{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T21:44:33Z","timestamp":1789249473952,"version":"build-2803163510"},"reference-count":57,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"U.S. Department of Agriculture Hatch Multistate Programmatic Funding"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Computer vision with artificial intelligence (AI) offers a promising tool for blueberry growers to accomplish orchard tasks such as harvest maturity assessment and yield estimation, which otherwise would be labor-intensive and prone to error. However, blueberry detection in natural environments remains challenging due to variable natural lighting, frequent occlusions by leaves and branches, and motion blur due to environmental factors and imaging devices. AI models such as deep learning-based object detectors promise to address these challenges, but they are data-driven, demanding a large-scale, diverse dataset that captures the complexities of real-world orchard conditions. Deployment of these models in practical scenarios often faces limited computing resources, highlighting the importance of achieving the right accuracy\/speed\/memory trade-off in model selection. This study presents a novel comparative benchmark analysis of advanced real-time object detectors, including YOLO (You Only Look Once) (v8\u2013v12) and RT-DETR (Real-Time Detection Transformers) (v1\u2013v2) families, consisting of 36 model variants, evaluated on a newly curated large dataset for blueberry detection. This dataset contained 661 canopy images collected with smartphones during the 2022\u20132023 seasons, consisting of 85,879 manually annotated instances (including 36,256 ripe and 49,623 unripe blueberries) that represent a broad range of lighting conditions, occlusions, and fruit maturity stages. Among the YOLO models, YOLOv12m achieved the best accuracy with a mAP@50 of 93.3%, while RT-DETRv2-X obtained a mAP@50 of 93.6%, the highest among all RT-DETR variants. The inference time varied with the model scale and complexity, and the mid-sized models appeared to offer a good balance between accuracy and speed. To further improve fruit detection performance, all models were fine-tuned using Unbiased Mean Teacher-based semi-supervised learning (SSL) with 1644 cross-source unlabeled canopy images acquired from ground-based machine vision platforms. SSL resulted in accuracy improvements of up to 2.0%, with RT-DETR-v2-X achieving the highest mAP@50 of 95.5%. These findings highlight the efficacy of SSL for leveraging cross-domain unlabeled data, although further research is needed to fully exploit its benefits. The curated dataset and developed software programs are publicly available to facilitate further research and practical deployment.<\/jats:p>","DOI":"10.3390\/s26144373","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:43:34Z","timestamp":1783683814000},"page":"4373","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Comparative Benchmark of Real-Time Detectors for Canopy Image-Based Blueberry Detection Toward Precision Orchard Management"],"prefix":"10.3390","volume":"26","author":[{"given":"Xinyang","family":"Mu","sequence":"first","affiliation":[{"name":"Department of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3636-1137","authenticated-orcid":false,"given":"Yuzhen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4582-4375","authenticated-orcid":false,"given":"Boyang","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Biosystems and Agricultural Engineering, Michigan State University, East Lansing, MI 48824, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1021\/jf072504n","article-title":"Berry fruits for cancer prevention: Status and prospects","volume":"56","author":"Seeram","year":"2008","journal-title":"J. Agric. Food Chem."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.jand.2014.11.001","article-title":"Daily blueberry consumption improves blood pressure and arterial stiffness in postmenopausal women with pre-and stage 1-hypertension: A randomized, double-blind, placebo-controlled clinical trial","volume":"115","author":"Johnson","year":"2015","journal-title":"J. Acad. Nutr. Diet."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.3945\/jn.110.124701","article-title":"Blueberries decrease cardiovascular risk factors in obese men and women with metabolic syndrome","volume":"140","author":"Basu","year":"2010","journal-title":"J. Nutr."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Krikorian, R., Skelton, M.R., Summer, S.S., Shidler, M.D., and Sullivan, P.G. (2022). Blueberry supplementation in midlife for dementia risk reduction. Nutrients, 14.","DOI":"10.3390\/nu14081619"},{"key":"ref_5","unstructured":"US Department of Agriculture, National Agricultural Statistics Service (2024, November 19). Noncitrus Fruits and Nuts 2023 Summary, Available online: https:\/\/www.nass.usda.gov\/Statistics_by_State\/Washington\/Publications\/Fruit\/index.php."},{"key":"ref_6","unstructured":"US Department of Agriculture, Foreign Agricultural Service (2026, July 01). Blueberries Around the Globe: Past, Present, and Future, Available online: https:\/\/fas.usda.gov\/data\/blueberries-around-globe-past-present-and-future."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Retamales, J.B., and Hancock, J.F. (2018). Blueberrie, Cabi.","DOI":"10.1079\/9781780647265.0000"},{"key":"ref_8","unstructured":"Michigan State University (2025). Growth Stages. MSU Extension Blueberries, Michigan State University. Available online: https:\/\/www.canr.msu.edu\/blueberries\/growing_blueberries\/growth-stages."},{"key":"ref_9","unstructured":"DeVetter, L.W., Yang, W.Q., Takeda, F., and Chen, J. (2022). Harvesting Blueberries: A Guide to Machine Pick Blueberries for Fresh Market, Washington State University Extension."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100620","DOI":"10.1016\/j.atech.2024.100620","article-title":"Detection, counting, and maturity assessment of blueberries in canopy images using YOLOv8 and YOLOv9","volume":"9","author":"Deng","year":"2024","journal-title":"Smart Agric. Technol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Bargoti, S., and Underwood, J. (2017). Deep fruit detection in orchards. 2017 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA.2017.7989417"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s11263-006-8707-x","article-title":"Weakly supervised scale-invariant learning of models for visual recognition","volume":"71","author":"Fergus","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1007\/s11263-011-0502-7","article-title":"Non-uniform deblurring for shaken images","volume":"98","author":"Whyte","year":"2012","journal-title":"Int. J. Comput. Vis."},{"key":"ref_14","unstructured":"Sapkota, R., Cheppally, R.H., Sharda, A., and Karkee, M. (2025). RF-DETR Object Detection vs YOLOv12: A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"109090","DOI":"10.1016\/j.compag.2024.109090","article-title":"Agricultural object detection with You Only Look Once (YOLO) Algorithm: A bibliometric and systematic literature review","volume":"223","author":"Badgujar","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Schumann, A.W., Mood, N.S., Mungofa, P.D., MacEachern, C., Zaman, Q., and Esau, T. (2019). Detection of three fruit maturity stages in wild blueberry fields using deep learning artificial neural networks. Proceedings of the 2019 ASABE Annual International Meeting, Boston, MA, USA, 7\u201310 July 2019, American Society of Agricultural and Biological Engineers.","DOI":"10.13031\/aim.201900533"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100099","DOI":"10.1016\/j.atech.2022.100099","article-title":"Detection of fruit maturity stage and yield estimation in wild blueberry using deep learning convolutional neural networks","volume":"3","author":"MacEachern","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zheng, H., Zhang, Y., Zhang, Q., Chen, H., Xu, X., and Wang, G. (2023). \u201cIs this blueberry ripe?\u201d: A blueberry ripeness detection algorithm for use on picking robots. Front. Plant Sci., 14.","DOI":"10.3389\/fpls.2023.1198650"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, C., and Munoz, P. (2023). Blueberry yield estimation through multi-view imagery with YOLOv8 object detection. Proceedings of the 2023 ASABE Annual International Meeting, Omaha, NE, USA, 9\u201312 July 2023, American Society of Agricultural and Biological Engineers.","DOI":"10.13031\/aim.202300883"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mehdipour, S., Mirroshandel, S.A., and Tabatabaei, S.A. (2025). Vision transformers in precision agriculture: A comprehensive survey. arXiv.","DOI":"10.1016\/j.iswa.2025.200617"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Aguilera, C.A., Figueroa-Flores, C., Aguilera, C., and Navarrete, C. (2023). Comprehensive analysis of model errors in blueberry detection and maturity classification: Identifying limitations and proposing future improvements in agricultural monitoring. Agriculture, 14.","DOI":"10.3390\/agriculture14010018"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, Y., Guo, Y., Li, J., Zhou, B., Chen, J., Zhang, M., Cui, Y., and Tang, J. (2024). RT-DETR-Tea: A multi-species tea bud detection model for unstructured environments. Agriculture, 14.","DOI":"10.3390\/agriculture14122256"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"391","DOI":"10.13031\/aea.16247","article-title":"Development and Preliminary Evaluation of a YOLO-Based Fruit Counting and Maturity Evaluation Mobile Application for Blueberries","volume":"41","author":"Deng","year":"2025","journal-title":"Appl. Eng. Agric."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110057","DOI":"10.1016\/j.compag.2025.110057","article-title":"In-field blueberry fruit phenotyping with a MARS-PhenoBot and customized BerryNet","volume":"232","author":"Li","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wasserman-Olin, R., G\u00f3mez, M.I., and Bj\u00f6rkman, T. (2023). Meeting the expectations of the customer: Consumer valuation of broccoli produced in the eastern United States and the impact of local marketing. Sustainability, 15.","DOI":"10.3390\/su15107878"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"8934","DOI":"10.1109\/TKDE.2022.3220219","article-title":"A survey on deep semi-supervised learning","volume":"35","author":"Yang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107624","DOI":"10.1016\/j.compag.2023.107624","article-title":"Weakly and semi-supervised detection, segmentation and tracking of table grapes with limited and noisy data","volume":"205","author":"Ciarfuglia","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Johanson, R., Wilms, C., Johannsen, O., and Frintrop, S. (2024, January 3\u20138). S3AD: Semi-Supervised Small Apple Detection in Orchard Environments. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00692"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, Z., and Ma, C. (2023, January 1\u20136). Dual-contrastive dual-consistency dual-transformer: A semi-supervised approach to medical image segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCVW60793.2023.00094"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Karthika, B., Dharssinee, M., Reshma, V., Venkatesan, R., and Sujarani, R. (2024). Object detection using YOLO-V8. 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), IEEE.","DOI":"10.1109\/ICCCNT61001.2024.10724411"},{"key":"ref_31","unstructured":"Lei, M., Li, S., Wu, Y., Hu, H., Zhou, Y., Zheng, X., Ding, G., Du, S., Wu, Z., and Gao, Y. (2025). YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"107984","DOI":"10.52202\/079017-3429","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Yeh, I.H., and Mark Liao, H.Y. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. European Conference on Computer Vision, Springer Nature.","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref_34","unstructured":"Tian, Y., Ye, Q., and Doermann, D. (2025). Yolov12: Attention-centric real-time object detectors. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 17\u201321). DETRs beat YOLOs on real-time object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_36","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., and Liu, Y. (2024). Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection transformer. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, S., Xia, C., Lv, F., and Shi, Y. (March, January 26). RT-DETRv3: Real-Time End-to-End Object Detection with Hierarchical Dense Positive Supervision. Proceedings of the 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA.","DOI":"10.1109\/WACV61041.2025.00166"},{"key":"ref_38","unstructured":"Liao, Z., Zhao, Y., Shan, X., Yan, Y., Liu, C., Lu, L., Ji, X., and Chen, J. (2025). RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Fang, K., Lu, Y., and Mu, X. (2026). Artificial intelligence-based detection of on-ground chestnuts toward automated picking. AgriEngineering, 8.","DOI":"10.3390\/agriengineering8030116"},{"key":"ref_40","unstructured":"Jocher, G., and Qiu, J. (2026, July 01). Ultralytics YOLO11. Available online: https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Deng, B., Lu, Y., and Brainard, D. (2025). Semi-supervised weed detection in vegetable fields: In-domain and cross-domain experiments. arXiv.","DOI":"10.1016\/j.ifacol.2025.11.770"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Deng, J., Li, W., Chen, Y., and Duan, L. (2021, January 20\u201325). Unbiased mean teacher for cross-domain object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00408"},{"key":"ref_43","unstructured":"Tarvainen, A., and Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_44","unstructured":"Liu, Y.C., Ma, C.Y., He, Z., Kuo, C.W., Chen, K., Zhang, P., Wu, B., Kira, Z., and Vajda, P. (2021). Unbiased teacher for semi-supervised object detection. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lin, X., Zhang, W., Wang, K., Tan, X., Han, J., Ding, E., Wang, J., and Li, G. (2023, January 17\u201324). Semi-DETR: Semi-supervised object detection with detection transformers. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.02280"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"107655","DOI":"10.1016\/j.compag.2023.107655","article-title":"YOLOWeeds: A novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems","volume":"205","author":"Dang","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Le, N.T., Thai, N.T., and Bui, C.V. (2024). Benchmarking Real-Time Object Detection: Evaluating YOLO and RT-DETR on Speed, Accuracy, and Efficiency. International Symposium on Information and Communication Technology, Springer Nature.","DOI":"10.1007\/978-981-96-4285-4_19"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Sarode, S., Stricker, D., and Afzal, M.Z. (2024). Towards end-to-end semi-supervised table detection with semantic aligned matching transformer. International Conference on Document Analysis and Recognition, Springer Nature.","DOI":"10.1007\/978-3-031-70549-6_18"},{"key":"ref_49","unstructured":"Mu, X., Lu, Y., and Bhatt, S.V. (2025, January 13\u201316). Development of a ground-based machine vision system for highbush blueberry yield estimation. Proceedings of the 2026 ASABE Annual International Meeting, Toronto, ON, Canada."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Chen, J., Ma, A., Huang, L., Su, Y., Li, W., Zhang, H., and Wang, Z. (2023). GA-YOLO: A lightweight YOLO model for dense and occluded grape target detection. Horticulturae, 9.","DOI":"10.3390\/horticulturae9040443"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Buczy\u0144ski, K., Kap\u0142an, M., and Jarosz, Z. (2025). Detection of Red, Yellow, and Purple Raspberry Fruits Using YOLO Models. Agriculture, 15.","DOI":"10.3390\/agriculture15242530"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Luo, R., Zhao, R., and Yi, B. (2025). Enhanced YOLO11n-Seg with Attention Mechanism and Geometric Metric Optimization for Instance Segmentation of Ripe Blueberries in Complex Greenhouse Environments. Agriculture, 15.","DOI":"10.3390\/agriculture15151697"},{"key":"ref_53","first-page":"100125","article-title":"Comprehensive performance evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on detecting and counting fruitlet in complex orchard environments","volume":"4","author":"Sapkota","year":"2026","journal-title":"Agric. Commun."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"100948","DOI":"10.1016\/j.atech.2025.100948","article-title":"Deep learning framework for fruit counting and yield mapping in tart cherry using YOLOv8 and YOLO11","volume":"11","author":"Safre","year":"2025","journal-title":"Smart Agric. Technol."},{"key":"ref_55","unstructured":"Sim\u00e9oni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khalidov, V., Szafraniec, M., Yi, S., and Ramamonjisoa, M. (2025). DINOv3. arXiv."},{"key":"ref_56","unstructured":"Deng, B., and Lu, Y. (2026). DINOv3 meets YOLO26 for weed detection in vegetable crops. arXiv."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"3063","DOI":"10.1002\/rob.22567","article-title":"Geometry-Aware 3D Point Cloud Learning for Precise Cutting-Point Detection in Unstructured Field Environments","volume":"42","author":"Wang","year":"2025","journal-title":"J. Field Robot."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4373\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:49:13Z","timestamp":1783684153000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4373"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":57,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144373"],"URL":"https:\/\/doi.org\/10.3390\/s26144373","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]}}}