基于深度学习的废旧塑料瓶颜色高效识别方法研究

谢世龙, 吴虎, 毛文杰, 初宪龙, 杨先海

PDF(2813 KB)
PDF(2813 KB)
塑料科技 ›› 2024, Vol. 52 ›› Issue (11) : 140-146. DOI: 10.15925/j.cnki.issn1005-3360.2024.11.027
问题探讨

基于深度学习的废旧塑料瓶颜色高效识别方法研究

作者信息 +

Research on Efficient Color Recognition Method for Waste Plastic Bottles Based on Deep Learning

Author information +
History +

摘要

针对废旧塑料瓶在回收过程中不同颜色存在价值差异的情况,为解决颜色识别分选问题,提出一种基于深度学习的YOLOv8n改进模型废旧塑料瓶颜色高效识别方法。在颈部(neck)网络中引入加权双向特征金字塔网络(BiFPN)进行多尺度特征融合,提升模型的泛化能力;头部(head)网络的解耦头(decoupled-head)结构中两个分支均仅采用1个Conv2d模块,并在分支前端添加重参数化卷积——RepConv模块,减少计算量并提升训练精度;选用WIOU v3损失函数替换CIOU损失函数,提升模型的检测精度。通过对比实验可知,文章提出的模型优于传统目标检测模型。结果表明:文章提出的模型参数量较原模型减少了44.8%,计算量较原模型减少了34.6%,在50%交并比下的均值平均精度(mAP50)较原模型提升了2.7%,对废旧塑料瓶颜色进行识别时,每秒检测帧数(FPS)可达66,较原模型提高了40.4%,实现了对废旧塑料瓶颜色实时且准确的检测。

Abstract

To address the value difference between different colors in the recycling process of waste plastic bottles, the study provides an efficient color recognition approach for waste plastic bottles based on a deep learning-upgraded YOLOv8n model to handle the problem of color recognition and sorting. Adding a Bidirectional Feature Pyramid Network (BiFPN) to the neck network for multi-scale feature fusion to improve the model's generalizability. The decoupled head structure of the head network uses only one Conv2d module for both branches, and a reparameterized convolution RepConv module is added at the front end of the branch to reduce computational complexity and improve training accuracy. Replace the CIOU loss function with the WIOU v3 loss function to improve the model's detection accuracy. Comparative trials demonstrate that the model suggested in the paper is superior to typical object detection models. The results showed that the model in the article had a 44.8% lower parameter count, a 34.6% lower computational complexity, and a 2.7% higher mean average precision at 50% IOU (mAP50) than the original model. When identifying the colors of waste plastic bottles, the frames per second (FPS) can reach 66, which is 40.4% faster than the original model. The colors of waste plastic bottles may now be detected in real time and with high accuracy.

关键词

YOLOv8n / 废旧塑料瓶 / 分类识别 / 目标检测

Key words

YOLOv8n / Waste plastic bottles / Classification recognition / Object detection

中图分类号

TP391.4

引用本文

导出引用
谢世龙 , 吴虎 , 毛文杰 , . 基于深度学习的废旧塑料瓶颜色高效识别方法研究. 塑料科技. 2024, 52(11): 140-146 https://doi.org/10.15925/j.cnki.issn1005-3360.2024.11.027
XIE Shi-long, WU Hu, MAO Wen-jie, et al. Research on Efficient Color Recognition Method for Waste Plastic Bottles Based on Deep Learning[J]. Plastics Science and Technology. 2024, 52(11): 140-146 https://doi.org/10.15925/j.cnki.issn1005-3360.2024.11.027

参考文献

1
李晔,许文.中国塑料制品市场分析与发展趋势[J].化学工业,2021,39(4):37-43.
2
薛志宏,刘鹏,高叶玲.废旧塑料回收与再利用现状研究[J].塑料科技,2021,49(4):107-110.
3
高珊.中国绿色包装材料研究现状与进展[J].内蒙古科技与经济,2018(17):3,6.
4
张文华,原心红,刘金妹,等.废旧塑料在道路工程建设中的应用[J].塑料科技,2022,50(2):93-97.
5
赵爱之.废弃塑料回收方法概述[J].塑料科技,2020,48(9):123-126.
6
张悦.塑料垃圾资源化处理探析[J].清洗世界,2023,39(10):178-180.
7
杨朝义,李海强,黄芬梅.计算机视觉技术在塑料成品检测中的应用[J].塑料科技,2021,49(5):99-102.
8
邢晶凯,刘腾腾,王波.可闭环回收塑料的研究进展[J].中外能源,2023,28(9):92-100.
9
李洪波,廖详刚,陈立.基于机器学习One-stage目标检测算法的塑料自动识别系统[J].塑料科技,2020,48(12):86-89.
10
周晓,焦晨,朱开瑄.基于卷积神经网络的废旧塑料瓶颜色分拣系统[J].数字制造科学,2021,19(3):227-232.
11
曾维,尹生阳,张凤.基于计算机视觉的垃圾塑料瓶识别与定位算法研究[J].电子测量技术,2021,44(23):12-17.
12
王振,方海峰,曹晋,等.基于YOLOv5s的轻量化可回收饮料瓶颜色识别[J].国外电子测量技术,2023,42(3):160-166.
13
KOKOULIN A N, TUR A I, YUZHAKOV A A. Convolutional neural networks application in plastic waste recognition and sorting[C]//2018 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus). New York: IEEE, 2018.
14
JIANG Y, SCHENCK E, KRANZ S, et al. CNN-based non-contact detection of food level in bottles from RGB images[C]//International Conference on Multimedia Modeling. Cham: Springer, 2019.
15
WANG Z K, PENG B B, HUANG Y J, et al. Classification for plastic bottles recycling based on image recognition[J]. Waste Management, 2019, 88: 170-181.
16
赵永强,饶元,董世鹏,等.深度学习目标检测方法综述[J].中国图象图形学报,2020,25(4):629-654.
17
许德刚,王露,李凡.深度学习的典型目标检测算法研究综述[J].计算机工程与应用,2021,57(8):10-25.
18
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. New York: IEEE, 2014.
19
GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2015.
20
REN S Q, HE K M, 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, 2017, 39(6): 1137-1149.
21
GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142-158.
22
LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I 14. Cham: Springer International Publishing, 2016.
23
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and pPattern Rrecognition. New York: IEEE,2016.
24
REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017.
25
REDMON J, FARHADI A. Yolov3: An incremental improvement[C]//Computer Vision and Pattern Recognition. Cham: Springer, 2018.
26
ZHOU F, ZHAO H, NIE Z. Safety helmet detection based on YOLOv5[C]//2021 IEEE International Conference on Power Electronics, Computer Applications. New York: IEEE, 2021.
27
WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2023.
28
侯学良,单腾飞,薛靖国.深度学习的目标检测典型算法及其应用现状分析[J].国外电子测量技术,2022,41(6):165-174.
29
FENG C, ZHONG Y, GAO Y, et al. Tood: Task-aligned one-stage object detection[C]//2021 IEEE/CVF International Conference on Computer Vision (ICCV). New York: IEEE Computer Society, 2021.
30
LI X, WANG W H, WU L J, et al. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection[J]. Advances in Neural Information Processing Systems, 2020, 33: 21002-21012.
31
TAN M, PANG R, LE Q V. Efficientdet: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Piscataway, NJ: IEEE Computer Society, 2020.
32
齐志,史旭龙,刘昊.一种无计算增量但提高精度的RepConv通用卷积模块及使用策略:CN114819073A[P].2022-07-29.
33
董恒祥,潘江如,董芙楠,等.基于YOLOv5s模型的边界框回归损失函数研究[J].现代电子技术,2024,47(3):179-186.

基金

国家自然科学基金(52075306)

评论

PDF(2813 KB)

Accesses

Citation

Detail

段落导航
相关文章

/