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

被引:0
作者
Park, Jeongmook [1 ]
Sim, Woodam [2 ]
Kim, Kyoungmin [3 ]
Lim, Joongbin [1 ]
Lee, Jung-Soo [4 ]
机构
[1] Natl Inst Forest Sci, Forest ICT Res Ctr, Seoul, South Korea
[2] Kangwon Natl Univ, Coll Forest Environm & Sci, Dept Forest Management, Chunchon, South Korea
[3] Natl Inst Forest Sci, Forest ICT Res Ctr, Seoul, South Korea
[4] Kangwon Natl Univ, Coll Forest & Environm Sci, Div Forest Sci, Chunchon, South Korea
关键词
Deep Learning; Computer Vision; Species Classification; Convolutional Neural Network;
D O I
10.7780/kjrs.2022.38.6.1.32
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
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 x 10 m, 30 x 30 m, and 50 x 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).
引用
收藏
页码:1407 / 1422
页数:16
相关论文
共 50 条
[21]   Deepening the Accuracy of Tree Species Classification: A Deep Learning-Based Methodology [J].
Cha, Sungeun ;
Lim, Joongbin ;
Kim, Kyoungmin ;
Yim, Jongsu ;
Lee, Woo-Kyun .
FORESTS, 2023, 14 (08)
[22]   Classification of TrashNet Dataset Based on Deep Learning Models [J].
Aral, Rahmi Arda ;
Keskin, Seref Recep ;
Kaya, Mahmut ;
Haciomeroglu, Murat .
2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA), 2018, :2058-2062
[23]   Hyperspectral Image Classification Using Spatial and Spectral Features Based on Deep Learning [J].
Gong Jie ;
Jiang Liang ;
Chu Tao ;
Wang Chengchen ;
Xu Fuhui ;
Zhang Dexiang .
PROCEEDINGS OF THE 36TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC 2024, 2024, :1167-1172
[24]   Hyperspectral Image Classification Using Spatial and Edge Features Based on Deep Learning [J].
Zhang, Dexiang ;
Kang, Jingzhong ;
Xun, Lina ;
Huang, Yu .
INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2019, 33 (09)
[25]   Banana and Guava dataset for machine learning and deep learning-based quality classification [J].
Kumari, Abiban ;
Singh, Jaswinder .
DATA IN BRIEF, 2024, 57
[26]   Pathomics and Deep Learning Classification of a Heterogeneous Fluorescence Histology Image Dataset [J].
Ioannidis, Georgios S. ;
Trivizakis, Eleftherios ;
Metzakis, Ioannis ;
Papagiannakis, Stilianos ;
Lagoudaki, Eleni ;
Marias, Kostas .
APPLIED SCIENCES-BASEL, 2021, 11 (09)
[27]   Sweetener classification model based on deep learning [J].
Xiao L. ;
Chen A. ;
Zhou G. ;
Yi J. .
Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2021, 37 (11) :285-291
[28]   Deep Learning-Based Plant-Image Classification Using a Small Training Dataset [J].
Batchuluun, Ganbayar ;
Nam, Se Hyun ;
Park, Kang Ryoung .
MATHEMATICS, 2022, 10 (17)
[29]   Medical Image Classification based on an Adaptive Size Deep Learning Model [J].
Liu, Xiangbin ;
He, Jiesheng ;
Song, Liping ;
Liu, Shuai ;
Srivastava, Gautam .
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 17 (03)
[30]   Optimal deep learning based fusion model for biomedical image classification [J].
Mansour, Romany F. ;
Alfar, Nada M. ;
Abdel-Khalek, Sayed ;
Abdelhaq, Maha ;
Saeed, Rashid A. ;
Alsaqour, Raed .
EXPERT SYSTEMS, 2022, 39 (03)