智能城市应用

基于树莓派与YOLOv5-Lite模型的日常垃圾识别系统

王嘉炜 (江西理工大学 能源与机械工程学院), 宁勇强 (江西理工大学 能源与机械工程学院), 卓赛龙 (江西理工大学 能源与机械工程学院)

摘要


利用深度学习实现视觉检测技术对日常生活垃圾的识别,从而识别种类繁多的传统生活垃圾有重要意义。把在PC端上训练好的YOLOv5s与YOLO v5-Lite目标检测模型分别部署在搭载树莓派系统平台上,并在此平台上搭建深度学习环境,构建垃圾识别系统。在不同光照条件下,对这两个模型进行分析对比,实验结果表明,在识别准确率相差1.5%的情况下,YOLO v5-Lite模型相对于原YOLOv5s模型,网络参数量下降了80.86%,模型内存大小下降了75.52%,检测速度提高85.94%。综上所述,文中提出的基于树莓派与YOLOv5-Lite的垃圾识别系统兼顾了准确性好、稳定性好、成本低等综合优点。

关键词


垃圾识别;YOLOv5-Lite;模型部署;树莓派

全文:

PDF

参考


魏潇潇,王小铭,李蕾,等.1979-2015年中国城市生活垃圾产生和处理时空特征[J].中国环境科学,2018,38(10):3833-3834.

梁建胜,温贺平.基于深度学习的视频关键帧提取与视频检索[J].控制工程,2019,26(5):965-970.

Mittal G,Yagnik K B,Garg M,et al.Spotgarbage:smart—phone app to detect garbage using deep learning[C].Heidelberg,GERMANY:Assoc Comp Machinery,2016.

Liu Y,Ge Z,Lv G,et a1.Research on automatic garbage detection system based on deep learning and narrowband internet of things[J].Journal of Physics:Conference Series,2018(1):1069-1076.

Howard A,Zhu M,Chen B,et al.MobileNets:efficient convolutional neural networks for mobile vision applications [C].Hawaii:Computer Vision and Pattern Recognition,2017.

WANG Ying,XU Zhang.Autonomous garbage detection for intelligent urbanmanagement[C].Shanghai:MATEC Web of Conferences,2018.

TAO X,ZHANG D P,WANG Z H.Detection of power line insulator defects using aerial images analyzed with convolutional neural networks[J].IEEE Transactions on Systems Man and Cybernetics Systems,2020,50(4):1486-1498.

Girshick R.Fast R-CNN[C].IEEE:Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago,2015.

REN S,HE K,GIRSHICKR.Faster R-CNN: towards real time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.

REDMIN J,DIVVALAS,GIRSHICK R,et al.You only look once: unified, realtime object detection[C].IEEE:2016 IEEE Conference on Computer Vision and Pattern Recognition,2016.

刘芳,韩笑.基于多尺度深度学习的自适应航拍目标检测[J].航空学报,2020,7(5):1-13.

Glenn Jocher. YOLOv5: The Leader in Realime Object Detection[EB/OL].[2023-03].

武张静,刘敏,史禹龙,等.语音示教十自主巡航智能垃圾分类机器人的研究与设计[J].科技创新与应用,2020(32):43-47.

Gu S,Ding L.A complex-valued VGG network based deep learning algorithm for image recognition[C].Wangzhou:Proceedings of the Ninth International Conference on Intelligent Control and Information Processing,2018.




DOI: https://doi.org/10.33142/sca.v8i3.15785

Refbacks

  • 当前没有refback。


版权所有(c){$ COPYRIGHTYEAR} {$ copyrightHolder}

Creative Commons License
此作品已接受知识共享署名-非商业性使用 4.0国际许可协议的许可。