智慧农业（中英文）2026，Vol.8Issue(4)：100-113,14.DOI:10.12133/j.smartag.SA202512013
基于改进RT-DETR的棉花成熟度检测算法
Cotton Maturity Detection Algorithm Based on Improved RT-DETR
摘要
Abstract
[Objective]Cotton maturity assessment is a vital task in precision agriculture,playing a crucial role in supporting timely irri-gation,fertilization,and harvesting decisions.However,traditional monitoring approaches are time-consuming and labor-intensive,and current deep learning-based models often struggle to effectively recognize cotton bolls at varying maturity stages,especially in complex field environments with dense foliage,occlusion,and illumination changes.To address these challenges,a high-accuracy and lightweight computer vision model was proposed for cotton maturity detection.[Methods]An enhanced detection framework named cotton maturity-detection transformer(CM-DETR)was proposed,based on an improved real-time detection transformer(RT-DETR)architecture.CM-DETR incorporated three core architectural innovations that significantly improved both detection accuracy and computational efficiency.First,to construct a lightweight and efficient backbone,a novel feature extraction module named Re-parame-terized Group Convolution Spatial Enhancement Lightweight Attention Network(RGCSPELAN)was introduced.This module inte-grated Progressive Convolution,which captured hierarchical and local contextual features,with Re-parameterized Convolution(Rep-Conv),which reduced computational complexity during inference by transforming multi-branch structures into a single-path represen-tation.The combination effectively enhanced the model's feature representation capabilities and gradient propagation while minimiz-ing the number of parameters and FLOPs.Furthermore,RGCSPELAN was designed with a scalable architecture,allowing its compu-tational capacity to be adjusted via a scaling factor.This ensured compatibility with both small and large models,facilitating flexible deployment across resource-constrained edge devices and high-performance systems alike.Second,to address the issue of small target feature loss,a new module termed Deep Robust Feature Downsampling(DRFD)was proposed.DRFD employed a multi-scale feature fusion strategy by integrating multiple downsampling branches(e.g.,convolutional,cut-based,and max-pooling pathways).This de-sign enabled the model to retain fine-grained spatial details while expanding its receptive field.Third,the original loss function in RT-DETR was replaced with Focaler-CIoU,and an adaptive regression optimization strategy integrating sample reweighting and geomet-ric constraints was implemented to improve bounding box localization under complex conditions.[Results and Discussions]Experimen-tal results demonstrated that CM-DETR achieved mAP50 and mAP50～95 scores of 80.8%and 51.1%,respectively,outperforming the baseline model by 3.7 and 1.8 percentage points.Meanwhile,CM-DETR reduced the parameter count and computational cost by 31.7%and 22.8%,respectively,indicating a favorable trade-off between detection accuracy and model efficiency.The incorporation of the DRFD module enhanced the model's sensitivity to small and subtly distinct features related to cotton maturity,improved robust-ness under diverse field conditions,and enabled more precise detection of cotton bolls at different growth stages.Moreover,the opti-mized regression strategy contributed to more stable bounding box prediction performance in scenarios involving occlusion,scale vari-ation,and dense foliage.Overall,the proposed architectural improvements effectively strengthened feature representation capability while maintaining lightweight characteristics,thereby demonstrating practical applicability in real-time agricultural environments.[Conclusions]The proposed CM-DETR model provides an efficient and scalable solution for automated cotton maturity detection.By enhancing multi-stage feature recognition,improving small-target sensitivity,and reducing the demand on computational resources,CM-DETR serves as a reliable tool for intelligent decision-making in precision agriculture.Its practical deployment can support more accurate timing for irrigation,fertilization,and harvesting,thereby contributing to improved crop management and yield optimization.关键词
棉花成熟度/RT-DETR/目标检测/RGCSPELAN/DRFD/Focaler-CIoU损失函数Key words
cotton maturity/RT-DETR/object detection/RGCSPELAN/DRFD/Focaler-CIoU loss function分类
信息技术与安全科学引用本文复制引用
史绮梦,汪军,徐晓峰,张玮逸..基于改进RT-DETR的棉花成熟度检测算法[J].智慧农业（中英文）,2026,8(4):100-113,14.基金项目
国家自然科学基金(62406004) （62406004）
安徽高校协同创新项目(GXXT-2019-020) National Natural Science Foundation of China(62406004) （GXXT-2019-020）
Collaborative Innovation Project of Anhui Higher Edu-cation Institutions(GXXT-2019-020) （GXXT-2019-020）
