skip to main content
10.1145/3473465.3473478acmotherconferencesArticle/Chapter ViewAbstractPublication PagesitccConference Proceedingsconference-collections
research-article

Multi Scale UNet Encoder-Decoder Network for Building Extraction

Published: 05 October 2021 Publication History

Abstract

Buildings in remote sensing images have large scale differences and complex shapes. And there are often distractors with visual features similar to buildings in complex scenes. The traditional methods used to extract buildings are limited by the ability of feature representation, resulting in low accuracy and low universality. The semantic segmentation network based on the Encoder-Decoder structure can automatically learn multi-level building feature representation from the data set, and achieve end-to-end building extraction. UNet is a typical semantic segmentation Encoder-Decoder network, but UNet cannot explore enough building information. Small buildings are easy to be missed, large buildings with complex colors and shapes are incompletely extracted, boundary segmentation is inaccurate. And the network is easily affected by roads, trees, shadows and other distractors. Therefore, this article improves UNet and proposes a multi-scale Encoder-Decoder network to learn multi-scale and distinguishable features to better identify buildings and backgrounds. We experiment with the improved network and the classic U-Net on two data sets, and show that the multi-scale Encoder-Decoder network can effectively improve the accuracy of building extraction.

References

[1]
hao W S W, Zhang Y Z Y, Wang L W L, Extraction building based on adaptive detection algorithm of key points[J]. 2011.
[2]
Wang Dan. A high-resolution remote sensing image building edge extraction method[J]. Environmental Protection and Circular Economy, 2009, 29(10): 26-28.
[3]
Ok A O . Automated detection of buildings from single VHR multispectral images using shadow information and graph cuts[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 86(12):21–40.
[4]
Maltezos E, Doulamis N, Doulamis A, Deep convolutional neural networks for building extraction from orthoimages and dense image matching point clouds[J]. Journal of Applied Remote Sensing, 2017, 11(4):042620-1-042620-22.
[5]
Huang X, Zhang L . A Multidirectional and Multiscale Morphological Index for Automatic Building Extraction from Multispectral GeoEye-1 Imagery[J]. Photogrammetric Engineering & Remote Sensing, 2011, 77(7):721-732.
[6]
Ji Shunping,Wei Shiqing.Convolutional neural network and open source dataset method for building extraction from remote sensing images[J].Journal of Surveying and Mapping,2019,48(04):448-459.
[7]
Ronneberger O, Fischer P, Brox T . U-Net: Convolutional Networks for Biomedical Image Segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2015.
[8]
Zhao H, Shi J, Qi X, Pyramid Scene Parsing Network[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017.
[9]
Chen L C, Zhu Y, Papandreou G, Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[J]. 2018.
[10]
Howard A, Sandler M, Chu G, Searching for MobileNetV3[J]. 2019.
[11]
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770–78.
[12]
Simonyan K, Zisserman A (2015) Very deep convolutionalnetworks for large -scale image recognition. In: ICLR.
[13]
Ma J, Wu L, Tang X, Building Extraction of Aerial Images by a Global and Multi-Scale Encoder-Decoder Network[J]. Remote Sensing, 2020, 12(15):2350.
[14]
Shao Z, Tang P, Wang Z, BRRNet: A Fully Convolutional Neural Network for Automatic Building Extraction From High-Resolution Remote Sensing Images[J]. Remote Sensing, 2020, 12(6):1050.
[15]
Wu G, Shao X, Guo Z, Automatic Building Segmentation of Aerial Imagery Using Multi-Constraint Fully Convolutional Networks[J]. Remote Sensing, 2018, 10(3):407.
[16]
Ji S, Wei S, Lu M . A scale robust convolutional neural network for automatic building extraction from aerial and satellite imagery[J]. International Journal of Remote Sensing, 2018:1-15.
[17]
Szegedy C, Vanhoucke V, Ioffe S, Rethinking the Inception Architecture for Computer Vision[J]. IEEE, 2016:2818-2826.TUG 2017. Institutional members of the LaTeX Users Group. Retrieved May 27, 2017 from http://wwtug.org/instmem.html

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ITCC '21: Proceedings of the 2021 3rd International Conference on Information Technology and Computer Communications
June 2021
126 pages
ISBN:9781450389884
DOI:10.1145/3473465
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 October 2021

Permissions

Request permissions for this article.

Check for updates

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Funding Sources

Conference

ITCC 2021

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 97
    Total Downloads
  • Downloads (Last 12 months)5
  • Downloads (Last 6 weeks)0
Reflects downloads up to 14 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media