基于改进YOLOv11n的多尺度茶叶病害检测方法OA

[Objective]Preventing and containing leaf diseases is a critical component of tea production,and accurate identification and localization of symptoms are essential for modern,automated plantation management.Field inspection in tea gardens poses distinctive challenges for vision-based detection algorithms:targets appeared at widely varying scales and morphologies under complex back-grounds and unfixed acquisition distances,which easily misled detectors.Models trained on standardized datasets with uniform dis-tance and background often underperform,leading to false alarms and missed detections.To support method development under realis-tic constraints,YOLO-SADMFA(You Only Look Once-Switchable Atrous Dynamic Multi-scale Frequency-aware Adaptive),a detec-tor based on the YOLOv11n backbone was proposed.The architecture aims to preserve fine details during repeated re-sampling(down-and up-sampling),strengthen modeling of lesions at varying scales,and refine multi-scale feature fusion.[Methods]The pro-posed architecture incorporated additional convolutional,feature extraction,upsampling,and detection head stages to better handle multi-scale representations,and a DMF-Upsample(Dynamic Multi-scale Frequency-aware Upsample)module that performed upsam-pling through multi-scale feature analysis and dynamic frequency adjustment fusion was introduced.This module enabled efficient multi-scale feature integration while effectively mitigating information loss during up-and down-sampling.Concretely,the DMF-Upsample analyzed multi-frequency responses from adjacent pyramid levels and fused them with dynamically learned frequency-se-lective weights,which preserved high-frequency lesion boundaries and textures while retaining low-frequency contextual structure such as leaf contours and global shading.A lightweight gating mechanism estimates per-location and per-channel coefficients to regu-late the contribution of different bands,and a residual bypass preserved identity information to further reduce aliasing and oversmooth-ing introduced by repeated resampling.Furthermore,the baseline C3k2 block was replaced with a switchable atrous convolution(SAConv)module,which enhanced multi-scale feature capture by combining outputs from different dilation rates and incorporates a weight locking mechanism to improve model stability and performance.In practice,the SAConv aggregated parallel atrous branched at multiple dilation factors through learned coefficients under weight locking,which expanded the effective receptive field without sac-rificing spatial resolution and suppressed gridding artifacts,while incurring modest parameter overhead.Lastly,an adaptive spatial fea-ture fusion(ASFF)mechanism was integrated into the detection head,forming an ASFF-Head that learned spatially varying fusion weights across different feature scales,effectively filters conflicting information,and strengthens the model's robustness and overall detection accuracy.Together,these components formed a deeper yet efficient multi-scale pathway suited to complex field scenes.[Re-sults and Discussions]Compared with the original YOLOv11n model,YOLO-SADMFA improved precision,recall,and mAP by 4.4,8.4,and 3.7 percentage points,respectively,indicating more reliable identification and localization across diverse field scenes.The de-tector was particularly effective for multi-scale targets where the lesion area occupied approximately 10％-65％of the image,reflect-ing the variability introduced by unfixed acquisition distance during tea garden patrols.Under low illumination and in complex back-grounds with occlusions and clutter,it maintained stable performance,reduced both missed detections and false alarms,and effective-ly distinguished disease categories with similar morphology and color.On edge computing devices,it sustained about 161 f/s,which met real-time requirements for mobile inspection robots and portable systems.These outcomes demonstrated strengthened robustness to background interference and improved sensitivity at extreme scales,which was consistent with practical demands where the acquisi-tion distance was not fixed.From an ablation perspective,DMF-Upsample preserved high-frequency lesion boundaries while retaining low-frequency structural context after resampling,SAConv expanded receptive fields through multi-dilation aggregation under a weight-locking mechanism,and the ASFF-Head mitigated conflicts among feature pyramids.Their combination yielded cumulative gains in stability and accuracy.Qualitative analyses further supported the quantitative results:Boundary localization improved for small,speckled lesions,large blotches were captured with fewer spurious edges,and distractors such as veins,shadows,and soil tex-tures were less frequently misclassified,confirming the benefits of dynamic multi-scale frequency-aware fusion and adaptive spatial weighting in real field conditions.[Conclusions]The proposed YOLO-SADMFA effectively addressed the multi-scale disease detec-tion challenge in complex tea garden environments,where acquisition distance was not fixed,lesion morphology and color were di-verse,and cluttered backgrounds easily caused misjudgments and omissions.It significantly improved detection accuracy and robust-ness relative to the original YOLOv11n model across a wide range of target scales,and it maintained stable performance under low il-lumination and complex backgrounds typical of field inspections.It provided reliable technical support for automated tea leaf disease inspection systems by enabling accurate localization and identification of lesions in real operating conditions and by sustaining real-time inference on edge devices suitable for patrol-style deployment.