Research Article | | Peer-Reviewed

Mangrove Interspecies Classification Based on UAV Hyperspectral Images

Received: 7 November 2023     Accepted: 9 December 2023     Published: 14 December 2023
Views:       Downloads:
Abstract

In recent years, the UAV light-weighted hyperspectral imaging system has become more available. It can provide high spatial and spectral resolution images for environment monitoring. Mangrove forest interspecies distribution map is important data source for the government to design the protection policy. A research on UAV hyperspectral remote sensing surveying of mangrove forest is implemented in Futian Nature Reserve area located In Shenzhen, China. The UAV-based hyperspectral images were collected and processed to get the geometrically corrected mosaicked reflectance data that was latter used to extract the mangrove interspecies map. Based on the hyperspectral data, the supervised pixel-based classification methods were implemented. Firstly, NDVI is used to distinguish mangrove forest from other ground object features based on the decision tree classification method with expert knowledge. Then MNF transformation is performed on the hyperspectral data to get the transformed feature that represents the most information of the hyperspectral bands. Next, the best exponential factor formula (OIF) method is used to analyze the first 10 band features chosen by the MNF transformation to get the optimal band combination for classification. Finally, the pixel-based maximum likelihood, minimum distance classification methods are used to classify the mangrove interspecies. The classification results show the distribution of mangrove areas. The pixel-based minimum distance method performs better and the overall classification accuracy can reach to 98.21%.

Published in Earth Sciences (Volume 12, Issue 6)
DOI 10.11648/j.earth.20231206.16
Page(s) 244-248
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

Mangrove, Hyperspectral, Information Extraction, Futian Nature Reserve

References
[1] Lin P. Mangrove. Beijing: Ocean Press, 1984.
[2] Fan H Q. Mangrove-Environmental Protection Guard at the Coastal Zone. Nanning: Guangxi Science and Technology Press, 2000: 32-37.
[3] Liao B W, Li M, Chen Y J, Guan W. Techniques on Restoration and Reconstruction of Mangrove Ecosystem in China. Beijing: SciencePress, 2010.
[4] Blasco F, Saenger P, Janodet E. Mangroves as indicators of coastal change [J]. Catena, 1996, 27 (3–4): 167-178.
[5] Wang Y T. Research on the Health Assessing System of Chinese Mangrove Ecosystems. Beijing: Chinese Academy of Sciences, 2010: 7-70.
[6] Duke N C, Meynecke J O, Dittmann S, et al. A world without mangroves [J]. Science, 2007, 317 (5834): 41.
[7] Liu L, Fan H Q, Li C G. Tide elevations for four mangrove species along western coast of Guangxi, China. Acta Ecologica Sinica, 2012, 32 (3): 690-698.
[8] Giri C, Ochieng E, Tieszen L L, et al. Status and distribution of mangrove forests of the world using earth observation satellite data [J]. Global Ecology & Biogeography, 2015, 20 (1): 154-159.
[9] Xu Z F, Wang S T, Wang C Y, et al. UHD185 hyperspectral image mosaicking based on SIFT [J]. Remote sensing information, 2017, 32 (1): 95-99.
[10] Kim J I, Kim T, Shin D, et al. Fast and robust geometric correction for mosaicking UAV images with narrow overlaps [J]. International Journal of Remote Sensing, 2017, 38 (8-10): 2557-2576.
[11] Hu Q W, Ai M Y, Yin W L, et al. Research on image fully automatic mosaic method with large rotation angle from unmanned aerial vehicle [J]. Computer engineering, 2012, 38 (15): 152-155.
[12] Xiao H Y, Zeng H, Zan Q J, et al. Decision Tree Model in Extraction of Mangrove Community Information Using Hyperspectral Image Data [J]. Journal of Remote Sensing, 2007 (04): 531-537.
[13] Li X, Liu K, Zhu Y H, et al. Study on Mangrove Species Classification based on ZY-3 Image [J]. Remote Sensing Technology and Application, 2018, 33 (02): 360-369.
[14] Yi, L.; Chen, J. M.; Zhang, G.; Xu, X.; Ming, X.; Guo, W. Seamless Mosaicking of UAV-Based Push-Broom Hyperspectral Images for Environment Monitoring. Remote Sens. 2021, 13, 4720.
[15] Zhang, H.; Xia, Q; Dai, S; Zheng, Q.; Zhang, YF; Deng, XS. Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images. Frontiers In Marine Science. 2023, DOI 10.3389/fmars.2023.1243116.
[16] Ou, JH; Tian, YC; Zhang, Q; Xie, XK; Zhang, YL; Tao, J; Lin, JL. Coupling UAV Hyperspectral and LiDAR Data for Mangrove Classification Using XGBoost in China's Pinglu Canal Estuary. Forests. 2023, 14 (9). DOI: 10.3390/f1409183.
Cite This Article
  • APA Style

    Yi, L., Zhang, G., Lu, F., Zhou, Y. (2023). Mangrove Interspecies Classification Based on UAV Hyperspectral Images. Earth Sciences, 12(6), 244-248. https://doi.org/10.11648/j.earth.20231206.16

    Copy | Download

    ACS Style

    Yi, L.; Zhang, G.; Lu, F.; Zhou, Y. Mangrove Interspecies Classification Based on UAV Hyperspectral Images. Earth Sci. 2023, 12(6), 244-248. doi: 10.11648/j.earth.20231206.16

    Copy | Download

    AMA Style

    Yi L, Zhang G, Lu F, Zhou Y. Mangrove Interspecies Classification Based on UAV Hyperspectral Images. Earth Sci. 2023;12(6):244-248. doi: 10.11648/j.earth.20231206.16

    Copy | Download

  • @article{10.11648/j.earth.20231206.16,
      author = {Lina Yi and Guifeng Zhang and Feiyang Lu and Yongcha Zhou},
      title = {Mangrove Interspecies Classification Based on UAV Hyperspectral Images},
      journal = {Earth Sciences},
      volume = {12},
      number = {6},
      pages = {244-248},
      doi = {10.11648/j.earth.20231206.16},
      url = {https://doi.org/10.11648/j.earth.20231206.16},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.earth.20231206.16},
      abstract = {In recent years, the UAV light-weighted hyperspectral imaging system has become more available. It can provide high spatial and spectral resolution images for environment monitoring. Mangrove forest interspecies distribution map is important data source for the government to design the protection policy. A research on UAV hyperspectral remote sensing surveying of mangrove forest is implemented in Futian Nature Reserve area located In Shenzhen, China. The UAV-based hyperspectral images were collected and processed to get the geometrically corrected mosaicked reflectance data that was latter used to extract the mangrove interspecies map. Based on the hyperspectral data, the supervised pixel-based classification methods were implemented. Firstly, NDVI is used to distinguish mangrove forest from other ground object features based on the decision tree classification method with expert knowledge. Then MNF transformation is performed on the hyperspectral data to get the transformed feature that represents the most information of the hyperspectral bands. Next, the best exponential factor formula (OIF) method is used to analyze the first 10 band features chosen by the MNF transformation to get the optimal band combination for classification. Finally, the pixel-based maximum likelihood, minimum distance classification methods are used to classify the mangrove interspecies. The classification results show the distribution of mangrove areas. The pixel-based minimum distance method performs better and the overall classification accuracy can reach to 98.21%.
    },
     year = {2023}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Mangrove Interspecies Classification Based on UAV Hyperspectral Images
    AU  - Lina Yi
    AU  - Guifeng Zhang
    AU  - Feiyang Lu
    AU  - Yongcha Zhou
    Y1  - 2023/12/14
    PY  - 2023
    N1  - https://doi.org/10.11648/j.earth.20231206.16
    DO  - 10.11648/j.earth.20231206.16
    T2  - Earth Sciences
    JF  - Earth Sciences
    JO  - Earth Sciences
    SP  - 244
    EP  - 248
    PB  - Science Publishing Group
    SN  - 2328-5982
    UR  - https://doi.org/10.11648/j.earth.20231206.16
    AB  - In recent years, the UAV light-weighted hyperspectral imaging system has become more available. It can provide high spatial and spectral resolution images for environment monitoring. Mangrove forest interspecies distribution map is important data source for the government to design the protection policy. A research on UAV hyperspectral remote sensing surveying of mangrove forest is implemented in Futian Nature Reserve area located In Shenzhen, China. The UAV-based hyperspectral images were collected and processed to get the geometrically corrected mosaicked reflectance data that was latter used to extract the mangrove interspecies map. Based on the hyperspectral data, the supervised pixel-based classification methods were implemented. Firstly, NDVI is used to distinguish mangrove forest from other ground object features based on the decision tree classification method with expert knowledge. Then MNF transformation is performed on the hyperspectral data to get the transformed feature that represents the most information of the hyperspectral bands. Next, the best exponential factor formula (OIF) method is used to analyze the first 10 band features chosen by the MNF transformation to get the optimal band combination for classification. Finally, the pixel-based maximum likelihood, minimum distance classification methods are used to classify the mangrove interspecies. The classification results show the distribution of mangrove areas. The pixel-based minimum distance method performs better and the overall classification accuracy can reach to 98.21%.
    
    VL  - 12
    IS  - 6
    ER  - 

    Copy | Download

Author Information
  • School of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, China

  • Key Laboratory of Computational Optics Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China; School of Opto-Electronics, University of Chinese Academy of Sciences, Beijing, China

  • School of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, China

  • School of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing, China

  • Sections