A Lightweight Underwater Object Detection Algorithm with Adaptive Image Enhancement Based on YOLOv8
2024 43rd Chinese Control Conference (CCC)(2024)
School of Automation
Abstract
This paper introduces a lightweight underwater object detection algorithm based on YOLOv8, essential for underwater robotics challenged by environmental complexity and real-time demands. Firstly, to enhance underwater image quality without significantly increasing computational demands, this study introduces an Adaptive Underwater Image Enhancement module utilizing lightweight convolutions and digital filters for dynamic enhancement. Secondly, a Re-parameterized Partial Convolution Block is proposed and integrated, replacing foundational blocks in the baseline model’s architecture, resulting in reduced detection network parameters and enhanced accuracy. Additionally, performance evaluation on the UTDAC dataset demonstrates our model achieving a $46.8 \% \mathrm{mAP}$, marking a 1.6% improvement over the baseline, with a total parameter count of merely 2.81 M. Ablation studies and extended experiments validate the effectiveness and adaptability of the proposed modules. Experimental results show that the model achieves a superior balance between accuracy and processing speed, making it particularly suitable for underwater robotic perception.
MoreTranslated text
Key words
Underwater Object Detection,Underwater Image Enhancement,YOLOv8,Structural Re-parameterization
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example

Generate MRT to find the research sequence of this paper
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper
Summary is being generated by the instructions you defined