{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T16:24:51Z","timestamp":1787934291290,"version":"build-2784847793"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"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:p>To address the low contrast and mild blur in aerial tea plantation imagery, this study introduces an RGB\u2013NIR dataset composed of UAV-acquired RGB and near-infrared images. The RGB\u2013NIR representation provides complementary visible and near-infrared information, enhancing the contrast between damaged and healthy leaf regions while reducing interference caused by shadows and highlights. This improves the separability of small pest-damaged areas and early disease lesions in weakly textured tea canopy scenes. Based on this, we propose TEA-LWNet, a lightweight multi-scale detection framework. Its backbone, Multi-FENet, leverages a DS-MBS module for simultaneous high-order semantic expansion and low-level detail preservation. The neck features an Adaptive Enhancement (AE) module for spatial-semantic alignment and an MDFF structure with embedded Gated Fusion (GF) to suppress background diffusion during upsampling. Optimization is driven by SAB-Loss\u2014combining IoU, Distributed Focal Loss, and BCE\u2014enforcing scale-invariant geometric constraints and sub-pixel boundary calibration to prioritize small target learning. Evaluations on a self-built RGB\u2013NIR dataset demonstrate that TEA-LWNet achieves an mAP@0.5 of 93.48% under strict parameter and FLOP constraints. Ablation studies confirm the functional complementarity of the proposed modules in cross-layer noise suppression and boundary refinement. Overall, TEA-LWNet achieves a favorable balance between detection accuracy and model complexity, indicating its potential for resource-constrained agricultural monitoring systems. However, its runtime performance on UAV or embedded edge hardware remains to be further validated.<\/jats:p>","DOI":"10.3389\/fpls.2026.1879101","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T15:38:39Z","timestamp":1787931519000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TEA-LWNet: a lightweight multispectral feature enhancement network based on RGB\u2013NIR fusion for detection of tea leaf diseases and pests"],"prefix":"10.3389","volume":"17","author":[{"given":"Zhenyun","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information Science and Technology, Nanjing Forestry University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, Nanjing Xiaozhuang University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haifeng","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Nanjing Forestry University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1038\/s41598-022-06181-z","article-title":"Detection and identification of tea leaf diseases based on AX-RetinaNet","volume":"12","author":"Bao","year":"2022","journal-title":"Sci. Rep."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107637","article-title":"UAV remote sensing detection of tea leaf blight based on DDMA-YOLO","volume":"205","author":"Bao","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"B3","doi-asserted-by":"publisher","first-page":"48925","DOI":"10.1007\/s11042-023-17472-6","article-title":"Res4net-CBAM: a deep cnn with convolution block attention module for tea leaf disease diagnosis","volume":"83","author":"Bhuyan","year":"2024","journal-title":"Multimed. Tools Appl"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","article-title":"DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention","volume":"33","author":"Chen","year":"2024","journal-title":"IEEE Trans. Img. Process."},{"key":"B5","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1038\/s41467-023-44365-x","article-title":"Mosaic: in-memory computing and routing for small-world spike-based neuromorphic systems","volume":"15","author":"Dalgaty","year":"2024","journal-title":"Nat. Commun."},{"key":"B6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1186\/s13007-024-01239-7","article-title":"A CNN model for early detection of pepper Phytophthora blight using multispectral imaging, integrating spectral and textural information","volume":"20","author":"Duan","year":"2024","journal-title":"Plant Methods"},{"key":"B7","first-page":"49","article-title":"A pipeline for tailored sampling for progressive visual analytics","author":"Hogr\u00e4fer","year":"2022"},{"key":"B8","doi-asserted-by":"publisher","first-page":"5601218","DOI":"10.1109\/TGRS.2023.3339765","article-title":"Detection of tea leaf blight in low-resolution UAV remote sensing images","volume":"62","author":"Hu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B9","first-page":"1740","article-title":"A decoupled spatial-channel inverted bottleneck for image compression","author":"Hu","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","first-page":"4746","DOI":"10.1109\/LRA.2025.3554103","article-title":"On motion blur and deblurring in visual place recognition","volume":"10","author":"Ismagilov","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"B11","doi-asserted-by":"publisher","first-page":"4903","DOI":"10.18494\/SAM5108","article-title":"Integrations of LabelImg, You Only Look Once (YOLO), and Open Source Computer Vision Library (OpenCV) for chicken open mouth detection","volume":"36","author":"Ke","year":"2024","journal-title":"Sens. Mater."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.17733","article-title":"YOLOv13: real-time object detection with hypergraph-enhanced adaptive visual perception","author":"Lei","year":"2025","journal-title":"arXiv"},{"key":"B13","first-page":"21002","article-title":"Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection","volume":"33","author":"Li","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109522","article-title":"Tea bud DG: a lightweight tea bud detection model based on dynamic detection head and adaptive loss function","volume":"227","author":"Lu","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B15","doi-asserted-by":"publisher","first-page":"9336","DOI":"10.1002\/jsfa.13756","article-title":"Early detection of gray blight in tea leaves and rapid screening of resistance varieties by hyperspectral imaging technology","volume":"104","author":"Mao","year":"2024","journal-title":"J. Sci. Food Agric."},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.23919\/CISTI.2019.8760873","article-title":"Spectral and spatial assessment of the Ikonos images fusion, using the Principal Components, Brovey Transform and Multiplicative","author":"Medina","year":"2019"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.lwt.2024.116401","article-title":"Machine learning for authentication of black tea from narrow-geographic origins: Combination of PCA and PLS with LDA and SVM classifiers","volume":"203","author":"Mohammadi","year":"2024","journal-title":"LWT Food Sci. Technol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/s42452-024-06073-z","article-title":"From pixels to plant health: accurate detection of banana Xanthomonas wilt in complex African landscapes using high-resolution UAV images and deep learning","volume":"6","author":"Mora","year":"2024","journal-title":"Discov. Appl. Sci."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.102262","article-title":"Picking point identification and localization method based on Swin-Transformer for high-quality tea","volume":"36","author":"Pan","year":"2024","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"B20","first-page":"11030","article-title":"Incremental residual concept bottleneck models","author":"Shang","year":"2024"},{"key":"B21","first-page":"24261","article-title":"MLP-Mixer: an all-MLP architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.104241","article-title":"MGFNet: An MLP-dominated gated fusion network for semantic segmentation of high-resolution multi-modal remote sensing images","volume":"135","author":"Wei","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15222372","article-title":"Study on the detection model of tea red scab severity class using hyperspectral imaging technology","volume":"15","author":"Wu","year":"2025","journal-title":"Agri."},{"key":"B24","doi-asserted-by":"publisher","first-page":"11799","DOI":"10.1038\/s41598-024-62451-y","article-title":"Classification and identification of tea diseases based on improved YOLOv7 model of MobileNeXt","volume":"14","author":"Xia","year":"2024","journal-title":"Sci. Rep."},{"key":"B25","doi-asserted-by":"publisher","first-page":"76","DOI":"10.19386\/j.cnki.jxnyxb.2026.04.010","article-title":"Physical and chemical properties of different tea germplasms damaged by Apolygus lucorum","volume":"38","author":"Xie","year":"2026","journal-title":"Acta Agric. Jiangxi"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.1002\/ps.7964","article-title":"Image detection model construction of Apolygus lucorum and Empoasca spp. based on improved YOLOv5","volume":"80","author":"Xiong","year":"2024","journal-title":"Pest Manage. Sci."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.atech.2025.100817","article-title":"A deep learning model based on RGB and hyperspectral images for efficiently detecting tea green leafhopper damage symptoms","volume":"10","author":"Xu","year":"2025","journal-title":"Smart Agric. Technol."},{"key":"B28","doi-asserted-by":"crossref","unstructured":"Yang\n              H.-M.\n            \n            \n              Zhang\n              X.-Y.\n            \n            \n              Yin\n              F.\n            \n            \n              Liu\n              C.-L.\n            \n          \n          Robust classification with convolutional prototype learning\n          \n          2018","DOI":"10.1109\/CVPR.2018.00366"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy14051034","article-title":"Improved YOLOv8 and SAHI model for the collaborative detection of small targets at the micro scale: A case study of pest detection in tea","volume":"14","author":"Ye","year":"2024","journal-title":"Agronomy-Basel"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3390\/s24092896","article-title":"YOLOv8-RMDA: Lightweight YOLOv8 network for early detection of small target diseases in tea","volume":"24","author":"Ye","year":"2024","journal-title":"Sensors"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/rs16152820","article-title":"LWSDNet: A lightweight wheat scab detection network based on UAV remote sensing images","volume":"16","author":"Yin","year":"2024","journal-title":"Remote Sens."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.10525","article-title":"Focaler-IoU: More focused intersection over union loss","author":"Zhang","year":"2024","journal-title":"arXiv:2401.10525"},{"key":"B33","doi-asserted-by":"publisher","first-page":"12993","DOI":"10.1609\/aaai.v34i07.6999","article-title":"Distance-IoU loss: faster and better learning for bounding box regression","volume":"34","author":"Zheng","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B34","doi-asserted-by":"publisher","first-page":"4504","DOI":"10.1109\/TNNLS.2024.3376563","article-title":"DPNet: Dual-path network for real-time object detection with lightweight attention","volume":"36","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1879101\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T15:38:42Z","timestamp":1787931522000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1879101\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":34,"alternative-id":["10.3389\/fpls.2026.1879101"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1879101","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"article-number":"1879101"}}