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
  • [41] Lightweight Underwater Target Detection Algorithm Based on Improved YOLOv8n
    Xie, Guobo
    Liang, Lihui
    Lin, Zhiyi
    Lin, Songze
    Su, Qing
    LASER & OPTOELECTRONICS PROGRESS, 2024, 61 (24)
  • [42] Human Pose Estimation Method Based on Optimized Multi-scale Feature Fusion
    Liu, Hongzhe
    Tao, Xiangru
    Xu, Cheng
    Cao, Dongpu
    Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2024, 60 (16): : 306 - 313
  • [43] LMANet: A Lightweight Asymmetric Semantic Segmentation Network Based on Multi-Scale Feature Extraction
    Chen, Hui
    Xiao, Zhexuan
    Ge, Bin
    Li, Xuedi
    ELECTRONICS, 2024, 13 (17)
  • [44] MSFF: A Multi-Scale Feature Fusion Network for Surface Defect Detection of Aluminum Profiles
    Sun, Lianshan
    Wei, Jingxue
    Du, Hanchao
    Zhang, Yongbin
    He, Lifeng
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2022, E105D (09) : 1652 - 1655
  • [45] Image Dehazing Algorithm Based on Multi-Scale Fusion and Adversarial Training
    Liu Yuhang
    Shuai, Wu
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (06)
  • [46] A Road Crack Segmentation Method Based on Transformer and Multi-Scale Feature Fusion
    Xu, Yang
    Xia, Yonghua
    Zhao, Quai
    Yang, Kaihua
    Li, Qiang
    ELECTRONICS, 2024, 13 (12)
  • [47] YOLOv8-AFA: A photovoltaic module fault detection method based on multi-scale feature fusion
    Chen, Wei
    Lu, Jinyu
    Pei, Tingting
    Yuan, Guojing
    ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2025, 47 (01) : 657 - 676
  • [48] Research on Improved Lightweight YOLOv5s for Multi-Scale Ship Target Detection
    Zhang, Peng
    Zhu, Peiqiao
    Sun, Ze
    Ding, Jun
    Zhang, Jiale
    Dong, Junwei
    Guo, Wei
    APPLIED SCIENCES-BASEL, 2024, 14 (14):
  • [49] Fast Target Recognition Method Based on Multi-Scale Fusion and Deep Learning
    Sun, Guangming
    Kuang, Bo
    Zhang, Yunkai
    TRAITEMENT DU SIGNAL, 2022, 39 (06) : 2173 - 2179
  • [50] Mosaic ceramic surface defect detection enhancement algorithm based on guided filter and multi-scale fusion
    Dong, Guanping
    You, Rui
    Liu, Sai
    Wu, Nanshou
    Kong, Xiangyu
    Huang, Pingnan
    Fan, Wenting
    Wang, Zixi
    MATERIALS TESTING, 2025, 67 (03) : 568 - 578