采用改进YOLOv5的蕉穗识别及其底部果轴定位  

Recognition of bananas to locate bottom fruit axis using improved YOLOv5

作　　者：段洁利[1,2] 王昭锐 邹湘军 袁浩天[1] 黄广生 杨洲 Duan Jieli;Wang Zhaorui;Zou Xiangjun;Yuan Haotian;Huang Guangsheng;Yang Zhou(College of Engineering,South China Agricultural University,Guangzhou 510642,China;Guangdong Laboratory of Lingnan Modern Agricultural Science and Technology,Guangzhou 510600,China;Key Laboratory of Conservation and Precise Utilization of Characteristic Agricultural Resources in Mountainous Areas of Guangdong Province,Jiaying University,Meizhou 514015,China)

机构地区：[1]华南农业大学工程学院,广州510642 [2]岭南现代农业科学与技术广东省实验室,广州510600 [3]嘉应学院广东省山区特色农业资源保护与精准利用重点实验室,梅州514015

出　　处：《农业工程学报》2022年第19期122-130,共9页Transactions of the Chinese Society of Agricultural Engineering

基　　金：岭南现代农业实验室科研项目(NT2021009);国家重点研发计划项目(2020YFD1000104);财政部和农业农村部:现代农业产业技术体系建设专项资金(CARS-31-10);广东省现代农业产业技术体系创新团队建设专项资金(2022KJ109)。

摘　　要：为提高香蕉采摘机器人的作业效率和质量,实现机器人末端承接机构的精确定位,该研究提出一种基于YOLOv5算法的蕉穗识别,并对蕉穗底部果轴进行定位的方法。将CA(Coordinate Attention)注意力机制融合到主干网络中,同时将C3(Concentrated-Comprehensive Convolution Block)特征提取模块与CA注意力机制模块融合构成C3CA模块,以此增强蕉穗特征信息的提取。用EIoU(Efficient Intersection over Union)损失对原损失函数CIoU(Complete Intersection over Union)进行替换,加快模型收敛并降低损失值。通过改进预测目标框回归公式获取试验所需定位点,并对该点的相机坐标系进行转换求解出三维坐标。采用D435i深度相机对蕉穗底部果轴进行定位试验。识别试验表明,与YOLOv5、Faster R-CNN等模型相比,改进YOLOv5模型的平均精度值(mean Average Precision,mAP)分别提升了0.17和21.26个百分点;定位试验表明,采用改进YOLOv5模型对蕉穗底部果轴定位误差均值和误差比均值分别为0.063 m和2.992%,与YOLOv5和Faster R-CNN模型相比,定位误差均值和误差比均值分别降低了0.022 m和1.173个百分点,0.105 m和5.054个百分点。试验实时可视化结果表明,改进模型能对果园环境下蕉穗进行快速识别和定位,保证作业质量,为后续水果采摘机器人的研究奠定了基础。Banana has been one of the major fruits in the production and consumption in China.But,the banana harvesting is a high labor consuming activity with the low efficiency and large fruit damage.This study aims to improve the operation efficiency and quality of the banana in the picking robot.An accurate and rapid recognition was also proposed to locate the fruit axis at the bottom of banana using the YOLOv5 algorithm.Specifically,a coordinate attention(CA)mechanism was fused into the backbone network.The Concentrated-Comprehensive Convolution Block(C3)feature extraction module was fused with the CA attention mechanism module to form the C3CA module,in order to enhance the extraction of the banana feature information.The original Complete Intersection over Union(CIoU)of loss function was replaced with the Efficient Intersection over Union(EIoU).As such,the convergence of the model was speeded up to reduce the loss value.After that,the anchor point was determined for the test to improve the regression formula of prediction target box.The camera coordinate system of the point was transformed to deal with the three-dimensional coordinates.D435i depth camera was then used to locate the fruit axis at the bottom of banana.The original YOLOv5,Faster R-CNN,and improved YOLOv5 model were trained to verify the model.The accuracy of the improved model increased by 2.8 percentage points,the recall rate reached 100%,and the average accuracy value increased by 0.17 percentage points,compared with the original.There were the 52.96 percentage points higher precision,17.91 percentage points higher recall,and 21.26 percentage points higher average precision value,compared with the Faster R-CNN model.The size of the improved model was reduced by 1.06MB,compared with the original.The field test was conducted on July 1,2022 in Dongguan Fruit and Vegetable Research Institute,Guangdong Province,China.A test was realized for the random real-time location of the fruit axis at the bottom of banana in the field environment.The original YOLOv5,

关 键 词：图像识别 机器人 香蕉采摘 果轴定位 注意力机制 损失函数 

分 类 号：S225.93[农业科学—农业机械化工程]