袁斌,张超军,李晨.基于MobileViT轻量级视觉模型的垃圾自动分类系统设计[J].包装工程,2023,44(23):208-215.
YUAN Bin,ZHANG Chao-jun,LI Chen.Design of Automatic Garbage Classification System Based on MobileViT Lightweight Visual Model[J].Packaging Engineering,2023,44(23):208-215. |
| 基于MobileViT轻量级视觉模型的垃圾自动分类系统设计 |
| Design of Automatic Garbage Classification System Based on MobileViT Lightweight Visual Model |
| 投稿时间：2022-12-08 |
| DOI：10.19554/j.cnki.1001-3563.2023.23.025 |
| 中文关键词: 垃圾分类 智能垃圾箱 MobileViT 轻量级 迁移学习 |
| 英文关键词: garbage classification smart garbage bin MobileViT lightweight transfer learning |
| 基金项目:国家自然科学基金(62103340) |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 针对传统机器视觉网络模型存在的参数量大、效率低、落地难等问题，设计一种更高效的基于轻量级网络模型的垃圾自动分类系统。方法 结构的创新设计可实现4种占比不同的垃圾分类存储和垃圾箱工作模式的自动切换。利用STM32控制机构的电机和多种传感器，与树莓派4B串口通信实现垃圾分类投放，采用云服务器实现小程序端物联网通信，提高管理效率。采用MobileViT轻量级模型在自建数据集上训练，并结合迁移学习，提高模型的训练速度和准确率，与主流模型对比，并验证其可行性。结果 MobileViT模型的准确率可以达到98.01%，实际测试平均单张图像的推理时间为17.8 ms，模型参数量仅为5.6×106;在与轻量化网络MobileNetV3参数量相近的情况下，准确率高出9.25%，各性能指标优于传统ResNet50、AlexNet模型。结论 基于MobileViT轻量级视觉模型的垃圾自动分类系统设计能够更高效地完成垃圾自动分类任务，模型精度和速度满足实际需求，对垃圾分类领域边缘设备非常友好。 |
| 英文摘要: |
| The work aims to design a more efficient automatic garbage classification system based on the lightweight network model to solve the problems of the traditional machine vision network model, such as large number of references, low efficiency and difficult landing. The innovative design of the structure could realize the automatic switching of four kinds of garbage classification and storage with different proportions and the working mode of the garbage bin. The STM32 control mechanism motor and a variety of sensors were used to communicate with the Raspberry PI 4B serial port to realize garbage classification and delivery. The cloud server realized the Internet of Things communication at the small program side to improve management efficiency. The MobileViT lightweight model was used to train on the self-built data set, and the training speed and accuracy of the model were improved by combining transfer learning. The feasibility was verified by comparing the model with the mainstream model. The accuracy of MobileViT model could reach 98.01%, the average reasoning time of a single image in the actual test was only 17.8 ms, and the number of model parameters was only 5.6×106. The accuracy was 9.25% higher than that of lightweight network MobileNetV3 under the similar parameters. The performance indexes were better than those of traditional ResNet50 and AlexNet models. The design of automatic garbage classification system based on MobileViT lightweight visual model can complete the task of automatic garbage classification more efficiently. The accuracy and speed of the model meet the actual demand, and it is very friendly to the edge equipment in the field of garbage classification. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501716号