{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T15:28:45Z","timestamp":1788967725805,"version":"build-2803163510"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>To address false positives and missed detections caused by complex orchard backgrounds and small target regions during citrus harvesting, this study proposes a lightweight LBM Detection Transformer for citrus recognition in citrus-picking robots, integrating cross-scale feature fusion. Firstly, a large-kernel attention module (LKAM) is introduced for feature extraction, where multi-scale large-kernel convolutions are employed to comprehensively capture global, local, and texture information while maintaining the lightweight nature of the model. Secondly, a multi-scale linear attention (MSLA) Transformer encoder is incorporated to further enhance feature discrimination, thereby enabling the network to focus more accurately on citrus targets and effectively suppress background interference. Finally, a bidirectional feature pyramid neck (BFPN) is designed to achieve efficient cross-layer feature fusion by integrating deep and shallow representations, which compensates for target information loss caused by occlusion. Experimental results on citrus orchard scenes demonstrate that, compared with the baseline model, the proposed LBM Detection Transformer reduces the parameter count by 5.54 M while improving mAP by 4.69%, mmAP by 5.14%, and R by 3.66%. These results indicate that the proposed method provides an accurate and lightweight solution for intelligent citrus management and automated harvesting applications.<\/jats:p>","DOI":"10.3389\/fpls.2026.1847836","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:36:44Z","timestamp":1781501804000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A lightweight LBM detection transformer with multi-scale feature fusion for citrus-picking robots"],"prefix":"10.3389","volume":"17","author":[{"given":"Ke","family":"Gao","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Lanzhou Jiaotong University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baijing","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Lanzhou Jiaotong University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiren","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Engineering, Jiujiang Polytechnic University of Science and Technology","place":["Jiujiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghui","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Lanzhou Jiaotong University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e36092","article-title":"Improved FasterViT model for citrus disease diagnosis","volume":"10","author":"Chen","year":"2024","journal-title":"Heliyon"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14102233","article-title":"Key technologies for autonomous fruit- and vegetable-picking robots: A review","volume":"14","author":"Chen","year":"2024","journal-title":"Agronomy-Basel"},{"key":"B3","doi-asserted-by":"crossref","unstructured":"Classification of citrus diseases using optimization deep learning approach-Web of Science Core Collection\n          \n          \n            \n              Elaraby\n              A.\n            \n            \n              Hamdy\n              W.\n            \n            \n              Alanazi\n              S.\n            \n          \n          \n          2022","DOI":"10.1155\/2022\/9153207"},{"key":"B4","doi-asserted-by":"publisher","first-page":"895","DOI":"10.32604\/cmc.2023.039781","article-title":"Deep transfer learning based detection and classification of citrus plant diseases","volume":"76","author":"Faisal","year":"2023","journal-title":"CMC-Comput. Mat. Contin."},{"key":"B5","first-page":"3490","article-title":"TOOD: Task-aligned one-stage object detection","author":"Feng","year":"2021"},{"key":"B6","first-page":"195","article-title":"Small object detection in remote sensing based on feature fusion and channel attention","author":"Ge","year":"2024"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2023.109908","article-title":"CitrusUAT: A dataset of orange Citrus sinensis leaves for abnormality detection using image analysis techniques","volume":"52","author":"G\u00f3mez-Flores","year":"2024","journal-title":"Data Brief"},{"key":"B8","unstructured":"Citrus diseases detection using innovative deep learning approach and hybrid meta-heuristic-Web of Science Core Collection\n          \n          \n            \n              Gu\n              Y.\n            \n            \n              Syafrudin\n              M.\n            \n          \n          \n          2025"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1007\/s11119-024-10169-2","article-title":"Detection and localization of citrus picking points based on binocular vision","volume":"25","author":"Hou","year":"2024","journal-title":"Precis. Agric."},{"key":"B10","unstructured":"Contour analysis and gridding-based navel orange recognition algorithm for automatic picking robot | Springer Nature Link\n          \n          \n            \n              Hu\n              X.\n            \n            \n              Liao\n              M.\n            \n            \n              Duan\n              J.\n            \n            \n              Luo\n              J.\n            \n            \n              Gong\n              P.\n            \n          \n          \n          2024"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3390\/s25113327","article-title":"RT-DETR-EVD: An emergency vehicle detection method based on improved RT-DETR","volume":"25","author":"Hu","year":"2025","journal-title":"Sensors"},{"key":"B12","first-page":"2778","article-title":"Bevanet: Bilateral efficient visual attention network for real-time semantic segmentation","author":"Huang","year":"2025"},{"key":"B13","doi-asserted-by":"publisher","first-page":"10788","DOI":"10.1109\/LRA.2024.3474473","article-title":"CitDet: A benchmark dataset for citrus fruit detection","volume":"9","author":"James","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.00201","article-title":"YOLO evolution: A comprehensive benchmark and architectural review of YOLOv12, YOLO11, and their previous versions","author":"Jegham","year":"2025","journal-title":"arXiv preprint"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.18823","article-title":"MSLAU-Net: A hybird CNN-transformer network for medical image segmentation","author":"Lan","year":"2025"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108721","article-title":"Design of citrus peel defect and fruit morphology detection method based on machine vision","volume":"219","author":"Lu","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B17","doi-asserted-by":"publisher","first-page":"24047","DOI":"10.1038\/s41598-025-08557-3","article-title":"A multi-kernel CNN model with attention mechanism for classification of citrus plants diseases","volume":"15","author":"R M","year":"2025","journal-title":"Sci. Rep."},{"key":"B18","unstructured":"A review on YOLOv8 and its advancements | Springer Nature Link\n          \n          \n            \n              Sohan\n              M.\n            \n            \n              Thotakura Sai Ram\n            \n            \n              Ch. Venkata Rami Reddy\n            \n          \n          \n          2024"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2020.00510","article-title":"Recognition and localization methods for vision-based fruit picking robots: A review","volume":"11","author":"Tang","year":"2020","journal-title":"Front. Plant Sci."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12524","article-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025"},{"key":"B21","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","first-page":"83535\u201383574","DOI":"10.1007\/s11042-024-18872-y","article-title":"YOLO-based object detection models: A review and its applications","volume":"83","author":"Vijayakumar","year":"2024","journal-title":"Multimed. Tools Appl"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14081346","article-title":"A review of perception technologies for berry fruit-picking robots: Advantages, disadvantages, challenges, and prospects","volume":"14","author":"Wang","year":"2024","journal-title":"Agriculture-Basel"},{"key":"B24","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MIM.2024.10505191","article-title":"A method of robot picking citrus based on 3D detection","volume":"27","author":"Xiao","year":"2024","journal-title":"IEEE Instrum. Meas. Mag."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3390\/foods13142208","article-title":"Monocular pose estimation method for automatic citrus harvesting using semantic segmentation and rotating target detection","volume":"13","author":"Xiao","year":"2024","journal-title":"Foods"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14081227","article-title":"Flexible hand claw picking method for citrus-picking robot based on target fruit recognition","volume":"14","author":"Xiao","year":"2024","journal-title":"Agriculture-Basel"},{"key":"B27","unstructured":"A detection algorithm for citrus huanglongbing disease based on an improved YOLOv8n-Web of Science Core Collection\n          \n          \n            \n              Xie\n              W.\n            \n            \n              Feng\n              F.\n            \n            \n              Zhang\n              H.\n            \n          \n          \n          2024"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103338","article-title":"SAMamba: Adaptive state space modeling with hierarchical vision for infrared small target detection","volume":"124","author":"Xu","year":"2025","journal-title":"Inf. Fusion"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/pr13051365","article-title":"Research on lightweight citrus leaf pest and disease detection based on PEW-YOLO","volume":"13","author":"Xue","year":"2025","journal-title":"Processes"},{"key":"B30","doi-asserted-by":"publisher","first-page":"7820","DOI":"10.1109\/TCSVT.2024.3376773","article-title":"Asymptotic feature pyramid network for labeling pixels and regions","volume":"34","author":"Yang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15222330","article-title":"The YOLO-OBB-based approach for citrus fruit stem pose estimation and robot picking","volume":"15","author":"Ye","year":"2025","journal-title":"Agriculture-Basel"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2022.861286","article-title":"Real-time target detection method based on lightweight convolutional neural network","volume":"10","author":"Yun","year":"2022","journal-title":"Front. Bioeng. Biotechnol."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14070996","article-title":"Optimizing contact force on an apple picking robot end-effector","volume":"14","author":"Zhang","year":"2024","journal-title":"Agriculture-Basel"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.03605","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022"},{"key":"B35","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.biosystemseng.2024.10.008","article-title":"Harvest motion planning for mango picking robot based on improved RRT-Connect","volume":"248","author":"Zhang","year":"2024","journal-title":"Biosyst. Eng."},{"key":"B36","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15141530","article-title":"Growth stages discrimination of multi-cultivar navel oranges using the fusion of near-infrared hyperspectral imaging and machine vision with deep learning","volume":"15","author":"Zhao","year":"2025","journal-title":"Agriculture-Basel"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14050910","article-title":"Detection of Gannan navel orange ripeness in natural environment based on YOLOv5-NMM","volume":"14","author":"Zhou","year":"2024","journal-title":"Agronomy-Basel"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1847836\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:36:48Z","timestamp":1781501808000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1847836\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":38,"alternative-id":["10.3389\/fpls.2026.1847836"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1847836","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"article-number":"1847836"}}