基于深度学习高分辨率遥感影像语义分割
作者:

Semantic Segmentation of High Resolution Remote Sensing Image Based on Deep Learning
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    高分辨率遥感影像含有丰富的地理信息. 目前基于传统神经网络的语义分割模型不能够对遥感影像中小物体进行更高维度的特征提取, 导致分割错误率较高. 本文提出一种基于编码与解码结构特征连接的方法, 对DeconvNet网络模型进行改进. 模型在编码时, 通过记录池化索引的位置并应用于上池化中, 能够保留空间结构信息; 在解码时, 利用编码与解码对应特征层连接的方式使模型有效地进行特征提取. 在模型训练时, 使用设计的预训练模型, 可以有效地扩充数据, 来解决模型的过拟合问题. 实验结果表明, 在对优化器、学习率和损失函数适当调整的基础上, 使用扩充后的数据集进行训练, 对遥感影像验证集的分割精确度达到95%左右, 相对于DeconvNet和UNet网络模型分割精确度有显著提升.

    Abstract:

    High-resolution remote sensing images contains rich geographic information. At present, the semantic segmentation model based on the traditional neural network cannot extract the features of small and medium-sized objects in remote sensing images, resulting in high segmentation error rate. This study proposes a method based on the connection of encoder and decoder structure features to improve the DeconvNet network model. The model can retain the spatial structure information by recording the location of the pool index and applying it to the upper pool when being encoded. During decoding, the model can effectively extract features by connecting the corresponding feature layer of encoder and decoder. During model training, the pre-training model designed can effectively expand the data to solve the problem of model over-fitting. The experimental results show that, based on the proper adjustment of optimizer, learning rate and loss function, the accuracy of remote sensing images semantic segmentation in the validation database is about 95% by using the extended dataset for training, which is significantly improved compared with the DeconvNet and UNet network models.

    参考文献
    [1] Martha TR, Kerle N, Van Westen CJ, et al. Segment optimization and data-driven thresholding for knowledge-based landslide detection by object-based image analysis. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(12): 4928-4943. [doi: 10.1109/tgrs.2011.2151866
    [2] Yao XW, Han JW, Cheng G, et al. Semantic annotation of high-resolution satellite images via weakly supervised learning. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(6): 3660-3671. [doi: 10.1109/TGRS.2016.2523563
    [3] 李月臣, 杨华, 刘春霞, 等. 土地覆盖变化遥感检测方法. 水土保持研究, 2006, 13(1): 209-216. [doi: 10.3969/j.issn.1005-3409.2006.01.070
    [4] 潘朝. 多尺度显著性引导的高分辨率遥感影像建筑物提取. 科技创新与生产力, 2017, (5): 106-109. [doi: 10.3969/j.issn.1674-9146.2017.05.106
    [5] 黄亮, 宋晶. 一种改进迭代条件模型的遥感影像语义分割方法. 软件导刊, 2019, 18(1): 183-185
    [6] 李欣, 唐文莉, 杨博. 利用深度残差网络的高分遥感影像语义分割. 应用科学学报, 2019, 37(2): 282-290
    [7] 苏健民, 杨岚心, 景维鹏. 基于U-Net的高分辨率遥感图像语义分割方法. 计算机工程与应用, 2019, 55(7): 207-213. [doi: 10.3778/j.issn.1002-8331.1806-0024
    [8] Noh H, Hong S, Han B. Learning deconvolution network for semantic segmentation. Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile. 2015. 1520-1528.
    [9] Zeiler MD, Taylor GW, Fergus R. Adaptive deconvolutional networks for mid and high level feature learning. Proceedings of 2011 International Conference on Computer Vision. Washington, WA, USA. 2012. 2018-2025.
    [10] Dumoulin V, Visin F. A guide to convolution arithmetic for deep learning. arXiv: 1603.07285, 2016.
    [11] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany. 2015. 234-241.
    [12] Bjorck J, Gomes C, Selman B, et al. Understanding batch normalization. arXiv: 1806.02375, 2018.
    [13] Erb RJ. Introduction to backpropagation neural network computation. Pharmaceutical Research, 1993, 10(2): 165-170. [doi: 10.1023/A:1018966222807
    [14] Booth DE. The cross-entropy method. Taylor & Francis Group, 2008. https://www.tandfonline.com/doi/citedby/10.1198/tech.2008.s534?scroll=top&needAccess=true.
    [15] Mnih V. Machine learning for aerial image labeling[Ph.D. Thesis]. Canada: University of Toronto, 2013.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

尚群锋,沈炜,帅世渊.基于深度学习高分辨率遥感影像语义分割.计算机系统应用,2020,29(7):180-185

复制
分享
文章指标
  • 点击次数:1415
  • 下载次数: 3679
  • HTML阅读次数: 3680
  • 引用次数: 0
历史
  • 收稿日期:2019-12-01
  • 最后修改日期:2020-01-03
  • 在线发布日期: 2020-07-04
  • 出版日期: 2020-07-15
文章二维码
您是第11204110位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号