电子科技2024，Vol.37Issue(4)：38-46,9.DOI:10.16180/j.cnki.issn1007-7820.2024.04.006
基于改进MobileNet网络的多类别垃圾分类算法
Research on Multiclass Garbage Classification Algorithm Based on Improved MobileNet Network
摘要
Abstract
view of the large amount of garbage and the fact that a picture contains multiple garbage objects,this study proposes a garbage detection and classification algorithm based on the improved MobileNet network,which in-tegrates the MobileNet network into YOLOv5(You Only Look Oncev5)target detection algorithm.At the same time,the CBAM(Convolutional Block Attention Modul)module is introduced in the backbone to filter meaningful informa-tion,and the vision transformer is used to aggregate and form image features.In addition,the weighted bidirectional feature pyramid network is used to distinguish the contribution of different features.At the same time,the ECA(Effi-cient Channel Attention)module is introduced to combine the image features and transmit them to the prediction lay-er.Finally,in order to obtain better performance when there is occlusion between garbage targets,soft-NMS(soft-Non Maximum Suppression)method and Alpha-IoU(Alpha-Intersection over Union)loss function is used to pre-dict the extracted features.The experimental results show that the method proposed in this study can realize the loca-tion and recognition of multi-target and multi-category garbage.,and the mAP(mean Average Percision)value reaches 90.31%,which is 4.95%higher than that of YOLOv5 network,and the processing speed is shortened by a-bout 2.4 seconds.Compared with the Faster R-CNN(Region-based Convolutional Neural Network)algorithm which integrates ResNet(Residual Network)network,the algorithm proposed in this study improves the processing efficiency on the premise of ensuring the accuracy.关键词
垃圾分类/目标检测/视觉Transformer/MobileNet/图像识别/特征集成/数据增强/平均准确率Key words
garbage classification/target detection/vision Transformer/MobileNet/image recognition/feature in-tegration/data enhancement/average accuracy分类
信息技术与安全科学引用本文复制引用
梁陈烨,张轩雄..基于改进MobileNet网络的多类别垃圾分类算法[J].电子科技,2024,37(4):38-46,9.基金项目
国家自然科学基金(62276167)National Natural Science Foundation of China(62276167) （62276167）
