{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T12:48:49Z","timestamp":1782218929109,"version":"3.54.5"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["18K11346 and 21K11931"],"award-info":[{"award-number":["18K11346 and 21K11931"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Inspection of combs is a critical task in beekeeping where the condition of the comb and the size of the bee population within a hive are assessed. Manual counting of bees is a cumbersome process that compromises efficiency and accuracy. To address this issue, we propose an automated, machine-learning-based inspection method that uses single images of combs with bees. This method eliminates the need for specialized equipment, such as optical sensors, video cameras, or additional entrance modifications for bee traffic monitoring. The research question was to determine which anatomical region of the honeybee provides the most accurate detection results, and whether combining multiple detection approaches could improve accuracy overall. We annotated three distinct parts of honeybees in comb images: the abdomen, head, and whole-body. The SSD models with VGG16 pretrained backbones and YOLOv11 were fine-tuned to detect each part, and their detection accuracies were compared. We also attempted to combine predicted bounding boxes using the Hungarian method to compensate for those that were not detected due to occlusions. Experimental results showed superior accuracy of the abdomen detector compared to the head and whole-body detectors across different densities of bee images. The integrated approach effectively reduced the number of undetected bees compared to individual detection methods. Furthermore, applying the matching framework to YOLOv11 yielded consistent recall improvements over whole-body detection alone, empirically demonstrating that the proposed matching strategy is detector-agnostic and addresses occlusion-induced false negatives independently of the underlying detection architecture. The proposed machine learning-based method successfully automates bee counting from single comb images. This offers a simple solution for beekeeping comb inspection automation.<\/jats:p>","DOI":"10.1007\/s42979-026-05189-w","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T11:57:15Z","timestamp":1782215835000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Honeybee Counting on Comb Images via Part-Level Annotation and Hungarian Matching"],"prefix":"10.1007","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9175-0609","authenticated-orcid":false,"given":"Naoya","family":"Tsuruta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keito","family":"Ohara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madoka","family":"Hasegawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"issue":"1","key":"5189_CR1","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1111\/aab.12727","volume":"180","author":"R Odemer","year":"2020","unstructured":"Odemer R. Approaches, challenges and recent advances in automated bee counting devices: a review. Ann Appl Biol. 2020;180(1):73\u201389. https:\/\/doi.org\/10.1111\/aab.12727.","journal-title":"Ann Appl Biol"},{"issue":"1","key":"5189_CR2","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1111\/2041-210X.13504","volume":"12","author":"MS Norouzzadeh","year":"2021","unstructured":"Norouzzadeh MS, Morris D, Beery S, Joshi N, Jojic N, Clune J. A deep active learning system for species identification and counting in camera trap images. Methods Ecol Evol. 2021;12(1):150\u201361. https:\/\/doi.org\/10.1111\/2041-210X.13504.","journal-title":"Methods Ecol Evol"},{"issue":"5","key":"5189_CR3","doi-asserted-by":"publisher","first-page":"1683","DOI":"10.1007\/s11119-023-10034-8","volume":"24","author":"G Farjon","year":"2023","unstructured":"Farjon G, Huijun L, Edan Y. Deep-learning-based counting methods, datasets, and applications in agriculture: a review. Precision Agric. 2023;24(5):1683\u2013711. https:\/\/doi.org\/10.1007\/s11119-023-10034-8.","journal-title":"Precision Agric"},{"key":"5189_CR4","doi-asserted-by":"publisher","unstructured":"Davidson P, Steininger M, Lautenschlager F, Kobs K, Krause A, Hotho A. Anomaly detection in beehives using deep recurrent autoencoders. In: Proceedings of the 9th International Conference on Sensor Networks. SCITEPRESS - Science and Technology Publications; 2020: 142\u2013149. https:\/\/doi.org\/10.5220\/0009161201420149.","DOI":"10.5220\/0009161201420149"},{"key":"5189_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.108560","volume":"217","author":"S Bilik","year":"2024","unstructured":"Bilik S, Zemcik T, Kratochvila L, Ricanek D, Richter M, Zambanini S, et al. Machine learning and computer vision techniques in continuous beehive monitoring applications: a survey. Comput Electron Agric. 2024;217:108560. https:\/\/doi.org\/10.1016\/j.compag.2023.108560.","journal-title":"Comput Electron Agric"},{"issue":"9","key":"5189_CR6","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.ifacol.2024.07.369","volume":"58","author":"S Bilik","year":"2024","unstructured":"Bilik S, Janakova I, Ligocki A, Karel Horak DF. Computer vision approaches for automated bee counting application. IFAC-PapersOnLine. 2024;58(9):43\u20138. https:\/\/doi.org\/10.1016\/j.ifacol.2024.07.369.","journal-title":"IFAC-PapersOnLine"},{"key":"5189_CR7","doi-asserted-by":"publisher","unstructured":"Sindagi V, Yasarla R, Patel V. Pushing the frontiers of unconstrained crowd counting: New dataset and benchmark method. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE; 2019: 1221\u20131231 https:\/\/doi.org\/10.1109\/ICCV.2019.00131.","DOI":"10.1109\/ICCV.2019.00131"},{"key":"5189_CR8","doi-asserted-by":"publisher","unstructured":"Arteta C, Lempitsky V, Zisserman A. Counting in the wild. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision \u2013 ECCV 2016. Springer International Publishing; 2016: 9911. https:\/\/doi.org\/10.1007\/978-3-319-46478-7_30.","DOI":"10.1007\/978-3-319-46478-7_30"},{"issue":"1","key":"5189_CR9","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1186\/s13007-017-0224-0","volume":"13","author":"H Lu","year":"2017","unstructured":"Lu H, Cao Z, Xiao Y, Zhuang B, Shen C. TasselNet: Counting maize tassels in the wild via local counts regression network. Plant Methods. 2017;13(1):79. https:\/\/doi.org\/10.1186\/s13007-017-0224-0.","journal-title":"Plant Methods"},{"key":"5189_CR10","doi-asserted-by":"publisher","unstructured":"Gao G, Gao J, Liu Q, Wang Q, Wang Y. CNN-based density estimation and crowd counting: a survey; 2020. https:\/\/doi.org\/10.48550\/arXiv.2003.12783. arXiv:2003.12783.","DOI":"10.48550\/arXiv.2003.12783"},{"key":"5189_CR11","doi-asserted-by":"publisher","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC. SSD: single shot multibox detector. In Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision \u2013 ECCV 2016. Springer International Publishing; 2016:9905. https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"5189_CR12","doi-asserted-by":"publisher","first-page":"24344","DOI":"10.1109\/ACCESS.2020.2971026","volume":"8","author":"S Zhai","year":"2020","unstructured":"Zhai S, Shang D, Wang S, Dong S. DF-SSD: An improved SSD object detection algorithm based on DenseNet and feature fusion. IEEE Access. 2020;8:24344\u201357. https:\/\/doi.org\/10.1109\/ACCESS.2020.2971026.","journal-title":"IEEE Access"},{"issue":"8","key":"5189_CR13","doi-asserted-by":"publisher","first-page":"11539","DOI":"10.1007\/s11042-020-10191-2","volume":"80","author":"S Zhou","year":"2021","unstructured":"Zhou S, Qiu J. Enhanced SSD with interactive multi-scale attention features for object detection. Multimed Tools Appl. 2021;80(8):11539\u201356. https:\/\/doi.org\/10.1007\/s11042-020-10191-2.","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"5189_CR14","doi-asserted-by":"publisher","first-page":"440","DOI":"10.3390\/app13010440","volume":"13","author":"Z Qi","year":"2022","unstructured":"Qi Z, Zhou M, Zhu G, Xue Y. Multiple pedestrian tracking in dense crowds combined with head tracking. Appl Sci. 2022;13(1):440. https:\/\/doi.org\/10.3390\/app13010440.","journal-title":"Appl Sci"},{"issue":"1\u20132","key":"5189_CR15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn HW. The Hungarian method for the assignment problem. Naval Res Log Quart. 1955;2(1\u20132):83\u201397. https:\/\/doi.org\/10.1002\/nav.3800020109.","journal-title":"Naval Res Log Quart"},{"key":"5189_CR16","unstructured":"Jocher G, Qiu J, Chaurasia A. Ultralytics YOLO11; 2024. https:\/\/github.com\/ultralytics\/ultralytics."}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-05189-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-026-05189-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-026-05189-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T11:57:20Z","timestamp":1782215840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-026-05189-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":16,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["5189"],"URL":"https:\/\/doi.org\/10.1007\/s42979-026-05189-w","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"26 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"605"}}