Combination of UAV Images and DSM for Land Cover Classification using Convolutional Neural Network
Main Article Content
Abstract
Machine learning applies predominantly to the classification of the satellite images, aerial photo, unmanned aerial vehicle (UAV) data, point clouds with considerable achievements. However, the dynamic and complex structures of land surface prevent accurate land cover segregation through built-in models, and there is a crucial need to investigate novel ones. This study integrates Catboost into a Convolutional neural network for land cover classification from UAV images, with a case study in Hanoi. The combination of these images and Digital surface model to form the input datasets. The results show that the overall accuracy reaches 91,5%, which is relatively higher than other comparing methods. The proposal model can be used as an alternative method for land cover classification.
Keywords:
UAV, Convolutional neural network, catboost, Hanoi
References
[1] D. Marcos, M. Volpi, B. Kellenberger, D. Tuia, Land Cover Mapping at Very High Resolution with Rotation Equivariant Cnns: Towards Small yet Accurate Models, ISPRS Journal of Photogrammetry and Remote Sensing Vol. 145, 2018, pp. 96-107, https://doi.org/10.1016/j.isprsjprs.2018.01.021.
[2] H. Wang, Y. Wang, Q. Zhang, S. Xiang, C. Pan, Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images, Remote Sensing Vol. 9, No. 5, 2017, 10.3390/rs9050446.
[3] W. Zhou, S. Newsam, C. Li, Z. Shao, Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval, Remote Sensing Vol. 9, No. 5, 2017, https://doi.org/10.3390/rs9050489.
[4] S. Srivastava, J. E. V. Muñoz, D. Tuia, Understanding Urban Landuse from the above and Ground Perspectives: A Deep Learning, Multimodal Solution, Remote Sensing of Environment Vol. 228, 2019, pp. 129-143, https://doi.org/10.1016/j.rse.2019.04.014.
[5] G. Scarpa, M. Gargiulo, A. Mazza, R. Gaetano, A Cnn-Based Fusion Method for Feature Extraction from Sentinel Data, Remote Sensing Vol. 10, No. 2, 2018, https://doi.org/10.3390/rs10020236.
[6] C. Tuna, G. Unal, E. Sertel, Single-Frame Super Resolution of Remote-Sensing Images by Convolutional Neural Networks, International Journal of Remote Sensing Vol. 39, No. 8, 2018, pp. 2463-2479, https://doi.org/10.1080/01431161.2018.1425561
[7] G. Tsagkatakis, A. Aidini, K. Fotiadou, M. Giannopoulos, A. Pentari, P. Tsakalides, Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement, Sensors,
Vol. 19, No. 18, 2019, https://doi.org/10.3390/s19183929.
[8] X. Hu, and Y. Yuan, Deep-Learning-Based Classification for Dtm Extraction from Als Point Cloud, Remote Sensing Vol. 8, No. 9, 2016, https://doi.org/10.3390/rs8090730.
[9] H. A. H. A. Najjar, B. Kalantar, B. Pradhan, V. Saeidi, A. A. Halin, N. Ueda, and S. Mansor, Land Cover Classification from Fused Dsm and Uav Images Using Convolutional Neural Networks, Remote Sensing Vol. 11, No. 12, 2019, https://doi.org/10.3390/rs11121461.
[10] F. Jahan, J. Zhou, M. Awrangjeb, Y. Gao, Fusion of Hyperspectral and Lidar Data Using Discriminant Correlation Analysis for Land Cover Classification, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 11, No. 10, 2018, pp. 3905-3917, https://doi.org/10.1109/JSTARS.2018.2868142.
[11] B. N. Quy, P. T. Anh, D. A. Quan, P. V. Hiep, T. T. Kien, H. X. Tu, N. D. Dong, N. D. Duc,
N. V. Hung, Research on Application of Unmanned Aerial Vehicles (Uavs) in Cadastral Mapping of Arable Land, Journal of Mining and Earth Sciences, Vol. 61, No. 5, 2020, pp. 43-53, (in Vietnamese), https://doi.org/10.46326/jmes.2020.61(5).05.
[12] S. Rahman, M. Irfan, M. Raza, K. Moyeezullah Ghori, S. Yaqoob, M. Awais, Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living, International Journal of Environmental Research and Public Health, Vol. 17, No. 3, 2020, https://doi.org/10.3390/ijerph17031082.
[13] H. Liu, P. Gong, J. Wang, N. Clinton, Y. Bai, S. Liang, Annual Dynamics of Global Land Cover and Its Long-Term Changes from 1982 to 2015, Earth Syst. Sci. Data Vol. 12, No. 2, 2020, pp. 1217-1243,
https://doi.org/10.5194/essd-12-1217-2020
[14] M. R. Machado, S. Karray, I. T. D. Sousa, Lightgbm: An Effective Decision Tree Gradient Boosting Method to Predict Customer Loyalty in the Finance Industry, pp. 1111-1116.
[15] B. Q. Thanh, T. Y. Chou, T. V. Hoang, Y. M. Fang, C. Y. Mu, P. H. Huang, P. V. Dong, N. Q. Huy, D. T. Anh, P. V. Manh, and M. E. Meadows, Gradient Boosting Machine and Object-Based Cnn for Land Cover Classification, Remote Sensing Vol. 13, No. 14, 2021, https://doi.org/10.3390/rs13142709.
[16] S. E. Jozdani, B. A. Johnson, D. Chen, Comparing Deep Neural Networks, Ensemble Classifiers, and Support Vector Machine Algorithms for Object-Based Urban Land Use/Land Cover Classification, Remote Sensing, Vol. 11, No. 14, 2019, https://doi.org/10.3390/rs11141713.
[17] M. J. Jun, A Comparison of a Gradient Boosting Decision Tree, Random Forests, and Artificial Neural Networks to Model Urban Land Use Changes: The Case of the Seoul Metropolitan Area, International Journal of Geographical Information Science 2021, pp. 1-19, https://doi.org/10.1080/13658816.2021.1887490.
[2] H. Wang, Y. Wang, Q. Zhang, S. Xiang, C. Pan, Gated Convolutional Neural Network for Semantic Segmentation in High-Resolution Images, Remote Sensing Vol. 9, No. 5, 2017, 10.3390/rs9050446.
[3] W. Zhou, S. Newsam, C. Li, Z. Shao, Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval, Remote Sensing Vol. 9, No. 5, 2017, https://doi.org/10.3390/rs9050489.
[4] S. Srivastava, J. E. V. Muñoz, D. Tuia, Understanding Urban Landuse from the above and Ground Perspectives: A Deep Learning, Multimodal Solution, Remote Sensing of Environment Vol. 228, 2019, pp. 129-143, https://doi.org/10.1016/j.rse.2019.04.014.
[5] G. Scarpa, M. Gargiulo, A. Mazza, R. Gaetano, A Cnn-Based Fusion Method for Feature Extraction from Sentinel Data, Remote Sensing Vol. 10, No. 2, 2018, https://doi.org/10.3390/rs10020236.
[6] C. Tuna, G. Unal, E. Sertel, Single-Frame Super Resolution of Remote-Sensing Images by Convolutional Neural Networks, International Journal of Remote Sensing Vol. 39, No. 8, 2018, pp. 2463-2479, https://doi.org/10.1080/01431161.2018.1425561
[7] G. Tsagkatakis, A. Aidini, K. Fotiadou, M. Giannopoulos, A. Pentari, P. Tsakalides, Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement, Sensors,
Vol. 19, No. 18, 2019, https://doi.org/10.3390/s19183929.
[8] X. Hu, and Y. Yuan, Deep-Learning-Based Classification for Dtm Extraction from Als Point Cloud, Remote Sensing Vol. 8, No. 9, 2016, https://doi.org/10.3390/rs8090730.
[9] H. A. H. A. Najjar, B. Kalantar, B. Pradhan, V. Saeidi, A. A. Halin, N. Ueda, and S. Mansor, Land Cover Classification from Fused Dsm and Uav Images Using Convolutional Neural Networks, Remote Sensing Vol. 11, No. 12, 2019, https://doi.org/10.3390/rs11121461.
[10] F. Jahan, J. Zhou, M. Awrangjeb, Y. Gao, Fusion of Hyperspectral and Lidar Data Using Discriminant Correlation Analysis for Land Cover Classification, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 11, No. 10, 2018, pp. 3905-3917, https://doi.org/10.1109/JSTARS.2018.2868142.
[11] B. N. Quy, P. T. Anh, D. A. Quan, P. V. Hiep, T. T. Kien, H. X. Tu, N. D. Dong, N. D. Duc,
N. V. Hung, Research on Application of Unmanned Aerial Vehicles (Uavs) in Cadastral Mapping of Arable Land, Journal of Mining and Earth Sciences, Vol. 61, No. 5, 2020, pp. 43-53, (in Vietnamese), https://doi.org/10.46326/jmes.2020.61(5).05.
[12] S. Rahman, M. Irfan, M. Raza, K. Moyeezullah Ghori, S. Yaqoob, M. Awais, Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living, International Journal of Environmental Research and Public Health, Vol. 17, No. 3, 2020, https://doi.org/10.3390/ijerph17031082.
[13] H. Liu, P. Gong, J. Wang, N. Clinton, Y. Bai, S. Liang, Annual Dynamics of Global Land Cover and Its Long-Term Changes from 1982 to 2015, Earth Syst. Sci. Data Vol. 12, No. 2, 2020, pp. 1217-1243,
https://doi.org/10.5194/essd-12-1217-2020
[14] M. R. Machado, S. Karray, I. T. D. Sousa, Lightgbm: An Effective Decision Tree Gradient Boosting Method to Predict Customer Loyalty in the Finance Industry, pp. 1111-1116.
[15] B. Q. Thanh, T. Y. Chou, T. V. Hoang, Y. M. Fang, C. Y. Mu, P. H. Huang, P. V. Dong, N. Q. Huy, D. T. Anh, P. V. Manh, and M. E. Meadows, Gradient Boosting Machine and Object-Based Cnn for Land Cover Classification, Remote Sensing Vol. 13, No. 14, 2021, https://doi.org/10.3390/rs13142709.
[16] S. E. Jozdani, B. A. Johnson, D. Chen, Comparing Deep Neural Networks, Ensemble Classifiers, and Support Vector Machine Algorithms for Object-Based Urban Land Use/Land Cover Classification, Remote Sensing, Vol. 11, No. 14, 2019, https://doi.org/10.3390/rs11141713.
[17] M. J. Jun, A Comparison of a Gradient Boosting Decision Tree, Random Forests, and Artificial Neural Networks to Model Urban Land Use Changes: The Case of the Seoul Metropolitan Area, International Journal of Geographical Information Science 2021, pp. 1-19, https://doi.org/10.1080/13658816.2021.1887490.