Next Article in Journal
Adsorption Mechanism of High-Concentration Ammonium by Chinese Natural Zeolite with Experimental Optimization and Theoretical Computation
Next Article in Special Issue
A Predictive Analysis Method of Shafting Vibration for the Hydraulic-Turbine Generator Unit
Previous Article in Journal
Sediment Budget Implications from Posidonia oceanica Banquette Removal in a Starved Beach System
Previous Article in Special Issue
Flood Disaster Monitoring and Emergency Assessment Based on Multi-Source Remote Sensing Observations
 
 
Article

CME-YOLOv5: An Efficient Object Detection Network for Densely Spaced Fish and Small Targets

1
State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing 100048, China
2
College of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang 443002, China
*
Author to whom correspondence should be addressed.
Academic Editors: Yizi Shang, Yongping Wei, Ling Shang, Akiyuki Kawasaki and Yuchuan Wang
Water 2022, 14(15), 2412; https://doi.org/10.3390/w14152412
Received: 6 July 2022 / Revised: 30 July 2022 / Accepted: 1 August 2022 / Published: 3 August 2022
Fish are indicative species with a relatively balanced ecosystem. Underwater target fish detection is of great significance to fishery resource investigations. Traditional investigation methods cannot meet the increasing requirements of environmental protection and investigation, and the existing target detection technology has few studies on the dynamic identification of underwater fish and small targets. To reduce environmental disturbances and solve the problems of many fish, dense, mutual occlusion and difficult detection of small targets, an improved CME-YOLOv5 network is proposed to detect fish in dense groups and small targets. First, the coordinate attention (CA) mechanism and cross-stage partial networks with 3 convolutions (C3) structure are fused into the C3CA module to replace the C3 module of the backbone in you only look once (YOLOv5) to improve the extraction of target feature information and detection accuracy. Second, the three detection layers are expanded to four, which enhances the model’s ability to capture information in different dimensions and improves detection performance. Finally, the efficient intersection over union (EIOU) loss function is used instead of the generalized intersection over union (GIOU) loss function to optimize the convergence rate and location accuracy. Based on the actual image data and a small number of datasets obtained online, the experimental results showed that the mean average precision ([email protected]) of the proposed algorithm reached 94.9%, which is 4.4 percentage points higher than that of the YOLOv5 algorithm, and the number of fish and small target detection performances was 24.6% higher. The results show that our proposed algorithm exhibits good detection performance when applied to densely spaced fish and small targets and can be used as an alternative or supplemental method for fishery resource investigation. View Full-Text
Keywords: densely spaced fish; small targets; CME-YOLOv5; attention mechanism; multiscale; loss function densely spaced fish; small targets; CME-YOLOv5; attention mechanism; multiscale; loss function
Show Figures

Figure 1

MDPI and ACS Style

Li, J.; Liu, C.; Lu, X.; Wu, B. CME-YOLOv5: An Efficient Object Detection Network for Densely Spaced Fish and Small Targets. Water 2022, 14, 2412. https://doi.org/10.3390/w14152412

AMA Style

Li J, Liu C, Lu X, Wu B. CME-YOLOv5: An Efficient Object Detection Network for Densely Spaced Fish and Small Targets. Water. 2022; 14(15):2412. https://doi.org/10.3390/w14152412

Chicago/Turabian Style

Li, Jianyuan, Chunna Liu, Xiaochun Lu, and Bilang Wu. 2022. "CME-YOLOv5: An Efficient Object Detection Network for Densely Spaced Fish and Small Targets" Water 14, no. 15: 2412. https://doi.org/10.3390/w14152412

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop