A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot

doi:10.1631/FITEE.2100473

	A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot
	Tian, Manjun 1,2; Li, Xiali 2; Kong, Shihan3 ; Wu, Licheng 2; Yu, Junzhi3,4
发表期刊	FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING
ISSN	2095-9184
	2022-08-01
卷号	23 期号:8 页码:1217-1228
通讯作者	Yu, Junzhi(junzhi.yu@ia.ac.cn)
摘要	To tackle the problem of aquatic environment pollution, a vision-based autonomous underwater garbage cleaning robot has been developed in our laboratory. We propose a garbage detection method based on a modified YOLOv4, allowing high-speed and high-precision object detection. Specifically, the YOLOv4 algorithm is chosen as a basic neural network framework to perform object detection. With the purpose of further improvement on the detection accuracy, YOLOv4 is transformed into a four-scale detection method. To improve the detection speed, model pruning is applied to the new model. By virtue of the improved detection methods, the robot can collect garbage autonomously. The detection speed is up to 66.67 frames/s with a mean average precision (mAP) of 95.099%, and experimental results demonstrate that both the detection speed and the accuracy of the improved YOLOv4 are excellent.
关键词	Object detection Aquatic environment Garbage cleaning robot Modified YOLOv4 TP242
DOI	10.1631/FITEE.2100473
关键词[WOS]	SCALE
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61725305] ; National Natural Science Foundation of China[U1909206] ; National Natural Science Foundation of China[T2121002] ; National Natural Science Foundation of China[62073196] ; Postdoctoral Innovative Talent Support Program[BX2021010] ; S&T Program of Hebei Province, China[F2020203037]
项目资助者	National Natural Science Foundation of China ; Postdoctoral Innovative Talent Support Program ; S&T Program of Hebei Province, China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Engineering, Electrical & Electronic
WOS记录号	WOS:000844190200007
出版者	ZHEJIANG UNIV PRESS
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50060
专题	复杂系统认知与决策实验室_先进机器人
通讯作者	Yu, Junzhi
作者单位	1.Minist Publ Secur PRC, Res Inst 1, Beijing 100048, Peoples R China 2.Minzu Univ China, Sch Informat Engn, Beijing 100081, Peoples R China 3.Peking Univ, Coll Engn, Dept Adv Mfg & Robot, Beijing 100871, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Tian, Manjun,Li, Xiali,Kong, Shihan,et al. A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot[J]. FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING,2022,23(8):1217-1228.
APA	Tian, Manjun,Li, Xiali,Kong, Shihan,Wu, Licheng,&Yu, Junzhi.(2022).A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot.FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING,23(8),1217-1228.
MLA	Tian, Manjun,et al."A modified YOLOv4 detection method for a vision-based underwater garbage cleaning robot".FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING 23.8(2022):1217-1228.