 010010, China and College of Mechanical and Electrical Engineering,Inner Mongolia Agricultural University,Hohhot,Inner Mongolia 010010, China |
| |
| Abstract: | Fractional vegetation coverage (FVC) is one of the important indicators for grassland degradation evaluation,and real-time,fast and accurate FVC acquisition is the basis for grassland degradation evaluation.This paper proposes a 3D-ResNet18 deep learning coverage extraction method using unmanned aerial vehicle (UAV) hyperspectral remote sensing images as the data source,compares this method with the regression model method and the ResNet18 classical deep learning method,and validates the extraction accuracy.The results show that the proposed 3D-ResNet18 method shows a better extraction effect on desert grassland FVC,with an overall estimation accuracy of 97.56%,which is 8.32%,5.92%,2.20%,2.14% and 1.87% higher compared to NDVI,SAVI,G_CR_NDVI,G_CR_ SAVI and ResNet18, respectively.The foundation for high-precision and efficient statistics of desert grassland FVC information is laid. |
| |
| Keywords: | unmanned aerial vehicle (UAV) hyperspectral remote sensing desert steppe deep learning fractional vegetation coverage (FVC) |
|
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
|
