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
  • [31] Multi-Scale Frequency-Adaptive-Network-Based Underwater Target Recognition
    Zhuang, Lixu
    Yang, Afeng
    Ma, Yanxin
    Li, David Day-Uei
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (10)
  • [32] Underwater Image Enhancement Based on Local Contrast Correction and Multi-Scale Fusion
    Gao, Farong
    Wang, Kai
    Yang, Zhangyi
    Wang, Yejian
    Zhang, Qizhong
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2021, 9 (02) : 1 - 17
  • [33] TransMF: Transformer-Based Multi-Scale Fusion Model for Crack Detection
    Ju, Xiaochen
    Zhao, Xinxin
    Qian, Shengsheng
    MATHEMATICS, 2022, 10 (13)
  • [34] DeepFusion: A deep learning based multi-scale feature fusion method for predicting drug-target interactions
    Song, Tao
    Zhang, Xudong
    Ding, Mao
    Rodriguez-Paton, Alfonso
    Wang, Shudong
    Wang, Gan
    METHODS, 2022, 204 : 269 - 277
  • [35] Few-Shot PCB Surface Defect Detection Based on Feature Enhancement and Multi-Scale Fusion
    Wang, Haodong
    Xie, Jun
    Xu, Xinying
    Zheng, Zihao
    IEEE ACCESS, 2022, 10 : 129911 - 129924
  • [36] TFNet: Transformer-Based Multi-Scale Feature Fusion Forest Fire Image Detection Network
    Liu, Hongying
    Zhang, Fuquan
    Xu, Yiqing
    Wang, Junling
    Lu, Hong
    Wei, Wei
    Zhu, Jun
    FIRE-SWITZERLAND, 2025, 8 (02):
  • [37] LMSD-YOLO: A Lightweight YOLO Algorithm for Multi-Scale SAR Ship Detection
    Guo, Yue
    Chen, Shiqi
    Zhan, Ronghui
    Wang, Wei
    Zhang, Jun
    REMOTE SENSING, 2022, 14 (19)
  • [38] A lightweight network for traffic sign recognition based on multi-scale feature and attention mechanism
    Wei, Wei
    Zhang, Lili
    Yang, Kang
    Li, Jing
    Cui, Ning
    Han, Yucheng
    Zhang, Ning
    Yang, Xudong
    Tan, Hongxin
    Wang, Kai
    HELIYON, 2024, 10 (04)
  • [39] Lightweight network for small target fall detection based on feature fusion and dynamic convolution
    Zhang, Qihao
    Bao, Xu
    Sun, Shantong
    Lin, Feng
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (01)
  • [40] Lightweight network for small target fall detection based on feature fusion and dynamic convolution
    Qihao Zhang
    Xu Bao
    Shantong Sun
    Feng Lin
    Journal of Real-Time Image Processing, 2024, 21