Deep Learning of High-Resolution Unmanned Aerial Vehicle Imagery for Classifying Halophyte Species: A Comparative Study for Small Patches and Mixed Vegetation

被引:3
作者
Kim, Keunyong [1 ]
Lee, Donguk [2 ]
Jang, Yeongjae [1 ]
Lee, Jingyo [1 ]
Kim, Chung-Ho [2 ]
Jou, Hyeong-Tae [2 ]
Ryu, Joo-Hyung [1 ]
机构
[1] Korea Inst Ocean Sci & Technol, Korea Ocean Satellite Ctr, Busan 49111, South Korea
[2] Korea Inst Ocean Sci & Technol, Ocean Climate Response & Ecosyst Report Dept, Busan 49111, South Korea
关键词
classification; deep learning; salt marsh vegetation; UAV-RGB image; U-Net; ECOSYSTEM SERVICES; PLANT-COMMUNITIES; SALT MARSHES; CLASSIFICATION; CARBON;
D O I
10.3390/rs15112723
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Recent advances in deep learning (DL) and unmanned aerial vehicle (UAV) technologies have made it possible to monitor salt marshes more efficiently and precisely. However, studies have rarely compared the classification performance of DL with the pixel-based method for coastal wetland monitoring using UAV data. In particular, many studies have been conducted at the landscape level; however, little is known about the performance of species discrimination in very small patches and in mixed vegetation. We constructed a dataset based on UAV-RGB data and compared the performance of pixel-based and DL methods for five scenarios (combinations of annotation type and patch size) in the classification of salt marsh vegetation. Maximum likelihood, a pixel-based classification method, showed the lowest overall accuracy of 73%, whereas the U-Net classification method achieved over 90% accuracy in all classification scenarios. As expected, in a comparison of pixel-based and DL methods, the DL approach achieved the most accurate classification results. Unexpectedly, there was no significant difference in overall accuracy between the two annotation types and labeling data sizes in this study. However, when comparing the classification results in detail, we confirmed that polygon-type annotation was more effective for mixed-vegetation classification than the bounding-box type. Moreover, the smaller size of labeling data was more effective for detecting small vegetation patches. Our results suggest that a combination of UAV-RGB data and DL can facilitate the accurate mapping of coastal salt marsh vegetation at the local scale.
引用
收藏
页数:16
相关论文
共 46 条
  • [1] Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review
    Adam, Elhadi
    Mutanga, Onisimo
    Rugege, Denis
    [J]. WETLANDS ECOLOGY AND MANAGEMENT, 2010, 18 (03) : 281 - 296
  • [2] Alongi DM, 2012, CARBON MANAG, V3, P313, DOI [10.4155/CMT.12.20, 10.4155/cmt.12.20]
  • [3] The value of estuarine and coastal ecosystem services
    Barbier, Edward B.
    Hacker, Sally D.
    Kennedy, Chris
    Koch, Evamaria W.
    Stier, Adrian C.
    Silliman, Brian R.
    [J]. ECOLOGICAL MONOGRAPHS, 2011, 81 (02) : 169 - 193
  • [4] Drone Image Segmentation Using Machine and Deep Learning for Mapping Raised Bog Vegetation Communities
    Bhatnagar, Saheba
    Gill, Laurence
    Ghosh, Bidisha
    [J]. REMOTE SENSING, 2020, 12 (16)
  • [5] Evaluating the Performance of High Spatial Resolution UAV-Photogrammetry and UAV-LiDAR for Salt Marshes: The Cadiz Bay Study Case
    Celeste Curcio, Andrea
    Peralta, Gloria
    Aranda, Maria
    Barbero, Luis
    [J]. REMOTE SENSING, 2022, 14 (15)
  • [6] Global carbon sequestration in tidal, saline wetland soils
    Chmura, GL
    Anisfeld, SC
    Cahoon, DR
    Lynch, JC
    [J]. GLOBAL BIOGEOCHEMICAL CYCLES, 2003, 17 (04)
  • [7] Chung S.H., 2021, KOREAN J PLANT RES, V31, P342
  • [8] Fine-Scale Mapping of Coastal Plant Communities in the Northeastern USA
    Correll, Maureen D.
    Hantson, Wouter
    Hodgman, Thomas P.
    Cline, Brittany B.
    Elphick, Chris S.
    Shriver, W. Gregory
    Tymkiw, Elizabeth L.
    Olsen, Brian J.
    [J]. WETLANDS, 2019, 39 (01) : 17 - 28
  • [9] Quantification of Extent, Density, and Status of Aquatic Reed Beds Using Point Clouds Derived from UAV-RGB Imagery
    Corti Meneses, Nicolas
    Brunner, Florian
    Baier, Simon
    Geist, Juergen
    Schneider, Thomas
    [J]. REMOTE SENSING, 2018, 10 (12)
  • [10] Characterizing spatial variability in coastal wetland biomass across multiple scales using UAV and satellite imagery
    Doughty, Cheryl L.
    Ambrose, Richard F.
    Okin, Gregory S.
    Cavanaugh, Kyle C.
    [J]. REMOTE SENSING IN ECOLOGY AND CONSERVATION, 2021, 7 (03) : 411 - 429