Detection of citrus in the natural environment using Dense-TRU-YOLO  

作　　者：Taixiong Zheng Yilin Zhu Siyu Liu Yongfu Li Mingzhe Jiang 

机构地区：[1]School of Advanced Manufacturing Engineering.Chongqing University of Posts and Telecommunications,Nan’an,Chongqing 400065,China

出　　处：《International Journal of Agricultural and Biological Engineering》2025年第1期260-266,共7页国际农业与生物工程学报(英文)

基　　金：supported by the special research project of the Innovation and Development Center for Ideological and Political Work in Colleges and Universities(Wuhan Donghu University)under the Ministry of Education in 2024(Practice Research on the Whole-process Fine Cultivation of New Engineering Talents with New Qualities in the Context of New Productive Forces,Grant No.WHDHSZZX2024085);the Humanities and Social Sciences Research project of the Chongqing Education Commission in 2024(Theory and Practice Research on Digital Portraits Enabling Comprehensive Quality Evaluation of College Students,Grant No.24SKGH100);the general project of the“14th Five-Year Plan”for Education Science in Chongqing in 2024(Research and Practice on the Construction of an Intelligent Recommendation Employment System for Person-Job Matching Enabled by Digital Portraits,Grant No.K24YG2060081).

摘　　要：Accurate detection of citrus in the natural orchard is crucial for citrus-picking robots.However,it has become a challenging task due to the influence of illumination,severe shading of branches and leaves,as well as overlapping of citrus.To this end,a Dense-TRU-YOLO model was proposed,which integrated the Denseblock with the Transformer and used UNet++network as the neck structure.First of all,the Denseblock structure was incorporated into YOLOv5,which added shallow semantic information to the deep part of the network and improved the flow of information and gradients.Secondly,the deepest Cross Stage Partial Connections(CSP)bottleneck with the 3 convolutions module of the backbone was replaced by the CSP Transformer with 3 convolutions module,which increased the semantic resolution and improved the detection accuracy of occlusion.Finally,the neck of the original network was replaced by the combined structure of UNet++feature pyramid networks(UNet++-FPN),which not only added cross-weighted links between nodes with the same size but also enhanced the feature fusion ability between nodes with different sizes,making the regression of the network to the target boundary more accurate.Ablation experiments and comparison experiments showed that the Dense-TRU-YOLO can effectively improve the detection accuracy of citrus under severe occlusion and overlap.The overall accuracy,recall,mAP@0.5,and F1 were 90.8%,87.6%,90.5%,and 87.9%,respectively.The precision of Dense-TRU-YOLO was the highest,which was 3.9%,6.45%,1.9%,7.4%,3.3%,4.9%,and 9.9%higher than that of the YOLOv5-s,YOLOv3,YOLOv5-n,YOLOv4-tiny,YOLOv4,YOLOX,and YOLOF,respectively.In addition,the reasoning speed was 9.2 ms,1.7 ms,10.5 ms,and 2.3 ms faster than that of YOLOv3,YOLOv5-n,YOLOv4,and YOLOX.Dense TRU-YOLO is designed to enhance the accuracy of fruit recognition in natural settings and boost the detection capabilities for small targets at extended ranges.

关 键 词：CITRUS picking robot Dense-TRU-YOLO Denseblock UNet++-FPN 

分 类 号：G63[文化科学—教育学]