{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:17Z","timestamp":1788934037443,"version":"build-2803163510"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"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 detection accuracy and frequent missed detections of citrus diseases caused by leaf occlusion, small lesion sizes, and high visual similarity among disease categories in complex orchard environments, this study proposes LCWG-DETR, a citrus disease detection method that combines wavelet edge features with Gaussian distance regression. First, an LGFE-ResNet18 network is developed for feature extraction. It integrates texture perception guided by the standard deviation of local intensity deviations with global structural encoding in the Fourier frequency domain. This design compensates for the attenuation of high frequency information from small lesions caused by stacked convolutional layers and improves the extraction of subtle disease features. Next, a cross scale adaptive feature fusion module, termed CAFF, is introduced. It employs progressive layerwise fusion and dynamic weighting to reduce the loss of spatial details during upsampling. In addition, a wavelet directional attention module, termed WDAM, is constructed. Haar wavelet decomposition is used to extract horizontal and vertical high frequency components and generate directional modulation weights, thereby guiding the network to focus more accurately on lesion boundaries and regions with abrupt texture variations. Finally, a Gaussian composite distance loss, termed GCD, is introduced. It represents bounding boxes as two dimensional Gaussian distributions with covariance matrices, which alleviates vanishing gradients and scale sensitivity during small lesion regression. Experimental results on the self collected JXDF dataset and the public OFDD dataset show that LCWG-DETR improves mAP by 5.07% and 3.41%, respectively, compared with the baseline model, while reducing the number of parameters by 0.35 M. These results demonstrate that the proposed method achieves a favorable balance between detection accuracy and real time performance. Moreover, it maintains stable detection performance and strong generalization under typical conditions involving occlusion, dense targets, backlighting, and complex backgrounds, providing reliable technical support for the visual perception systems of citrus harvesting robots.<\/jats:p>","DOI":"10.3389\/fpls.2026.1942627","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:49:58Z","timestamp":1788932998000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LCWG-DETR: a wavelet-enhanced detection transformer for citrus disease detection improving visual perception in harvesting"],"prefix":"10.3389","volume":"17","author":[{"given":"Dalin","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Information Technology, Nanchang Vocational University","place":["Jiangxi, 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":"Ke","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Information Technology, Nanchang Vocational University","place":["Jiangxi, China"]},{"name":"School of Electronic and Information Engineering, Lanzhou Jiaotong University","place":["Lanzhou, 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":[[2026,9,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.compag.2017.04.008","article-title":"Symptom based automated detection of citrus diseases using color histogram and textural descriptors","volume":"138","author":"Ali","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"B2","doi-asserted-by":"publisher","first-page":"852","DOI":"10.31018\/jans.v15i2.4630","article-title":"Performance analysis of support vector machine for early identification of citrus diseases","volume":"15","author":"Barman","year":"2023","journal-title":"J. Appl. Natural Sci."},{"key":"B3","doi-asserted-by":"publisher","first-page":"6910","DOI":"10.1109\/TCE.2025.3563993","article-title":"A consumer electronics-enhanced UAV system for agricultural farm tracking with fuzzy SMO and actuator fault detection control algorithms","volume":"71","author":"Bilal","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.02138","article-title":"An implementation of faster RCNN with study for region sampling","author":"Chen","year":"2017","journal-title":"arXiv"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/plants14081206","article-title":"Rice growth estimation and yield prediction by combining the DSSAT model and remote sensing data using the Monte Carlo Markov chain technique","volume":"14","author":"Chen","year":"2025","journal-title":"Plants"},{"key":"B6","doi-asserted-by":"publisher","first-page":"6061","DOI":"10.1109\/TITS.2023.3336659","article-title":"Multi-objective multi-picking-robot task allocation: Mathematical model and discrete artificial bee colony algorithm","volume":"25","author":"Dai","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/su15054576","article-title":"Smart disease detection system for citrus fruits using deep learning with edge computing","volume":"15","author":"Dhiman","year":"2023","journal-title":"Sustainability"},{"key":"B8","first-page":"1","article-title":"Smart agriculture: Farm management through IoT with predictive and precision monitoring","author":"Dobre","year":"2024"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.64898\/2025.12.09.693306","article-title":"CitriBEiTNet: A hybrid CNN-transformer architecture combining MobileNetV2 with BEiT\u2019s global attention for automated citrus leaf disease diagnosis","author":"Eman","year":"2025"},{"key":"B10","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"},{"key":"B11","first-page":"3490","article-title":"TOOD: Task-aligned one-stage object detection","author":"Feng","year":"2021"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1847836","article-title":"A lightweight LBM detection transformer with multi-scale feature fusion for citrus-picking robots","volume":"17","author":"Gao","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B13","doi-asserted-by":"publisher","first-page":"12659","DOI":"10.1038\/s41598-025-97159-0","article-title":"Integrating advanced deep learning techniques for enhanced detection and classification of citrus leaf and fruit diseases","volume":"15","author":"Goyal","year":"2025","journal-title":"Sci. Rep."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2025.3531970","article-title":"Gaussian combined distance: A generic metric for object detection","volume":"22","author":"Guan","year":"2025","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture16101058","article-title":"PCSNet-YOLOv12: YOLOv12-based target detection model for winged aphids on sticky traps with precise coordinate synergy network","volume":"16","author":"Guan","year":"2026","journal-title":"Agriculture"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/s25071971","article-title":"Citrus disease detection based on dilated reparam feature enhancement and shared parameter head","volume":"25","author":"Guo","year":"2025","journal-title":"Sensors"},{"key":"B17","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":"B18","doi-asserted-by":"publisher","DOI":"10.62486\/latia2025122","article-title":"Detection of citrus diseases using artificial intelligence: A systematic review","volume":"3","author":"Injante","year":"2025","journal-title":"LatIA"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102302","article-title":"A dual track deep fusion network for citrus disease classification using group shuffle depthwise feature pyramid and Swin transformer","volume":"78","author":"Karthik","year":"2023","journal-title":"Ecol. Inf."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/horticulturae8080748","article-title":"Bio-circular perspective of citrus fruit loss caused by pathogens: Occurrences, active ingredient recovery and applications","volume":"8","author":"Khamsaw","year":"2022","journal-title":"Horticulturae"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eja.2024.127496","article-title":"Using remotely sensed vegetation indices and multi-stream deep learning improves county-level corn yield predictions","volume":"164","author":"Khan","year":"2025","journal-title":"Eur. J. Agron."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.17725","article-title":"YOLOv11: An overview of the key architectural enhancements","author":"Khanam","year":"2024","journal-title":"arXiv"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy12071505","article-title":"Pre-harvest fruit splitting of citrus","volume":"12","author":"Krajewski","year":"2022","journal-title":"Agronomy"},{"key":"B24","first-page":"34050","article-title":"Statistical characteristic-guided denoising for rapid high-resolution transmission electron microscopy imaging","author":"Li","year":"2026"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3390\/horticulturae11101225","article-title":"MSHLB-DETR: Transformer-based multi-scale citrus huanglongbing detection in orchards with aggregation enhancement","volume":"11","author":"Liu","year":"2025","journal-title":"Horticulturae"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15060630","article-title":"RT-DETR-MCDAF: Multimodal fusion of visible light and near-infrared images for citrus surface defect detection in the compound domain","volume":"15","author":"Luo","year":"2025","journal-title":"Agriculture"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.foodcont.2025.111849","article-title":"Advances in the machine learning construction process for citrus quality and disease detection","volume":"182","author":"Mai","year":"2026","journal-title":"Food Control"},{"key":"B28","first-page":"1","article-title":"Exploring DenseNet121 for disease-specific classification in orange crop health monitoring","author":"Mir","year":"2025"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1742689","article-title":"A review of remote sensing-based crop yield estimation: Machine learning techniques and environmental, algorithmic, and hardware limitations","volume":"17","author":"Muhammad","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B30","first-page":"15516","article-title":"It takes two: A duet of periodicity and directionality for burst flicker removal","author":"Qu","year":"2026"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture16040417","article-title":"Satellite remote sensing for crop yield prediction: A review","volume":"16","author":"Rado\u010daj","year":"2026","journal-title":"Agriculture"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.14347","article-title":"DINO-X: A unified vision model for open-world object detection and understanding","author":"Ren","year":"2025","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compag.2010.02.007","article-title":"A review of advanced techniques for detecting plant diseases","volume":"72","author":"Sankaran","year":"2010","journal-title":"Comput. Electron. Agric."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.cropro.2025.107181","article-title":"Multi-component image analysis for citrus disease detection using convolutional neural networks","volume":"193","author":"Sharma","year":"2025","journal-title":"Crop Prot."},{"key":"B35","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1007\/s13197-026-06632-9","article-title":"Harnessing the potential of fruit processing industrial waste for circular economy: A comprehensive review","volume":"63","author":"Singh","year":"2026","journal-title":"J. Food Sci. Technol."},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.52202\/085713-2627","article-title":"YOLOv12: Attention-centric real-time object detectors","author":"Tian","year":"2025"},{"key":"B37","first-page":"1","article-title":"YOLOv8: A novel object detection algorithm with enhanced performance and robustness","author":"Varghese","year":"2024"},{"key":"B38","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"B39","doi-asserted-by":"publisher","first-page":"3438","DOI":"10.1109\/TCSVT.2025.3625990","article-title":"DICFusion: Infrared and visible image fusion via a deep integrated and semantic-coordinated network","volume":"36","author":"Wang","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2026.1783499","article-title":"A multi-scale parallel weighted fusion dynamic attention method for citrus leaf disease recognitions","volume":"17","author":"Wu","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B41","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s44267-024-00072-9","article-title":"FusionMamba: Dynamic feature enhancement for multimodal image fusion with Mamba","volume":"2","author":"Xie","year":"2024","journal-title":"Vis. Intell."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.fcr.2025.110057","article-title":"Chlorophyll dynamic fusion based on high-throughput remote sensing and machine learning algorithms for cotton yield prediction","volume":"333","author":"Yang","year":"2025","journal-title":"Field Crops Res."},{"key":"B43","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1016\/j.inpa.2025.02.006","article-title":"Detection of fungal disease in citrus fruit based on hyperspectral imaging","volume":"12","author":"Yu","year":"2025","journal-title":"Inf. Process. Agric."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2025.3630246","article-title":"ISGLNet: Infrared small target detection with intrinsic sensitivity and guided learning","volume":"63","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B45","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.3390\/agronomy13092232","article-title":"Application progress of UAV-LARS in identification of crop diseases and pests","volume":"13","author":"Zhao","year":"2023","journal-title":"Agronomy"}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1942627\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:50:00Z","timestamp":1788933000000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1942627\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":46,"alternative-id":["10.3389\/fpls.2026.1942627"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1942627","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]},"article-number":"1942627"}}