文献类型：期刊文献

中文题名：基于改进YOLOv8的实时菠萝成熟度目标检测方法

英文题名：Real-time object detection method of pineapple ripeness based on improved YOLOv8

作者：周涛[1];王骥[1,2];麦仁贵[3]

机构：[1]广东海洋大学电子与信息工程学院,湛江524088;[2]广东省智慧海洋传感网及其设备工程技术研究中心,湛江524088;[3]广东海洋大学数学与计算机学院,湛江524088

年份：2024

卷号：43

期号：5

起止页码：10

中文期刊名：华中农业大学学报

外文期刊名：Journal of Huazhong Agricultural University

收录：北大核心2023、CSTPCD、、CSCD2023_2024、北大核心、CSCD

基金：广东省普通高校重点领域新一代信息技术专项(2020ZDZX3008)。

语种：中文

中文关键词：菠萝果实;成熟度;YOLOv8;目标检测

外文关键词：pineapple fruit;ripeness;YOLOv8;object detection

中文摘要：为提高不同成熟度种植区域的机械采摘菠萝准确率,保证菠萝品质,提出了基于改进YOLOv8的实时菠萝成熟度目标检测方法。针对自然环境下菠萝机械采摘中存在目标小、数量密集和光线遮挡等问题,改进模型把原始YOLOv8模型中主干部分、颈部部分的公共卷积替换成深度可分离卷积(depthwise separable convo-lution,DSConv),精简模型参数;在融合特征前增加了卷积注意力机制模块(convolutional block attention mod-ule,CBAM),使特征融合更关注重要的特征,提升目标检测的准确率;使用EIoU损失函数替换YOLOv8网络原损失函数CIoU,加快网络收敛速度。结果显示,改进模型对菠萝成熟度检测的平均精度均值为97.33%,与FasterR-CNN、YOLOv4、YOLOv5、YOLOv7对比发现,平均精度均值分别提升5.53、7.91、4.38、4.66百分点;在保证检测精度的前提下,算法模型参数量仅为16.8×10^(6)。结果表明,改进模型提高了菠萝成熟度识别的精度和推理速度,具有更强的鲁棒性。

外文摘要：A real-time object detection method of pineapple ripeness based on improved YOLOv8 was proposed to improve the accuracy of mechanical harvesting of pineapples in planting areas with different ripeness and ensure the quality of pineapples.The improved model replaced the common convolutions in the backbone and neck parts of the original YOLOv8 model with depth-wise separable convolutions(DSConv)to streamline parameters of model to solve the problems of small object size,dense quantity,and light occlusion of picked mechanical pineapple picking in natural environments.Convolutional block at?tention mechanism(CBAM)module was introduced before feature fusion to prioritize important features and improve the accuracy of object detection.The original loss function CIoU of YOLOv8 network was re?placed with the EIoU loss function to accelerate the speed of network convergence.The results showed that the mean of average precision(PmA)of the improved model for detecting the pineapple ripeness was 97.33%.The PmA of improved model was 5.53,7.91,4.38,and 4.66 percentage points higher than that of Faster R-CNN,YOLOv4,YOLOv5 and YOLOv7,respectively.The number of parameters of the algo?rithm model was only 16.8×10^(6)on the premise of ensuring the accuracy of detection.It is indicated that the improved model improves the accuracy and inference speed of recognizing pineapple ripeness,and has stron?ger robustness.