Remote sensing image feature segmentation method based on deep learning

Yan-shan SHEN; A-chuan WANG

doi:10.37188/CJLCD.2020-0294

您当前的位置：

首页 >

文章列表页 >

Remote sensing image feature segmentation method based on deep learning

Image Processing | 更新时间：2021-04-28

- Remote sensing image feature segmentation method based on deep learning
- Chinese Journal of Liquid Crystals and Displays Vol. 36, Issue 5, Pages: 733-740(2021)
- 作者机构：
  
  东北林业大学信息与计算机工程学院, 黑龙江哈尔滨 150000
- 作者简介：
- 基金信息：
  
  Natural Science Foundation of Heilongjiang Province(C201414);Harbin Foundation for Good Leaders of Disciplines(2014RFXXJ040)
- DOI：10.37188/CJLCD.2020-0294
  CLC： TP391
- Received：03 November 2020，
  
  Revised：25 November 2020，
  
  Published：2021-05
- 稿件说明：
移动端阅览
Yan-shan SHEN, A-chuan WANG. Remote sensing image feature segmentation method based on deep learning[J]. Chinese journal of liquid crystals and displays, 2021, 36(5): 733-740.
DOI：

Yan-shan SHEN, A-chuan WANG. Remote sensing image feature segmentation method based on deep learning[J]. Chinese journal of liquid crystals and displays, 2021, 36(5): 733-740. DOI： 10.37188/CJLCD.2020-0294.

摘要

针对传统方法难以同时有效地进行多目标分割，现有基于全卷积神经网络的地物分类方法在复杂场景下分类精度不高的问题，提出了一种基于U-net改进的全卷积神经网络DL-Unet，实现了对遥感图像不同类别地物的有效分割。该网络改进了传统的卷积方式，引入扩张卷积，在不增加网络参数的同时增大感受野。针对遥感影像中地物类别不均衡的问题，使用带权重的交叉熵作为模型的损失函数，有效克服了模型的选择偏好。对预测结果采用了相对多数投票策略进一步提高了各个地物类别的像素准确率(PA)。实验结果表明，该模型在各地物类别的平均像素准确率(MPA)和均交并比(MIoU)上相较于经典U-net网络分别提高了5.94%和9.45%，实现了对地物信息的有效分割。

Abstract

In view of the difficulty of traditional methods for simultaneous and effective multi-target segmentation

the existing ground object classification methods based on fully convolutional neural networks have low classification accuracy in complex scenes

this paper proposes an improved encoder-decoder based on the U-shaped network structure DL-Unet

which realizes the effective segmentation of remote sensing images. This network improves the traditional convolution method and introduces the expanded convolution

which increases the receptive field without increasing the network parameters. Aiming at the problem of imbalance in the clssification of featares in remote sensing images

weighted cross-entropy is used as the loss function of the model

which effectively overcomes the selection preference of the model function of the model effectively. The relative majority voting strategy is adopted for the prediction results to further improve the pixel accuracy (PA) of each feature category. The experimental results show that the mean pixel accuracy (MPA) and mean intersection over union (MIoU) of this model are improved by 5.94% and 9.45% respectively compared with the classic U-net

which verifies that the method in this paper is an effective remote sensing image classification method.

关键词

Keywords

references

林晨曦 , 周艺 , 王世新 , 等 . 基于变差函数的中高分辨率SAR影像农村建筑区提取 . 中国图象图形学报 , 2016 . 21 ( 5 ): 674 - 682 .

C X LIN , Y ZHOU , S X WANG , 等 . Variogram-based rural build-up area extraction from middle and high resolution SAR images . Journal of Image and Graphics , 2016 . 21 ( 5 ): 674 - 682 .

李亮 , 申学林 , 李胜 , 等 . 一种综合光谱、纹理、结构特征的高分辨率遥感影像变化检测方法 . 测绘通报 , 2019 . ( S1 ): 113 - 118 . https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB2019S1025.htm https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB2019S1025.htm .

L LI , X L SHEN , S LI , 等 . A change detection method by combining spectral, textural and structural features for VHR remote sensing imagery . Bulletin of Surveying and Mapping , 2019 . ( S1 ): 113 - 118 . https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB2019S1025.htm https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB2019S1025.htm .

惠振阳 , 胡友健 . 机载LiDAR点云中道路的提取方法 . 测绘科学 , 2017 . 42 ( 3 ): 70 - 74 .

Z Y HUI , Y J HU . A review on road extraction methods from airborne LiDAR . Science of Surveying and Mapping , 2017 . 42 ( 3 ): 70 - 74 .

胡唯 , 胡庆武 , 艾明耀 . 多星形先验和图割的遥感影像交互式分割 . 遥感信息 , 2016 . 31 ( 2 ): 19 - 23 . DOI: 10.3969/j.issn.1000-3177.2016.02.004 http://doi.org/10.3969/j.issn.1000-3177.2016.02.004 .

W HU , Q W HU , M Y AI . Interactive remote sensing image segmentation based on multiple star prior and graph cuts . Remote Sensing Information , 2016 . 31 ( 2 ): 19 - 23 . DOI: 10.3969/j.issn.1000-3177.2016.02.004 http://doi.org/10.3969/j.issn.1000-3177.2016.02.004 .

E SHELHAMER , J LONG , T DARRELL . Fully convolutional networks for semantic segmentation . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 . 39 ( 4 ): 640 - 651 . DOI: 10.1109/TPAMI.2016.2572683 http://doi.org/10.1109/TPAMI.2016.2572683 .

RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]// Proceedings of the 18 th International Conference on Medical Image Computing and Computer-Assisted Intervention . Munich: Springer, 2015.

V BADRINARAYANAN , A KENDALL , R CIPOLLA . SegNet: a deep convolutional encoder-decoder architecture for image segmentation . Transactions on Pattern Analysis and Machine Intelligence , 2017 . 39 ( 12 ): 2481 - 2495 . DOI: 10.1109/TPAMI.2016.2644615 http://doi.org/10.1109/TPAMI.2016.2644615 .

周鹏 , 姚剑敏 , 林志贤 , 等 . 融合注意力机制的移动端人像分割网络 . 液晶与显示 , 2020 . 35 ( 6 ): 547 - 554 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203506.0547 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203506.0547 .

P ZHOU , J M YAO , Z X LIN , 等 . Mobile-based portrait segmentation network with attention mechanism . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 6 ): 547 - 554 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203506.0547 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20203506.0547 .

ZHAO H S, SHI J P, QI X J, et al . Pyramid scene parsing network[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 2881-2890.

张哲晗 , 方薇 , 杜丽丽 , 等 . 基于编码-解码卷积神经网络的遥感图像语义分割 . 光学学报 , 2020 . 40 ( 3 ): 0310001 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB202003005.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB202003005.htm .

Z H ZHANG , W FANG , L L DU , 等 . Semantic segmentation of remote sensing image based on encoder-decoder convolutional neural network . Acta Optica Sinica , 2020 . 40 ( 3 ): 0310001 https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB202003005.htm https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB202003005.htm .

陈献明 , 王阿川 , 王春艳 . 基于深度学习的木材表面缺陷图像检测 . 液晶与显示 , 2019 . 34 ( 9 ): 879 - 887 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193409.0879 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193409.0879 .

X M CHEN , A C WANG , C Y WANG . Image detection of wood surface defects based on deep learning . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 9 ): 879 - 887 . http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193409.0879 http://cjlcd.lightpublishing.cn/thesisDetails#10.3788/YJYXS20193409.0879 .

YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[C]// International Conference on Learning Representations . Caribe Hilton: IEEE, 2016.

X GLOROT , A BORDES , Y BENGIO . Deep sparse rectifier neural networks . Journal of Machine Learning Research , 2011 . 15 315 - 323 . http://www.researchgate.net/publication/215616967_Deep_Sparse_Rectifier_Neural_Networks http://www.researchgate.net/publication/215616967_Deep_Sparse_Rectifier_Neural_Networks .

CLEVERT D A, UNTERTHINER T, HOCHREITER S. Fast and accurate deep network learning by Exponential Linear Units (ELUs)[C]// Proceedings of the 4 th International Conference on Learning Representations . San Juan, Puerto Rico: IEEE, 2016.

IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]// Proceedings of the 32 nd International Conference on International Conference on Machine Learning . Lille: ACM, 2015.

景庄伟 , 管海燕 , 彭代峰 , 等 . 基于深度神经网络的图像语义分割研究综述 . 计算机工程 , 2020 . 46 ( 10 ): 1 - 17 .

Z W JING , H Y GUAN , D F PENG , 等 . Survey of research in image semantic segmentation based on deep neural network . Computer Engineering , 2020 . 46 ( 10 ): 1 - 17 .

Views

176

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Scene recognition based on deep metric learning and semantic segmentation

Development of AOI inspection of Mura defects on TFT-LCD surface

FRKDNet： feature refine semantic segmentation network based on knowledge distillation

High resolution scene parsing network based on semantic segmentation

Related Author

Yan-shan SHEN

A-chuan WANG

JIA Xuan

ZHANG Ye

CHANG Xuling

SUN Jianbo

CHEN Zekang

SHEN Yi

Related Institution

College of Information and Computer Engineering， Northeast Forestry University

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

College of Engineering， Shantou University

Guangdong Provincial Key Laboratory of Automotive Display and Touch Technologies

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰