基于改进U-Net模型的农业大棚遥感提取方法

doi:10.7523/j.ucas.2023.060

中国科学院大学学报 ›› 2024, Vol. 41 ›› Issue (3): 375-386.DOI: 10.7523/j.ucas.2023.060

• 电子信息与计算机科学 • 上一篇下一篇

基于改进U-Net模型的农业大棚遥感提取方法

王寅达^1,2, 彭玲¹, 陈德跃^1,3, 李玮超¹

1. 中国科学院空天信息创新研究院, 北京 100094;
2. 中国科学院大学电子电气与通信工程学院, 北京 100049;
3. 中国科学院大学资源与环境学院, 北京 100049

收稿日期:2023-02-21 修回日期:2023-05-18 发布日期:2024-05-17
通讯作者: 彭玲,E-mail:pengling@aircas.ac.cn
基金资助:
全球能源互联网集团有限公司科技项目(SGGEIG00JYJS2100032)资助

Remote sensing extraction method of agricultural greenhouse based on an improved U-Net model

WANG Yinda^1,2, PENG Ling¹, CHEN Deyue^1,3, LI Weichao¹

1. Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China;
2. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China;
3. College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2023-02-21 Revised:2023-05-18 Published:2024-05-17

摘要/Abstract

摘要： 农业大棚是一种农业设施，依据表面透光度分为阳棚和阴棚。大范围统计农业大棚对农业设施普查、农业政策制定、县域经济发展规划具有重要意义。针对人工统计费时费力问题，基于卷积神经网络和高分辨率遥感影像实现农业大棚遥感信息提取。针对U-Net模型对遥感影像中语义信息提取不足和边缘信息利用不充分问题，提出以下改进方案：1)优化语义分割任务，使用ConvNeXt和注意力机制提取遥感影像中农业大棚的深层语义信息；2)引入边缘检测任务，采用门控卷积层和拼接操作融合编码器的语义特征和解码器输出的图像梯度，进而结合边缘信息优化分割结果。经测试，改进后的模型能同时提取阴阳2种大棚信息且识别效果良好，相对传统方法有较大提高。

关键词: U-Net, Google影像, 多任务学习, 农业大棚信息提取

Abstract: The agricultural greenhouse is a kind of agricultural facility, which is divided into transparent and non-transparent according to the surface transmittance. The large-scale statistics of agricultural greenhouses are of great significance to the survey of agricultural facilities, the formulation of agricultural policies, and the planning of county economic development. Aiming at the problem that manual statistics are time-consuming and laborious, this paper utilizes the convolutional neural network to extract agricultural greenhouses information from high-resolution remote sensing images. To solve the problems of insufficient semantic information extraction in remote sensing images and insufficient utilization of edge information of the U-Net model, this paper proposes the following improvements: 1) The semantic segmentation task is optimized, and ConvNeXt and attention mechanism is utilized to extract deep semantic information of agricultural greenhouses in remote sensing images. 2) The edge detection task is introduced, and the gated convolution layer and concate operation are used to fuse the semantic features of the encoder and the image gradient output by the decoder, and then the edge information is combined to optimize the segmentation results. After testing, the improved model can extract both transparent and non-transparent agricultural greenhouses information at the same time and the recognition effect is good, which is greatly improved compared with the traditional method.

Key words: U-Net, Google images, multi-task learning, information extraction of agricultural greenhouses

中图分类号:

S127
TP751

王寅达, 彭玲, 陈德跃, 李玮超. 基于改进U-Net模型的农业大棚遥感提取方法[J]. 中国科学院大学学报, 2024, 41(3): 375-386.

WANG Yinda, PENG Ling, CHEN Deyue, LI Weichao. Remote sensing extraction method of agricultural greenhouse based on an improved U-Net model[J]. Journal of University of Chinese Academy of Sciences, 2024, 41(3): 375-386.

参考文献

[1] 陈经纬, 李宇, 陈俊, 等. 基于MFF-Deeplabv3+ 网络的高分辨率遥感影像建筑物提取方法[J/OL]. 中国科学院大学学报.(2023-03-21)[2023-05-10]. DOI:10.7523/j.ucas.2023.010.
[2] 王雪英, 郭卫华. 面向对象的高分一号卫星影像大棚信息提取研究[J].湖北农业科学, 2019,58(24):217-220.DOI:10.14088/j.cnki.issn0439-8114.2019.24.053.
[3] 汤紫霞, 李蒙蒙, 汪小钦, 等. 基于GF-2遥感影像的葡萄大棚信息提取[J].中国农业科技导报, 2020,22(11):95-105.DOI:10.13304/j.nykjdb.2019.0759.
[4] Yang D D, Chen J, Zhou Y, et al. Mapping plastic greenhouse with medium spatial resolution satellite data: development of a new spectral index[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 128: 47-60.DOI:10.1016/j.isprsjprs.2017.03.002.
[5] Shi L F, Huang X J, Zhong T Y, et al. Mapping plastic greenhouses using spectral metrics derived from GaoFen-2 satellite data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 13: 49-59.DOI:10.1109/JSTARS.2019.2950466.
[6] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.DOI:10.1007/978-3-319-24574-4_28.
[7] Sun K, Xiao B, Liu D, et al. Deep high-resolution representation learning for human pose estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 15-20, 2019, Long Beach, CA, USA.IEEE,2020:5686-5696.DOI: 10.1109/CVPR.2019.00584.
[8] Tan M X, Le Q V. EfficientNet: rethinking model scaling for convolutional neural networks[EB/OL]. 2019: arXiv: 1905.11946.(2019-05-24)[2023-05-10]. https://arxiv.org/abs/1905.11946.
[9] Li M, Zhang Z J, Lei L P, et al. Agricultural greenhouses detection in high-resolution satellite images based on convolu-tional neural networks: comparison of faster R-CNN, YOLO v3 and SSD[J]. Sensors, 2020, 20(17): 4938. DOI: 10.3390/s20174938.
[10] Redmon J, Farhadi A. YOLOv3: An incremental improve-ment[EB/OL]. 2018: arXiv: 1804.02767.(2018-04-08)[2023-05-10]. https://arxiv.org/abs/1804.02767.
[11] Feng Q L, Niu B W, Chen B A, et al. Mapping of plastic greenhouses and mulching films from very high resolution remote sensing imagery based on a dilated and non-local convolutional neural network[J]. International Journal of Applied Earth Observation and Geoinformation, 2021, 102: 102441. DOI: 10.1016/j.jag.2021.102441.
[12] Baghirli O, Ibrahimli I, Mammadzada T. Greenhouse seg-mentation on high-resolution optical satellite imagery using deep learning techniques[EB/OL]. 2020: arXiv: 2007. 11222.(2020-07-22)[2023-05-10]. https://arxiv.org/abs/2007.11222.
[13] Feng J N, Wang D L, Yang F, et al. PODD: a dual-task detection for greenhouse extraction based on deep learning[J]. Remote Sensing, 2022, 14(19): 5064. DOI: 10. 3390/rs14195064.
[14] Zhang X P, Cheng B, Chen J F, et al. High-resolution boundary refined convolutional neural network for automatic agricultural greenhouses extraction from GaoFen-2 satellite imageries[J]. Remote Sensing, 2021, 13(21): 4237. DOI: 10.3390/rs13214237.
[15] Zhang Z X, Liu Q J, Wang Y H. Road extraction by deep residual U-net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749-753. DOI: 10.1109/LGRS.2018.2802944.
[16] Liu Z, Mao H Z, Wu C Y, et al. A ConvNet for the 2020s[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 18-24, 2022, New Orleans, LA, USA. IEEE, 2022: 11966-11976. DOI: 10.1109/CVPR 52688.2022.01167.
[17] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Com-puter Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 770-778. DOI: 10.1109/CVPR.2016.90.
[18] Liu Z, Lin Y T, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). October 10-17, 2021, Montreal, QC, Canada. IEEE, 2022: 9992-10002. DOI: 10.1109/ICCV48922.2021.00986.
[19] Hou Q B, Zhou D Q, Feng J S. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 20-25, 2021, Nashville, TN, USA. IEEE, 2021: 13708-13717. DOI: 10.1109/CVPR46437.2021. 01350.
[20] Woo S, Park J, Lee J Y, et al. CBAM: convolutional block attention module[C]//European Conference on Computer Vision. Cham: Springer, 2018: 3-19.DOI:10.1007/978-3-030-01234-2_1.
[21] Takikawa T, Acuna D, Jampani V, et al. Gated-SCNN: gated shape CNNs for semantic segmentation[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). October 27-November 2, 2019, Seoul, Korea (South). IEEE, 2020: 5228-5237. DOI: 10.1109/ICCV.2019.00533.
[22] Zhen M M, Wang J L, Zhou L, et al. Joint semantic segmentation and boundary detection using iterative pyramid contexts[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 13-19, 2020, Seattle, WA, USA. IEEE, 2020: 13663-13672. DOI: 10.1109/CVPR42600.2020.01368.
[23] Loshchilov I, Hutter F. Fixing weight decay regularization in Adam[EB/OL]. 2017: arXiv: 1711.05101.(2017-11-14)[2023-05-10]. https://arxiv.org/abs/1711.05101.
[24] Ding L, Tang H, Bruzzone L. LANet: local attention embedding to improve the semantic segmentation of remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(1): 426-435. DOI: 10.1109/TGRS.2020.2994150.
[25] Chen L C, Zhu Y K, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmen-tation[C]//European Conference on Computer Vision. Cham: Springer, 2018: 833-851.10.1007/978-3-030-01234-2_49.

基于改进U-Net模型的农业大棚遥感提取方法

Remote sensing extraction method of agricultural greenhouse based on an improved U-Net model

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	邹绍悦, 刘朔, 夏昊. 基于卫星影像的输电线路周边地表隐患识别方法[J]. 中国科学院大学学报, 2023, 40(6): 778-787.
[2]	王健飞, 张卫强, 刘加. 基于多状态跳转模型的场景独立音频事件检测方法[J]. 中国科学院大学学报, 2019, 36(2): 218-225.
[3]	郑敬华, 郭世泽, 高梁, 赵楠. 基于多任务学习的大五人格预测[J]. 中国科学院大学学报, 2018, 35(4): 550-560.