Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 9, Issue 1, 2025

A Comparative Study of Deep Learning-Based Semantic Segmentation Methods for High-Resolution Remote Sensing Imagery

Download as PDF

DOI: 10.23977/acss.2025.090102 | Downloads: 35 | Views: 719

Author(s)

Yongsong Jiang 1

Affiliation(s)

1 School of Information Science and Technology, Yunnan Normal University, Yunnan, Kunming, China

Corresponding Author

Yongsong Jiang

ABSTRACT

Remote sensing image information extraction plays a crucial role in land use planning, environmental monitoring, and natural disaster assessment. However, traditional machine learning-based methods often face challenges such as high computational complexity and limited feature representation ability when processing large-scale remote sensing data, leading to difficulties in meeting both efficiency and accuracy requirements. With the rapid development of deep learning, its application to remote sensing data processing has become a powerful solution. This paper uses the standard Potsdam dataset provided by ISPRS and tests and compares the accuracy of several commonly used deep learning convolutional networks, including SegNet, PspNet, Unet, UNet++, DeepLab V3+, SegFormer, and SegVit, in remote sensing image information extraction. Experimental results show that SegVit performs exceptionally well in accuracy, detail preservation, and edge clarity, achieving higher precision compared to other networks. This finding provides an effective solution for remote sensing image information extraction and offers strong support for research and applications in related fields. It is worth noting that although SegVit excels in accuracy, it may require more computational resources and time during training and inference. Therefore, in practical applications, it is necessary to balance efficiency and accuracy and choose a network model that suits the specific task requirements.

KEYWORDS

Deep Learning; Convolutional Neural Networks; Remote Sensing Imagery; Semantic Segmentation

CITE THIS PAPER

Yongsong Jiang, A Comparative Study of Deep Learning-Based Semantic Segmentation Methods for High-Resolution Remote Sensing Imagery. Advances in Computer, Signals and Systems (2025) Vol. 9: 8-13. DOI: http://dx.doi.org/10.23977/acss.2025.090102.

REFERENCES

[1] Likas A, Vlassis N, Verbeek J J. The global k-means clustering algorithm[J]. Pattern recognition, 2003, 36(2): 451-461.
[2] Carson C, Belongie S, Greenspan H, et al. Blobworld: Image segmentation using expectation-maximization and its application to image querying [J]. IEEE Transactions on pattern analysis and machine intelligence, 2002, 24(8): 1026-1038. 
[3] Shuang L, Sheng-yan D, Le-xiang Q. The decision tree classification and its application research in land cover[J]. Remote sensing technology and application, 2011, 17(1): 6-11. 
[4] Song M, Civco D. Road extraction using SVM and image segmentation[J]. Photogrammetric Engineering & Remote Sensing, 2004, 70(12): 1365-1371. 
[5] Guindon S, Gascuel O. A simple, fast, and accurate algorithm to estimate large phylogenies by maximum likelihood [J]. Systematic biology, 2003, 52(5): 696-704.
[6] Jordan M I, Mitchell T M. Machine learning: Trends, perspectives, and prospects[J]. Science, 2015, 349(6245): 255-260. 
[7]Gu Xiaotian, Gao Xiaohong, Ma Huijuan, et al. Comparison of machine learning methods for land use/land cover classification in the complicated terrain regions [J]. Remote Sensing Technology and Application, 2019, 34(1): 59-69. 
[8] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25. 
[9] Deng J, Dong W, Socher R, et al. Imagenet: A large-scale hierarchical image database[C]//2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009: 248-255. 
[10] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3431-3440. 
[11] Wang Y, Tan L, Wang G, et al. Study on the impact of spatial resolution on fractional vegetation cover extraction with single-scene and time-series remote sensing data[J]. Remote Sensing, 2022, 14(17): 4165. 
[12] Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 801-818. 
[13] Zhang B, Tian Z, Tang Q, et al. Segvit: Semantic segmentation with plain vision transformers[J]. Advances in Neural Information Processing Systems, 2022, 35: 4971-4982. 

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 38553
Visits: 697934

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.