A Comprehensive Analysis of State-of-the-Art Transfer Learning Models for Remote Sensing Scene Classification
Keywords:
Remote sensing, Land Use Scene Classification, Image Classification, Computer Vision, Transfer LearningAbstract
Remote Sensing classification plays a significant role in numerous fields, such as Urban Planning, Environmental Monitoring, Land Management and Remote Sensing Analysis. The primary goal of this study is to compare the efficacy of DenseNet121, InceptionV3, and VGG16 as potential models for land use scene classification. To achieve this objective, a comprehensive experimental framework is constructed, encompassing data pre-processing, model training, and performance evaluation. The UC Merced dataset was augmented four times and then was utilized in this study. The dataset consists of high-definition aerial photos that cover a broad range of land use scenes, The models are refined through a process of fine-tuning, followed by a comprehensive assessment of their performance using a wide array of evaluation metrics. These metrics encompass Accuracy, Precision, Recall, F1-score, Inference Time, and Model Size for all three models. DenseNet121 exhibited superior performance in capturing fine-grained features, achieving an accuracy of 91.94%. InceptionV3 excelled in handling variations in scale and rotation and achieved a relatively higher accuracy of 92.45%, while VGG16 demonstrated a balance between simplicity and accuracy achieving an accuracy of 88.89%.
Downloads
References
Al-Doski, Jwan, Shattri B. Mansorl, and Helmi Zulhaidi Mohd Shafri. "Image classification in remote sensing." Department of Civil Engineering, Faculty of Engineering, University Putra, Malaysia 3.10 (2013).
R. Pires de Lima and K. Marfurt, “Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis,” Remote Sensing, vol. 12, no. 1, p. 86, Dec. 2019: http://dx.doi.org/10.3390/rs12010086
Weixun Zhou, Shawn Newsam, Congmin Li, Zhenfeng Shao, PatternNet: A benchmark dataset for performance evaluation of remote sensing image retrieval, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 145, Part A, 2018, Pages 197-209, ISSN 0924-2716, https://doi.org/10.1016/j.isprsjprs.2018.01.004.
Dhanaraj, K., & Angadi, D. P. (2022). Land use land cover mapping and monitoring urban growth using remote sensing and GIS techniques in Mangaluru, India. GeoJournal, 87(2), 1133-1159.
Netzband, M., Stefanov, W. L., & Redman, C. L. (2007). Remote sensing as a tool for urban planning and sustainability. Applied remote sensing for urban planning, governance and sustainability, 1- 23.
Skidmore, A. K., Bijker, W., Schmidt, K., & Kumar, L. (1997). Use of remote sensing and GIS for sustainable land management. ITC journal, 3(4), 302-315.
Ahmed, B., & Alam, A. (2022). Remote Sensing of Natural Hazards. MDPI, Basel.
Li, J., Pei, Y., Zhao, S., Xiao, R., Sang, X., & Zhang, C. (2020). A review of remote sensing for environmental monitoring in China. Remote Sensing, 12(7), 1130.
Xie, Y., Sha, Z., & Yu, M. (2008). Remote sensing imagery in vegetation mapping: a review. Journal of plant ecology, 1(1), 9-23.
Hall, A., Lamb, D. W., Holzapfel, B., & Louis, J. (2002). Optical remote sensing applications in viticulture‐a review. Australian journal of grape and wine research, 8(1), 36-47.
Thakur, P. K., Nikam, B. R., Garg, V., Aggarwal, S. P., Chouksey, A., Dhote, P. R., & Ghosh, S. (2017). Hydrological parameters estimation using remote sensing and GIS for Indian region: a review. Proceedings of the National Academy of Sciences, India Section A: Physical Sciences, 87, 641-659.
Davenport, G.. (2001). Remote sensing applications in forensic investigations. Historical Archaeology. 35. 87-100. 10.1007/BF03374530.
R. Pires de Lima and K. Marfurt, “Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis,” Remote Sensing, vol. 12, no. 1, p. 86, Dec. 2019, doi: 10.3390/rs12010086.
G. Cheng, X. Xie, J. Han, L. Guo and G. -S. Xia, "Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13, pp. 3735-3756, 2020, doi: 10.1109/JSTARS.2020.3005403.
J. Zhang, T. Li, X. Lu and Z. Cheng, "Semantic Classification of High-Resolution Remote-Sensing Images Based on Mid-level Features," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, no. 6, pp. 2343-2353, June 2016, doi: 10.1109/JSTARS.2016.2536943.
Maryam Mehmood, Ahsan Shahzad, Bushra Zafar, Amsa Shabbir, Nouman Ali, "Remote Sensing Image Classification: A Comprehensive Review and Applications", Mathematical Problems in Engineering, vol. 2022, Article ID 5880959, 24 pages, 2022. https://doi.org/10.1155/2022/588095
R. Naushad, T. Kaur, and E. Ghaderpour, “Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative Study,” Sensors, vol. 21, no. 23, p. 8083, Dec. 2021, doi: 10.3390/s21238083.
Esam Othman, Yakoub Bazi, Naif Alajlan, Haikel Alhichri & Farid Melgani (2016) Using convolutional features and a sparse autoencoder for land-use scene classification, International Journal of Remote Sensing, 37:10, 2149-2167, DOI: 10.1080/01431161.2016.1171928
Castelluccio, M., Poggi, G., Sansone, C., & Verdoliva, L. (2015). Land Use Classification in Remote Sensing Images by Convolutional Neural Networks. ArXiv, abs/1508.00092.
G. Cheng, C. Ma, P. Zhou, X. Yao and J. Han, "Scene classification of high resolution remote sensing images using convolutional neural networks," 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China, 2016, pp. 767-770, doi: 10.1109/IGARSS.2016.7729193.
A. Das and S. Chandran, "Transfer Learning with Res2Net for Remote Sensing Scene Classification," 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India, 2021, pp. 796-801, doi: 10.1109/Confluence51648.2021.9377148.
D. Zhang, Z. Liu and X. Shi, "Transfer Learning on EfficientNet for Remote Sensing image Classification," 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), Harbin, China, 2020, pp. 2255-2258, doi: 10.1109/ICMCCE51767.2020.00489.
S.-C. Hung, H.-C. Wu, and M.-H. Tseng, “Remote Sensing Scene Classification and Explanation Using RSSCNet and LIME,” Applied Sciences, vol. 10, no. 18, p. 6151, Sep. 2020, doi: 10.3390/app10186151.
M. Akhtar, I. Murtza, M. Adnan, and A. Saadia, “Cross-Domain Transfer Learning for Natural Scene Classification of Remote- Sensing Imagery,” Applied Sciences, vol. 13, no. 13, p. 7882, Jul. 2023, doi: 10.3390/app13137882.
Y. Bazi and F. Melgani, "Gaussian Process Approach to Remote Sensing Image Classification," in IEEE Transactions on Geoscience and Remote Sensing, vol. 48, no. 1, pp. 186-197, Jan. 2010, doi: 10.1109/TGRS.2009.2023983.
Bozinovski, Stevo. (2020). Reminder of the First Paper on Transfer Learning in Neural Networks, 1976. Informatica. 44. 10.31449/inf.v44i3.2828.
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014 Sep 4.
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 2818-2826).
Jianming Zhang , Chaoquan Lu , Xudong Li , Hye-Jin Kim, Jin Wang. A full convolutional network based on DenseNet for remote sensing scene classification[J]. Mathematical Biosciences and Engineering, 2019, 16(5): 3345-3367. doi: 10.3934/mbe.2019167
Ramoliya, D., Goel, P., Vaidya, J., & Vadaliya, P. (2022, September). University Indoor Scene Classification using Transfer Learning. In 2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 793-797). IEEE
Yi Yang and Shawn Newsam. 2010. Bag-of-visual-words and spatial extensions for land-use classification. In Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems (GIS '10). Association for Computing Machinery, New York, NY, USA, 270–279. https://doi.org/10.1145/1869790.186982
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
