Lightweight object detection scheme for garbage classification scenario

被引：0
|
作者：
Chen J. [1 ]
Cai Y. [1 ]
机构：
[1] School of Opto-Electronic and Communication Engineering, Xiamen University of Technology, Xiamen
来源：
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) | 2024年 / 58卷 / 01期
关键词：
depthwise separable convolution; garbage classification; K-means++ algorithm; Stem module; Yolov5;
D O I：
10.3785/j.issn.1008-973X.2024.01.008
中图分类号：
学科分类号：
摘要：
A lightweight Yolov5 garbage detection solution was proposed aiming at the issue of poor real-time performance in garbage detection classification on edge devices. The Stem module was introduced to enhance the model’s ability to extract features from input images. The C3 module of the backbone was improved to increase feature extraction capabilities. Depthwise separable convolution was used to replace the 3×3 downsampling convolutions in the network, achieving model lightweighting. The K-means++ algorithm was employed to recompute anchor box values for objects, enabling the model to better predict target box sizes during training. Experimental research and comparisons show that the improved model achieves a 0.8% increase in mAP_0.5 and a 3% increase in mAP_0.5:0.95, while reducing model parameters by 77.9% and improving inference speed by 21.9% compared with the Yolov5s model, significantly enhancing the detection performance of the model. © 2024 Zhejiang University. All rights reserved.
引用
收藏
页码：71 / 77
页数：6
相关论文
共 24 条
  • [1] GIRSHICK R, DONAHUE J, DARRELL T, Et al., Rich feature hierarchies for accurate object detection and semantic segmentation [C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)
  • [2] HE K M, ZHANG X, REN S, Et al., Spatial pyramid pooling in deep convolutional networks for visual recognition [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 9, pp. 1904-1916, (2015)
  • [3] GIRSHICK R., Fast R-CNN [C], 2015 IEEE International Conference on Computer Vision, pp. 1440-1448, (2015)
  • [4] REN S, HE K, GIRSHICK R, Et al., Faster R-CNN: towards real time object detection with region proposal networks [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [5] REDMON J, DIVVALA S, GIRSHICK R, Et al., You only look once: unified, real-time object detection [C], 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 6517-6525, (2015)
  • [6] LIU W, ANGUELOV D, ERHAN D, Et al., SSD: single shot multi-box detector [C], 14th European Conference on Computer Vision, pp. 21-37, (2016)
  • [7] LI Xiaobo, LI Yanggui, GUO ning, Et al., Yolov5 mask detection algorithm integrating attention mechanism [J], Journal of Graphics, 44, 1, pp. 16-25, (2023)
  • [8] DAI Xuan, ZHAO Xu, LI Lianpeng, Et al., Infrared dim small target detection algorithm based on improved Yolov5 in complex background [J], Infrared Technology, 44, 5, pp. 504-512, (2022)
  • [9] LI Renying, QIAN Huifang, GUO Jiahao, Et al., Lightweight target detection algorithm based on M-Yolov4 model [J], Foreign Electronic Measurement Technology, 41, 4, pp. 15-21, (2022)
  • [10] WANG Chen, YUAN Qingni, BAI Huan, Et al., Lightweight object detection algorithm for warehousing goods [J], Progress in Laser and Optoelectronics, 59, 24, pp. 74-80, (2022)
123