Comprehensive Study on Binary Classification for CNN-LNet Based Urban Change Detection Using Satellite Images
DOI:
https://doi.org/10.70112/ajcst-2025.14.1.4330Keywords:
Remote Sensing, Change Detection, Deep Learning (DL), Land Cover Labels, CNN-LNetAbstract
These days, a large array of images obtained from various satellites are available due to the rapid development of remote sensing (RS) technology. Change detection from remote sensing images is a crucial component of remote sensing analysis and is applied extensively in various fields, including catastrophe assessment, urban planning, and resource monitoring. Due to their practical applications, deep learning (DL) algorithms are now widely utilized in change detection processes. However, despite the substantial amount of raw satellite data currently available, the labels for various forms of land cover remain limited. Land cover labels, typically produced through labor-intensive manual processes, are essential for training and validating machine learning models. The effectiveness of statistical learning techniques heavily depends on the availability of extensive and accurately labeled datasets, making the lack of labeled data a significant challenge. Change detection refers to the quantitative evaluation and analysis of surface changes in objects or phenomena during two different time periods. The study presented in this paper demonstrates CNN-LNet-based change detection for binary classification in satellite images, achieving an accuracy of 95.24%, sensitivity of 97.7%, and an F1-score of 97.14% in identifying locations where significant changes have occurred.
References
Q. Zhu, X. Guo, Z. Li, and D. Li, “A review of multi-class change detection for satellite remote sensing imagery,” Geo-spatial Information Science, vol. 27, no. 1, pp. 1–15, 2024.
S. Shah Heydari, J. C. Vogeler, O. S. Cardenas-Ritzert, S. K. Filippelli, M. McHale, and M. Laituri, “Multi-tier land use and land cover mapping framework and its application in urbanization analysis in three African countries,” Remote Sensing, vol. 16, no. 14, p. 2677, 2024.
A. Safonova, G. Ghazaryan, S. Stiller, M. Main-Knorn, C. Nendel, and M. Ryo, “Ten deep learning techniques to address small data problems with remote sensing,” International Journal of Applied Earth Observation and Geoinformation, vol. 125, p. 103569, 2023.
J. S. Babu and T. Sudha, “A novel remote sensing technology on land analysis use change detection,” Asian Journal of Computer Science and Technology, vol. 8, no. 3, pp. 10–14, 2019.
A. Vali, S. Comai, and M. Matteucci, “An automated machine learning framework for adaptive and optimized hyperspectral-based land cover and land-use segmentation,” Remote Sensing, vol. 16, no. 14, p. 2561, 2024.
S. Cao, Y. Tang, E. Yan, J. Jiang, and D. Mo, “Bridging domains and resolutions: Deep learning-based land cover mapping without matched labels,” Remote Sensing, vol. 16, no. 8, p. 1449, 2024.
B. R. Adhikari, S. Gautam, T. P. P. Sharma, and S. Devkota, “Land cover, land use change and its implication to disasters in the Hindu Kush Himalayan region,” in Surface Environments and Human Interactions: Reflections from Asia. Springer, 2024, pp. 7–27.
R. Mostafazadeh and H. Talebi Khiavi, “Landscape change assessment and its prediction in a mountainous gradient with diverse land-uses,” Environment, Development and Sustainability, vol. 26, no. 2, pp. 3911–3941, 2024.
S. Singh et al., “Fruit disease detection using convolution neural network approach,” Asian Journal of Computer Science and Technology, vol. 7, no. 2, pp. 62–65, 2018.
T. D. Singh and R. Bharti, “Detection and classification of plant diseases in crops (Solanum lycopersicum) due to pests using deep learning techniques: A review,” Asian Journal of Computer Science and Technology, vol. 12, no. 2, pp. 39–47, 2023.
Y. Kumar and V. Singh, “A comprehensive hybrid model for language-independent defect prediction in microservices architecture,” Asian Journal of Computer Science and Technology, vol. 12, no. 2, pp. 48–65, 2023.
I. Bidari, S. Chickerur, A. Kulkarni, A. Mahajan, A. Nikkam, and S. Akella, “Change detection and classification using hyperspectral imagery,” in 2021 2nd International Conference on Range Technology (ICORT), IEEE, 2021, pp. 1–6.
A. Tahraoui, R. Kheddam, and A. Belhadj-Aissa, “Land change detection in Sentinel-2 images using IR-MAD and deep neural network,” in 2023 International Conference on Earth Observation and Geospatial Information (ICEOGI), IEEE, 2023, pp. 1–6.
H. Fang, S. Guo, X. Wang, S. Liu, C. Lin, and P. Du, “Automatic urban scene-level binary change detection based on a novel sample selection approach and advanced triplet neural network,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–18, 2023.
H. He, J. Yan, D. Liang, Z. Sun, J. Li, and L. Wang, “Time-series land cover change detection using deep learning-based temporal semantic segmentation,” Remote Sensing of Environment, vol. 305, p. 114101, 2024.
L. Martinez-Sanchez, L. See, M. Yordanov, A. Verhegghen, N. Elvekjaer, D. Muraro, R. d’Andrimont, and M. Van der Velde, “Automatic classification of land cover from LUCAS in-situ landscape photos using semantic segmentation and a random forest model,” Environmental Modelling & Software, vol. 172, p. 105931, 2024.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Centre for Research and Innovation
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
