Dataset Creation Methodology for CNN Land Use/ Cover Classification: Thailand’s Rural Area Study Case
Main Article Content
Abstract
Land cover is a powerful tool and takes advantage of Convolutional Neural Network
(CNN) in remote sensing image recognition. However, the existing datasets are pretty small
or are not relied to the studied class where the land cover is performed. In this paper,
a methodology is proposed and detailed to create dataset images to be used for land cover
through CNN. This method consists in 4 steps. Firstly, large remote sensing images are collected.
Then, a large amount of tiles are created using an adequate sampling method. Using a coarse
model tiles are automatically labeled. Finally, dataset is cleaned from mislabeled images in
order to be used in a CNN model. Rural area in Thailand is used as study case for a 4 class
dataset: buildings, forest, roads and wasteland. In a first step, satellite images are cropped using
overlapping process to create dataset tiles. Then, coarse model based on pixel RGB bands
value is developed and by applying ratio on these RGB filters, tiles can be classified. Results
show that building and wasteland class can be created with a very high precision of at least
98% demonstrating the robustness of the proposed method to quickly perform a dataset
image. Forest presents a good precision with a value of 90%. On the opposite, roads class
presents a low precision of 68% and therefore, this datasets needs to be manually cleaned by
the users. Finally, effects of cropping and overlapping size are investigated and results show
that using a different cropping size requires a new calibration of the methodology.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Journal of TCI is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence, unless otherwise stated. Please read our Policies page for more information...
References
S. A. A. Rafee et al., “Large-Scale Hydrological Modelling of the Upper Paraná River Basin,” Water, vol. 11, no. 5, p. 882, 2019.
Y. Bai, M. Feng, H. Jiang, J. Wang, Y. Zhu, and Y. Liu, “Assessing Consistency of Five Global Land Cover Datasets in China,” Remote Sens., vol. 6, no. 9, pp. 8739 - 8759, 2014.
J. A. Foley et al., “Global Consequences of Land Use,” Science, vol. 309, no. 5734, pp. 570 - 574, 2005.
M. Höjer et al., “Scenarios in Selected Tools for Environmental Systems Analysis,” J. Clean. Prod., vol. 16, no. 18, pp. 1958 - 1970, 2008.
R. Hollmann et al., “The ESA Climate hange Initiative: Satellite Data Records for Essential Climate Variables,” Bull. Amer.Meteorological Soc., vol. 94, no. 10, pp. 1541 - 1552, 2013.
C. Homer et al., “Completion of the 2011 National Land Cover Database for the Conterminous United States-Representing a Decade of Land Cover Change Information,” Photogramm. Eng. Remote Sens., vol. 81, no. 5, pp. 345 - 354, 2015.
J. A. Martins, V. S. Brand, M. N. Capucim, C. B. Machado, D. G. A. Piccilli, and L. D. Martins, “The Impact of Rainfall and Land Cover Changes on the Flow of a Medium-sized River in the South of Brazil,” Energy Procedia, vol. 95, pp. 272 - 278, 2016.
W. B. Meyer and B. L. Turner II, Changes in Land Use and Land Cover: A Global Perspective. 1st ed. Cambridge, UK: Cambridge Univ. Press, 1994.
M. V. B. de Morais, V. V. U. Guerrero, L. D. Martins, and J. A. Martins, “Dynamical Downscaling of Future Climate Change Scenarios in Urban Heat Island and Its Neigh borhood in a Brazilian Subtropical Area,” in 2nd Int. Electron. Conf. Atmospheric Sci., Proc., vol. 1, no. 15, Jul. 2017, pp. 1 - 13.
R. H. Moss et al., “The Next Generation of Scenarios for Climate Change Research and Assessment,” Nature, vol. 463, pp. 747 - 756, 2010.
M. Schaefer and N. X. Thinh, “Evaluation of Land Cover Change and Agricultural Protection Sites: A GIS and Remote Sensing Approach for Ho Chi Minh City, Vietnam,” Heliyon, vol. 5, no. 5, p.e01773, 2019.
S. D. Tarigan, “Land Cover Change and Its Impact on Flooding Frequency of Batanghari Watershed, Jambi Province, Indonesia,” Procedia Environ. Sci., vol. 33, pp. 386 - 392, 2016, doi: 10.1016/ j.proenv.2016.03.089.
D. T. Nguyen, I. Iskandar, and S. Ho, “Land Cover Change and the CO2 Stock in the Palembang City, Indonesia: A Study Using Remote Sensing, GIS Technique and LUMENs,” Egypt. J. Remote. Sens. Space Sci., vol. 19, no. 2, pp. 313 - 321, Dec. 2016, doi: 10.1016/j.ejrs.2016.08.004.
K. Trincsi, T-T-H. Pham, and S. Turner, “Mapping Mountain Diversity: Ethnic Minorities and Land Use Land Cover Change in Vietnam’s Borderlands,” Land Use Policy, vol. 41, pp. 484 - 497, 2014.
N. D. A. Halim et al., “Spatial Aassessment of Land Use Impact on Air Quality in Mega Urban Regions, Malaysia,” Sustain. Cities Soc., vol. 63, 2020.
D. P. Shrestha, M. Suriyaprasit, and S. Prachansri, “Assessing Soil Erosion in Inaccessible Mountainous Areas in the Tropics: The Use of Land Cover and Topographic Parameters in a Case Study in Thailand,” Catena, vol. 121, pp. 40 - 52, Oct. 2014, doi: 10.1016/ j.catena.2014.04.016.
R. Patarasuk, “Road Network Connectivity and Land-cover Dynamics in Lop Buri Province, Thailand,” J. Transp. Geogr., vol. 28, pp. 111 - 123, 2013.
R. Patarasuk and M. W. Binford, “Longitudinal Analysis of the Road Network Development and Land-cover Change in Lop Buri Province, Thailand, 1989-2006,” Appl. Geogr., vol. 32, no. 2, pp. 228 - 239, 2012.
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based Learning Applied to Document Recognition,” in Proc. IEEE, vol. 86, no. 11, pp. 2278 - 2324, 1998.
K. He, X. Zhang, S. Ren, and J. Sun, “Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition,” in IEEE Trans.Pattern Anal. Mach. Intell., vol. 37, no. 9, pp. 1904-1916, 2015, doi: 10.1109/ TPAMI.2015.2389824.
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” in IEEE Conf. Comput. Vision Pattern Recognit., 2016, pp. 2261 - 2269.
O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int. J. Comput.Vis., vol. 115, pp. 211 – 252, Apr. 2015, doi: 10.1007/s11263-015-0816-y.
K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” in ICLR 2015, May. 2015, pp. 1 - 14.
C. Szegedy et al., “Going Deeper with Convolutions,” in 2015IEEE Conf. Comput. Vision Pattern Recognit. (CVPR), Boston, MA, USA, 2015, pp. 1 - 9, doi: 10.1109/ CVPR.2015.7298594.
B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, “Learning Transferable Architectures for Scalable Image Recognition,” in 2018 IEEE/CVF Conf. Comput. Vision Pattern Recognit., Salt Lake City, UT, USA, 2018, pp. 8697 - 8710, doi: 10.1109/ CVPR.2018.00907.
W. Li, C. Chen, M. Zhang, H. Li, and Q. Du, “Data Augmentation for Hyperspectral Image Classification With Deep CNN,” in IEEE Geosci. Remote Sens. Lett., vol. 16, no. 4, pp. 593 - 597, 2019.
L. Ma, Y. Liu, X. Zhang, Y. Ye, G. Yin, and B. A. Johnson, “Deep Learning in Remote Sensing Applications: A Meta-analysis and Review,” ISPRS J. Photogramm. Remote Sens., vol. 152, pp. 166 - 177, 2019.
M. Panahi, N. Sadhasivam, H. R. Pourghasemi, F. Rezaie, and S. Lee, “Spatial Prediction of Groundwater Potential Mapping Based on Convolutional Neural Network (CNN) and Support Vector Regression (SVR),” J. Hydrol., vol. 588, p.125033, 2020.
S. Ji, Z. Chi, A. Xu, Y. Shi, and Y. Duan, “3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images,” Remote Sens., vol. 10, p. 75, Jan. 2018, doi: 10.3390/ rs10010075.
C. Yoo, D. Han, J. Im, and B. Bechtel, “Comparison between Convolutional Neural Networks and Random Forest for Local Climate Zone Classification in Mega Urban Areas Using Landsat Images,” ISPRS J. Photogramm. Remote Sens., vol. 157, pp. 155 - 170, 2019.
F. S. Y. Watanabe et al., “Inland Water’s Trophic Status Classification Based on Machine Learning and Remote Sensing Data,” RemoteSens. Appl.:Soc.Environ., vol. 19, p. 100326, 2020.
K. Chen, K. Fu, M. Yan, X. Gao, X. Sun, and X. Wei, “Semantic Segmentation of Aerial Images With Shuffling Convolutional Neural Networks,” in IEEE Geosci. Remote Sens. Lett., vol. 15, no. 2, pp. 173 - 177, 2018.
D. Marmanis, J. D. Wegner, S. Galliani, K. Schindler, M. Datcu, and U. Stilla, “Semantic Segmentation of Aerial Images with an Ensemble of CNNS,” ISPRS Ann. Photogramm.RemoteSens.Spat. Inf.Sci., vol. III-3, pp. 473 – 480, 2016.
C. Zhang, P. Yue, D. Tapete, B. Shangguan, M. Wang, and Z. Wu, “A Multi-level Context-guided Classification Method with Object-based Convolutional Neural Network for Land Cover Classification Using Very High Resolution Remote Sensing Images,” Int. J. Appl. Earth Obs. Geoinf., vol. 88, p. 102086, 2020.
D. Konstantinidis, V. Argyriou, T. Stathaki, and N. Grammalidis, “A Modular CNN-based Building Detector for Remote Sensing Images. Comput. Netw., vol. 168, p. 107034, 2020.
J.-D. Sylvain, G. Drolet, and N. Brown, “Mapping Dead Forest Cover Using a Deep Convolutional Neural Network and Digital Aerial Photography,” ISPRS J. Photogramm. Remote Sens., vol. 156, pp. 14 - 26, 2019.
R. Shang, J. He, J. Wang, K. Xu, L. Jiao, and R. Stolkin, “Dense Connection and Depthwise Separable Convolution Based CNN for Polarimetric SAR Image Classification,” Knowl. Based Syst., vol. 194, p. 105542, 2020.
K. D. Ngo, A. M. Lechner, and T. T. Vu, “Land Cover Mapping of the Mekong Delta to Support Natural Resource Management with Multi-temporal Sentinel-1A Synthetic Aperture Radar Imagery,” Remote Sens. Appl.: Soc. Environ., vol. 17, p. 100272, 2020.
S. Baamonde, M. Cabana, N. Sillero, M. G. Penedo, H. Naveira, and J. Novo, “Fully Automatic Multi-temporal Land Cover Classification Using Sentinel-2 Image Data,” Procedia Comput. Sci., vol. 159, pp. 650 - 657, 2019, doi: 10.1016/ j.procs.2019.09.220.
T. Talema and B. T. Hailu, “Mapping Rice Crop Using Sentinels (1 SAR and 2 MSI) Images in Tropical Area: A Case Study in Fogera Wereda, Ethiopia,” Remote Sens. Appl.: Soc. Environ., vol. 18, Apr. 2020, doi: 10.1016/j.rsase.2020.100290.
Y. Shendryk, Y. Rist, C. Ticehurst, and P. Thorburn, “Deep Learning for Multi-modal Classification of Cloud, Shadow and Land Cover Scenes in Planet Scope and Sentinel-2 Imagery,” ISPRSJ.Photogramm. RemoteSens., vol. 157, pp. 124 - 136, Nov. 2019, doi: 10.1016/j.isprsjprs.2019.08.018.
Z. Xu, K. Guan, N. Casler, B. Peng, and S. Wang, “3D Convolutional Neural Network Method for Land Cover Classification Using LiDAR and Multi-temporal Landsat Imagery,” ISPRS J. Photogramm. Remote Sens., vol. 144, pp. 423 - 434, Oct. 2018, doi: 10.1016/j.isprsjprs.2018.08.005.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet Classification with Deep Convolutional Neural Networks,” in Adv. Neural Inf. Process. Syst., vol. 25, pp. 1097 - 1105, 2012.
M. U. Müller, N. Ekhtiari, R. M. Almeida, and C. Rieke, “Super-resolution of Multispectral Satellite Images Using Convolutional Neural Networks,” ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., vol. 1-2020, pp. 33 - 40, 2020.
G. Castilla and G. J. Hay, “Uncertainties in Land Use Data,” Hydrol. Earth Syst. Sci., vol. 11, no. 6, pp. 1857 - 1868, 2007.
R. Fuchs, M. Herold, P. H. Verburg, and J. G. P. W. Clevers, “A High-resolution and Harmonized Model Approach for Reconstructing and Analysing Historic Land Changes in Europe,” Biogeosciences, vol. 10, pp. 1543 - 1559, 2013.
P. H. Verburg, K. Neumann, and L. Nol, “Challenges in Using Land Use and Land Cover Data for Global Change Studies,” Glob.ChangeBiol., vol. 17, pp. 974 - 989, 2011, doi: 10.1111/j.1365-2486.2010.02307.x.
Y. Yang and S. Newsam,“Bag-of-visual-words and Spatial Extensions for Land-use Cassification,” in 18th ACM SIGSPATIAL Int. Conf. Adv. Geographic Inf. Syst. (ACM SIGSPATIAL GIS2010), San Jose, CA, USA, Nov. 2010, pp. 270 - 279.
S. Basu, S. Ganguly, S. Mukhopadhyay, R. DiBiano, M. Karki, and R. Nemani, “Deepsat: A Learning Framework for Satellite Imagery,” in 23rd SIGSPATIAL Int. Conf. Adv. Geographic Inf. Syst., Nov. 2015, pp. 1 - 10.
P. Helber, B. Bischke, A. Dengel, and D. Borth, “EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification,” in IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 12, no. 7, pp. 2217 - 2226, 2019, doi: 10.1109/JSTARS.2019.2918242.
G. Sumbul, M. Charfuelan, B. Demir, and V. Markl, “BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding,” in 2019 IEEE Int. Geosci. Remote Sens. Symp., Yokohama, Japan, 2019, pp. 5901 - 5904, doi: 10.1109/IGARSS.2019.8900532.
P. R. Emparanza, N. Hongkarnjanakul, D. Rouquette, C. Schwob, and L. Mezeix, “Land Cover Classification in Thailand’s Eastern Economic Corridor (EEC) Using Convolutional Neural Network on Satellite Images.” RemoteSens. Appl.:Soc.Environ., vol. 20, p. 100394, 2020.
P. Chermprayong, N. Hongkarnjanakul, D. Rouquette, C. Schwob, and L. Mezeix, “Convolutional Neural Network for Thailand’s Eastern Economic Corridor (EEC) Land Cover Classification Using Overlapping Process on Satellite Images.” RemoteSens. Appl.:Soc.Environ., vol. 23, p. 100543, 2021.
G. Sheng, W. Yang, T. Xu, and H. Sun, “High-resolution Satellite Scene Classification Using a Sparse Coding Based Multiple Feature Combination,” Int. J. Remote Sens., vol. 33, no. 8, pp. 2395 - 2412, Apr. 2012, doi:10.1080/ 01431161.2011.608740.
Q. Zou, L. Ni, T. Zhang, and Q. Wang, “Deep Learning Based Feature Selection for Remote Sensing Scene Classification,” in IEEE Geosci. Remote Sens. Lett., vol. 12, no. 11, pp. 2321 - 2325, Nov. 2015, doi: 10.1109/LGRS.2015.2475299.
Kristo and C. C. Chua, “Cost Effective Window Arrangement for Spatial Pyramid Matching,” J. Vis. Commun. Image Represent., vol. 29, pp. 79 - 88, 2015.
G.-S. Xia et al., “AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 7, pp. 3965 - 3981, Jul. 2017, doi: 10.1109/ TGRS.2017.2685945.
G. Cheng, J. Han, and X. Lu, “Remote Sensing Image Scene Classification: Benchmark and State of the Art,” inProc. IEEE, vol. 105, no. 10, pp. 1865 - 1883, 2017.
H. Li et al., “RSI-CB: A Large-Scale Remote Sensing Image Classification Benchmark Using Crowdsourced Data,”Sensors, vol. 20, no. 6, p. 1594, 2020.
W. Zhou, S. Newsam, C. Li, and Z. Shao, “PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval,” ISPRS J. Photogramm. RemoteSens., vol. 145, Part A, pp. 197 - 209. Nov. 2018, doi: 10.1016/j.isprsjprs.2018.01.004.
G.-S. Xia, W. Yang, J. Delon, Y. Gousseau, H. Sun, and H. Maitre, “Structural High-resolution Satellite Image Indexing,” in ISPRSTC VIISymp.-100Years ISPRS, Vienna, Austria, Jul. 2010, vol. 38, pp. 298 - 303.
L. Zhao, P. Tang, and L.-Z. Huo, “Feature Significance-based Multibag-of-visual -words Model for Remote Sensing Image Scene Classification,” J. Appl. Remote Sens., vol. 10, no. 3, p. 035004. Jun. 2016, doi: 10.1117/1.JRS.10.035004.
M. Wang, H. Zhang, W. Sun, S. Li, F. Wang, and G. Yang, “A Coarse-to-Fine Deep Learning Based Land Use Change Detection Method for High-Resolution Remote Sensing Images,” Remote Sens., vol. 12, no. 12, p. 1933, 2020.
G. C. Veerabhadrappa, S. C., T. K. Jaya Ram, and A. Haswanth, “Unsupervised Learning for Satellite Image Classification,” IOSRJ. VLSI Signal Processing, vol. 4, no. 2, pp. 01 - 04, Jan. 2014, doi: 10.9790/4200 -04240104.
The World Bank. “Indicators.” DATA. WORLDBANK.org. https://data.worldbank. org/indicator (accessed Dec. 14, 2021).
Anonymous. “Statistica.” STATISTA.com. https://www.statista.com/ (accessed Dec. 17, 2021).
Britannica. “Encyclopædia Britannica.” BRITANNICA.com. https://www.britannica. com (accessed Jul. 28, 2011).
Food and Agriculture Organization of the United Nations, “National Agro-Economic Zoning for Major Crops in Thailand (NAEZ),” FAO, Rome, Italy, Rep. Project TCP/THA/3403, 2017.
V. Mnih and G. E. Hinton, “Learning to Detect Roads in High-resolution Aerial Images,” in Proc. 11th European Conf. Comput. Vision (ECCV), Sep. 2010.
A. R. Choudhury, B. Parajuli, and P. Kumar, “Quad Road: An Ensemble of CNNs for Road Segmentation,” Procedia Comput. Sci., vol. 176, pp. 138 - 147, 2020.