基于Sentinel-2A遥感影像的潍坊市冬小麦种植面积提取研究  

Research on extraction of winter wheat planting area in Weifang City based on Sentinel-2A remote sensing image

作　　者：孙逸飞 柳平增[1,2,3] 张艳 宋长青[1,2,3] 张大雷[4] 马学文 Sun Yifei;Liu Pingzeng;Zhang Yan;Song Changqing;Zhang Dalei;Ma Xuewen(School of Information Science and Engineering,Shandong Agricultural University,Tai'an,271000,China;Agricultural Big Data Research Center of Shandong Agricultural University,Tai'an,271000,China;Key Laboratory of Intelligent Agriculture Technology of the Yellow and Huaihai Sea,Ministry of Agriculture and Rural Affairs,Tai'an,271000,China;Taishan College of Science and Technology,Tai'an,271000,China;Shandong Nongda Fertilizer Technology Co.,Ltd.,Tai'an,271000,China)

机构地区：[1]山东农业大学信息科学与工程学院,山东泰安271000 [2]山东农业大学农业大数据研究中心,山东泰安271000 [3]农业农村部黄淮海智慧农业技术重点实验室,山东泰安271000 [4]山东科技大学泰山科技学院,山东泰安271000 [5]山东农大肥业科技有限公司,山东泰安271000

出　　处：《中国农机化学报》2022年第7期98-105,共8页Journal of Chinese Agricultural Mechanization

基　　金：山东省农业重大应用技术创新项目(SD2019ZZ019);2019年度山东省重点研发计划(公益类专项)项目(2019GNC106103);山东省科技特派员项目(2020KJTPY078);山东省重大科技创新工程项目(2019JZZY010713)。

摘　　要：为准确、高效、自动化的提取大尺度范围冬小麦种植面积,利用Sentinel-2A卫星影像进行试验,提出一种基于中等分辨率影像的面向对象结合深度学习的遥感冬小麦提取方法。利用面向对象分类法和随机森林分类算法对2021年潍坊市冬小麦种植面积及种植区域进行提取和结果对比,证明面向对象分类法在提取冬小麦种植面积时的可行性和有效性。此外,利用面向对象方法得到的二值分类图像作为标签图像,基于TensorFlow框架,利用U-Net构建深度学习神经网络模型,使用训练得到最优模型提取2017—2021年潍坊市冬小麦种植面积。使用实地调查数据对分类结果进行精度验证,并对潍坊市近五年冬小麦种植面积进行年际变化分析。该分类方法的总体分类精度达93.1%,Kappa系数为0.91。本研究方法可为大范围的冬小麦种植指导和农业结构调整提供科学、可靠的依据。To extract winter wheat planting areas accurately,efficiently,and automatically over a large area,experiments were conducted using Sentinel-2A satellite images.The remote sensing winter wheat extraction method is proposed based on object-oriented and deep learning for medium-resolution images.The area and planting area of winter wheat in Weifang city in 2021 were extracted and compared by using object-oriented classification method and random forest classification algorithm,which proved the feasibility and effectiveness of object-oriented classification method in extracting planting area of winter wheat.In addition,using object-oriented binary classification images as label images,U-Net is used to build a deep learning neural network model based on the TensorFlow framework.The optimal model obtained by training is used to extract the winter wheat planting area in Weifang City from 2017 to 2021.Field survey data was used to verify the accuracy of the classification results and to analyze the inter-annual changes in the winter wheat planting area in Weifang City in the past five years.The overall classification accuracy of this classification method reached 93.1%,and the Kappa coefficient was 0.91.This research method can provide a reliable scientific basis for large-scale winter wheat planting guidance and agricultural structure adjustment.

关 键 词：Sentinel-2A 冬小麦 面向对象 随机森林 深度学习 面积提取 

分 类 号：S127[农业科学—农业基础科学]