Education, Science, Technology, Innovation and Life
Open Access
Sign In

Remote Sensing Image Segmentation and Extraction Based on U-Net Convolutional Neural Network Model

Download as PDF

DOI: 10.23977/jipta.2023.060111 | Downloads: 32 | Views: 1252


Chen Xiong 1, Jiaqi Huang 2


1 Xi'an Jiaotong University City College, Xi'an, 710000, China
2 Wuchang University of Technology, Wuhan, 430223, China

Corresponding Author

Chen Xiong


Remote sensing images are essential for quickly acquiring large-scale ground information. Segmentation and extraction of high-resolution remote sensing images are widely used in many fields, such as agricultural monitoring, urban and rural planning, and map production and updating. In this paper, a U-Net convolutional neural network model is built on the Tensor Flow framework. A data enhancement strategy is specially designed for the training task of remote sensing image parcel segmentation to enhance the model's generalization ability. The experimental results choose accuracy as the evaluation index, and the final model accuracy can reach 0.9440. The remote sensing image parcel segmentation method proposed in this paper has high training efficiency and is suitable for high-accuracy remote sensing image segmentation and extraction.


U-Net; Data Enhancement; Remote sensing images; Image Segmentation


Chen Xiong, Jiaqi Huang, Remote Sensing Image Segmentation and Extraction Based on U-Net Convolutional Neural Network Model. Journal of Image Processing Theory and Applications (2023) Vol. 6: 93-99. DOI:


[1] Yin Hao. Research on remote sensing image segmentation method based on convolutional neural network [D]. Shandong Agricultural University, 2021.
[2] Fu Xiuli, Li Lingping, Mao Kebiao et al. Remote sensing image classification based on convolutional neural network model [J]. High Technology Communication, 2017, 27(03): 203-212.
[3] Zhao Danxin, Sun Shengli. A new method of aircraft target detection based on ResNet for remote sensing images [J]. Electronic Design Engineering, 2018, 26(22): 164-168.
[4] Qu XY, Zhang E. Remote sensing image parcel target classification based on active learning [J]. Computers and Modernization, 2021(11): 50-55+60.
[5] Yang JY, Zhou ZX, Du ZJR, Xu QQ, Yin H, Liu R. Extraction of rural construction land based on SegNet semantic model for high-resolution remote sensing images [J]. Journal of Agricultural Engineering, 2019, 35(05): 251-258.
[6] Marco Castelluccio, Giovanni Poggi, Carlo Sansone, Luisa Verdoliva. Land Use Classification in Remote Sensing Images by Convolutional Neural Networks. [J]. CoRR, 2015, abs/1508.00092.
[7] Baoxuan Jin, Peng Ye, Xueying Zhang, Weiwei Song, Shihua Li. Object-Oriented Method Combined with Deep Convolutional Neural Networks for Land-Use- Type Classification of Remote Sensing Images [J]. Journal of the Indian Society of Remote Sensing, 2019, 47(6).

Downloads: 1452
Visits: 107569

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.