Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.1.32

The Accuracy Assessment of Species Classification according to Spatial Resolution of Satellite Image Dataset Based on Deep Learning Model  

Park, Jeongmook (Forest ICT Research Center, National Institute of Forest Science)
Sim, Woodam (Department of Forest Management, College of Forest & Environmental Sciences, Kangwon National University)
Kim, Kyoungmin (Department of Forest Management, College of Forest & Environmental Sciences, Kangwon National University)
Lim, Joongbin (Forest ICT Research Center, National Institute of Forest Science)
Lee, Jung-Soo (Division of Forest Science, College of Forest & Environmental Sciences, Kangwon National University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_1, 2022 , pp. 1407-1422 More about this Journal
Abstract
This study was conducted to classify tree species and assess the classification accuracy, using SE-Inception, a classification-based deep learning model. The input images of the dataset used Worldview-3 and GeoEye-1 images, and the size of the input images was divided into 10 × 10 m, 30 × 30 m, and 50 × 50 m to compare and evaluate the accuracy of classification of tree species. The label data was divided into five tree species (Pinus densiflora, Pinus koraiensis, Larix kaempferi, Abies holophylla Maxim. and Quercus) by visually interpreting the divided image, and then labeling was performed manually. The dataset constructed a total of 2,429 images, of which about 85% was used as learning data and about 15% as verification data. As a result of classification using the deep learning model, the overall accuracy of up to 78% was achieved when using the Worldview-3 image, the accuracy of up to 84% when using the GeoEye-1 image, and the classification accuracy was high performance. In particular, Quercus showed high accuracy of more than 85% in F1 regardless of the input image size, but trees with similar spectral characteristics such as Pinus densiflora and Pinus koraiensis had many errors. Therefore, there may be limitations in extracting feature amount only with spectral information of satellite images, and classification accuracy may be improved by using images containing various pattern information such as vegetation index and Gray-Level Co-occurrence Matrix (GLCM).
Keywords
Deep Learning; Computer Vision; Species Classification; Convolutional Neural Network;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Grabska, E., P. Hostert, D. Pflugmacher, and K. Ostapowicz, 2019. Forest stand species mapping using the Sentinel-2 time series, Remote Sensing, 11(10): 1197. https://doi.org/10.3390/rs11101197   DOI
2 Hawkins, D. M., 2004. The problem of overfitting, Journal of Chemical Information and Computer Sciences, 44(1): 1-12. https://doi.org/10.1021/ci0342472   DOI
3 He, T., Y. Lu, L. Jiao, Y. Zhang, X. Jiang, and Y. Yin, 2020. Developing deep learning models to automate rosewood tree species identification for CITES designation and implementation, Holzforschung, 74(12): 1123-1133. https://doi.org/10.1515/hf-2020-0006   DOI
4 Hu, J., L. Shen, and G. Sun, 2018. Squeeze-and-excitation networks, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, Jun. 18-23, pp. 7132-7141.
5 Jin, C., S. Park, H. Kim, Y. Chun, and C. Choi, 2010. Comparison of High Resolution Image by Ortho Rectification Accuracy and Correlation Each Band, Journal of Korean Society for Geospatial Information Science, 18(2): 35-45 (in Korean with English abstract).
6 Kim, K., C. Kim, and E. Jun, 2009. Study on the standard for 1: 25,000 scale digital forest type map production in Korea, Journal of the Korean Association of Geographic Information Studies, 12(3): 143-151 (in Korean with English abstract).
7 Krizhevsky, A., I. Sutskever, and G.E. Hinton, 2017. Imagenet classification with deep convolutional neural networks, Communications of the ACM, 60(6): 84-90. https://doi.org/10.1145/3065386   DOI
8 Kukenbrink, D., M. Marty, R. Bosch, and C. Ginzler, 2022. Benchmarking laser scanning and terrestrial photogrammetry to extract forest inventory parameters in a complex temperate forest, International Journal of Applied Earth Observation and Geoinformation, 113: 102999. https://doi.org/10.1016/j.jag.2022.102999   DOI
9 Franklin, S. E. and O. S. Ahmed, 2018. Deciduous tree species classification using object-based analysis and machine learning with unmanned aerial vehicle multispectral data, International Journal of Remote Sensing, 39(15-16): 5236-5245. https://doi.org/10.1080/01431161.2017.1363442   DOI
10 Abbas, S., Q. Peng, M.S. Wong, Z. Li, J. Wang, K.T.K. Ng, C.Y.T. Kwok, and K.K.W. Hui, 2021. Characterizing and classifying urban tree species using bi-monthly terrestrial hyperspectral images in Hong Kong, ISPRS Journal of Photogrammetry and Remote Sensing, 177: 204-216. https://doi.org/10.1016/j.isprsjprs.2021.05.003   DOI
11 Mishra, N.B., K.P. Mainali, B.B. Shrestha, J. Radenz, and D. Karki, 2018. Species-level vegetation mapping in a Himalayan treeline ecotone using unmanned aerial system (UAS) imagery, ISPRS International Journal of Geo-Information, 7(11): 445. https://doi.org/10.3390/ijgi7110445   DOI
12 Motohka, T., K.N. Nasahara, H. Oguma, and S. Tsuchida, 2010. Applicability of green-red vegetation index for remote sensing of vegetation phenology, Remote Sensing, 2(10): 2369-2387. https://doi.org/10.3390/rs2102369   DOI
13 Pearse, G.D., M.S. Watt, J. Soewarto, and A.Y. Tan, 2021. Deep learning and phenology enhance large-scale tree species classification in aerial imagery during a biosecurity response, Remote Sensing, 13(9): 1789. https://doi.org/10.3390/rs13091789   DOI
14 Hutchinson, J. S., A. Jacquin, S. L. Hutchinson, and J. Verbesselt, 2015. Monitoring vegetation change and dynamics on US Army training lands using satellite image time series analysis, Journal of Environmental Management, 150: 355-366. https://doi.org/10.1016/j.jenvman.2014.08.002   DOI
15 Liu, B., X. Yu, A. Yu, and G. Wan, 2018. Deep convolutional recurrent neural network with transfer learning for hyperspectral image classification, Journal of Applied Remote Sensing, 12(2): 026028. https://doi.org/10.1117/1.JRS.12.026028   DOI
16 Yan, S., L. Jing, and H. Wang, 2021. A new individual tree species recognition method based on a convolutional neural network and high-spatial resolution remote sensing imagery, Remote Sensing, 13(3): 479. https://doi.org/10.3390/rs13030479   DOI
17 Anderson, H.B., L. Nilsen, H. Tommervik, S.R. Karlsen, S. Nagai, and E.J. Cooper, 2016. Using ordinary digital cameras in place of near-infrared sensors to derive vegetation indices for phenology studies of High Arctic vegetation, Remote Sensing, 8(10): 847. https://doi.org/10.3390/rs8100847   DOI
18 Cifuentes-Croquevielle, C., D.E. Stanton, and J.J. Armesto, 2020. Soil invertebrate diversity loss and functional changes in temperate forest soils replaced by exotic pine plantations, Scientific Reports, 10(1): 1-11. https://doi.org/10.1038/s41598-020-64453-y   DOI
19 Deur, M., M. Gasparovic, and I. Balenovic, 2020. Tree species classification in mixed deciduous forests using very high spatial resolution satellite imagery and machine learning methods, Remote Sensing, 12(23): 3926. https://doi.org/10.3390/rs12233926   DOI
20 Lee, J., X. Cai, J. Lellmann, M. Dalponte, Y. Malhi, N. Butt, M. Morecroft, C. Schonlieb, and D.A. Coomes, 2016. Individual tree species classification from airborne multisensor imagery using robust PCA, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(6): 2554-2567. https://doi.org/10.1109/JSTARS.2016.2569408   DOI
21 Mohd Zaki, N. A. and Z. Abd Latif, 2017. Carbon sinks and tropical forest biomass estimation: a review on role of remote sensing in aboveground-biomass modelling, Geocarto International, 32(7): 701-716. https://doi.org/10.1080/10106049.2016.1178814   DOI
22 NIFS (National Institute of Forest Science), 2016. Field survey of forest resources in Kwangnung Experimental Forest, National Institute of Forest Science, Seoul, Republic of Korea. pp. 23-36.
23 Briechle, S., P. Krzystek, and G. Vosselman, 2021. Silvi-Net-A dual-CNN approach for combined classification of tree species and standing dead trees from remote sensing data, International Journal of Applied Earth Observation and Geoinformation, 98: 102292. https://doi.org/10.1016/j.jag.2020.102292   DOI
24 Fayek, H.M., M. Lech, and L. Cavedon, 2017. Evaluating deep learning architectures for speech emotion recognition, Neural Networks, 92: 60-68. https://doi.org/10.1016/j.neunet.2017.02.013   DOI
25 Maxwell, A.E. and T.A. Warner, 2020. Thematic classification accuracy assessment with inherently uncertain boundaries: An argument for center-weighted accuracy assessment metrics, Remote Sensing, 12(12): 1905. https://doi.org/10.3390/rs12121905   DOI
26 Moisen, G.G., E.A. Freeman, J.A. Blackard, T.S. Frescino, N.E. Zimmermann, and T.C. Edwards Jr., 2006. Predicting tree species presence and basal area in Utah: a comparison of stochastic gradient boosting, generalized additive models, and tree-based methods, Ecological Modeling, 199(2): 176-187. https://doi.org/10.1016/j.ecolmodel.2006.05.021   DOI
27 Yuhendra, T.S. Joshapat, and K. Hiroaki, 2011. Performance analyzing of high resolution pan-sharpening techniques: increasing image quality for classification using supervised kernel support vector machine, Research Journal of Information Technology, 3(1): 12-23. https://doi.org/10.3923/rjit.2011.12.23   DOI
28 Spanhol, F.A., L.S. Oliveira, C. Petitjean, and L. Heutte, 2016. Breast cancer histopathological image classification using convolutional neural networks, Proc. of 2016 International Joint Conference on Neural Networks, Vancouver, BC, Canada, Jul. 24-29, pp. 2560-2567. https://doi.org/10.1109/IJCNN.2016.7727519   DOI
29 Turlej, K., M. Ozdogan, and V.C. Radeloff, 2022. Mapping forest types over large areas with Landsat imagery partially affected by clouds and SLC gaps, International Journal of Applied Earth Observation and Geoinformation, 107: 102689. https://doi.org/10.1016/j.jag.2022.102689   DOI
30 Karasiak, N., J. Dejoux, M. Fauvel, J. Willm, C. Monteil, and D. Sheeren, 2019. Statistical stability and spatial instability in mapping forest tree species by comparing 9 years of satellite image time series, Remote Sensing, 11(21): 2512. https://doi.org/10.3390/rs11212512   DOI
31 Zhao, L. and L. Zhu, 2012. Research on method of extracting vegetation information based on band combination, Proc. of 2012 20th International Conference on Geoinformatics, Hong Kong, China, Jun. 15-17, pp. 1-5. https://doi.org/10.1109/Geoinformatics.2012.6270287   DOI
32 Xi, Y., C. Ren, Z. Wang, S. Wei, J. Bai, B. Zhang, H. Xiang, and L. Chen, 2019. Mapping tree species composition using OHS-1 hyperspectral data and deep learning algorithms in Changbai mountains, Northeast China, Forests, 10(9): 818. https://doi.org/10.3390/f10090818   DOI
33 Zhang, B., L. Zhao, and X. Zhang, 2020. Three-dimensional convolutional neural network model for tree species classification using airborne hyperspectral images, Remote Sensing of Environment, 247: 111938. https://doi.org/10.1016/j.rse.2020.111938   DOI
34 Hartling, S., V. Sagan, P. Sidike, M. Maimaitijiang, and J. Carron, 2019. Urban tree species classification using a WorldView-2/3 and LiDAR data fusion approach and deep learning, Sensors, 19(6): 1284. https://doi.org/10.3390/s19061284   DOI
35 Zhong, L., L. Hu, and H. Zhou, 2019. Deep learning based multi-temporal crop classification, Remote Sensing of Environment, 221: 430-443. https://doi.org/10.1016/j.rse.2018.11.032   DOI
36 Somers, B. and G.P. Asner, 2014. Tree species mapping in tropical forests using multi-temporal imaging spectroscopy: Wavelength adaptive spectral mixture analysis, International Journal of Applied Earth Observation and Geoinformation, 31: 57-66. https://doi.org/10.1016/j.jag.2014.02.006   DOI