尹昊,张承明,李剑萍,韩颖娟,侯学会

• 1:山东农业大学信息科学与工程学院
• 2:中国气象局旱区特色农业气象灾害监测预警与风险管理重点实验室
• 3:山东省农业科学院农业信息与经济研究所

摘要(Abstract)：

针对当前遥感图像分割结果中提取对象边缘像素的分割精度低的问题，为提高边缘像素特征与内部像素特征的一致性，该文建立了一种融合语义特征与边缘特征的高分辨率遥感图像分割方法(EFFNet)。EFFNet分别从遥感图像中提取语义特征，从遥感图像和边缘图中提取边缘特征，并对两类特征采取多尺度分级融合，以获取到兼有较高的类间区分性和类内一致性的特征向量，实现良好的分割结果。实验结果表明，EFFNet对宁夏地区的枸杞空间分布提取结果的召回率、准确率、精确率和F1分数均优于其他7个对比方法。EFFNet模型可用于获取高精度枸杞等农作物空间分布信息，EFFNet的提取结果能够为大范围枸杞等农作物面积统计提供参考。

关键词(KeyWords)： 卷积神经网络;图像分割;高分辨率遥感影像;语义特征;边缘特征;枸杞

Abstract:

Keywords:

基金项目(Foundation): 中国气象局旱区特色农业气象灾害监测预警与风险管理重点实验室指令性项目(CAMP-201916);; 宁夏回族自治区重点研发计划项目(2019BEH03008);; 山东省自然科学基金项目(ZR2017MD018);; 山东省农业科学院农业科技创新工程项目(CXGC2021A26)

作者(Author): 尹昊,张承明,李剑萍,韩颖娟,侯学会

DOI: 10.16251/j.cnki.1009-2307.2022.04.015

参考文献(References)：

• [1] KEMKER R,SALVAGGIO C,KANAN C.Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,145(11):60-77.
• [2] 李士进，占迪，高祥涛，等.基于梯度与颜色信息融合的水文资料图像分割[J].数据采集与处理，2016,31(1):94-101.(LI Shijin,ZHAN Di,GAO Xiangtao,et al.Hydrological sheet color image segmentation based on gradient and color information[J].Journal of Data Acquisition and Processing,2016,31(1):94-101.)
• [3] 龙鹏飞，贺亮，吕回，等.基于BEMD和灰度共生矩阵的图像特征提取[J].计算机工程与应用，2009,45(16):201-203.(LONG Pengfei,HE Liang,LYU Hui,et al.Image feature extraction based on BEMD and gray level co-occurrence matrix[J].Computer Engineering and Applications,2009,45(16):201-203.)
• [4] MOYA L,ZAKERI H,YAMAZAKI F,et al.3D gray level co-occurrence matrix and its application to identifying collapsed buildings[J].ISPRS Journal of Photogrammetry and Remote Sensing,2019,149(3):14-28.
• [5] GAETANO R,IENCO D,OSE K,et al.A two-branch CNN architecture for land cover classification of PAN and MS imagery[J].Remote Sensing,2018,10(11):1746.
• [6] 赵春江.农业遥感研究与应用进展[J].农业机械学报，2014,45(12):277-293.(ZHAO Chunjiang.Advances of research and application in remote sensing for agriculture[J].Transactions of the Chinese Society for Agricultural Machinery,2014,45(12):277-293.)
• [7] PAN Yaozhong,LI Le,ZHANG Jinshui,et al.Crop area estimation based on MODIS-EVI time series according to distinct characteristics of key phenology phases:a case study of winter wheat area estimation in small-scale area[J].Journal of Remote Sensing,2011,15(3):578-594.
• [8] XIE S N,TU Z W.Holistically-nested edge detection[C]//2015 IEEE International Conference on Computer Vision (ICCV).[S.l.]:[s.n.],2015:1395-1403.
• [9] 哈斯图亚，陈仲新，李彩，等.面向对象的覆膜农田信息遥感表征方法[J].测绘科学，2021,46(3):140-146.(HASITUYA,CHEN Zhongxin,LI Cai,et al.Characterizing the plastic-mulched farmland using object-based image analysis[J].Science of Surveying and Mapping,2021,46(3):140-146.)
• [10] AL-OBEIDAT F,AL-TAANI A T,BELACEL N,et al.A fuzzy decision tree for processing satellite images and Landsat data[J].Procedia Computer Science,2015,52(6):1192-1197.
• [11] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2015:3431-3440.
• [12] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
• [13] ZHANG C,PAN X,LI H P,et al.A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,140(6):133-144.
• [14] ZHU Q,ZHANG Y,WANG L,et al.A global context-aware and batch-independent network for road extraction from VHR satellite imagery[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,175(12):353-365.
• [15] 黄巍，黄辉先，徐建闽，等.基于Canny边缘检测思想的改进遥感影像道路提取方法[J].国土资源遥感，2019,31(1):65-70.(HUANG Wei,HUANG Huixian,XU Jianmin,et al.An improved road extraction method for remote sensing images based on Canny edge detection[J].Remote Sensing for Land & Resources,2019,31(1):65-70.)
• [16] LYU H R,FU H Y,HU X J,et al.Esnet:edge-based segmentation network for real-time semantic segmentation in traffic scenes[C]//2019 IEEE International Conference on Image Processing (ICIP).[S.l.]:IEEE,2019:1855-1859.
• [17] MARMANIS D,SCHINDLER K,WEGNER J D,et al.Classification with an edge:improving semantic image segmentation with boundary detection[J].ISPRS Journal of Photogrammetry and Remote Sensing,2018,135(1):158-172.
• [18] LIU S,DING W R,LIU C H,et al.ERN:edge loss reinforced semantic segmentation network for remote sensing images[J].Remote Sensing,2018,10(9):1339.
• [19] 徐常青，刘赛，徐荣，等.我国枸杞主产区生产现状调研及建议[J].中国中药杂志，2014,39(11):1979-1984.(XU Changqing,LIU Sai,XU Rong,et al.Investigation of production status in major wolfberry producing areas of China and some suggestions[J].China Journal of Chinese Materia Medica,2014,39(11):1979-1984.)
• [20] 雷春苗，肖建设，史飞飞，等.柴达木地区枸杞种植区遥感提取方法对比研究[J].中国农学通报，2020,36(17):134-143.(LEI Chunmiao,XIAO Jianshe,SHI Feifei,et al.Extraction methods of wolfberry plantation in Qaidam region:a comparative study[J].Chinese Agricultural Science Bulletin,2020,36(17):134-143.)
• [21] 苏占胜，秦其明，陈晓光，等.GIS技术在宁夏枸杞气候区划中的应用[J].资源科学，2006,28(6):68-72.(SU Zhansheng,QIN Qiming,CHEN Xiaoguang,et al.Application of GIS for climate mapping of Chinese wolfberry in Ningxia Hui autonomous region[J].Resources Science,2006,28(6):68-72.)
• [22] 单治彬，孔金玲，张永庭，等.面向对象的特色农作物种植遥感调查方法研究[J].地球信息科学学报，2018,20(10):1509-1519.(SHAN Zhibin,KONG Jinling,ZHANG Yongting,et al.Remote sensing investigation method of object-oriented crops with special characteristics[J].Journal of Geo-Information Science,2018,20(10):1509-1519.)
• [23] TONG X Y,XIA G S,LU Q K,et al.Learning transferable deep models for land-use classification with high-resolution remote sensing images[EB/OL].(2019-11-20) [2021-03-15].https://arxiv.org/pdf/1807.05713.pdf.