| 地块尺度的山区耕地精准提取方法 |
| |
| 引用本文： | 周楠,杨鹏,魏春山,沈占锋,余娟娟,马晓宇,骆剑承.地块尺度的山区耕地精准提取方法[J].农业工程学报,2021,37(19):260-266. |
| |
| 作者姓名： | 周楠 杨鹏 魏春山 沈占锋 余娟娟 马晓宇 骆剑承 |
| |
| 作者单位： | 1. 中国科学院空天信息创新研究院，北京 100101; 2. 中国科学院大学，北京 100049;;3. 河海大学地球科学与工程学院，南京 211100;;4. 河北工程大学地球科学与工程学院，邯郸 056000; |
| |
| 基金项目： | 国家重点研发计划项（2018YFB0505000）；国家自然科学基金项目（41971375） |
| |
| 摘 要： | 山地丘陵区域耕地资源稀缺，耕地碎片化现象严重，耕地地块细小狭窄且结构复杂，导致了地块级别的耕地信息难以快速、精准获取，阻碍了基于高分辨率遥感影像的精准数字农业服务在山地丘陵地区的应用。现有基于边缘检测/语义分割的耕地提取方法忽略了地块的结构化特征，对于狭长地块提取效果不佳，存在边界模糊问题。针对上述问题，该研究以西南山区湖南省邵东县为研究区，提出一种面向地块尺度的山区耕地遥感影像高精度提取方法。该研究模型主要有以下特征：1）将耕地边缘作为独立于耕地地块外的新类别，使得语义分割能够更好地区分耕地地块边缘和内部区域；2）级联语义分割网络和边缘检测网络，实现耕地边缘线特征和面特征的融合，使耕地边缘特征强化，提高耕地地块边缘检测精度；3）针对高分影像中耕地边缘像素远少于耕地内部像素问题，借助聚焦训练方法，使模型在训练过程中更加关注边缘像素，提高边缘检测精度。试验结果证明，该研究提出的方法在测试集上分类准确率和交并比分别为92.91%和82.84%，相比基准方法分别提升4.28%和8.01%。该研究所提取的耕地地块相比于现有方法更符合耕地的实际分布形态，为地块尺度的耕地信息精准提取提供了实用化方法。
|
| 关 键 词： | 遥感 高分辨率影像 山区 耕地 语义分割 边缘检测 耕地地块 |
| 收稿时间： | 2021/6/17 0:00:00 |
| 修稿时间： | 2021/9/28 0:00:00 |
Accurate extraction method for cropland in mountainous areas based on field parcel |
| |
| Zhou Nan,Yang Peng,Wei Chunshan,Shen Zhanfeng,Yu Juanjuan,Ma Xiaoyu,Luo Jiancheng.Accurate extraction method for cropland in mountainous areas based on field parcel[J].Transactions of the Chinese Society of Agricultural Engineering,2021,37(19):260-266. |
| |
| Authors: | Zhou Nan Yang Peng Wei Chunshan Shen Zhanfeng Yu Juanjuan Ma Xiaoyu Luo Jiancheng |
| |
| Institution: | 1. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China; 2. University of Chinese Academy of Sciences, Beijing 100049, China;;3. School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China;;4. School of Earth Sciences and Engineering, Hebei University of Engineering, Hebei University of Engineering, Handan 056000, China; |
| |
| Abstract: | In mountainous and hilly areas, cultivated land resources are scarce, and the phenomenon of cultivated land fragmentation is serious. The long and narrow arable land plots are complex in structure, which makes it difficult to obtain the information of cultivated land at the land level quickly and accurately, and hinders the application of precise digital agricultural services based on high resolution remote sensing images in mountainous and hilly areas. Parcle-level cultivated land information can intuitively show the spatial distribution, boundary details of farmland, and is of great significance for precision agriculture management, distribution of planting subsidies, and agricultural resource survey. Existing edge detection/semantic segmentation networks-based farmland extraction methods ignore the structural features of the parcel, thus have limit performance for handling narrow and small plots, and there is also a blurring boundary problem. To address these issues, we proposed an accurate extraction method of cropland in mountainous area based on geographic parcels. This method combines the advantages of semantic segmentation and edge detection, and effectively extracts and integrates the linear features of the boundary and the internal texture features of the parcel, so as to improve the recognition accuracy of the cultivated land. The main features of the model in this paper are as follows: 1) The edge of cultivated land is regarded as a new class independent of cultivated land parcels, so that the semantic segmentation network can better distinguish the edge and internal area of cultivated land parcels; 2) A cascaded semantic segmentation and edge detection network is introduced to correlate the prediction of cultivated land surface and line, realize the fusion of boundary and texture features of cultivated land parcels and strengthen the edge features of cultivated land, so as to improving the accuracy of cultivated land block edge detection; 3) A focus training technique is proposed to address the problem that the edge pixels of cultivated land are far fewer than non-edge pixels, by enforcing the model pay more attention to the important but underrepresented edge pixels in high resolution remote sensing images in the training process, so as to improve the edge detection accuracy. We conduct experiments in Shaodong County, Hunan Province in the southwest mountainous area, using the Google Earth high-resolution remote sensing images as the data source, with a spatial resolution of 0.53 m. After manual selection, a total of 1000 512×512 image patches are obtained. Among them, 600 pieces are used as the training set, 200 pieces are used as the verification set, and 200 pieces are used as the test set. Experimental results show that the presented model achieves satisfying results with an overall accuracy of 92.91% and IoU (Intersection-Over-Union) of 82.84% on the test set, which was 4.28% and 8.01% higher than the baseline method respectively. Compared with the existing methods, the cultivated land extracted in this study is more consistent with the actual distribution pattern of cultivated land, which provides a practical method for accurate extraction of cultivated land information at the plot scale in mountainous and hilly regions. |
| |
| Keywords: | high resolution image hilly and mountainous areas semantic segmentation edge detection cropland-parcel extraction |
|
| 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 |
|
