| 青海诺木洪地区多源遥感及多特征组合地物分类 |
| |
| 引用本文： | 姚金玺,王浪,李建忠,张焜,张志.青海诺木洪地区多源遥感及多特征组合地物分类[J].农业工程学报,2022,38(3):247-256. |
| |
| 作者姓名： | 姚金玺 王浪 李建忠 张焜 张志 |
| |
| 作者单位： | 1. 中国地质大学<武汉>地球物理与空间信息学院，武汉 430074;;3. 中国地质调查局乌鲁木齐自然资源综合调查中心，乌鲁木齐 830057;;4. 中国地质调查局应用地质研究中心，成都 610036;;2. 青海省青藏高原北部地质过程与矿产资源重点实验室，西宁 810300; |
| |
| 基金项目： | 青海省青藏高原北部地质过程与矿产资源重点实验室开放课题（2019-kz-01）；青海省科技厅创新平台建设专项项目（2019-ZJ-T04） |
| |
| 摘 要： | 遥感技术是研究土地覆盖类型的重要手段，但大部分研究仅采用单一数据源、少特征，该研究基于GEE环境对多源遥感数据、多特征协同进行地物类型分类研究。采用哨兵一号（Sentinel-1）合成孔径雷达数据、哨兵二号（Sentinel-2）多光谱数据和国产高分二号（GF-2）多光谱数据，构建了青海省诺木洪地区地表8类地物的波段特征、植被指数特征、纹理特征和极化特征空间，利用特征优化算法和RF算法实现了研究区域地物的有监督分类，以此评估构建的多特征空间性能及多源数据协同分类的能力。结果表明，基于Sentinel-1与Sentinel-2数据源，使用多特征空间协同分类时的总体精度和Kappa系数可达到97.62%和0.971 6，精度均高于使用单一数据或部分特征的分类精度（总体精度为95.91%，Kappa系数为0.951 1）。而基于Sentinel-1、Sentinel-2与GF-2数据提取的波段、植被指数、纹理特征和极化特征进行的协同地物分类结果总体精度达到了96.67%，Kappa系数达到了0.960 2。总体上，基于多数据源、多特征协同分类结果精度要优于单一数据源或少特征分类结果，而不同空间分辨率图像提取的纹理特征对分类结果有着不同影响，在适宜的分辨率下提取纹理特征参与分类才能达到更好的效果。
|
| 关 键 词： | 土地覆盖 协同分类 特征优选 随机森林 Google Earth Engine |
| 收稿时间： | 2021/10/11 0:00:00 |
| 修稿时间： | 2022/2/13 0:00:00 |
Multi-source remote sensing and multi-feature combination ground object classification in Nuomuhong areas, Qinghai Province of China |
| |
| Yao Jinxi,Wang Lang,Li Jianzhong,Zhang Kun,Zhang Zhi.Multi-source remote sensing and multi-feature combination ground object classification in Nuomuhong areas, Qinghai Province of China[J].Transactions of the Chinese Society of Agricultural Engineering,2022,38(3):247-256. |
| |
| Authors: | Yao Jinxi Wang Lang Li Jianzhong Zhang Kun Zhang Zhi |
| |
| Institution: | 1. Institute of Geophysics & Geomatics, China University of Geoscience, Wuhan 430074, China;;3. Urumqi Comprehensive Survey Center on Natural Resources, China Geological Survey, Urumqi 830057, China;;4. Applied Geology Research Center of China Geological Survey, Chengdu 610036, China;;2. Key Laboratory of the Northern Qinghai-Tibet Plateau Geological Processes and Minera, Xining 810300, China; |
| |
| Abstract: | Remote sensing has been one of the most important means to interpret land cover types in recent years. A great challenge still remains on the scattered distribution of land use types, fragmented agricultural landscapes, and complex crop planting structures in most agricultural areas in China. Much effort has been focused on only a single data source and a few types of features. Therefore, it is a high demand to accurately and effectively classify the land use types, in order to reduce the type misclassification in previous cases. In this study, an accurate and rapid classification was carried out in the Google Earth Engine (GEE) environment for an image collection using multiple remote sensing data sources and multiple features. Taking the Nuomuhong area, Qinghai Province of China as the study areas, the distribution map of main characteristic types was captured to evaluate the agricultural planting and ecological security. The data sources were from the Sentinel-1 synthetic aperture radar data, Sentinel-2 and Gaofen-2 multispectral data. The band, vegetation index, texture and polarization characteristics were calculated to construct the required space of feature classifications. Feature optimization and random forest (RF) were selected to realize the supervised classification, where the data redundancy from multiple features was reduced to improve the calculation efficiency of the classifier. The spatial performance of constructed multi-features was evaluated to collaboratively classify the multi-source data. The results show that the overall accuracy and Kappa coefficient reached 97.62% and 0.971 6 in the collaborative classification under the band, vegetation index, and texture features using Sentinel-1 and Sentinel-2 data sources, which were higher than that using single data or partial features. In the classification accuracy, the overall accuracy was 95.91%, and the Kappa coefficient was 0.9511. In the collaborative ground object classification, the overall accuracy and the Kappa coefficient reached 96.67%, and 0.960 2, respectively, when using the band, vegetation index, texture, and polarization feature extracted from Sentinel-1, Sentinel-2 and GF-2 data. In general, the multi-data source and multi-feature collaborative classification presented a higher accuracy than the single data source or the few feature classification. There were also different effects on the texture features in the images with various spatial resolutions during classification. Nevertheless, an optimal extraction of texture features can be achieved to predict the images at the appropriate resolution. Consequently, the combined multi-source data and multi-feature can be widely expected to classify the ground objects on the cloud platform, in order to effectively improve the classification accuracy of crops. The accurate crop-based extraction can provide the decision-making on the crop pattern change, yield estimation, and security early warning. |
| |
| Keywords: | Land cover type collaborative classification feature selection random forest Google Earth Engine |
|
| 点击此处可从《农业工程学报》浏览原始摘要信息 |
| 点击此处可从《农业工程学报》下载免费的PDF全文 |
|
