{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T13:48:59Z","timestamp":1788961739158,"version":"build-2803163510"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Accurate fruit detection is a key component of precision agriculture applications such as crop yield estimation, orchard management, and intelligent harvesting. In scenarios where immature fruits exhibit visual similarity to the background or where significant varietal differences exist, traditional models often lack sufficient generalization ability, resulting in reduced detection accuracy and unstable predictions. To address this problem, this paper proposes a fruit detection model, MSRRT-DETR, which achieves a balance of high accuracy, real-time performance, and strong generalization capability. To improve detection accuracy and robustness in complex orchard environments, MSRRT-DETR introduces three major enhancements to the RT-DETR framework: a Multi-Scale Convolutional Attention Module (MSBlock) to enhance feature representation at different scales; a Spatial and Channel Synergistic Attention Module (SCSA) to improve object focus and discriminative capability; and a Re-parameterized Feature Pyramid Network (RepGFPN) to achieve efficient multi-scale feature fusion. Experimental results show that MSRRT-DETR achieves a mAP50 of 87.3% on the self-constructed TSApple dataset, outperforming mainstream lightweight models YOLOv8, YOLO11, and YOLO12 by 2.0\u20137.9 percentage points, exceeding two-stage detectors including Faster R-CNN, Mask R-CNN, and Cascade R-CNN by 5.1\u20138.6 percentage points, and surpassing the RT-DETR series by 1.1\u20132.6 percentage points. With an inference speed of 30.2 FPS, comparable to the YOLO series, MSRRT-DETR achieves an excellent balance between accuracy and real-time performance. In addition, MSRRT-DETR demonstrates outstanding cross-domain generalization capability on four public datasets including MinneApple, validating its stable applicability across diverse scenarios and fruit varieties. MSRRT-DETR combines high recognition accuracy, fast inference, and strong cross-domain generalization, fully meeting the requirements of fruit detection in complex agricultural scenarios. The model provides robust technical support for intelligent monitoring and automated orchard management in precision agriculture, and holds significant practical value and broad potential for application.<\/jats:p>","DOI":"10.1371\/journal.pone.0342854","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T17:32:31Z","timestamp":1773423151000},"page":"e0342854","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["MSRRT-DETR: A high-precision apple detection method with strong cross-domain generalization capability in complex orchard scenes"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2635-2334","authenticated-orcid":true,"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sawut","family":"Mamat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiufen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Run","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangjie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaotong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"issue":"8","key":"pone.0342854.ref001","doi-asserted-by":"crossref","first-page":"495","DOI":"10.3390\/biomimetics9080495","article-title":"Apple-harvesting robot based on the YOLOv5-RACF Model","volume":"9","author":"F Zhu","year":"2024","journal-title":"Biomimetics (Basel)"},{"key":"pone.0342854.ref002","doi-asserted-by":"crossref","unstructured":"YOLO-ALW: An Enhanced High-Precision Model for Chili Maturity Detection. https:\/\/www.mdpi.com\/1424-8220\/25\/5\/1405. Accessed 2025 July 10.","DOI":"10.3390\/s25051405"},{"issue":"5","key":"pone.0342854.ref003","doi-asserted-by":"crossref","first-page":"483","DOI":"10.3390\/agriculture15050483","article-title":"Research on apple detection and tracking count in complex scenes based on the improved YOLOv7-Tiny-PDE","volume":"15","author":"D Cao","year":"2025","journal-title":"Agriculture"},{"issue":"20","key":"pone.0342854.ref004","doi-asserted-by":"crossref","first-page":"23336","DOI":"10.1007\/s10489-023-04742-x","article-title":"Bunet: An effective and efficient segmentation method based on bilateral encoder-decoder structure for rapid detection of apple tree branches","volume":"53","author":"S Zhang","year":"2023","journal-title":"Appl Intell"},{"issue":"6","key":"pone.0342854.ref005","doi-asserted-by":"crossref","first-page":"1625","DOI":"10.3390\/agronomy13061625","article-title":"Fruit detection and recognition based on deep learning for automatic harvesting: An overview and review","volume":"13","author":"F Xiao","year":"2023","journal-title":"Agronomy"},{"issue":"12","key":"pone.0342854.ref006","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.3390\/agriculture15121238","article-title":"LGVM-YOLOv8n: A lightweight apple instance segmentation model for standard orchard environments","volume":"15","author":"W Han","year":"2025","journal-title":"Agriculture"},{"key":"pone.0342854.ref007","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.biosystemseng.2023.09.005","article-title":"Twice matched fruit counting system: An automatic fruit counting pipeline in modern apple orchard using mutual and secondary matches","volume":"234","author":"Z Wu","year":"2023","journal-title":"Biosystems Engineering"},{"key":"pone.0342854.ref008","doi-asserted-by":"crossref","first-page":"105634","DOI":"10.1016\/j.compag.2020.105634","article-title":"Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN","volume":"176","author":"F Gao","year":"2020","journal-title":"Computers and Electronics in Agriculture"},{"key":"pone.0342854.ref009","doi-asserted-by":"crossref","first-page":"59069","DOI":"10.1109\/ACCESS.2019.2914929","article-title":"Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks","volume":"7","author":"P Jiang","year":"2019","journal-title":"IEEE Access"},{"issue":"9","key":"pone.0342854.ref010","doi-asserted-by":"crossref","first-page":"102220","DOI":"10.1016\/j.jksuci.2024.102220","article-title":"DNE-YOLO: A method for apple fruit detection in Diverse Natural Environments","volume":"36","author":"H Wu","year":"2024","journal-title":"Journal of King Saud University - Computer and Information Sciences"},{"issue":"1","key":"pone.0342854.ref011","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1186\/s13007-025-01387-4","article-title":"An advanced deep learning method for pepper diseases and pests detection","volume":"21","author":"X Wang","year":"2025","journal-title":"Plant Methods"},{"key":"pone.0342854.ref012","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1186\/s13007-020-00624-2","article-title":"Early recognition of tomato gray leaf spot disease based on MobileNetv2-YOLOv3 model","volume":"16","author":"J Liu","year":"2020","journal-title":"Plant Methods"},{"key":"pone.0342854.ref013","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.compag.2019.01.012","article-title":"Apple detection during different growth stages in orchards using the improved YOLO-V3 model","volume":"157","author":"Y Tian","year":"2019","journal-title":"Computers and Electronics in Agriculture"},{"issue":"5","key":"pone.0342854.ref014","article-title":"ESC-YOLO: optimizing apple fruit recognition with efficient spatial and channel features in YOLOX","volume":"21","author":"J Sun","year":"2024","journal-title":"J Real-Time Image Proc"},{"issue":"1","key":"pone.0342854.ref015","doi-asserted-by":"crossref","first-page":"114","DOI":"10.3390\/agriculture14010114","article-title":"AG-YOLO: A rapid citrus fruit detection algorithm with global context fusion","volume":"14","author":"Y Lin","year":"2024","journal-title":"Agriculture"},{"key":"pone.0342854.ref016","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_13","article-title":"End-to-End Object Detection with Transformers","author":"N Carion","year":"2020"},{"issue":"1","key":"pone.0342854.ref017","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s13007-025-01382-9","article-title":"Plant recognition of maize seedling stage in UAV remote sensing images based on H-RT-DETR","volume":"21","author":"Y Wu","year":"2025","journal-title":"Plant Methods"},{"issue":"18","key":"pone.0342854.ref018","article-title":"Apple recognition in complex environments based on FC-DETR","volume":"10","author":"L Hu","year":"2024","journal-title":"Heliyon"},{"key":"pone.0342854.ref019","doi-asserted-by":"crossref","first-page":"108298","DOI":"10.1016\/j.compag.2023.108298","article-title":"Transforming unmanned pineapple picking with spatio-temporal convolutional neural networks","volume":"214","author":"F Meng","year":"2023","journal-title":"Computers and Electronics in Agriculture"},{"issue":"10","key":"pone.0342854.ref020","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.3390\/agriculture15101104","article-title":"YOLO11-ARAF: An accurate and lightweight method for apple detection in real-world complex orchard environments","volume":"15","author":"Y Lin","year":"2025","journal-title":"Agriculture"},{"key":"pone.0342854.ref021","unstructured":"\u2018DETRs Beat YOLOs on Real-time Object Detection | IEEE Conference Publication | IEEE Xplore\u2019. Accessed: Jul. 10, 2025. https:\/\/ieeexplore.ieee.org\/document\/10657220"},{"key":"pone.0342854.ref022","author":"K He","year":"2015","journal-title":"Deep Residual Learning for Image Recognition"},{"issue":"6","key":"pone.0342854.ref023","doi-asserted-by":"crossref","first-page":"4240","DOI":"10.1109\/TPAMI.2025.3538473","article-title":"YOLO-MS: Rethinking multi-scale representation learning for real-time object detection","volume":"47","author":"Y Chen","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"pone.0342854.ref024","doi-asserted-by":"crossref","first-page":"2691","DOI":"10.3390\/s25092691","article-title":"Trinocular vision-driven robotic fertilization: Enhanced YOLOv8n for precision mulberry growth synchronization","volume":"25","author":"M Ming","year":"2025","journal-title":"Sensors (Basel)"},{"key":"pone.0342854.ref025","doi-asserted-by":"crossref","first-page":"129866","DOI":"10.1016\/j.neucom.2025.129866","article-title":"SCSA: Exploring the synergistic effects between spatial and channel attention","volume":"634","author":"Y Si","year":"2025","journal-title":"Neurocomputing"},{"key":"pone.0342854.ref026","doi-asserted-by":"crossref","first-page":"1541266","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":"D Wang","year":"2025","journal-title":"Front Plant Sci"},{"key":"pone.0342854.ref027","author":"X Xu","year":"2023"},{"issue":"4","key":"pone.0342854.ref028","doi-asserted-by":"crossref","first-page":"839","DOI":"10.3390\/agronomy15040839","article-title":"MSPB-YOLO: High-precision detection algorithm of multi-site pepper blight disease based on improved YOLOv8","volume":"15","author":"X Zheng","year":"2025","journal-title":"Agronomy"},{"key":"pone.0342854.ref029","unstructured":"Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation. IEEE Journals & Magazine. https:\/\/ieeexplore-ieee-org-443.webvpn.xju.edu.cn:8040\/document\/9523600. Accessed 2025 July 10."},{"issue":"11","key":"pone.0342854.ref030","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.3390\/agronomy14112734","article-title":"YOLOv8-GDCI: Research on the phytophthora blight detection method of different parts of chili based on improved YOLOv8 model","volume":"14","author":"Y Duan","year":"2024","journal-title":"Agronomy"},{"issue":"12","key":"pone.0342854.ref031","doi-asserted-by":"crossref","first-page":"734","DOI":"10.3390\/drones8120734","article-title":"Autonomous yield estimation system for small commercial orchards using UAV and AI","volume":"8","author":"S Kodors","year":"2024","journal-title":"Drones"},{"issue":"2","key":"pone.0342854.ref032","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/LRA.2020.2965061","article-title":"MinneApple: A benchmark dataset for apple detection and segmentation","volume":"5","author":"N Hani","year":"2020","journal-title":"IEEE Robot Autom Lett"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T17:32:39Z","timestamp":1773423159000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0342854"}},"subtitle":[],"editor":[{"given":"Muhammad Waqar","family":"Akram","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0342854","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]}}}