Pendeteksian Lahan dari Citra High Resolution Remote Sensing Berbasis Metode Single-class Convolutional Neural Network
DOI:
https://doi.org/10.26418/jp.v11i1.89587Keywords:
convolutional neural network, deep learning, kelas tunggal, klasifikasi lahan, pemrosesan citraAbstract
pendektesian lahan dengan memanfaatkan citra satelit telah berkembang pesat sebagai suatu solusi dalam mengidentifikasi jenis lahan. Namun, hal ini terkendala oleh keterbatasan algoritma seperti convolutional neural network atau CNN dalam mengidentifikasi permukaan lahan dengan citra yang mirip. Penelitian ini mengagas konsep CNN baru dengan mengabungkan sekelompok model kecil yang hanya mempelajari 1 kelas, yang disebut sebagai single-class CNN atau SC-CNN. Hasil validasi pada citra satelit Gaofen-2 menunjukan bahwa metode SC-CNN mampu meningkatkan akurasi model prediktif dari metode CNN sebesar 3% dalam mengidentifikasi permukaan lahan. Lebih lanjut, meskipun dengan menggunakan data yang lebih sedikit (hanya 480 citra), metode SC-CNN menunjukan kualitas prediktif yang sama dengan metode CNN yang menggunakan 800 citra. Hasil ini menunjukan potensi dari SC-CNN dalam mengklasifikasikan citra satelit, sekaligus sebagai metode klasifikasi gambar dengan jumlah citra yang terbatas.
References
X.-Y. Tong et al., “Land-cover classification with high-resolution remote sensing images using transferable deep models,†Remote Sens Environ, vol. 237, p. 111322, Feb. 2020, doi: 10.1016/j.rse.2019.111322.
R. Deticio et al., “Application of a U-Net Segmentation Model in Land Cover Classification for Use in Automated Data Prefiltering Onboard Nanosatellites,†in TENCON 2023 - 2023 IEEE Region 10 Conference (TENCON), IEEE, Oct. 2023, pp. 71–75. doi: 10.1109/TENCON58879.2023.10322528.
R. Nedd, K. Light, M. Owens, N. James, E. Johnson, and A. Anandhi, “A Synthesis of Land Use/Land Cover Studies: Definitions, Classification Systems, Meta-Studies, Challenges and Knowledge Gaps on a Global Landscape,†Land (Basel), vol. 10, no. 9, p. 994, Sep. 2021, doi: 10.3390/land10090994.
Y. Qichi et al., “A novel alpine land cover classification strategy based on a deep convolutional neural network and multi-source remote sensing data in Google Earth Engine,†GIsci Remote Sens, vol. 60, no. 1, Dec. 2023, doi: 10.1080/15481603.2023.2233756.
S. Suresh and S. Lal, “A metaheuristic framework based automated Spatial-Spectral graph for land cover classification from multispectral and hyperspectral satellite images,†Infrared Phys Technol, vol. 105, p. 103172, Mar. 2020, doi: 10.1016/j.infrared.2019.103172.
H. E. E. S. Haga, A. B. Nilsen, H. A. Ullerud, and A. Bryn, “Quantification of accuracy in fieldâ€based land cover maps: A new method to separate different components,†Appl Veg Sci, vol. 24, no. 2, Apr. 2021, doi: 10.1111/avsc.12578.
G. Cecili, P. De Fioravante, P. Dichicco, L. Congedo, M. Marchetti, and M. Munafò, “Land Cover Mapping with Convolutional Neural Networks Using Sentinel-2 Images: Case Study of Rome,†Land (Basel), vol. 12, no. 4, p. 879, Apr. 2023, doi: 10.3390/land12040879.
N. Memon, H. Parikh, S. B. Patel, D. Patel, and V. D. Patel, “Automatic land cover classification of multi-resolution dualpol data using convolutional neural network (CNN),†Remote Sens Appl, vol. 22, p. 100491, Apr. 2021, doi: 10.1016/j.rsase.2021.100491.
Susana, C. Fatichah, and A. Saikhu, “Classification of very high-resolution remote sensing image ground objects using deep learning,†in 2023 14th International Conference on Information & Communication Technology and System (ICTS), IEEE, Oct. 2023, pp. 111–116. doi: 10.1109/ICTS58770.2023.10330839.
T. Kattenborn, J. Leitloff, F. Schiefer, and S. Hinz, “Review on Convolutional Neural Networks (CNN) in vegetation remote sensing,†ISPRS Journal of Photogrammetry and Remote Sensing, vol. 173, pp. 24–49, Mar. 2021, doi: 10.1016/j.isprsjprs.2020.12.010.
D. Bhatt et al., “CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope,†Electronics (Basel), vol. 10, no. 20, p. 2470, Oct. 2021, doi: 10.3390/electronics10202470.
Y. Li, J. Nie, and X. Chao, “Do we really need deep CNN for plant diseases identification?†Comput Electron Agric, vol. 178, p. 105803, Nov. 2020, doi: 10.1016/j.compag.2020.105803.
E. Arkin, N. Yadikar, X. Xu, A. Aysa, and K. Ubul, “A survey: object detection methods from CNN to transformer,†Multimed Tools Appl, vol. 82, no. 14, pp. 21353–21383, Jun. 2023, doi: 10.1007/s11042-022-13801-3.
S. Pan et al., “Land-cover classification of multispectral LiDAR data using CNN with optimized hyper-parameters,†ISPRS Journal of Photogrammetry and Remote Sensing, vol. 166, pp. 241–254, Aug. 2020, doi: 10.1016/j.isprsjprs.2020.05.022.
R. Fan, R. Feng, L. Wang, J. Yan, and X. Zhang, “Semi-MCNN: A Semisupervised Multi-CNN Ensemble Learning Method for Urban Land Cover Classification Using Submeter HRRS Images,†IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 13, pp. 4973–4987, 2020, doi: 10.1109/JSTARS.2020.3019410.
T. Lu, L. Wan, S. Qi, and M. Gao, “Land Cover Classification of UAV Remote Sensing Based on Transformer–CNN Hybrid Architecture,†Sensors, vol. 23, no. 11, p. 5288, Jun. 2023, doi: 10.3390/s23115288.
D. Ienco, Y. J. E. Gbodjo, R. Gaetano, and R. Interdonato, “Weakly Supervised Learning for Land Cover Mapping of Satellite Image Time Series via Attention-Based CNN,†IEEE Access, vol. 8, pp. 179547–179560, 2020, doi: 10.1109/ACCESS.2020.3024133.
A. M. Tegegne, “Applications of Convolutional Neural Network for Classification of Land Cover and Groundwater Potentiality Zones,†Journal of Engineering, vol. 2022, pp. 1–8, Jan. 2022, doi: 10.1155/2022/6372089.
A. M. Censi, D. Ienco, Y. J. E. Gbodjo, R. G. Pensa, R. Interdonato, and R. Gaetano, “Attentive Spatial Temporal Graph CNN for Land Cover Mapping From Multi Temporal Remote Sensing Data,†IEEE Access, vol. 9, pp. 23070–23082, 2021, doi: 10.1109/ACCESS.2021.3055554.
D. Fitton, E. Laurens, N. Hongkarnjanakul, C. Schwob, and L. Mezeix, “Land cover classification through Convolutional Neur-al Network model assembly: A case study of a local rural area in Thailand,†Remote Sens Appl, vol. 26, p. 100740, Apr. 2022, doi: 10.1016/j.rsase.2022.100740.
F. Zhang and X. Yang, “Improving land cover classification in an urbanized coastal area by random forests: The role of variable selection,†Remote Sens Environ, vol. 251, p. 112105, Dec. 2020, doi: 10.1016/j.rse.2020.112105.
P. Zeng, “Research on Similar Animal Classification Based on CNN Algorithm,†J Phys Conf Ser, vol. 2132, no. 1, p. 012001, Dec. 2021, doi: 10.1088/1742-6596/2132/1/012001.
S. Y. Chaganti, I. Nanda, K. R. Pandi, T. G. N. R. S. N. Prudhvith, and N. Kumar, “Image Classification using SVM and CNN,†in 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA), IEEE, Mar. 2020, pp. 1–5. doi: 10.1109/ICCSEA49143.2020.9132851.
A. Patil and M. Rane, “Convolutional Neural Networks: An Overview and Its Applications in Pattern Recognition,†2021, pp. 21–30. doi: 10.1007/978-981-15-7078-0_3.
N. Ketkar and J. Moolayil, “Convolutional Neural Networks,†in Deep Learning with Python, Berkeley, CA: Apress, 2021, pp. 197–242. doi: 10.1007/978-1-4842-5364-9_6.
Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,†IEEE Trans Neural Netw Learn Syst, vol. 33, no. 12, pp. 6999–7019, Dec. 2022, doi: 10.1109/TNNLS.2021.3084827.
X.-Y. Tong et al., “Land-cover classification with high-resolution remote sensing images using transferable deep models,†Remote Sens Environ, vol. 237, p. 111322, Feb. 2020, doi: 10.1016/j.rse.2019.111322.
