{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T07:01:56Z","timestamp":1790146916584,"version":"4.0.1"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>Accurate delineation of individual tree crowns is essential for forest resource management and carbon stock estimation. However, traditional manual interpretation is inefficient under complex forest conditions, and existing deep learning-based object detection models remain vulnerable to crown overlap and background interference. To address these limitations, this study proposes an improved YOLOv8-CAFM model. By integrating the local feature extraction capability of convolutional neural networks (CNNs) with the global contextual modeling capability of transformers, the CAFM module enhances the detection of small and partially occluded crowns. Two plantation forests with contrasting canopy densities, dominated by Pinus sylvestris var. mongolica and Pinus tabuliformis in Zhangwu County, Liaoning Province, China, were selected as the study sites. An individual tree crown dataset was manually delineated from high-resolution UAV imagery to support automated crown detection. The proposed model was compared with widely used crown detection models, including Faster R-CNN, YOLOx, and DeepForest. Based on the detected crowns, field measurements, species-specific allometric equations, and carbon content coefficients were further combined to estimate individual-tree aboveground carbon (AGC) stocks. The results showed that YOLOv8-CAFM performed well in both sparse and dense forests, achieving mAP@0.5:0.95 values of 0.736 and 0.609, respectively, and F1-scores of 0.974 and 0.856, outperforming Faster R-CNN, YOLOx, and DeepForest. The extracted crown areas were also highly consistent with the reference data (R\u00b2 = 0.898 for sparse forests and 0.794 for dense forests), demonstrating strong boundary delineation capability. Furthermore, the estimated forest AGC stocks showed significant correlations with field measurements, with R\u00b2 values of 0.53 for Pinus sylvestris var. mongolica and 0.60 for Pinus tabuliformis. By jointly modeling local and global features, the proposed method improves individual tree detection, particularly in dense-canopy stand, and provides efficient technical support for accurate forest carbon sink monitoring.<\/jats:p>","DOI":"10.3389\/fpls.2026.1958828","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T06:20:44Z","timestamp":1790144444000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based automatic tree-level crown detection from high-resolution UAV imagery for aboveground carbon stock estimation"],"prefix":"10.3389","volume":"17","author":[{"given":"Hancong","family":"Fu","sequence":"first","affiliation":[{"name":"School of Energy, Environmental and Geomatics Engineering, Anqing Normal University","place":["Anqing, Anhui, China"]},{"name":"College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengqian","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiadan","family":"Huangfu","sequence":"additional","affiliation":[{"name":"College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Han","sequence":"additional","affiliation":[{"name":"College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing)","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1101\/2022.07.10.499480","article-title":"Accurate delineation of individual tree crowns in tropical forests from aerial RGB imagery using Mask R\u2010CNN","volume":"9","author":"Ball","year":"2023","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"B2","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1038\/s41586-020-2824-5","article-title":"An unexpectedly large count of trees in the West African Sahara and Sahel","volume":"587","author":"Brandt","year":"2020","journal-title":"Nature"},{"key":"B3","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/s001380050091","article-title":"Automated delineation of individual tree crowns in high spatial resolution aerial images by multiple-scale analysis","volume":"11","author":"Brandtberg","year":"1998","journal-title":"Mach. Vision Appl."},{"key":"B4","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1002\/(sici)1097-4571(199401)45:1<12::aid-asi2>3.0.co;2-l","article-title":"The relationship between recall and precision","volume":"45","author":"Buckland","year":"1994","journal-title":"J. Am. Soc. For. Inf. Sci."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/f14050863","article-title":"Tree recognition and crown width extraction based on novel Faster-RCNN in a dense loblolly pine environment","volume":"14","author":"Cai","year":"2023","journal-title":"Forests"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3390\/f12091145","article-title":"Mapping boreal forest spruce beetle health status at the individual crown scale using fused spectral and structural data","volume":"12","author":"Cessna","year":"2021","journal-title":"Forests"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1111\/gcb.15569","article-title":"Forest microclimates and climate change: Importance, drivers and future research agenda","volume":"27","author":"De Frenne","year":"2021","journal-title":"Global Change Biol."},{"key":"B8","first-page":"303","article-title":"Comparative analysis of deep learning models for olive tree crown and shadow segmentation towards biovolume estimation","author":"Demissie","year":"2025"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3390\/f13060911","article-title":"Recent advances in forest insect pests and diseases monitoring using UAV-based data: A systematic review","volume":"13","author":"Duarte","year":"2022","journal-title":"Forests"},{"key":"B10","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.rse.2016.08.013","article-title":"Review of studies on tree species classification from remotely sensed data","volume":"186","author":"Fassnacht","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"B11","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.isprsjprs.2019.01.019","article-title":"Tree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis","volume":"149","author":"Ferreira","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"B12","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1093\/sjaf\/19.4.177","article-title":"The relationship of diameter at breast height and crown diameter for four species groups in Hardin County, Tennessee","volume":"19","author":"Gering","year":"1995","journal-title":"South. J. Appl. For."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.foreco.2021.119868","article-title":"Growing stock monitoring by European National Forest Inventories: Historical origins, current methods and harmonisation","volume":"505","author":"Gschwantner","year":"2022","journal-title":"For. Ecol. Manage."},{"key":"B14","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.isprsjprs.2021.06.003","article-title":"Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN)","volume":"178","author":"Hao","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"B15","doi-asserted-by":"publisher","first-page":"3753","DOI":"10.1080\/17538947.2023.2257636","article-title":"The co-effect of image resolution and crown size on deep learning for individual tree detection and delineation","volume":"16","author":"Hao","year":"2023","journal-title":"Int. J. Digital Earth"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1080\/15481603.2021.1974275","article-title":"Urban tree species classification using UAV-based multi-sensor data fusion and machine learning","volume":"58","author":"Hartling","year":"2021","journal-title":"GIScience Remote Sens."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5194\/gmd-2022-64","article-title":"Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not","volume":"2022","author":"Hodson","year":"2022","journal-title":"Geosci. Model. Dev. Discuss."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1080\/01431161.2022.2032455","article-title":"UAV remote sensing monitoring of pine forest diseases based on improved Mask R-CNN","volume":"43","author":"Hu","year":"2022","journal-title":"Int. J. Remote Sens."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/lgrs.2024.3370299","article-title":"Hybrid convolutional and attention network for hyperspectral image denoising","volume":"21","author":"Hu","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2253","DOI":"10.1109\/jstars.2018.2830410","article-title":"Individual tree crown detection and delineation from very-high-resolution UAV images based on bias field and marker-controlled watershed segmentation algorithms","volume":"11","author":"Huang","year":"2018","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"B21","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1109\/TASLP.2015.2409733","article-title":"Maximum F1-score discriminative training criterion for automatic mispronunciation detection","volume":"23","author":"Huang","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"B22","doi-asserted-by":"publisher","first-page":"9525","DOI":"10.1080\/01431161.2020.1800127","article-title":"Individual tree detection using template matching of multiple rasters derived from multispectral airborne laser scanning data","volume":"41","author":"Huo","year":"2020","journal-title":"Int. J. Remote Sens."},{"key":"B23","doi-asserted-by":"publisher","first-page":"415","DOI":"10.3390\/f10050415","article-title":"Characterizing seedling stands using leaf-off and leaf-on photogrammetric point clouds and hyperspectral imagery acquired from unmanned aerial vehicle","volume":"10","author":"Imangholiloo","year":"2019","journal-title":"Forests"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2019","DOI":"10.1080\/15481603.2022.2143872","article-title":"A deep learning model using geostationary satellite data for forest fire detection with reduced detection latency","volume":"59","author":"Kang","year":"2022","journal-title":"GIScience Remote Sens."},{"key":"B25","first-page":"8266","article-title":"Shadowsense: Unsupervised domain adaptation and feature fusion for shadow-agnostic tree crown detection from rgb-thermal drone imagery","author":"Kapil","year":"2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","article-title":"Review on convolutional neural networks (CNN) in vegetation remote sensing","volume":"173","author":"Kattenborn","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3390\/rs15184394","article-title":"Unveiling the potential of drone-borne optical imagery in forest ecology: A study on the recognition and mapping of two evergreen coniferous species","volume":"15","author":"Korznikov","year":"2023","journal-title":"Remote Sens."},{"key":"B28","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.isprsjprs.2022.05.002","article-title":"Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery","volume":"189","author":"Lassalle","year":"2022","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.3390\/rs12071078","article-title":"Individual tree crown segmentation of a larch plantation using airborne laser scanning data based on region growing and canopy morphology features","volume":"12","author":"Ma","year":"2020","journal-title":"Remote Sens."},{"key":"B30","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.jag.2018.05.002","article-title":"Testing and evaluating different LiDAR-derived canopy height model generation methods for tree height estimation","volume":"71","author":"Mielcarek","year":"2018","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101207","article-title":"Individual tree crown delineation from high-resolution UAV images in broadleaf forest","volume":"61","author":"Miraki","year":"2021","journal-title":"Ecol. Inf."},{"key":"B32","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1111\/j.2041-210x.2012.00266.x","article-title":"Error propagation in biomass estimation in tropical forests","volume":"4","author":"Molto","year":"2013","journal-title":"Methods Ecol. Evol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"111747","DOI":"10.1016\/j.rse.2020.111747","article-title":"The application of unmanned aerial vehicles (UAVs) to estimate above-ground biomass of mangrove ecosystems","volume":"242","author":"Navarro","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/cli8020021","article-title":"Forest contribution to climate change mitigation: Management oriented to carbon capture and storage","volume":"8","author":"Nunes","year":"2020","journal-title":"Climate"},{"key":"B35","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1038\/s41598-020-79653-9","article-title":"Explainable identification and mapping of trees using UAV RGB image and deep learning","volume":"11","author":"Onishi","year":"2021","journal-title":"Sci. Rep."},{"key":"B36","doi-asserted-by":"publisher","first-page":"2392","DOI":"10.1080\/01431161.2016.1264028","article-title":"Determining tree height and crown diameter from high-resolution UAV imagery","volume":"38","author":"Panagiotidis","year":"2017","journal-title":"Int. J. Remote Sens."},{"key":"B37","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.isprsjprs.2020.08.005","article-title":"Detecting and mapping tree seedlings in UAV imagery using convolutional neural networks and field-verified data","volume":"168","author":"Pearse","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102946","article-title":"Automatic detection of snow breakage at single tree level using YOLOv5 applied to UAV imagery","volume":"112","author":"Puliti","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B39","first-page":"1","article-title":"Individual tree crown detection using GAN and RetinaNet on tropical forest","author":"Roslan","year":"2021"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3390\/s21051617","article-title":"Olive tree biovolume from UAV multi-resolution image segmentation with mask R-CNN","volume":"21","author":"Safonova","year":"2021","journal-title":"Sensors"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40663-019-0210-2","article-title":"Review on carbon storage estimation of forest ecosystem and applications in China","volume":"7","author":"Sun","year":"2020","journal-title":"For. Ecosyst."},{"key":"B42","doi-asserted-by":"publisher","first-page":"127685","DOI":"10.1016\/j.neucom.2024.127685","article-title":"Multi-YOLOv8: An infrared moving small object detection model based on YOLOv8 for air vehicle","volume":"588","author":"Sun","year":"2024","journal-title":"Neurocomputing"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"B44","doi-asserted-by":"publisher","first-page":"7751","DOI":"10.1109\/jstars.2021.3100748","article-title":"Delineation of individual tree crowns using high spatial resolution multispectral WorldView-3 satellite imagery","volume":"14","author":"Tong","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"B45","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1109\/lgrs.2013.2242044","article-title":"Directional local filtering for stand density estimation in closed forest canopies using VHR optical and LiDAR data","volume":"10","author":"Van Coillie","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.3390\/f10090793","article-title":"Individual rubber tree segmentation based on ground-based LiDAR data and faster R-CNN of deep learning","volume":"10","author":"Wang","year":"2019","journal-title":"Forests"},{"key":"B47","doi-asserted-by":"publisher","first-page":"2659","DOI":"10.3390\/agronomy12112659","article-title":"Convolutional neural networks in computer vision for grain crop phenotyping: A review","volume":"12","author":"Wang","year":"2022","journal-title":"Agronomy-Basel"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.1101\/2020.07.07.191551","article-title":"DeepForest: A Python package for RGB deep learning tree crown delineation","volume":"11","author":"Weinstein","year":"2020","journal-title":"Methods Ecol. Evol."},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105504","article-title":"Extracting apple tree crown information from remote imagery using deep learning","volume":"174","author":"Wu","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"B50","doi-asserted-by":"publisher","first-page":"4762","DOI":"10.3390\/rs14194762","article-title":"Object-oriented canopy gap extraction from UAV images based on edge enhancement","volume":"14","author":"Xia","year":"2022","journal-title":"Remote Sens."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.876357","article-title":"Deep learning-based segmentation of peach diseases using convolutional neural network","volume":"13","author":"Yao","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B52","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.rse.2018.12.034","article-title":"Individual mangrove tree measurement using UAV-based LiDAR data: Possibilities and challenges","volume":"223","author":"Yin","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.107062","article-title":"Complete and accurate holly fruits counting using YOLOX object detection","volume":"198","author":"Zhang","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B54","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1080\/01431161.2015.1030043","article-title":"Agent-based region growing for individual tree crown delineation from airborne laser scanning (ALS) data","volume":"36","author":"Zhen","year":"2015","journal-title":"Int. J. Remote Sens."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1958828\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T06:20:45Z","timestamp":1790144445000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1958828\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":54,"alternative-id":["10.3389\/fpls.2026.1958828"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1958828","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"1958828"}}