Version 1
: Received: 21 August 2024 / Approved: 22 August 2024 / Online: 22 August 2024 (08:57:05 CEST)
How to cite:
Li, W.; Li, Y.; Li, R.; Shen, H.; Li, W.; Yue, K. Research on Rapid Detection of Underwater Targets Based on Global Differential Model Compression. Preprints2024, 2024081630. https://doi.org/10.20944/preprints202408.1630.v1
Li, W.; Li, Y.; Li, R.; Shen, H.; Li, W.; Yue, K. Research on Rapid Detection of Underwater Targets Based on Global Differential Model Compression. Preprints 2024, 2024081630. https://doi.org/10.20944/preprints202408.1630.v1
Li, W.; Li, Y.; Li, R.; Shen, H.; Li, W.; Yue, K. Research on Rapid Detection of Underwater Targets Based on Global Differential Model Compression. Preprints2024, 2024081630. https://doi.org/10.20944/preprints202408.1630.v1
APA Style
Li, W., Li, Y., Li, R., Shen, H., Li, W., & Yue, K. (2024). Research on Rapid Detection of Underwater Targets Based on Global Differential Model Compression. Preprints. https://doi.org/10.20944/preprints202408.1630.v1
Chicago/Turabian Style
Li, W., Wenjun Li and Keqiang Yue. 2024 "Research on Rapid Detection of Underwater Targets Based on Global Differential Model Compression" Preprints. https://doi.org/10.20944/preprints202408.1630.v1
Abstract
Large-scale deep learning models have produced significant results in underwater visual image target detection. However, deploying these models on underwater embedded devices poses a series of issues and challenges. Firstly, underwater devices have limited communication capabilities and carry relatively short supply of energy, resulting in constrained computing power for edge devices. Secondly, the large scale of deep neural networks creates a conflict in power demands with unmanned underwater equipment. Thirdly, insufficient underwater light and turbid water quality will lead to degradation problems in the images acquired by the device. In this paper, we build an offline system to complete the task of underwater scene target recognition. This paper introduces several innovations: 1) The new YOLO-TN model is developed by compressing the target recognition model based on YOLO-V5. The model use a model compression algorithm replace the YOLO-V5’s backbone network with a lightweight network, then perform parameter pruning on the model detection head, while reduce the size of the input image. The model uses a Teacher-guided Neural Architecture Search method based on YOLO-V5, named as YOLO-TN. 2)A method for constructing and processing real underwater environment data sets is designed. The datasets are all captured using underwater unmanned vehicles in real underwater environments, addressing issues present in existing underwater datasets, such as unbalanced target volume and single-image environment. Experimental results demonstrate that the YOLO-TN model significantly reduces the model size while maintaining the original recognition accuracy. Furthermore, it achieves 28.6 FPS on embedded devices, which is 12 times that of the original model.
Keywords
target detection; model compression; underwater embedded system; deep learning
Subject
Engineering, Marine Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
