Underwater Target Detection Lightweight Algorithm Based on Multi-Scale Feature Fusion

被引:15
|
作者
Chen, Liang [1 ]
Yang, Yuyi [1 ]
Wang, Zhenheng [1 ]
Zhang, Jian [1 ]
Zhou, Shaowu [1 ]
Wu, Lianghong [1 ]
机构
[1] Hunan Univ Sci & Technol, Sch Informat & Elect Engn, Xiangtan 411201, Peoples R China
基金
中国国家自然科学基金;
关键词
underwater target detection; multi-scale fusion; transformer; YOLOv5; lightweight;
D O I
10.3390/jmse11020320
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] Lightweight Underwater Target Detection Algorithm Based on YOLOv7
    Xin, Shiao
    Ge, Haibo
    Yuan, Hao
    Yang, Yudi
    Yao, Yang
    Ma, Sai
    2024 6TH INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING, ICNLP 2024, 2024, : 387 - 391
  • [22] Dynamically Enhanced lane detection with multi-scale semantic feature fusion
    Deng, Liwei
    Cao, He
    Lan, Qi
    COMPUTERS & ELECTRICAL ENGINEERING, 2024, 118
  • [23] Underwater image enhancement based on color balance and multi-scale fusion
    Hu Z.
    Chen Q.
    Zhu D.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2022, 30 (17): : 2133 - 2146
  • [24] Lightweight real-time vehicle collision warning based on deep learning multi-scale feature fusion
    Qiu, Chengqun
    Tang, Hao
    Xu, Xixi
    Peng, Yu
    Liu, Xin
    Ji, Jie
    Meng, Mingyu
    Tang, Yunqing
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING, 2024,
  • [25] Underwater Image Enhancement Based on Color Balance and Multi-Scale Fusion
    Chen, Qi
    Zhang, Ze
    Li, Gelun
    IEEE PHOTONICS JOURNAL, 2022, 14 (06):
  • [26] MFEFNet: A Multi-Scale Feature Information Extraction and Fusion Network for Multi-Scale Object Detection in UAV Aerial Images
    Zhou, Liming
    Zhao, Shuai
    Wan, Ziye
    Liu, Yang
    Wang, Yadi
    Zuo, Xianyu
    DRONES, 2024, 8 (05)
  • [27] DPMFformer: an underwater image enhancement network based on deep pooling and multi-scale fusion transformer
    Xiang, Dan
    Yang, Wenlei
    Zhou, Zebin
    Zhang, Jinwen
    Li, Jianxin
    Ouyang, Jian
    Ling, Jing
    EARTH SCIENCE INFORMATICS, 2025, 18 (01)
  • [28] Underwater image enhancement based on adaptive color correction and multi-scale fusion
    Jinyu Shi
    Shanshan Yu
    Huanan Li
    Xiuguo Zhang
    Changxin Liu
    Multimedia Tools and Applications, 2024, 83 : 12535 - 12559
  • [29] Research on Multi-Scale Feature Fusion Network Algorithm Based on Brain Tumor Medical Image Classification
    Zhou, Yuting
    Yang, Xuemei
    Yin, Junping
    Liu, Shiqi
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 79 (03): : 5313 - 5333
  • [30] Underwater image enhancement based on adaptive color correction and multi-scale fusion
    Shi, Jinyu
    Yu, Shanshan
    Li, Huanan
    Zhang, Xiuguo
    Liu, Changxin
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (05) : 12535 - 12559