{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:15:36Z","timestamp":1783577736970,"version":"3.55.0"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006533","name":"Ministerstvo Zem\u011bd\u011blstv\u00ed","doi-asserted-by":"publisher","award":["QL24010368"],"award-info":[{"award-number":["QL24010368"]}],"id":[{"id":"10.13039\/501100006533","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>This paper presents a method to estimate apple tree flower cluster count using image analysis techniques. The main research question is how accurately flower clusters on apple trees can be counted using a camera-based approach and weakly-supervised learning, compared to traditional visual estimation. A camera is used to capture images of blooming apple trees from two sides. These images are processed by a weakly-supervised model based on a ResNet feature extractor and a feature pyramid network serving as the feature aggregator. The model is trained and validated using reference data obtained through manual flower cluster counts in the orchard and from estimations based on camera images. The model was trained using field-validated data and visually-estimated data, enabling a comparative evaluation. The proposed model surpassed conventional image segmentation methods in estimating both manually counted and visually estimated flower clusters. The proposed method achieves a relative error of 10.26% in estimating flower cluster quantities, demonstrating its effectiveness and improved accuracy over traditional approaches. Its reliance on field-validated reference data adds to its robustness and practical relevance.<\/jats:p>","DOI":"10.3389\/fpls.2026.1869941","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:34:06Z","timestamp":1783575246000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-view weakly-supervised learning for apple tree flower counting"],"prefix":"10.3389","volume":"17","author":[{"given":"Martin","family":"Vitousek","sequence":"first","affiliation":[{"name":"Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague","place":["Prague, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Vrba","sequence":"additional","affiliation":[{"name":"Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague","place":["Prague, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matous","family":"Cejnek","sequence":"additional","affiliation":[{"name":"Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague","place":["Prague, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakub","family":"Jura","sequence":"additional","affiliation":[{"name":"Department of Instrumentation and Control Engineering, Faculty of Mechanical Engineering, Czech Technical University in Prague","place":["Prague, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Klara","family":"Schankova","sequence":"additional","affiliation":[{"name":"Research and Breeding Institute of Pomology Holovousy Ltd.","place":["Holovousy, Czechia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/tpami.2012.120","article-title":"Slic superpixels compared to state-of-the-art superpixel methods","volume":"34","author":"Achanta","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B2","doi-asserted-by":"publisher","first-page":"117115","DOI":"10.1109\/access.2019.2936536","article-title":"Date fruit classification for robotic harvesting in a natural environment using deep learning","volume":"7","author":"Altaheri","year":"2019","journal-title":"IEEE Access"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/tpami.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109534","article-title":"Agregnet: A deep regression network for flower and fruit density estimation, localization, and counting in orchards","volume":"227","author":"Bhattarai","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2022.103635","article-title":"A weakly-supervised approach for flower\/fruit counting in apple orchards","volume":"138","author":"Bhattarai","year":"2022","journal-title":"Comput. Ind."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","article-title":"Yolov4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/horticulturae5010003","article-title":"Precision crop load management of apple (malus x domestica borkh.) without chemicals","volume":"5","author":"Bound","year":"2018","journal-title":"Horticulturae"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13245053","article-title":"A weakly supervised crowd counting method via joint cnn and transformer network","volume":"13","author":"Cai","year":"2024","journal-title":"Electronics"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eja.2024.127213","article-title":"Strategies to overcome biennial bearing in apple \u2013 a review","volume":"158","author":"Campbell","year":"2024","journal-title":"Eur. J. Agron."},{"key":"B10","doi-asserted-by":"publisher","first-page":"21986","DOI":"10.1109\/access.2021.3056082","article-title":"Identification of fruit tree pests with deep learning on embedded drone to achieve accurate pesticide spraying","volume":"9","author":"Chen","year":"2021","journal-title":"IEEE Access"},{"key":"B11","first-page":"3642","article-title":"Multi-column deep neural networks for image classification","author":"Ciregan","year":"2012"},{"key":"B12","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"B13","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.compind.2018.03.010","article-title":"Apple flower detection using deep\u00a0convolutional networks","volume":"99","author":"Dias","year":"2018","journal-title":"Comput. Ind."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jafr.2023.100930","article-title":"Deep learning based flower detection and counting in highly populated images: A peach grove case study","volume":"15","author":"Estrada","year":"2024","journal-title":"J.\u00a0Agric. Food Res."},{"key":"B15","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s11119-019-09679-1","article-title":"Detection and counting of flowers on apple trees for better chemical thinning decisions","volume":"21","author":"Farjon","year":"2020","journal-title":"Precis. Agric."},{"key":"B16","doi-asserted-by":"publisher","first-page":"2902","DOI":"10.1109\/lra.2021.3062586","article-title":"Deep regression versus detection for counting in robotic phenotyping","volume":"6","author":"Gomez","year":"2021","journal-title":"IEEE Rob. Autom. Lett."},{"key":"B17","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B18","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.106812","article-title":"Fruit yield prediction and estimation in orchards: A state-of-the-art comprehensive review for both direct and indirect methods","volume":"195","author":"He","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/s23135903","article-title":"Fruit detection and counting in apple orchards based on improved yolov7 and multi-object tracking methods","volume":"23","author":"Hu","year":"2023","journal-title":"Sensors"},{"key":"B21","volume-title":"Software repository","author":"Jocher","year":"2020"},{"key":"B22","volume-title":"Software repository","author":"Jocher","year":"2023"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106641","article-title":"Real-time detection of kiwifruit flower and bud simultaneously in orchard using yolov4 for robotic pollination","volume":"193","author":"Li","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B24","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.34133\/plantphenomics.0172","article-title":"A framework for single-panicle litchi flower counting by regression with multitask learning","volume":"6","author":"Lin","year":"2024","journal-title":"Plant Phenomics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1007\/s11119-022-09882-7","article-title":"Estimating litchi flower number using a multicolumn convolutional neural network based on a density map","volume":"23","author":"Lin","year":"2022","journal-title":"Precis. Agric."},{"key":"B27","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2015"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.05101","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"B29","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1002\/rse2.275","article-title":"Automatic flower detection and phenology monitoring using time-lapse cameras and deep learning","volume":"8","author":"Mann","year":"2022","journal-title":"Remote Sens. Ecol. Conserv."},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3390\/app152413211","article-title":"Learning to count crowds from low-altitude aerial views using weakly supervised feature-adaptive fusion","volume":"15","author":"Mao","year":"2025","journal-title":"Appl. Sci."},{"key":"B31","doi-asserted-by":"publisher","first-page":"41","DOI":"10.5073\/JfK.2009.02.01","article-title":"The bbch system to coding the phenological growth stages of plants-history and publications","volume":"61","author":"Meier","year":"2009","journal-title":"J. Kulturpflanz."},{"key":"B32","first-page":"14013","article-title":"Free lunch enhancements for multi-modal crowd counting","author":"Meng","year":"2025"},{"key":"B33","article-title":"Countformer: Multi-view crowd counting transformer","author":"Mo","year":"2024"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2022.100151","article-title":"Mask r-cnn based apple flower detection and king flower identification for precision pollination","volume":"4","author":"Mu","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2020.105796","article-title":"Automated grapevine flower detection and quantification method based on computer vision and deep learning from on-the-go imaging using a mobile sensing platform under field conditions","volume":"178","author":"Palacios","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00484-006-0043-x","article-title":"Phenological models for blooming of apple in a mountainous region","volume":"51","author":"Rea","year":"2006","journal-title":"Int. J. Biometeorol."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv preprint"},{"key":"B38","first-page":"219","article-title":"Studies in precision crop load management of apple","author":"Robinson","year":"2022"},{"key":"B39","doi-asserted-by":"publisher","first-page":"6","DOI":"10.17660\/actahortic.2020.1281.53","article-title":"Precision crop load management","volume":"21","author":"Robinson","year":"2013","journal-title":"NY Fruit Q."},{"key":"B40","first-page":"90","article-title":"Learning to count with deep object features","author":"Segu\u00ed","year":"2015"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109389","article-title":"Using unmanned aerial vehicle acquired RGB images and Density-Cluster-Count model for tree-level apple flower quantification","volume":"226","author":"Shang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"B44","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.biosystemseng.2024.08.010","article-title":"Three-view cotton flower counting through multi-object tracking and rgb-d imagery","volume":"246","author":"Tan","year":"2024","journal-title":"Biosyst. Eng."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-981-10-1509-0_10","article-title":"Computer vision technology in agricultural automation\u2014a review","volume":"7","author":"Tian","year":"2020","journal-title":"Inf. Process. Agric."},{"key":"B46","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1080\/14620316.2022.2149425","article-title":"Review on crop load management in apple (malus x domestica borkh.)","volume":"98","author":"Verma","year":"2023","journal-title":"J. Hortic. Sci. Biotechnol."},{"key":"B47","first-page":"7464","article-title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1541266","article-title":"YO-AFD: an improved YOLOv8-based deep learning approach for rapid and accurate apple flower detection","volume":"16","author":"Wang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B49","volume-title":"Fundamentals of Temperate Zone Tree Fruit Production","author":"Wertheim","year":"2005"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107803","article-title":"MTYOLOX: Multi-transformers-enabled YOLO for tree-level apple inflorescences detection and density mapping","volume":"209","author":"Xia","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.3390\/s24217012","article-title":"Automatic apple detection and counting with AD-YOLO and MR-SORT","volume":"24","author":"Yang","year":"2024","journal-title":"Sensors"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2021.106383","article-title":"Technological advancements towards developing a robotic pruner for apple trees: A review","volume":"189","author":"Zahid","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103457","article-title":"Object-detection from multi-view remote sensing images: A case study of fruit and flower detection and counting on a central florida strawberry farm","volume":"123","author":"Zheng","year":"2023","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B54","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/jproc.2023.3238524","article-title":"Object detection in 20 years: A survey","volume":"111","author":"Zou","year":"2023","journal-title":"Proc. IEEE"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1869941\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:34:08Z","timestamp":1783575248000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1869941\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":54,"alternative-id":["10.3389\/fpls.2026.1869941"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1869941","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"article-number":"1869941"}}