| 耕地"非农化"遥感解译样本分类体系及应用 |
| |
| 引用本文： | 厉芳婷,张过,石婷婷,李乐.耕地"非农化"遥感解译样本分类体系及应用[J].农业工程学报,2022,38(15):297-304. |
| |
| 作者姓名： | 厉芳婷 张过 石婷婷 李乐 |
| |
| 作者单位： | 1. 武汉大学测绘遥感信息工程国家重点实验室,武汉 430079; 2. 湖北省测绘工程院,武汉 430074;;3. 湖北省航测遥感院,武汉 430074;;4. 广东工业大学管理学院,广州 510520; |
| |
| 基金项目： | 国家自然科学基金项目（41901345） |
| |
| 摘 要： | 了解耕地"非农化"的时空格局及其演变过程,是合理制定土地利用政策的重要依据;卫星遥感具有大范围的时空监测能力,基于遥感影像进行耕地监测,极为高效。针对耕地"非农化"类型复杂多样、"非农化"遥感监测分类体系缺乏的问题,该研究提出了耕地"非农化"遥感解译样本分类体系,进而构建耕地"非农化"遥感解译样本库。针对样本采集效率低、质量差的问题,该研究提出了一种基于地理国情监测成果的快速样本采集方法,用于快速获取高精度、高可靠性的"非农化"遥感解译样本。为验证方法的可行性和有效性,选取湖北省范围作为研究区域,利用该研究所提出的耕地"非农化"样本体系和样本采集方法,采集了覆盖平原、丘陵、山地、高山等地形的9类样本,并形成了深度学习模型训练的样本库;选择EfficientNet深度学习网络提取湖北省耕地"非农业"空间分布。结果表明：1）基于地理国情监测成果的样本采集方法可以极大地利用地理国情监测数据空间、属性精度高的特点,快速、精确定位变化样本。2）依据分类体系采集的样本用于模型优化后,样本数量超过5 000时,模型精度有明显提高。在验证区域,采用目视解译和外业核查点的方式进行精度验证,其正检率分别为67.0%和76.5%,召回率分别为77.9%和76.5%。3）利用样本体系训练构建的网络模型相较于全要素样本训练模型,精度有显著提高,5个核查区正检率均提高20个百分点以上。因此,该研究提出的方法可以提高耕地"非农化"遥感监测的效率和精度,可适用于区域尺度的耕地遥感季度监测。
|
| 关 键 词： | 遥感 分类 解译 样本 耕地 非农化 精度评价 |
| 收稿时间： | 2022/3/11 0:00:00 |
| 修稿时间： | 2022/7/7 0:00:00 |
Classification system and application of remote sensing interpretation samples of cultivated land non-agriculturalization |
| |
| Li Fangting,Zhang Guo,Shi Tingting,Li Le.Classification system and application of remote sensing interpretation samples of cultivated land non-agriculturalization[J].Transactions of the Chinese Society of Agricultural Engineering,2022,38(15):297-304. |
| |
| Authors: | Li Fangting Zhang Guo Shi Tingting Li Le |
| |
| Institution: | 1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China; 2. Hubei Institute of Surveying and Mapping Engineering, Wuhan 430074, China;;3. Hubei Institute of Photogrammetry Remote Sensing, Wuhan 430074, China;; 4. School of Management ,Guangdong University of Technology, Guangzhou 510520, China; |
| |
| Abstract: | Cultivated land non-agriculturalization has been a major challenge for the food security in China. The spatial-temporal pattern and evolution of cultivated land non-agriculturalization can be one of the most important steps for the decision-making on land use. The high-resolution satellite images have been widely used in surface remote sensing monitoring. However, it is still lacking on the classification system of non-agricultural monitoring using remote sensing, due to the complexity and diversity of the cultivated land non-agriculturalization types. In this study, a classification system was proposed for the remote sensing interpretation samples of the cultivated land non-agriculturalization, in order to construct the corresponding remote sensing interpretation sample database. At the same time, a fast sample collection was also proposed to improve the efficiency and quality of the sample collection using geographical condition monitoring. As such, high temporal, spatial precision and attribute reliability were achieved to verify the feasibility and effectiveness of the classification system and sample collection. The Hubei Province of China was selected as the study area. Nine types of samples were collected in the cultivated land non-agricultural sample system. The geographical conditions covered the flatland, hill, mountain, high-mountain and other terrains. The sample library was formed after training the deep learning model. The Efficient Net deep learning network was selected to extract the spatial distribution of cultivated land non-agricultural in study area. The result showed that: 1) The sample collection using geographical condition monitoring performed the best in the attribute accuracy. The changing pattern was quickly and accurately located in the more efficient solution for sample collection. 2) The model accuracy was significantly improved, when the number of samples exceeded 5000. The accuracy was verified by the internal visual interpretation and field verification points in the verification area. The positive detection rates were 67.0 % and 76.5%, respectively, and the recall rates were 77.9% and 76.5%, respectively. 3) The sample classification system was also used to train the optimized model. There was a significantly improved accuracy of the non-agricultural cultivated land automatic identification in the study area, compared with the full factor sample training model. The positive detection rate of the five verification areas increased by more than 20 percentage points. Therefore, the classification system can be expected to improve the efficiency and accuracy of remote sensing monitoring of cultivated land non-agriculturalization using deep learning. The improved system can be applied to the seasonal remote sensing monitoring of cultivated land at the regional scale. |
| |
| Keywords: | remote sensing classification interpretation sample cultivated land non-agricultural precision evaluation |
|
| 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 |
|
