基于改进YOLOv5对果园环境中李的识别
Recognizing plums in orchard environment based on improved YOLOv5
贺英豪 1唐德钊 2倪铭 1蔡起起2
作者信息
- 1. 四川农业大学信息工程学院,雅安 625014;雅安市数字农业工程技术研究中心,雅安 625014
- 2. 四川农业大学信息工程学院,雅安 625014
- 折叠
摘要
为提高果园中高遮挡和密集的李(Prunus salicina Lindl.)的检测精度,提出一种改进YOLOv5s模型,在促进模型轻量化的同时提高模型对李的检测精度.首先,使用新的结构Focus-Maxpool模块替换主干网络中的下采样卷积,使改进模型在下采样时能够保留更多高遮挡目标和小目标的特征信息.其次,使用focal loss和交叉熵函数的加权损失作为改进模型的分类损失,提升改进模型对粘连目标的识别能力.最后,设计若干组检测试验来评价改进模型的性能.结果显示,改进YOLOv5s模型的平均精度优于YOLOv5s、YOLOv4、Faster-RCNN、SSD和Centernet;与YOLOv5s模型的检测结果相比,改进YOLOv5s模型的平均精度、召回率和精度分别提高2.84、9.53和1.66百分点,检测速度可达到91.37帧/s,能够满足实时检测需求.研究结果表明,改进的YOLOv5s模型在真实果园环境下具有较高的检测精度和鲁棒性.
Abstract
This article proposed an improved YOLOv5s model to improve the accuracy of detecting plums(Prunus salicina Lindl.)with high occlusion and density in orchards and the lightweight.Firstly,a new Focus-Maxpool module was used to replace the down-sampling convolution in the backbone network,enabling the model to retain more feature information of small and highly occluded targets during down-sampling.Secondly,the weighted loss of focal loss and cross-entropy function was used as the classifica-tion loss of the model to improve its recognition ability for adhesive targets.Finally,several sets of detec-tion experiments were designed to evaluate the performance of the model.The results showed that the aver-age accuracy of the improved YOLOv5s model was better than that of YOLOv5s,YOLOv4,Faster RCNN,SSD,and Centernet.Compared with the detection results of the YOLOv5s model,the average ac-curacy,recall rate,and accuracy of the improved model increased by 2.84,9.53,and 1.66 percentages,respectively.The detection speed of the improved model reached 91.37 frames per second,meeting the re-quirements of real-time detection.It is indicated that the model improved has higher accuracy of detection and robustness in real orchard environments.It will provide data reference for studying fruit-picking robots and monitoring orchard environments.
关键词
李/机械采摘/果实识别/YOLOv5/图像处理/注意力机制/目标检测Key words
Prunus salicina Lindl./mechanical harvesting/fruit recognition/YOLOv5/image pro-cessing/attention mechanism/object detection引用本文复制引用
出版年
2024
NETL
NSTL
万方数据