您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (6): 139-145.doi: 10.6040/j.issn.1672-3961.0.2021.328

• 机器学习与数据挖掘 • 上一篇    

基于深度学习的遥感图像道路分割

李旭涛1,2,杨寒玉1,卢业飞1,张玮1,3*   

  1. 1.齐鲁工业大学(山东省科学院)计算机科学与技术学部, 山东 济南 250353;2.湖北大学数学与统计学学院, 湖北 武汉 430062;3.山东省计算中心(国家超级计算济南中心)山东省计算机网络重点实验室, 山东 济南 250000
  • 发布日期:2022-12-23
  • 作者简介:李旭涛(1999— ),男,河北保定人,硕士研究生,主要研究方向为数据挖掘和深度学习. E-mail:alitt5@stu.hubu.edu.cn. *通信作者简介:张玮(1983— ),男,山东莱芜人,研究员,博士,主要研究方向为未来网络体系结构和算网融合与边缘计算. E-mail:wzhang@sdas.org.
  • 基金资助:
    国家自然科学基金资助项目(61802233);山东省自然科学基金资助项目(ZR2021LZH001);山东省自然科学基金资助项目(ZR2020LZH010)

Road segmentation of remote sensing image based on deep learning

LI Xutao1,2, YANG Hanyu1, LU Yefei1, ZHANG Wei1,3*   

  1. 1. Faculty of Computer Science and Technology, Qilu University of Technology(Shandong Academy of Sciences), Jinan 250353, Shandong, China;
    2. School of Mathematics and Statistics, Hubei University, Wuhan 430062, Hubei, China;
    3. Shandong Provincial Key Laboratory of Computer Networks, Shandong Computer Science Center(National Supercomputer Center in Jinan), Jinan 250000, Shandong, China
  • Published:2022-12-23

PDF (PC)

177

摘要： 为在遥感图像中提取出来道路信息,利用深度学习技术,引入U2-Net模型进行遥感图像道路分割。相比于传统的道路提取方法,基于U2-Net方法可以实现道路的自动化提取。为验证U2-Net模型分割效果,选取U-Net、DeepLabV3+等近几年较为流行的语义分割方法进行对比试验,并进一步分析U2-Net显著图融合模块中卷积核对道路提取效果的影响。试验结果表明,U2-Net模型能较有效地提取出道路信息,模型在测试集上的平均交并比达到了76.49%,Kappa达到了0.701 2,分割精度优于U-Net、DeepLabV3+等语义分割方法。基于U2-Net模型的深度学习方法可以用于解决遥感图像中的道路分割问题,并具有较好的分割效果。

关键词: 语义分割, 深度学习, 遥感图像, U2-Net模型, 高分辨率

中图分类号: 

  • TP363
[1] 徐辉, 祝玉华, 甄彤, 等. 深度神经网络图像语义分割方法综述[J]. 计算机科学与探索, 2021, 15(1): 47-59 XU Hui, ZHU Yuhua, ZHEN Tong, et al. Review of image semantic segmentation based on deep neural network[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(1): 47-59.
[2] GAO Xun, SUN Xian, ZHANG Yi, et al. An end-to-end neural network for road extraction from remote sensing imagery by multiple feature pyramid network[J]. IEEE Access, 2018, 6(1): 39401-39414.
[3] YAGER N, SOWMYA A. Support vector machines for road extraction from remotely sensed images[C] //Proceedings of International Conference on Computer Analysis of Images and Patterns. Berlin, Germany: Springer, 2003: 285-292.
[4] ANIL P N, NATARAJAN S. A novel approach using active contour model for semi-automatic road extraction from high resolution satellite imagery[C] //Proceedings of 2010 Second International Conference on Machine Learning and Computing. Bangalore, India: IEEE, 2010: 263-266.
[5] 罗巍, 王东亮. 利用角度纹理特征提取高分辨率遥感影像中城市主干道路[J]. 中国图象图形学报, 2017, 22(11): 1584-1591. LUO Wei, WANG Dongliang. Extraction of urban main roads from high-resolution remote sensing images using angular texture features[J]. Journal of Image and Graphics, 2017, 22(11): 1584-1591.
[6] LONG Jonathan, EVAN S, TREVOR D. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[7] CHEN L, PAPANDREOU G, KOKKINOS I, et al. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4): 834-848.
[8] VIJAY B, ALEX K, ROBERTO C. Segnet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[9] LEI Sen, SHI Zhenwei, WU Xi, et al. Simultaneous super-resolution and segmentation for remote sensing images[C] //Proceedings of IEEE International Geoscience and Remote Sensing Symposium. Yokohama, Japan: IEEE, 2019: 3121-3124.
[10] ZHONG Zilong, LI Jonathan, CUI Weihong, et al. Fully convolutional networks for building and road extraction: preliminary results[C] //Proceedings of IEEE International Geoscience and Remote Sensing Symposium. Beijing, China: IEEE, 2016: 1591-1594.
[11] ZHANG Zhengxin, LIU Qingjie, WANG Yunhong. Road extraction by deep residual U-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749-753.
[12] RONNEBERGER O, FISCHER P, BROX T. U-net: Con-volutional networks for biomedical image segmentation[C] //Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany: Springer, 2015: 234-241.
[13] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, USA: IEEE, 2016: 770-778.
[14] 张新长, 江鑫. 多深度神经网络集成的道路提取[J]. 地理信息世界, 2020, 27(6): 87-92. ZHANG Xinchang, JIANG Xin. Road extraction based on multi depth neural network ensemble[J]. Geomatics World, 2020, 27(6): 87-92.
[15] 殷晓航, 王永才, 李德英. 基于U-Net结构改进的医学影像分割技术综述[J]. 软件学报, 2021, 32(2): 519-550. YIN Xiaohang, WANG Yongcai, LI Deying. A review of medical image segmentation technology based on U-Net structure improvement[J]. Journal of Software, 2021, 32(2): 519-550.
[16] 王斌,陈占龙,吴亮,等. 兼顾连通性的U-Net网络高分辨率遥感影像道路提取[J]. 遥感学报, 2020, 24(12): 1488-1499. WANG Bin, CHEN Zhanlong, WU Liang, et al. Road extraction from high resolution remote sensing images with U-Net network considering connectivity[J]. National Remote Sensing Bulletin, 2020, 24(12): 1488-1499.
[17] 张翠军,安冉,马丽. 改进U-Net的遥感图像中建筑物变化检测[J]. 计算机工程与应用, 2021, 57(3): 239-246. ZHANG Cuijun, AN Ran, MA Li. Building change detection in remote sensing image based on improved U-Net[J]. Computer Engineering and Application, 2021, 57(3): 239-246.
[18] 张欢,仇大伟,冯毅博,等. U-Net模型改进及其在医学图像分割上的研究综述[J]. 激光与光电子学进展, 2022, 59(2): 1-17. ZHANG Huan, QIU Dawei, FENG Yibo, et al. U-Net Model Improvement and Review of Research on Medical Image Segmentation[J]. Laser & Optoelectronics Progress, 2022, 59(2): 1-17.
[19] 曹建芳, 田晓东, 贾一鸣, 等. 改进DeepLabV3+模型在壁画分割中的应用[J]. 计算机应用, 2021, 41(5): 1471-1476. CAO Jianfang, TIAN Xiaodong, JIA Yiming, et al. Application of improved DeepLabV3+ model in mural segmentation[J]. Journal of Computer Applications, 2021, 41(5): 1471-1476.
[20] CHEN L, ZHU Yukun, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C] //Proceedings of the European Conference on Computer Vision(ECCV). Munich, Germany: Springer, 2018: 801-818.
[21] ZHAO Hengshuang, SHI Jianping, QI Xiaojuan, et al. Pyramid scene parsing network[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 2881-2890.
[22] 吴秋怡. 基于语义分割网络模型的路面裂缝识别[J]. 交通科技, 2020(3): 80-83. WU Qiuyi. Pavement crack recognition based on semantic segmentation network model[J]. Transportation Science & Technology, 2020(3): 80-83.
[23] XU Shihuai, LU Huijuan, YE Minchao, et al. Improved cascade R-CNN for medical images of pulmonary nodules detection combining dilated HRNet[C] //Proceedings of the 2020 12th International Conference on Machine Learning and Computing. Shenzhen, China: ACM, 2020: 283-288.
[24] SUN Ke, XIAO Bin, LIU Dong, et al. Deep high-resolution representation learning for human pose estimation[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 5693-5703.
[25] WANG Jingdong, SUN Ke, CHENG Tianheng, et al. Deep high-resolution representation learning for visual recog-nition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(10): 3349-3364.
[26] QIN Xuebin, ZHANG Zichen, HUANG Chenyang, et al. U2-Net: going deeper with nested U-structure for salient object detection[J]. Pattern Recognition, 2020, 106(107404): 1-12.
[27] 叶明, 李晓丞, 刘凯. 一种基于U2-Net模型的电阻抗成像方法[J]. 仪器仪表学报, 2021, 42(2): 235-243. YE Ming, LI Xiaocheng, LIU Kai, et al. A method of electrical impedance tomography based on U2-net model [J]. Chinese Journal of Scientific Instrument, 2021, 42(2): 235-243.
[28] MNIH Volodymyr. Machine learning for aerial image labeling[D]. Ontario, Canada: Department of Computer Science, University of Toronto, 2013.
[29] 康萌萌, 杨浩, 谷小婧, 等. 基于融合路径监督的多波段图像语义分割[J]. 华东理工大学学报(自然科学版), 2021, 47(2): 233-240. KANG Mengmeng, YANG Hao, GU Xiaojing, et al. Multispectral image semantic segmentation based on supervised feature fusion[J]. Journal of East China University of Science and Technology, 2021, 47(2): 233-240.
[1] 袁钺,王艳丽,刘勘. 基于空洞卷积块架构的命名实体识别模型[J]. 山东大学学报 (工学版), 2022, 52(6): 105-114.
[2] 侯月武,刘兆英,张婷,李玉鑑,孙长明. 基于改进的DUNet遥感图像道路提取[J]. 山东大学学报 (工学版), 2022, 52(4): 29-37.
[3] 孟令灿,聂秀山,张雪. 基于遮挡目标去除的公交车拥挤度分类算法[J]. 山东大学学报 (工学版), 2022, 52(4): 83-88.
[4] 杨霄,袭肖明,李维翠,杨璐. 基于层次化双重注意力网络的乳腺多模态图像分类[J]. 山东大学学报 (工学版), 2022, 52(3): 34-41.
[5] 王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[6] 尹旭,刘兆英,张婷,李玉鑑. 基于弱监督和半监督学习的红外舰船分割方法[J]. 山东大学学报 (工学版), 2022, 52(2): 99-106.
[7] 蒋桐雨,陈帆,和红杰. 基于非对称U型金字塔重建的轻量级人脸超分辨率网络[J]. 山东大学学报 (工学版), 2022, 52(1): 1-8, 18.
[8] 吴建清,宋修广. 同步定位与建图技术发展综述[J]. 山东大学学报 (工学版), 2021, 51(5): 16-31.
[9] 杨修远,彭韬,杨亮,林鸿飞. 基于知识蒸馏的自适应多领域情感分析[J]. 山东大学学报 (工学版), 2021, 51(3): 15-21.
[10] 柴庆发,孙守晶,邱吉福,陈明,魏振,丛伟. 气象灾害条件下电网应急物资预测方法[J]. 山东大学学报 (工学版), 2021, 51(3): 76-83.
[11] 曹春红,段鸿轩,曹玲,张乐乐,胡凯,肖芬. 基于多级特征级联的遥感图像实时语义分割[J]. 山东大学学报 (工学版), 2021, 51(2): 19-25.
[12] 廖锦萍,莫毓昌,YAN Ke. 基于C-LSTM的短期用电预测模型和应用[J]. 山东大学学报 (工学版), 2021, 51(2): 90-97.
[13] 蔡国永,贺歆灏,储阳阳. 基于空间注意力和卷积神经网络的视觉情感分析[J]. 山东大学学报 (工学版), 2020, 50(4): 8-13.
[14] 刘帅,王磊,丁旭涛. 基于Bi-LSTM的脑电情绪识别[J]. 山东大学学报 (工学版), 2020, 50(4): 35-39.
[15] 李怡霏,郭尊华. 一种Chirplet神经网络自动目标识别算法[J]. 山东大学学报 (工学版), 2020, 50(3): 8-14.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发