{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T09:45:01Z","timestamp":1768556701239,"version":"3.49.0"},"reference-count":50,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"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:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>In modern agriculture, tomatoes, as key economic crops, face challenges during harvesting due to complex growth environments; traditional object detection technologies are limited by performance and struggle to accurately identify and locate ripe and small-target tomatoes under leaf occlusion and uneven illumination.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To address these issues, this study sets YOLOv8n as the baseline model, focusing on improving it to enhance performance per tomato detection\u2019s core needs. First, it analyzes YOLOv8n\u2019s inherent bottlenecks in feature extraction and small-target recognition, then proposes targeted schemes: specifically, to boost feature extraction, a Space-to-Depth convolution module (SPD) is introduced by restructuring convolutional operations; to improve small-target detection, a dedicated small-target detection layer is added and integrated with the Parallelized Patch-Aware Attention mechanism (PPA); meanwhile, to balance performance and efficiency, a lightweight Slim-Neck structure and a self-developed Detect_CBAM detection head are adopted; finally, the Distance-Intersection over Union loss function (DIoU) optimizes gradient distribution during training. Experiments are conducted on the self-built \u201ctomato_dataset\u201d (7,160 images, divided into 5,008 for training, 720 for validation, 1,432 for testing) with evaluation metrics including bounding box precision, recall, mAP@0.5, mAP@0.5:0.95, Parameters, and FLOPS, and performance comparisons made with mainstream YOLO models (YOLOv5n, YOLOv6n, YOLOv8n), lightweight models (SSD-MobileNetv2, EfficientDet-D0), and two-stage algorithms (Faster R-CNN, Cascade R-CNN).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Results show the improved model achieves 89.6% precision, 87.3% recall, 93.5% mAP@0.5, 58.6% mAP@0.5:0.95, significantly outperforming YOLOv8n and most comparative models, and the two-stage algorithms in both detection accuracy and efficiency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>In conclusion, this study solves detection problems of ripe and small-target tomatoes in polymorphic environments, improves the model\u2019s accuracy and robustness, provides reliable technical support for automated harvesting, and contributes to modern agricultural intelligent development.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2025.1660480","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T15:36:07Z","timestamp":1768491367000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing polymorphic tomato picking detection: improved YOLOv8n architecture to tackle data under complex environments"],"prefix":"10.3389","volume":"16","author":[{"given":"Qiang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2020.571299","article-title":"Tomato fruit detection and counting in greenhouses using deep learning","volume":"11","author":"Afonso","year":"2020","journal-title":"Front. Plant Sci."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1093\/jxb\/erf072","article-title":"Ethylene biosynthesis and action in tomato: a model for climacteric fruit ripening","volume":"53","author":"Alexander","year":"2002","journal-title":"J. Exp. Bot."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/foods10010045","article-title":"Nutritional composition and bioactive compounds in tomatoes and their impact on human health and disease: A review","volume":"10","author":"Ali","year":"2020","journal-title":"Foods"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15040377","article-title":"Machine learning in sustainable agriculture: systematic review and research perspectives","volume":"15","author":"Botero-Valencia","year":"2025","journal-title":"Agriculture"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","article-title":"Cascade R-CNN: high quality object detection and instance segmentation","volume":"43","author":"Cai","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097","article-title":"Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks","author":"Chattopadhyay","year":"2017","journal-title":"2018 IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1614881","article-title":"A detection method for synchronous recognition of string tomatoes and picking points based on keypoint detection","volume":"16","author":"Deng","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1447263","article-title":"Multi-stage tomato fruit recognition method based on improved YOLOv8","volume":"15","author":"Fu","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B9","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"B10","first-page":"2980","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture13091814","article-title":"An overview of the application of machine vision in recognition and localization of fruit and vegetable harvesting robots","volume":"13","author":"Hou","year":"2023","journal-title":"Agriculture"},{"key":"B12","first-page":"1314","article-title":"Searching for mobileNetV3","author":"Howard","year":"2019"},{"key":"B13","doi-asserted-by":"publisher","first-page":"154683","DOI":"10.1109\/ACCESS.2019.2949343","article-title":"Automatic detection of single ripe tomato on plant combining faster R-CNN and intuitionistic fuzzy set","volume":"7","author":"Hu","year":"2019","journal-title":"IEEE Access"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109520","article-title":"Excellent tomato detector based on pruning and distillation to balance accuracy and lightweight","volume":"227","author":"Huang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1596739","article-title":"AITP-YOLO: improved tomato ripeness detection model based on multiple strategies","volume":"16","author":"Huang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B16","doi-asserted-by":"publisher","first-page":"207672","DOI":"10.1109\/ACCESS.2020.3038184","article-title":"Using fuzzy mask R-CNN model to automatically identify tomato ripeness","volume":"8","author":"Huang","year":"2020","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1007\/978-3-030-01264-9_45","article-title":"CornerNet: detecting objects as paired keypoints","volume-title":"Computer Vision \u2013 ECCV 2018(ECCV)","author":"Law","year":"2018"},{"key":"B18","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","volume":"21","author":"Li","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.04388","article-title":"Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection","author":"Li","year":"2020","journal-title":"arXiv"},{"key":"B20","doi-asserted-by":"publisher","first-page":"4522","DOI":"10.1109\/ACCESS.2019.2963080","article-title":"Pruning of network filters for small dataset","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1492110","article-title":"CTDA: an accurate and efficient cherry tomato detection algorithm in complex environments","author":"Liang","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B22","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"SSD: single shot multiBox detector","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Liu","year":"2016"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2022.942875","article-title":"TomatoDet: Anchor-free detector for tomato detection","volume":"13","author":"Liu","year":"2022","journal-title":"Front. Plant Sci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"356","DOI":"10.3390\/agriengineering4020024","article-title":"Prediction of harvest time of tomato using mask R-CNN","volume":"4","author":"Minagawa","year":"2022","journal-title":"AgriEngineering"},{"key":"B25","unstructured":"NanoDet-Plus: Super fast and high accuracy lightweight anchor-free object detection model\n          \n          2021"},{"key":"B26","first-page":"779","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"B27","first-page":"1137","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2017"},{"key":"B28","first-page":"4510","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"B29","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2016","journal-title":"arXiv"},{"key":"B30","doi-asserted-by":"publisher","first-page":"60","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":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108728","article-title":"Optimizing tomato plant phenotyping detection: Boosting YOLOv8 architecture to tackle data complexity","volume":"218","author":"Solimani","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1447855","article-title":"Study on the fusion of improved YOLOv8 and depth camera for bunch tomato stem picking point recognition and localization","volume":"15","author":"Song","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1451018","article-title":"Enhanced tomato detection in greenhouse environments: a lightweight model based on S-YOLO with high accuracy","volume":"15","author":"Sun","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture8120196","article-title":"Detection of key organs in tomato based on deep migration learning in a complex background","volume":"8","author":"Sun","year":"2018","journal-title":"Agriculture"},{"key":"B35","first-page":"443","article-title":"No more strided convolutions or pooling: A new CNN building block for low-resolution images and small objects","volume-title":"Joint European conference on machine learning and knowledge discovery in databases","author":"Sunkara","year":"2022"},{"key":"B36","first-page":"10778","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"B37","doi-asserted-by":"publisher","first-page":"03762","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101886","article-title":"An improved Faster R-CNN model for multi-object tomato maturity detection in complex scenarios","volume":"72","author":"Wang","year":"2022","journal-title":"Ecol. Inf."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture11111059","article-title":"Tomato young fruits detection method under near color background based on improved faster R-CNN with attention mechanism","volume":"11","author":"Wang","year":"2021","journal-title":"Agriculture"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108833","article-title":"NVW-YOLOv8s: An improved YOLOv8s network for real-time detection and segmentation of tomato fruits at different ripeness stages","volume":"219","author":"Wang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B41","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/ISMSIT52890.2021.9604534","article-title":"Image-based tomato maturity classification and detection using faster R-CNN method","volume-title":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","author":"Widiyanto","year":"2021"},{"key":"B42","first-page":"3","volume-title":"CBAM: Convolutional Block Attention Module","author":"Woo","year":"2018"},{"key":"B43","first-page":"1","article-title":"HCF-net: hierarchical context fusion network for infrared small object detection","author":"Xu","year":"2024"},{"key":"B44","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s40648-022-00233-9","article-title":"Automated harvesting by a dual-arm fruit harvesting robot","volume":"9","author":"Yoshida","year":"2022","journal-title":"Robomech. J."},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.01471","article-title":"UnitBox: an advanced object detection network","author":"Yu","year":"2016","journal-title":"arXiv"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture10050160","article-title":"Robust cherry tomatoes detection algorithm in greenhouse scene based on SSD","volume":"10","author":"Yuan","year":"2020","journal-title":"Agriculture"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107625","article-title":"Lightweight tomato real-time detection method based on improved YOLO and mobile deployment","volume":"205","author":"Zeng","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1618214","article-title":"Ta-YOLO: overcoming target blocked challenges in greenhouse tomato detection and counting","volume":"16","author":"Zhao","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B49","doi-asserted-by":"publisher","first-page":"08287","DOI":"10.48550\/arXiv.1911.08287","article-title":"Distance-ioU loss: faster and better learning for bounding box regression","volume":"34","author":"Zheng","year":"2019","journal-title":"arXiv"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.3390\/s21237842","article-title":"Detection and segmentation of mature green tomatoes based on mask R-CNN with automatic image acquisition approach","volume":"21","author":"Zu","year":"2021","journal-title":"Sensors"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1660480\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T15:36:14Z","timestamp":1768491374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1660480\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":50,"alternative-id":["10.3389\/fpls.2025.1660480"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1660480","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]},"article-number":"1660480"}}