Underwater Target Detection Based on Improved YOLOv7

doi:10.3390/jmse11030677

	Underwater Target Detection Based on Improved YOLOv7
	Liu, Kaiyue 1,2,3; Sun, Qi 4; Sun, Daming 4; Peng, Lin 1,2; Yang, Mengduo 3,5; Wang, Nizhuan1,2,6
	2023-03-01
发表期刊	JOURNAL OF MARINE SCIENCE AND ENGINEERING (IF:2.7[JCR-2023],2.8[5-Year])
EISSN	2077-1312
卷号	11 期号:3
发表状态	已发表
DOI	10.3390/jmse11030677
摘要	Underwater target detection is a crucial aspect of ocean exploration. However, conventional underwater target detection methods face several challenges such as inaccurate feature extraction, slow detection speed, and lack of robustness in complex underwater environments. To address these limitations, this study proposes an improved YOLOv7 network (YOLOv7-AC) for underwater target detection. The proposed network utilizes an ACmixBlock module to replace the 3 x 3 convolution block in the E-ELAN structure, and incorporates jump connections and 1 x 1 convolution architecture between ACmixBlock modules to improve feature extraction and network reasoning speed. Additionally, a ResNet-ACmix module is designed to avoid feature information loss and reduce computation, while a Global Attention Mechanism (GAM) is inserted in the backbone and head parts of the model to improve feature extraction. Furthermore, the K-means++ algorithm is used instead of K-means to obtain anchor boxes and enhance model accuracy. Experimental results show that the improved YOLOv7 network outperforms the original YOLOv7 model and other popular underwater target detection methods. The proposed network achieved a mean average precision (mAP) value of 89.6% and 97.4% on the URPC dataset and Brackish dataset, respectively, and demonstrated a higher frame per second (FPS) compared to the original YOLOv7 model. In conclusion, the improved YOLOv7 network proposed in this study represents a promising solution for underwater target detection and holds great potential for practical applications in various underwater tasks.
关键词	underwater target detection marine resources computer vision image analysis YOLOv7-AC GAM K-means++
URL	查看原文
收录类别	SCI
语种	英语
WOS研究方向	Engineering ; Oceanography
WOS类目	Engineering, Marine ; Engineering, Ocean ; Oceanography
WOS记录号	WOS:000956713200001
出版者	MDPI
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/292190
专题	生物医学工程学院_PI研究组_沈定刚组
通讯作者	Peng, Lin; Yang, Mengduo; Wang, Nizhuan
作者单位	1.Jiangsu Ocean Univ, Coinnovat Ctr Jiangsu Marine Bioind Technol, Jiangsu Key Lab Marine Bioresources & Environm, Jiangsu Key Lab Marine Biotechnol, Lianyungang 222005, Peoples R China 2.Jiangsu Ocean Univ, Sch Marine Technol & Geomat, Lianyungang 222005, Peoples R China 3.Soochow Univ, Prov Key Lab Comp Informat Proc Technol, Suzhou 215301, Peoples R China 4.Beijing KnowYou Technol Co Ltd, Beijing 100086, Peoples R China 5.Suzhou Inst Trade & Commerce, Sch Informat Technol, Suzhou 215009, Peoples R China 6.ShanghaiTech Univ, Sch Biomed Engn, Shanghai 201210, Peoples R China
通讯作者单位	生物医学工程学院
推荐引用方式 GB/T 7714	Liu, Kaiyue,Sun, Qi,Sun, Daming,et al. Underwater Target Detection Based on Improved YOLOv7[J]. JOURNAL OF MARINE SCIENCE AND ENGINEERING,2023,11(3).
APA	Liu, Kaiyue,Sun, Qi,Sun, Daming,Peng, Lin,Yang, Mengduo,&Wang, Nizhuan.(2023).Underwater Target Detection Based on Improved YOLOv7.JOURNAL OF MARINE SCIENCE AND ENGINEERING,11(3).
MLA	Liu, Kaiyue,et al."Underwater Target Detection Based on Improved YOLOv7".JOURNAL OF MARINE SCIENCE AND ENGINEERING 11.3(2023).