{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:15:10Z","timestamp":1767852910943,"version":"3.49.0"},"reference-count":46,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T00:00:00Z","timestamp":1684886400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007049","name":"Korea Institute of Ocean Science and Technology","doi-asserted-by":"publisher","award":["PEA0115"],"award-info":[{"award-number":["PEA0115"]}],"id":[{"id":"10.13039\/501100007049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/rs15112723","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T02:00:55Z","timestamp":1684980055000},"page":"2723","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Learning of High-Resolution Unmanned Aerial Vehicle Imagery for Classifying Halophyte Species: A Comparative Study for Small Patches and Mixed Vegetation"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2452-0778","authenticated-orcid":false,"given":"Keunyong","family":"Kim","sequence":"first","affiliation":[{"name":"Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0835-2943","authenticated-orcid":false,"given":"Donguk","family":"Lee","sequence":"additional","affiliation":[{"name":"Ocean Climate Response & Ecosystem Report Department, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]},{"given":"Yeongjae","family":"Jang","sequence":"additional","affiliation":[{"name":"Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]},{"given":"Jingyo","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]},{"given":"Chung-Ho","family":"Kim","sequence":"additional","affiliation":[{"name":"Ocean Climate Response & Ecosystem Report Department, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]},{"given":"Hyeong-Tae","family":"Jou","sequence":"additional","affiliation":[{"name":"Ocean Climate Response & Ecosystem Report Department, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]},{"given":"Joo-Hyung","family":"Ryu","sequence":"additional","affiliation":[{"name":"Korea Ocean Satellite Center, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1890\/10-1510.1","article-title":"The value of estuarine and coastal ecosystem services","volume":"81","author":"Barbier","year":"2011","journal-title":"Ecol. Monogr."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.ocecoaman.2012.03.011","article-title":"Beyond carbon: Conceptualizing payments for ecosystem services in blue forests on carbon and other marine and coastal ecosystem services","volume":"83","author":"Lau","year":"2013","journal-title":"Ocean Coast. Manag."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1080\/21664250.2021.1894815","article-title":"Quantifying blue carbon for the largest salt marsh in southern British Columbia: Implications for regional coastal management","volume":"3","author":"Gailis","year":"2021","journal-title":"Coast. Eng. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e2022JF006612","DOI":"10.1029\/2022JF006612","article-title":"The Importance of Storm Surge for Sediment Delivery to Microtidal Marshes","volume":"127","author":"Zhu","year":"2022","journal-title":"JGR Earth Surf."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1146\/annurev.marine.010908.163930","article-title":"Centuries of human-driven change in salt marsh ecosystems","volume":"1","author":"Gedan","year":"2009","journal-title":"Annu. Rev. Mar. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Perrino, E.V., and Wagensommer, R.P. (2022). Crop Wild Relatives (CWRs) Threatened and Endemic to Italy: Urgent Actions for Protection and Use. Biology, 11.","DOI":"10.3390\/biology11020193"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s11273-022-09900-5","article-title":"Changing landscapes: Habitat monitoring and land transformation in a long-time used Mediterranean coastal wetland","volume":"31","author":"Tomaselli","year":"2023","journal-title":"Wetl. Ecol. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1046\/j.1526-100X.2003.00182.x","article-title":"A Comparison of Remote Sensing and Ground-Based Methods for Monitoring Wetland Restoration Success","volume":"11","author":"Shuman","year":"2003","journal-title":"Restor. Ecol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1146\/annurev.energy.30.050504.144248","article-title":"Wetland Resources: Status, Trends, Ecosystem Services, and Restorability","volume":"30","author":"Zedler","year":"2005","journal-title":"Annu. Rev. Environ. Resour."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Guo, M., Li, J., Sheng, C., Xu, J., and Wu, L. (2017). A review of Wetland Remote Sensing. Sensors, 17.","DOI":"10.3390\/s17040777"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.ecss.2018.08.007","article-title":"Classification mapping of salt marsh vegetation by flexible monthly NDVI time-series using Landsat imagery","volume":"213","author":"Sun","year":"2018","journal-title":"Estuar. Coast. Shelf Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Meneses, N.C., Brunner, F., Baier, S., Geist, J., and Schneider, T. (2018). Quantification of Extent, Density, and Status of Aquatic Reed Beds Using Point Clouds Derived from UAV\u2013RGB Imagery. Remote Sens., 10.","DOI":"10.3390\/rs10121869"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1080\/01431161.2016.1271480","article-title":"Mapping of invasive phragmites (common reed) in Gulf of Mexico coastal wetlands using multispectral imagery and small unmanned aerial systems","volume":"38","author":"Samiappan","year":"2017","journal-title":"Int. J. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1002\/rse2.198","article-title":"Characterizing spatial variability in coastal wetland biomass across multiple scales using UAV and satellite imagery","volume":"7","author":"Doughty","year":"2021","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1080\/14498596.2014.913272","article-title":"Effects of class granularity and cofactors on the performance of unsupervised classification of wetlands using multi-spectral aerial photography","volume":"59","author":"Martin","year":"2014","journal-title":"J. Spat. Sci."},{"key":"ref_16","first-page":"106","article-title":"Mapping wild taro with color-infrared aerial photography and image processing","volume":"45","author":"Everitt","year":"2007","journal-title":"J. Aquat. Plant. Manag."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1080\/22797254.2017.1373602","article-title":"Object-Based Classification of Wetland Vegetation Using Very High-Resolution Unmanned Air System Imagery","volume":"50","author":"Liu","year":"2017","journal-title":"Eur. J. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"012098","DOI":"10.1088\/1755-1315\/169\/1\/012098","article-title":"Comparison of pixel-based and object-based image classification techniques in extracting information from UAV imagery data","volume":"169","author":"Sibaruddin","year":"2018","journal-title":"IOP Conf. Ser. Earth Environ. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6380","DOI":"10.3390\/rs70506380","article-title":"Object-Based Image Analysis in Wetland Research: A Review","volume":"7","author":"Dronova","year":"2015","journal-title":"Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2621","DOI":"10.1007\/s13157-020-01373-7","article-title":"Unmanned Aircraft System Photogrammetry for Mapping Diverse Vegetation Species in a Heterogeneous Coastal Wetland","volume":"40","author":"Durgan","year":"2020","journal-title":"Wetlands"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zheng, J.-Y., Hao, Y.-Y., Wang, Y.-C., Zhou, S.-Q., Wu, W.-B., Yuan, Q., Gao, Y., Guo, H.-Q., Cai, X.-X., and Zhao, B. (2022). Coastal Wetland Vegetation Classification Using Pixel-Based, Object-Based and Deep Learning Methods Based on RGB-UAV. Land, 11.","DOI":"10.3390\/land11112039"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s11273-009-9169-z","article-title":"Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: A review","volume":"18","author":"Adam","year":"2010","journal-title":"Wetl. Ecol. Manag."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.3390\/rs3102222","article-title":"Hyperspectral data for mangrove species mapping: A comparison of pixel-based and object-based approach","volume":"3","author":"Kamal","year":"2011","journal-title":"Remote Sens."},{"key":"ref_24","first-page":"5512615","article-title":"Hyperspectral and Multispectral Classification for Coastal Wetland Using Depthwise Feature Interaction Network","volume":"60","author":"Gao","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4296","DOI":"10.1080\/01431161.2016.1211349","article-title":"Identifying Spatial Variability and Complexity in Wetland Vegetation Using an Object-Based Approach","volume":"37","author":"Owers","year":"2016","journal-title":"Int. J. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s13157-018-1028-3","article-title":"Fine-Scale Mapping of Coastal Plant Communities in the Northeastern USA","volume":"39","author":"Correll","year":"2019","journal-title":"Wetlands"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bhatnagar, S., Gill, L., and Ghosh, B. (2020). Drone Image Segmentation Using Machine and Deep Learning for Mapping Raised Bog Vegetation Communities. Remote Sens., 12.","DOI":"10.3390\/rs12162602"},{"key":"ref_28","first-page":"84","article-title":"Dynamics of zonal halophyte communities in salt marshes in the world","volume":"7","author":"Lee","year":"2018","journal-title":"J. Mar. Isl. Cult."},{"key":"ref_29","unstructured":"Park, J.W. (2021). Studies on the Characteristics of Distribution and Environmental Factor of Halophyte Vegetation in Western and Southern Coast in Korea. [Master\u2019s Thesis, Graduate School of Kongju National University]. (Korean with English Abstract)."},{"key":"ref_30","first-page":"38","article-title":"Estimating blue carbon accumulated in a halophyte community using UAV imagery: A case study of the southern coastal wetlands in South Korea","volume":"25","author":"Park","year":"2021","journal-title":"J. Coast. Res."},{"key":"ref_31","first-page":"342","article-title":"Features and Functions of Purple Pigment Compound in Halophytic Plant Suaeda japonica: Antioxidant\/Anticancer Activities and Osmolyte Function in Halotolerance","volume":"31","author":"Chung","year":"2021","journal-title":"Korean J. Plant Res."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015: 18th International Conference, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_33","unstructured":"Mandelli, S., Lipari, V., Bestagini, P., and Tubaro, S. (2019). Interpolation and Denoising of Seismic Data using Convolutional Neural Networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1111\/j.1365-2699.2006.01461.x","article-title":"Distribution of saltmarsh plant communities associated with environmental factors along a latitudinal gradient on the south-west Atlantic coast","volume":"33","author":"Isacch","year":"2006","journal-title":"J. Biogeogr."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2441","DOI":"10.1038\/s41598-017-18721-z","article-title":"Ecophysiological response of native and exotic salt marsh vegetation to waterlogging and salinity: Implications for the effects of sea level rise","volume":"8","author":"Li","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Curcio, A.C., Peralta, G., Aranda, M., and Barbero, L. (2022). Evaluating the Performance of High Spatial Resolution UAV-Photogrammetry and UAV-LiDAR for Salt Marshes: The C\u00e1diz Bay Study Case. Remote Sens., 14.","DOI":"10.3390\/rs14153582"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"102529","DOI":"10.1016\/j.jag.2021.102529","article-title":"Hyperspectral image-based vegetation index (HSVI): A new vegetation index for urban ecological research","volume":"103","author":"Sun","year":"2021","journal-title":"Int. J. Appl. Earth Observ. Geoinform."},{"key":"ref_38","first-page":"313","article-title":"Carbon Sequestration in Mangrove Forests","volume":"3","author":"Alongi","year":"2012","journal-title":"Carb. Manag."},{"key":"ref_39","first-page":"1111","article-title":"Global carbon sequestration in tidal, saline wetland soils","volume":"17","author":"Chmura","year":"2003","journal-title":"Glob. Biogechem. Cycles"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1038\/s43017-021-00224-1","article-title":"Blue Carbon as a Natural Climate Solution","volume":"2","author":"Macreadie","year":"2021","journal-title":"Nat. Rev. Earth Environ."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"nwaa296","DOI":"10.1093\/nsr\/nwaa296","article-title":"Global blue carbon accumulation in tidal wetlands increases with climate change","volume":"8","author":"Wang","year":"2021","journal-title":"Natl. Sci. Rev."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Pham, T.D., Xia, J., Ha, N.T., Bui, D.T., Le, N.N., and Takeuchi, W. (2019). A Review of Remote Sensing Approaches for Monitoring Blue Carbon Ecosystems: Mangroves, Seagrasses and Salt Marshes during 2010\u20132018. Sensors, 19.","DOI":"10.3390\/s19081933"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s13157-011-0148-9","article-title":"Ecosystem carbon stocks of Micronesian mangrove forests","volume":"31","author":"Kauffman","year":"2011","journal-title":"Wetlands"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1496","DOI":"10.1007\/s12237-017-0362-7","article-title":"Coastal Blue Carbon Assessment of Mangroves, Salt Marshes, and Salt Barrens in Tampa Bay, Florida, USA","volume":"41","author":"Radabaugh","year":"2018","journal-title":"Estuaries Coasts"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Meng, X., Shang, N., Zhang, X., Li, C., Zhao, K., Qiu, X., and Weeks, E. (2017). Photogrammetric UAV Mapping of Terrain under Dense Coastal Vegetation: An Object-Oriented Classification Ensemble Algorithm for Classification and Terrain Correction. Remote Sens., 9.","DOI":"10.3390\/rs9111187"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.rse.2006.10.007","article-title":"Mapping mixed vegetation communities in salt marshes using airborne spectral data","volume":"107","author":"Wang","year":"2007","journal-title":"Remote Sens. Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/11\/2723\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:41:00Z","timestamp":1760125260000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/11\/2723"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,24]]},"references-count":46,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["rs15112723"],"URL":"https:\/\/doi.org\/10.3390\/rs15112723","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,24]]}}}