An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s

Yi Zhan; Yuanping Xu; Chaolong Zhang; Zhijie Xu; Benjun Guo

doi:10.1145/3532342.3532344

An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s

Yi Zhan, Yuanping Xu, Chaolong Zhang, Zhijie Xu, Benjun Guo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Waste sorting and recycling play a significant role in carbon neutrality, and the government has promoted waste sorting stations in various cities while the stations have limited efficiency due to the absence of intelligent surveillance systems to monitor and analyze the scene in waste stations, especially to detect the irregularly dropped garbage. To take the most advantage of these stations, this study proposes an improved YOLO (You Only Look Once) v5s detector named YOLOv5s-Garbage to monitor waste sorting stations in real-time. This study enhances its ability to detect garbage by introducing CBAM (Convolutional Block Attention Module) and using EIoU (Efficient Intersection over Union) to accelerate the convergence of the bonding box loss. According to experiments, the mAP of YOLOv5s-Garbage on the waste sorting dataset reaches 89.7%, which is 3.3% higher than the classical YOLOv5s. This study then combines the DeepSort tracking algorithm and re-filter process to filter the target garbage to distinguish the irregularly dropped garbage and normal one, which reduces the false alarm significantly.

Original language	English
Title of host publication	SSPS 2022
Subtitle of host publication	Proceedings of the 4th International Symposium on Signal Processing Systems
Publisher	Association for Computing Machinery (ACM)
Pages	7-13
Number of pages	7
ISBN (Electronic)	9781450396103
DOIs	https://doi.org/10.1145/3532342.3532344
Publication status	Published - 25 Mar 2022
Event	4th International Symposium on Signal Processing Systems - Virtual, Online, China Duration: 25 Mar 2022 → 27 Mar 2022 Conference number: 4

Publication series

Name	ACM International Conference Proceeding Series
Volume	Par F180473

Conference

Conference	4th International Symposium on Signal Processing Systems
Abbreviated title	SSPS 2022
Country/Territory	China
City	Virtual, Online
Period	25/03/22 → 27/03/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3532342.3532344Licence: Unspecified

Cite this

Zhan, Y., Xu, Y., Zhang, C., Xu, Z., & Guo, B. (2022). An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s. In SSPS 2022: Proceedings of the 4th International Symposium on Signal Processing Systems (pp. 7-13). (ACM International Conference Proceeding Series; Vol. Par F180473). Association for Computing Machinery (ACM). https://doi.org/10.1145/3532342.3532344

@inproceedings{5dfd6fabd8fb42689baecd17fe4bcbea,

title = "An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s",

abstract = "Waste sorting and recycling play a significant role in carbon neutrality, and the government has promoted waste sorting stations in various cities while the stations have limited efficiency due to the absence of intelligent surveillance systems to monitor and analyze the scene in waste stations, especially to detect the irregularly dropped garbage. To take the most advantage of these stations, this study proposes an improved YOLO (You Only Look Once) v5s detector named YOLOv5s-Garbage to monitor waste sorting stations in real-time. This study enhances its ability to detect garbage by introducing CBAM (Convolutional Block Attention Module) and using EIoU (Efficient Intersection over Union) to accelerate the convergence of the bonding box loss. According to experiments, the mAP of YOLOv5s-Garbage on the waste sorting dataset reaches 89.7%, which is 3.3% higher than the classical YOLOv5s. This study then combines the DeepSort tracking algorithm and re-filter process to filter the target garbage to distinguish the irregularly dropped garbage and normal one, which reduces the false alarm significantly. ",

keywords = "Object detection, Real-time monitoring, Waste sorting, YOLOv5s",

author = "Yi Zhan and Yuanping Xu and Chaolong Zhang and Zhijie Xu and Benjun Guo",

note = "Funding Information: This research is supported by the National Natural Science Foundation of China (NSFC) (61203172); the Sichuan Science and Technology Programs (2019YFH0187 and 2021113). Publisher Copyright: {\textcopyright} 2022 ACM.; 4th International Symposium on Signal Processing Systems, SSPS 2022 ; Conference date: 25-03-2022 Through 27-03-2022",

year = "2022",

month = mar,

day = "25",

doi = "10.1145/3532342.3532344",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery (ACM)",

pages = "7--13",

booktitle = "SSPS 2022",

address = "United States",

}

Zhan, Y, Xu, Y, Zhang, C, Xu, Z & Guo, B 2022, An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s. in SSPS 2022: Proceedings of the 4th International Symposium on Signal Processing Systems. ACM International Conference Proceeding Series, vol. Par F180473, Association for Computing Machinery (ACM), pp. 7-13, 4th International Symposium on Signal Processing Systems, Virtual, Online, China, 25/03/22. https://doi.org/10.1145/3532342.3532344

An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s. / Zhan, Yi; Xu, Yuanping; Zhang, Chaolong et al.

SSPS 2022: Proceedings of the 4th International Symposium on Signal Processing Systems. Association for Computing Machinery (ACM), 2022. p. 7-13 (ACM International Conference Proceeding Series; Vol. Par F180473).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s

AU - Zhan, Yi

AU - Xu, Yuanping

AU - Zhang, Chaolong

AU - Xu, Zhijie

AU - Guo, Benjun

N1 - Conference code: 4

PY - 2022/3/25

Y1 - 2022/3/25

N2 - Waste sorting and recycling play a significant role in carbon neutrality, and the government has promoted waste sorting stations in various cities while the stations have limited efficiency due to the absence of intelligent surveillance systems to monitor and analyze the scene in waste stations, especially to detect the irregularly dropped garbage. To take the most advantage of these stations, this study proposes an improved YOLO (You Only Look Once) v5s detector named YOLOv5s-Garbage to monitor waste sorting stations in real-time. This study enhances its ability to detect garbage by introducing CBAM (Convolutional Block Attention Module) and using EIoU (Efficient Intersection over Union) to accelerate the convergence of the bonding box loss. According to experiments, the mAP of YOLOv5s-Garbage on the waste sorting dataset reaches 89.7%, which is 3.3% higher than the classical YOLOv5s. This study then combines the DeepSort tracking algorithm and re-filter process to filter the target garbage to distinguish the irregularly dropped garbage and normal one, which reduces the false alarm significantly.

AB - Waste sorting and recycling play a significant role in carbon neutrality, and the government has promoted waste sorting stations in various cities while the stations have limited efficiency due to the absence of intelligent surveillance systems to monitor and analyze the scene in waste stations, especially to detect the irregularly dropped garbage. To take the most advantage of these stations, this study proposes an improved YOLO (You Only Look Once) v5s detector named YOLOv5s-Garbage to monitor waste sorting stations in real-time. This study enhances its ability to detect garbage by introducing CBAM (Convolutional Block Attention Module) and using EIoU (Efficient Intersection over Union) to accelerate the convergence of the bonding box loss. According to experiments, the mAP of YOLOv5s-Garbage on the waste sorting dataset reaches 89.7%, which is 3.3% higher than the classical YOLOv5s. This study then combines the DeepSort tracking algorithm and re-filter process to filter the target garbage to distinguish the irregularly dropped garbage and normal one, which reduces the false alarm significantly.

KW - Object detection

KW - Real-time monitoring

KW - Waste sorting

KW - YOLOv5s

UR - http://www.scopus.com/inward/record.url?scp=85133780802&partnerID=8YFLogxK

UR - https://dl.acm.org/doi/proceedings/10.1145/3532342

U2 - 10.1145/3532342.3532344

DO - 10.1145/3532342.3532344

M3 - Conference contribution

AN - SCOPUS:85133780802

T3 - ACM International Conference Proceeding Series

SP - 7

EP - 13

BT - SSPS 2022

PB - Association for Computing Machinery (ACM)

T2 - 4th International Symposium on Signal Processing Systems

Y2 - 25 March 2022 through 27 March 2022

ER -

An Irregularly Dropped Garbage Detection Method Based on Improved YOLOv5s

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this