Abstract
Land type information is essential for urban planning, ecological monitoring and management. To improve ground class information extraction, the depth separable convolution operation and Dropout layer are added to the U-Net network structure. Additionally, the ReLU and TReLU functions are combined to create a ReLU-TReLU hybrid activation function, which is then used to create a method for extracting ground class information from remote sensing images based on IU-Net. The outcomes of the experiment demonstrated the ReLU-TReLU hybrid activation function’s quick convergence speed and robust learning capacity. Using accuracy, precision of producer, user accuracy, commission errors, omission errors, overall classification accuracy and Kappa coefficient as evaluation indicators, IU-Net achieved the highest test scores of 96.1%, 98.62%, 98.32%, 0.30, 0.90, 96.82% and 0.95, respectively. IU-Net had the lowest mistake rate and maximum accuracy of information extraction when compared to other approaches. Additionally, it often ran in less than 5 min, which is quicker and offers technical support for the land categorization project for the development of hilly urban green space.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
All data generated or analysed during this study are included in this published article.
References
Chan M, Ganti VG, Inan OT (2022) Respiratory Rate Estimation Using U-Net-Based Cascaded Framework from Electrocardiogram and Seismocardiogram Signals. IEEE J Biomed Health Inform 26(6):2481–2492. https://doi.org/10.1109/JBHI.2022.3144990
Chen T, Lu Z, Yang Y et al (2022) A Siamese Network Based U-Net for Change Detection in High Resolution Remote Sensing Images. IEEE J Selected Top Appl Earth Observ Remote Sensing 15:2357–2369. https://doi.org/10.1109/JSTARS.2022.3157648
Chra A, Verma S, Raghuvanshi AS et al (2022) CCsNeT: Automated Corpus Callosum segmentation using fully convolutional network based on U-Net. Biocybern Biomed Eng 42(1):187–203. https://doi.org/10.1016/j.bbe.2021.12.008
Gao K, Huang L, Zheng Y (2022) Fault Detection on Seismic Structural Images Using a Nested Residual U-Net. IEEE Trans Geosci Remote Sens 60:1–15. https://doi.org/10.1109/TGRS.2021.3073840
Guang X, Biao Z, Ibrahim H (2020) Information extraction and dynamic evaluation of soil salinization with a remote sensing method in a typical county on the Huang-Huai-Hai Plain of China. Pedosphere 30(4):329-340. (CNKI:SUN:TRQY.0.2020–04–007)
Jiang M, Zhao Y, Chiu B (2021) Segmentation of common and internal carotid arteries from 3D ultrasound images using adaptive triple U-Net. Med Phys 48(9):5096–5114. https://doi.org/10.1002/mp.15127
Kothari NS, Meher SK, Panda G (2020) Improved Spatial Information Based Semisupervised Classification of Remote Sensing Images. IEEE J Selected Top Appl Earth Observ Remote Sens 13(99):329–340. https://doi.org/10.1109/JSTARS.2019.2961985
Li S, Zheng J, Li D (2021) Precise segmentation of non-enhanced computed tomography in patients with ischemic stroke based on multi-scale U-Net deep network model. Comput Meth Prog Biomed 208(5):106278.1-106278.5. https://doi.org/10.1016/j.cmpb
Lin CH, Wang TY (2021) A novel convolutional neural network architecture of multispectral remote sensing images for automatic material classification. Signal Proc Image Commun 97(105):1163291–116329. https://doi.org/10.1016/j.image.2021.116329
Lv Z, Li G, Jin Z, Benediktsson JA, Foody GM (2020) Iterative Training Sample Expansion to Increase and Balance the Accuracy of Land Classification From VHR Imagery. IEEE Trans Geosci Remote Sensing 59(1):139–150. https://doi.org/10.1109/TGRS.2020.2996064
Martins V, Kaleita A, Gelder B et al (2020) Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution. ISPRS J Photogram Remote Sensing 168:56–73. https://doi.org/10.1016/j.isprsjprs.2020.08.004
Mu Y, Li J, Luo T (2022) A Lightweight Model of VGG-U-Net for Remote Sensing Image Classification”. Comput, Mat Continuum 12:6195–6205. https://doi.org/10.32604/cmc.2022.026880
Park J, Choi J, Seol SJ et al (2021) A method for adequate selection of training data sets to reconstruct seismic field data using a convolutional U-Net. Geophysics 86(5):V375–V388. https://doi.org/10.1190/geo2019-0708.1
Pavl SD, Craus M (2023) Reaction-diffusion model applied to enhancing U-Net accuracy for semantic image segmentation. Discrete Contin Dynamical Syst - S 16(1):54–74. https://doi.org/10.3934/dcdss
Rajmohan G, Chinnappan CV, William A et al (2020) Revamping land coverage analysis using aerial satellite image mapping. Trans Emerg Telecommun Technol 32(7):e3927.1-e3927.15. https://doi.org/10.1002/ett.3927
Rohman B, Nishimoto M, Ogata K (2022) Reconstruction of Missing Ground-Penetrating Radar Traces Using Simplified U-Net. IEEE Geosci Remote Sensing Lett 19:1–5. https://doi.org/10.1109/LGRS.2021.3072028
Saba T, Akbar S, Kolivand H et al (2021) Automatic detection of papilledema through fundus retinal images using deep learning. Microscopy Res Technique 84(12):3066–3077. https://doi.org/10.1002/jemt.23865
Selvaraju RR, Cogswell M, Das A et al (2020) Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. Int J Comput Vision 128(2):336–359. https://doi.org/10.1007/s11263-019-01228-7
Shuai Y, Tuerhanjiang L, Shao C et al (2020) Re-understanding of land surface albedo and related terms in satellite-based retrievals. Big Data on Earth 4(1):45–67. https://doi.org/10.1080/20964471.2020.1716561
Tang Y, Yang P, Zhou Z et al (2021) Improving cloud type classification of ground-based images using region covariance descriptors. Atmospheric Measure Tech 14(1):737–747. https://doi.org/10.5194/amt-14-737-2021
Tian S, Dong Y, Feng R et al (2022) Mapping mountain glaciers using an improved U-Net model with cSE. Int J Dig Earth 15(1):463–477. https://doi.org/10.1080/17538947.2022.2036834
Tran TH, Tran DH, Do KL et al (2022) DCS-UNet: Dual-path Framework for Segmentation of Reflux Esophagitis Lesions from Endoscopic Images with U-Net-based Segmentation and Color/Texture Analysis. Vietnam J Comput Sci 10(2):217–242. https://doi.org/10.1142/S2196888822500385
Tunga PP, Singh V, Aditya VS et al (2020) U-Net Model Based Classification and Description of Brain Tumor in MRI Images. Int J Image Graph 14(1):737–747. https://doi.org/10.5194/amt-14-737-2021
Usman AM, Abdullah MK (2023) An Assessment of Building Energy Consumption Characteristics Using Analytical Energy and Carbon Footprint Assessment Model. Green Low-Carbon Eco 1(1):28–40. https://doi.org/10.47852/bonviewGLCE3202545
Vinard NA, Drijkoningen GG, Verschuur DJ (2022) Localizing microseismic events on field data using a U-Net-based convolutional neural network trained on synthetic data. Geophysics 87(2):KS33–KS43. https://doi.org/10.1109/TGRS.2021.3073840
Wei J, Mi L, Hu Y et al (2022) Effects of Lossy Compression on Remote Sensing Image Classification Based on Convolutional Sparse Coding. IEEE Geosci Remote Sensing Lett 19:1–5. https://doi.org/10.1109/LGRS.2020.3047789
Yong W (2020) Classification of High Resolution Satellite Images Using Improved U-Net. Int J Appl Mathematics Comput Sci 30(3):399–413. https://doi.org/10.34768/amcs-2020-0030
Zhang Y, He M, Chen Z et al (2021) Bridge-Net: Context-involved U-net with patch-based loss weight mapping for retinal blood vessel segmentation. Exp Syst with Appl 195(1):116526.1-116526.15. https://doi.org/10.1016/j.eswa.2022.116526
Funding
The research is supported by: Research Fund for Young Teachers of Forestry College of Inner Mongolia Agricultural University: Research and Application of Hohhot Landscape GIS Information System (No. DC2000001009).
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Yafeng Li, Yongzhi Yang, Xiaoyun Yan and Yingjie Li. The first draft of the manuscript was written by Yafeng Li and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing Interests
The authors report there is no competing interests to declare.
Additional information
Communicated by H. Babaie.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, Y., Yang, Y., Yan, X. et al. Engineering Applications of Urban Green Space Planning in Mountainous Areas: An Improved Structure-based RS Land Class Information Extraction Method for U-Net Networks. Earth Sci Inform 16, 4187–4198 (2023). https://doi.org/10.1007/s12145-023-01162-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01162-w