Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.6.2.9

A Study on Deep Learning Optimization by Land Cover Classification Item Using Satellite Imagery  

Lee, Seong-Hyeok (Center for Environmental Data Strategy, Korea Environment Institute)
Lee, Moung-jin (Center for Environmental Data Strategy, Korea Environment Institute)
Publication Information
Korean Journal of Remote Sensing / v.36, no.6_2, 2020 , pp. 1591-1604 More about this Journal
Abstract
This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.
Keywords
Land cover; Classification; Deep learning; Kompsat; Semantic segmentation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Zhang, Y. and R. K. Mishra, 2012. A review and comparison of commercially available pansharpening techniques for high resolution satellite image fusion, Proc. of 2012 IEEE International Geoscience and Remote Sensing Symposium, Munich, GER, Jul. 22-27, pp. 182-185.
2 Zhang, H., H. Lin, and Y. Li, 2015. Impacts of feature normalization on optical and SAR data fusion for land use/land cover classification, IEEE Geoscience and Remote Sensing Letters, 12(5): 1061-1065.   DOI
3 Zhang, Y., P. David, and B. Gong, 2017. Curriculum domain adaptation for semantic segmentation of urban scenes, Proc. of the 2017 IEEE International Conference on Computer Vision, Venice, ITA, Oct. 22-29, pp. 2020-2030.
4 Papadomanolaki, M., M. Vakalopoulou, and K. Karantzalos, 2019. A novel object-based deep learning framework for semantic segmentation of very high-resolution remote sensing data: Comparison with convolutional and fully convolutional networks, Remote Sensing, 11(6): 684.   DOI
5 Peng, H., C. Xue, Y. Shao, K. Chen, J. Xiong, Z. Xie, and L. Zhang, 2020. Semantic Segmentation of Litchi Branches Using DeepLabV3 Model, IEEE Access, 8: 164546-164555.   DOI
6 Rana, V. K. and T. M. V. Suryanarayana, 2020. Performance evaluation of MLE, RF and SVM classification algorithms for watershed scale land use/land cover mapping using sentinel 2 bands, Remote Sensing Applications: Society and Environment, 19: 100351.   DOI
7 Rieder, M. and R. Verbeet, 2019. Robot-human-learning for robotic picking processes, Artificial Intelligence and Digital Transformation in Supply Chain Management: Innovative Approaches for Supply Chains, Proc. of 2019 Hamburg International Conference of Logistics (HICL), Hamburg, GER, Sep. 25-27, vol. 27, pp. 87-114.
8 Rodriguez-Galiano, V. F., B. Ghimire, J. Rogan, M. Chica-Olmo, and J. P. Rigol-Sanchez, 2012. An assessment of the effectiveness of a random forest classifier for land-cover classification, ISPRS Journal of Photogrammetry and Remote Sensing, 67: 93-104.   DOI
9 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-net: Convolutional networks for biomedical image segmentation, Proc. of 2015 International Conference on Medical image computing and computer-assisted intervention, Munich, GER, Oct. 5-9 pp. 234-241.
10 Soni, A., R. Koner, and V. G. K. Villuri, 2020. M-UNet: Modified U-Net Segmentation Framework with Satellite Imagery, Proc. of the Global AI Congress 2019, Kolkata, IND, Sep. 12-14, pp. 47-59.
11 Zhang, C., I. Sargent, X. Pan, A. Gardiner, J. Hare, and P. M. Atkinson, 2018. VPRS-based regional decision fusion of CNN and MRF classifications for very fine resolution remotely sensed images, IEEE Transactions on Geoscience and Remote Sensing, 56(8): 4507-4521.   DOI
12 Stoian, A., V. Poulain, J. Inglada, V. Poughon, and D. Derksen, 2019. Land cover maps production with high resolution satellite image time series and convolutional neural networks: Adaptations and limits for operational systems, Remote Sensing, 11(17): 1986.   DOI
13 Volpi, M. and V. Ferrari, 2015. Semantic segmentation of urban scenes by learning local class interactions, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, MA, Jun. 7-12, pp. 1-9.
14 Voulodimos, A., N. Doulamis, A. Doulamis, and E. Protopapadakis, 2018. Deep learning for Computer vision: A brief review, Computational intelligence and neuroscience, 2018: 1-14.
15 Zhang, C., S. Wei, S. Ji, and M. Lu, 2019. Detecting large-scale urban land cover changes from very high resolution remote sensing images using cnn-based classification, ISPRS International Journal of Geo-Information, 8(4): 189.   DOI
16 Arief, H. A., G. Strand, H. Tveite, and U. G. Indahl, 2018. Land cover segmentation of airborne LiDAR data using stochastic atrous network, Remote Sensing, 10(6): 973.   DOI
17 Audebert, N., B. Le Saux, and S. Lefevre, 2018. Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks, ISPRS Journal of Photogrammetry and Remote Sensing, 140: 20-32.   DOI
18 Badrinarayanan, V., A. Handa, and R. Cipolla, 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12): 2481-2495.   DOI
19 Andersson, V., 2017. Semantic Segmentation: Using Convolutional Neural Networks and Sparse dictionaries Overview, https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1127291&dswid=-8672, Accessed on Aug. 14, 2020.
20 Akhtar, N. and A. Mian, 2018. Threat of adversarial attacks on deep learning in computer vision: A survey, IEEE Access, 6: 14410-14430.   DOI
21 Bardenet, R., M. Brendel, B. Kegl, and M. Sebag, 2013. Collaborative hyperparameter tuning, Proc. of 2013 International Conference on Machine Learning, Atlanta, USA, Jun. 16-21, pp. 199-207.
22 Bhosle, K. and V. Musande, 2019. Evaluation of deep learning CNN model for land use land cover classification and crop identification using hyperspectral remote sensing images, Journal of the Indian Society of Remote Sensing, 47(11): 1949-1958.   DOI
23 Cao, R. and G. Qiu, 2018. Urban land use classification based on aerial and ground images, Proc. of 2018 International Conference on Content-Based Multimedia Indexing (CBMI), La Rochelle, FRA, Sep. 4-6, pp. 1-6.
24 Chavez, P. S., 1996. Image-based atmospheric correctionsrevisited and improved, Photogrammetric Engineering and Remote Sensing, 62(9): 1025-1035.
25 Chen, L., Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, 2018. Encoder-decoder with atrous separable convolution for semantic image segmentation, Proc. of the European conference on computer vision (ECCV), Munich, GER, Sep. 8-14, pp. 801-818.
26 Chen, Y., D. Ming, and X. Lv, 2019. Superpixel based land cover classification of VHR satellite image combining multi-scale CNN and scale parameter estimation, Earth Science Informatics, 12(3): 341-363.   DOI
27 Foody, G. M., 2002. Status of land cover classification accuracy assessment, Remote Sensing of Environment, 80(1): 185-201.   DOI
28 Kampffmeyer, M., A. Salberg, and R. Jenssen, 2016. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks, Proc. of the 2016 IEEE conference on computer vision and pattern recognition workshops, Las Vegas, NV, Jun. 27-30, pp. 1-9.
29 Gaetano, R., D. Ienco, K. Ose, and R. Cresson, 2018. A two-branch CNN architecture for land cover classification of PAN and MS imagery, Remote Sensing, 10(11): 1746.   DOI
30 Garcia-Garcia, A., S. Orts-Escolano, S. Oprea, V. VillenaMartinez, and J. Garcia-Rodriguez, 2017. A review on deep learning techniques applied to semantic segmentation, Arxiv preprint, 1704.06857 (v1): 1-23.
31 Kemker, R., C. Salvaggio, and C. Kanan, 2018. Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning, ISPRS Journal of Photogrammetry and Remote Sensing, 145: 60-77.   DOI
32 Kendall, A., V. Badrinarayanan, and R. Cipolla, 2015. Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding, Arxiv preprint, 1511.02680 (v2): 1-11.
33 Korea Forest Service Home Page Overview, http://forest.go.kr, Accessed on Feb. 30, 2019.
34 Kussul, N., M. Lavreniuk, S. Skakun, and A. Shelestov, 2017. Deep learning classification of land cover and crop types using remote sensing data, IEEE Geoscience and Remote Sensing Letters, 14(5): 778-782.   DOI
35 LeCun, Y., Y. Bengio, and G. Hinton, 2015. Deep learning, Nature, 521(7553): 436-444.   DOI
36 Lee, D. G., Y. H. Shin, and D. Lee, 2020. Land Cover Classification Using SegNet with Slope, Aspect, and Multidirectional Shaded Relief Images Derived from Digital Surface Model, Journal of Sensors, 2020: 1-21.
37 Ma, L., M. Li, X. Ma, L. Cheng, P. Du, and Y. Liu, 2017. A review of supervised object-based land-cover image classification, ISPRS Journal of Photogrammetry and Remote Sensing, 130: 277-293.   DOI
38 Li, F., J. Johnson, and S. Yeung, 2017. Convolutional neural networks for visual recognition lecture notes Overview, https://sites.google.com/site/aidysft/lecturenotes, Accessed on Jun. 13, 2020.
39 Liu, S., L. Qi, H. Qin, J. Shi, and J. Jia, 2018. Path aggregation network for instance segmentation, Proc. of the 2018 IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, Jun. 19-21, pp. 8759-8768.
40 Long, J., E. Shelhamer, and T. Darrell, 2015. Fully convolutional networks for semantic segmentation, Proc. of the 2015 IEEE conference on computer vision and pattern recognition, Boston, MA, Jun. 7-12, pp. 3431-3440.
41 Mao, Q., H. Sun, Y. Liu, and R. Jia, 2019. Mini-YOLOv3: real-time object detector for embedded applications, IEEE Access, 7: 133529-133538.   DOI
42 Ning, H., Z. Li, C. Wang, and L. Yang, 2020. Choosing an appropriate training set size when using existing data to train neural networks for land cover segmentation, Annals of GIS, 2020: 1-14.   DOI
43 Paisitkriangkrai, S., J. Sherrah, P. Janney, and V. Hengel, 2015. Effective semantic pixel labelling with convolutional networks and conditional random fields, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, MA, Jun. 7-12, pp. 36-43.