Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr 12;24(8):2483.
doi: 10.3390/s24082483.

YOLOv8-C2f-Faster-EMA: An Improved Underwater Trash Detection Model Based on YOLOv8

Jin Zhu  1 , Tao Hu  1 , Linhan Zheng  1 , Nan Zhou  1 , Huilin Ge  1 , Zhichao Hong  2   3
Affiliations

YOLOv8-C2f-Faster-EMA: An Improved Underwater Trash Detection Model Based on YOLOv8

Jin Zhu et al. Sensors (Basel). .

Abstract

Anthropogenic waste deposition in aquatic environments precipitates a decline in water quality, engendering pollution that adversely impacts human health, ecological integrity, and economic endeavors. The evolution of underwater robotic technologies heralds a new era in the timely identification and extraction of submerged litter, offering a proactive measure against the scourge of water pollution. This study introduces a refined YOLOv8-based algorithm tailored for the enhanced detection of small-scale underwater debris, aiming to mitigate the prevalent challenges of high miss and false detection rates in aquatic settings. The research presents the YOLOv8-C2f-Faster-EMA algorithm, which optimizes the backbone, neck layer, and C2f module for underwater characteristics and incorporates an effective attention mechanism. This algorithm improves the accuracy of underwater litter detection while simplifying the computational model. Empirical evidence underscores the superiority of this method over the conventional YOLOv8n framework, manifesting in a significant uplift in detection performance. Notably, the proposed method realized a 6.7% increase in precision (P), a 4.1% surge in recall (R), and a 5% enhancement in mean average precision (mAP). Transcending its foundational utility in marine conservation, this methodology harbors potential for subsequent integration into remote sensing ventures. Such an adaptation could substantially enhance the precision of detection models, particularly in the realm of localized surveillance, thereby broadening the scope of its applicability and impact.

Keywords: YOLOv8; remote sensing; underwater target detection; water contamination.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Architecture for YOLOv8 module.
Figure 2
Figure 2
FasterNet’s overall architecture. It consists of four hierarchical layers, each containing a stack of FasterNet blocks, with a preceding embed or fusion layer. Feature classification is performed in the last three layers. Within each FasterNet block, two PWConv levels follow one PConv level.
Figure 3
Figure 3
Comparison of various convolution patterns.
Figure 4
Figure 4
EMA module. Here * means the process of re-weight.
Figure 5
Figure 5
C2f module.
Figure 6
Figure 6
C2f-Faster module.
Figure 7
Figure 7
C2f-Faster-EMA module.
Figure 8
Figure 8
Architecture for the YOLOv8-C2f-Faster-EMA module.
Figure 9
Figure 9
Sample of partial datasets.
Figure 10
Figure 10
Comparison of batch-size before and after the addition of the Mosaic algorithm.
Figure 11
Figure 11
Loss changes of each model.
Figure 12
Figure 12
Changes in the four indicators of each mode.
Figure 13
Figure 13
Test result graphs of YOLOv8n.
Figure 14
Figure 14
Test result graphs of YOLOv8-C2f-Faster-EMAv3.
Figure 15
Figure 15
Comparison of heat maps of different network models. (a) Original figure; (b) YOLOv8n heat map; (c) YOLOv8-C2f-Faster-EMAv3 heat map.
Figure 15
Figure 15
Comparison of heat maps of different network models. (a) Original figure; (b) YOLOv8n heat map; (c) YOLOv8-C2f-Faster-EMAv3 heat map.
See this image and copyright information in PMC

References

    1. Lebreton L.C.M., van der Zwet J., Damsteeg J.-W., Slat B., Andrady A., Reisser J. River plastic emissions to the world’s oceans. Nat. Commun. 2017;8:15611. doi: 10.1038/ncomms15611. - DOI - PMC - PubMed
    1. Lim X.Z. Microplastics Are Everywhere—But Are They Harmful? Nature. 2021;593:22–25. doi: 10.1038/d41586-021-01143-3. - DOI - PubMed
    1. Zocco F., Lin T.-C., Huang C.-I., Wang H.-C., Khyam M.O., Van M. Towards More Efficient EfficientDets and Real-Time Marine Debris Detection. IEEE Robot. Autom. Lett. 2023;8:2134–2141. doi: 10.1109/LRA.2023.3245405. - DOI
    1. Yang J., Xin L., Huang H., He Q. An Improved Algorithm for the Detection of Fastening Targets Based on Machine Vision. Comput. Model. Eng. Sci. 2021;128:779–802. doi: 10.32604/cmes.2021.014993. - DOI
    1. Li C.F., Liu L., Zhao J.J., Liu X.F. LF-CNN: Deep Learning-Guided Small Sample Target Detection for Remote Sensing Classification. CMES-Comp. Model. Eng. Sci. 2022;131:429–444. doi: 10.32604/cmes.2022.019202. - DOI