您好，欢迎访问河南省农业科学院 机构知识库！
河南省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Deep segmentation and classification of complex crops using multi-feature satellite imagery

文献类型： 外文期刊

作者： Wang, Lijun 1 ; Wang, Jiayao 1 ; Zhang, Xiwang 1 ; Wang, Laigang 6 ; Qin, Fen 1 ;

作者机构： 1.Henan Univ, Henan Ind Technol Acad Spatio Temporal Big Data, Kaifeng 475004, Peoples R China

2.Henan Univ, Coll Geog & Environm Sci, Kaifeng 475004, Peoples R China

3.Henan Univ, Key Lab Geospatial Technol Middle & Lower Yellow R, Minist Educ, Kaifeng 475004, Peoples R China

4.Henan Univ, Key Res Inst Yellow River Civilizat & Sustainable, Minist Educ, Kaifeng 475004, Peoples R China

5.Henan Univ, Henan Technol Innovat Ctr Spatial Temporal Big Dat, Kaifeng 475004, Peoples R China

6.Henan Acad Agr Sci, Inst Agr Econ & Informat, Zhengzhou 450002, Peoples R China

关键词： Deep segmentation and classification; Feature fusion; Sentinel-2A; UNet plus plus; Spatiotemporal transfer

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：6.757； 五年影响因子：6.817 ）

ISSN： 0168-1699

年卷期： 2022 年 200 卷

页码：

收录情况： SCI

摘要： Accurate remote sensing-based land use and crop maps provide important and timely information for decision support in large-scale agricultural monitoring. Most existing multi-crop products for complex agricultural areas based on traditional machine learning algorithms are not suitable for large agricultural management because of the poor model transfer capabilities. Therefore, a deep segmentation and classification model including spatiotemporal transfer across regions and years must be developed. In this study, a deep learning approach was developed based on the UNet++ architecture by integrating feature fusion and upsampling of small samples for large-scale land use and crop mapping. Classification experiments were conducted for ten categories at four sites using 10 m resolution Sentinel-2A images from 2019 to 2021 containing 4,194,304 pixels. The joint loss, including the label smoothing cross entropy and Dice coefficient, and the mean intersection over union (mIoU) were used to evaluate the model performance depending on different features and upsampling schemes. The joint loss and mIoU values of the training model and the prediction accuracies of the test sites indicate that the scheme including the upsampling and fusion of spectral bands, vegetation indices, and texture features yields the optimal model performance. For comparison, UNet, DeepLab V3+, Pyramid Scene Parsing Network (PSPNet), and random forest models were built. The improved UNet++ model exhibits the best performance, with an overall accuracy, kappa, and macro F1 above 91 %, 85 %, and 51 %, respectively. The deep segmentation and classification results without training samples demonstrate the spatiotemporal transfer capability of the UNet++ architecture during the key crop growth period. The patch parameter values also indicate that the improved model exhibits a better shape compactness and significantly reduces and suppresses patch fragmentation. Based on the analysis of the overall confusion matrix, the proposed method improves the classification accuracy for datasets with imbalanced land cover and crop types. This study provides a strategy for large-scale and complex land use and crop mapping based on the integration of feature fusion and deep learning.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：河南省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台