基于CBAM-U-HRNet模型和Sentinel-2数据的棉花种植地块提取

靳宁; 孙林; 张东彦; 张选; 李毅; 姚宁

基于CBAM-U-HRNet模型和Sentinel-2数据的棉花种植地块提取

靳宁¹,
孙林²,
张东彦^2,3,,
张选⁴,
李毅⁵,
姚宁⁵

1. 山西能源学院资源与环境工程系;
2. 安徽大学农业生态大数据分析与应用技术国家地方联合工程研究中心;
3. 西北农林科技大学机械与电子工程学院;
4. 新疆生产建设兵团第三师农业科学研究所;
5. 西北农林科技大学水利与建筑工程学院

基金项目:

山西省基础研究计划自然科学研究面上项目(202203021221231)

详细信息

作者简介:
靳宁(1983—),男,副教授,博士,主要从事生态环境遥感和信息化研究,E-mail:jinn.13b@igsnrr.ac.cn

通讯作者:
张东彦(1982—),男,教授,主要从事遥感信息处理和大数据挖掘与应用研究,E-mail:zhangdy@ahu.edu.cn

中图分类号: S562;S127
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0
出版历程
- 收稿日期: 2023-06-04
- 刊出日期: 2023-11-24

Classification of Cotton Planting Area Using CBAM-U-HRNet Model and Sentinel-2 Data

1. Department of Resources and Environment, Shanxi Institute of Energy;
2. National Engineering Research Center of Agro-Ecological Big Data Analysis and Application,Anhui University;
3. College of Mechanical and Electronic Engineering, Northwest A&F University;
4. Institute of Agricultural Science and Technology of Third Division, Xinjiang Production and Construction Corps;
5. College of Water Resources and Architectural Engineering, Northwest A&F University

摘要

摘要: 棉花是我国重要的经济作物和战略储备物资，及时、准确地获取棉花空间分布信息对于棉花产量预测、农业政策的制定与调整具有重要意义。针对高分辨率遥感影像获取难度大以及传统机器学习对特征信息利用不足的问题，本文以新疆南部地区图木舒克市为目标区域，提出一种以U-HRNet为基本框架，融合CBAM注意力机制的CBAM-U-HRNet棉花种植地块提取模型。选择U-Net、HRNet和U-HRNet作为对比模型，评估CBAM-U-HRNet模型在Sentinel-2(10 m)和GF-2(1 m)2种空间分辨率数据集上的表现以及在棉花地块提取的优势。结果表明，基于Sentinel-2遥感影像的CBAM-U-HRNet组合模型对棉花地块的提取精度最优，mIoU和mPA分别达到92.78%和95.32%。与Sentinel-2数据集相比，空间分辨率更高的GF-2数据在HRNet、U-Net和U-HRNet网络上取得了更高的精度。对于两种不同空间分辨率的数据集，基于CBAM-U-HRNet模型的棉花地块提取精度较为接近，表明CBAM-U-HRNet模型能够减少由于数据集空间分辨率不同导致的错分。与随机森林算法相比，CBAM-U-HRNet模型对棉花地块提取的准确率更高。研究结果可以为干旱地区棉花识别与种植地块快速提取提供技术支撑。
- 棉花 /
- 种植地块提取 /
- 注意力机制 /
- CBAM-U-HRNet模型 /
- Sentinel-2
Abstract: Cotton is an important economic crop and strategic reserve material in China, timely and accurate acquisition of cotton spatial distribution information is of great significance for cotton yield prediction and agricultural policy development and adjustment. In order to address the problems of the difficult availability of high-resolution remote sensing data and insufficient usability of feature information by traditional machine learning, a CBAM-U-HRNet classification model was established to extract cotton planted area, where U-HRNet and CBAM attention mechanism were combined, and Tumxuk City in the southern Xinjiang was taken as an study area. Firstly, the Sentinel-2 remote sensing data were pre-processed and annotated. Secondly, the attention mechanism CBAM was introduced into U-HRNet to enhance the important features for cotton classification, suppress the relatively unimportant features, and reduce the interference caused by complex background information. Finally, U-Net, HRNet and U-HRNet were selected to compare with CBAM-U-HRNet model to test their performance in the classification of cotton planted area. During this process, two different spatial resolution datasets such as Sentinel-2（10 m） and GF-2（1 m） were used, and the advantages of CBAM-U-HRNet model were evaluated by using the best feature subset. The results showed the CBAM-U-HRNet model that using Sentinel-2 remote sensing data had the best classification accuracy for cotton planted area, with mIoU and mPA reaching 92.78% and 95.32%, respectively. Comparing with the Sentinel-2 dataset, the GF-2 data had higher spatial resolution and achieved higher accuracy by using HRNet, U-Net and U-HRNet networks. For the two datasets with different spatial resolutions, the classification accuracies of cotton planted area using the CBAM-U-HRNet model was comparable to each other. The CBAM-U-HRNet model can reduce the misclassification induced by the difference in spatial resolution of the two datasets. Comparing with the random forest algorithm, the CBAM-U-HRNet model had higher accuracy in the classification of cotton. The research results can provide technical support for the classification of cotton, and the fast and objective extraction of vegetation planted area in arid regions.
- cotton /
- planting area classification /
- attention mechanism /
- CBAM-U-HRNet model /
- Sentinel-2

HTML全文

参考文献(33)

[1]	HU T,HU Y,DONG J,et al.Integrating Sentinel-1/2 data and machine learning to map cotton fields in Northern Xinjiang,China[J].Remote Sensing,2021,13(23):4819.
[2]	MURA M,BOTTALICO F,GIANNETTI F,et al.Exploiting the capabilities of the Sentinel-2 multi spectral instrument for predicting growing stock volume in forest ecosystems[J].International Journal of Applied Earth Observation and Geoinformation,2018,66:126-134.
[3]	吕绍伦,赵阳,陈万基,等.基于遥感云计算的阿拉尔市棉花种植面积提取[J].棉花科学,2022,44(4):19-25.LÜ Shaolun,ZHAO Yang,CHEN Wanji,et al.Extraction of cotton planting area in Alaer based on remote sensing cloud computing[J].Cotton Sciences,2022,44(4):19-25.(in Chinese)
[4]	田野,张清,李希灿,等.基于多时相影像的棉花种植信息提取方法研究[J].干旱区研究,2017,34(2):423-430.TIAN Ye,ZHANG Qing,LI Xican,et al.Extraction method of cotton plantation information based on multi-temporal images[J].Arid Zone Research,2017,34(2):423-430.(in Chinese)
[5]	AL-SHAMMARI D,FUENTES I,WHELAN B M,et al.Mapping of cotton fields within-season using phenology-based metrics derived from a time series of Landsat imagery[J].Remote Sensing,2020,12(18):3038.
[6]	赵晋陵,詹媛媛,王娟,等.基于SE-UNet的冬小麦种植区域提取方法[J].农业机械学报,2022,53(9):189-196.ZHAO Jinling,ZHAN Yuanyuan,WANG Juan,et al.SE-UNet-based extraction of winter wheat planting areas[J].Transactions of the Chinese Society for Agricultural Machinery,2022,53(9):189-196.(in Chinese)
[7]	董金玮,吴文斌,黄健熙,等.农业土地利用遥感信息提取的研究进展与展望[J].地球信息科学学报,2020,22(4):772-783.DONG Jinwei,WU Wenbin,HUANG Jianxi,et al.State of the art and perspective of agricultural land use remote sensing information extraction[J].Journal of Geo-information Science,2020,22(4):772-783.(in Chinese)
[8]	司凯凯,汪传建,赵庆展,等.基于哨兵2号遥感影像最优时相组合的棉花提取方法[J].石河子大学学报,2022,40(5):639-647.SI Kaikai,WANG Chuanjian,ZHAO Qingzhan,et al.Cotton extraction method based on optimal time phase combination of Sentinel-2 remote sensing images[J].Journal of Shihezi University (Natural Science),2022,40(5):639-647.(in Chinese)
[9]	伊尔潘·艾尼瓦尔,买买提·沙吾提,买合木提·巴拉提.基于GF-2影像和Unet模型的棉花分布识别[J].自然资源遥感,2022,34(2):242-250.ERPAN A,MAMAT S,MAIHEMUTI B,et al.Cotton distribution recognition based on GF-2 image and Unet model[J].Remote Sensing for Natural Resources,2022,34(2):242-250.(in Chinese)
[10]	LI H,WANG G,DONG Z,et al.Identifying cotton fields from remote sensing images using multiple deep learning networks[J].Agronomy,2021,11(1):174.
[11]	胡航,牛晓伟,左昊,等.基于改进HRNet架构的图像语义分割算法应用研究[J].现代计算机,2022,28(18):23-29.HU Hang,NIU Xiaowei,ZUO Hao,et al.Application study of image semantic segmentation algorithm based on improved HRNet architecture[J].Modern Computer,2022,28(18):23-29.(in Chinese)
[12]	SUN K,ZHAO Y,JIANG B,et al.High-resolution representations for labeling pixels and regions[J].arXiv,2019,1:13.
[13]	WANG J,LONG X,CHEN G,et al.U-HRNet:delving into improving semantic representation of high resolution network for dense prediction[J].arXiv,2022,1:13.
[14]	DELEGIDO J,VERRELST J,ALONSO L,et al.Evaluation of Sentinel-2 red-edge bands for empirical estimation of green LAI and chlorophyll content[J].Sensors,2011,11(7):7063-7081.
[15]	黄双燕,杨辽,陈曦,等.机器学习法的干旱区典型农作物分类[J].光谱学与光谱分析,2018,38(10):3169-3176.HUANG Shuangyan,YANG Liao,CHEN Xi,et al.Study of typical arid crops classification based on machine learning[J].Spectroscopy and Spectral Analysis,2018,38(10):3169-3176.(in Chinese)
[16]	SUN Y,QIN Q,REN H,et al.Red-edge band vegetation indices for leaf area index estimation from Sentinel-2/MSI imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2019,58(2):826-840.
[17]	刘传迹,金晓斌,徐伟义,等.2000—2020年南疆地区棉花种植空间格局及其变化特征分析[J].农业工程学报,2021,37(16):223-232.LIU Chuanji,JIN Xiaobin,XU Weiyi,et al.Analysis of the spatial distribution and variation characteristics of cotton planting in southern Xinjiang from 2000 to 2020[J].Transactions of the CSAE,2021,37(16):223-232.(in Chinese)
[18]	FEI H,FAN Z,WANG C,et al.Cotton classification method at the county scale based on multi-features and random forest feature selection algorithm and classifier[J].Remote Sensing,2022,14(4):829.
[19]	王汇涵,张泽,康孝岩,等.基于Sentinel-2A的棉花种植面积提取及产量预测[J].农业工程学报,2022,38(9):205-214.WANG Huihan,ZHANG Ze,KANG Xiaoyan,et al.Cotton planting area extraction and yield prediction based on Sentinel-2A[J].Transactions of the CSAE,2022,38(9):205-214.(in Chinese)
[20]	ZHU M,SHE B,HUANG L,et al.Identification of soybean based on Sentinel-1/2 SAR and MSI imagery under a complex planting structure[J].Ecological Informatics,2022,72:101825.
[21]	LIU J,FENG Q,GONG J,et al.Winter wheat mapping using a random forest classifier combined with multi-temporal and multi-sensor data[J].International Journal of Digital Earth,2018,11(8):783-802.
[22]	LIU S,PENG D,ZHANG B,et al.The accuracy of winter wheat identification at different growth stages using remote sensing[J].Remote Sensing,2022,14(4):893.
[23]	LUO K,LU L,XIE Y,et al.Crop type mapping in the central part of the North China Plain using Sentinel-2 time series and machine learning[J].Computers and Electronics in Agriculture,2023,205:107577.
[24]	YANG S,GU L,LI X,et al.Crop classification method based on optimal feature selection and hybrid CNN-RF networks for multi-temporal remote sensing imagery[J].Remote Sensing,2020,12(19):3119.
[25]	樊湘鹏,周建平,许燕,等.基于优化 Faster R-CNN 的棉花苗期杂草识别与定位[J].农业机械学报,2021,52(5):26-34.FAN Xiangpeng,ZHOU Jianping,XU Yan,et al.Identification and localization of weeds based on optimized Faster R-CNN in cotton seedling stage[J].Transactions of the Chinese Society for Agricultural Machinery,2021,52(5):26-34.(in Chinese)
[26]	GUL M S K,MUKATI M U,BÄTZ M,et al.Light-field view synthesis using a convolutional block attention module[C]//2021 IEEE International Conference on Image Processing (ICIP).IEEE,2021:3398-3402.
[27]	CHANG R,HOU D,CHEN Z,et al.Automatic extraction of urban impervious surface based on SAH-Unet[J].Remote Sensing,2023,15(4):1042.
[28]	SYRRIS V,HASENOHR P,DELIPETREV B,et al.Fully convolutional networks for semantic segmentation[J].Remote Sensing,2019,11(8):907.
[29]	ZHANG S,GUO J,LUO N,et al.Improving Wi-Fi fingerprint positioning with a pose recognition-assisted SVM algorithm[J].Remote Sensing,2019,11(6):652.
[30]	WANG N,ZHAI Y,ZHANG L.Automatic cotton mapping using time series of Sentinel-2 images[J].Remote Sensing,2021,13(7):1355.
[31]	REN B,ZHOU H,SHEN H,et al.Research on cotton information extraction based on Sentinel-2 time series analysis[C]//2019 8th International Conference on Agro-Geoinformatics (Agro-Geoinformatics).IEEE,2019:1-6.
[32]	TAMIMINIA H,SALEHI B,MAHDIANPARI M,et al.Google Earth Engine for geo-big data applications:a meta-analysis and systematic review[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,164:152-170.
[33]	MAO H,MENG J,JI F,et al.Comparison of machine learning regression algorithms for cotton leaf area index retrieval using Sentinel-2 spectral bands[J].Applied Sciences,2019,9(7):1459.