Ship Segmentation via Combined Attention Mechanism and Efficient Channel Attention High-Resolution Representation Network

被引:0
|
作者
Li, Xiaoyi [1 ]
机构
[1] Shanghai Maritime Univ, Merchant Marine Coll, Shanghai 201306, Peoples R China
基金
中国国家自然科学基金;
关键词
ship segmentation; attention mechanism; smart shipping; visual navigation;
D O I
10.3390/jmse12081411
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
Ship segmentation with small imaging size, which challenges ship detection and visual navigation model performance due to imaging noise interference, has attracted significant attention in the field. To address the issues, this study proposed a novel combined attention mechanism and efficient channel attention high-resolution representation network (CA2HRNET). More specially, the proposed model fulfills accurate ship segmentation by introducing a channel attention mechanism, a multi-scale spatial attention mechanism, and a weight self-adjusted attention mechanism. Overall, the proposed CA2HRNET model enhances attention mechanism performance by focusing on the trivial yet important features and pixels of a ship against background-interference pixels. The proposed ship segmentation model can accurately focus on ship features by implementing both channel and spatial fusion attention mechanisms at each scale feature layer. Moreover, the channel attention mechanism helps the proposed framework allocate higher weights to ship-feature-related pixels. The experimental results show that the proposed CA2HRNET model outperforms its counterparts in terms of accuracy (Accs), precision (Pc), F1-score (F1s), intersection over union (IoU), and frequency-weighted IoU (FIoU). The average Accs, Pc, F1s, IoU, and FIoU for the proposed CA2HRNET model were 99.77%, 97.55%, 97%, 96.97%, and 99.55%, respectively. The research findings can promote intelligent ship visual navigation and maritime traffic management in the smart shipping era.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] Image super-resolution via channel attention and spatial attention
    Lu, Enmin
    Hu, Xiaoxiao
    [J]. APPLIED INTELLIGENCE, 2022, 52 (02) : 2260 - 2268
  • [32] Efficient Attention Pyramid Network for Semantic Segmentation
    Yang, Qirui
    Ku, Tao
    Hu, Kunyuan
    [J]. IEEE ACCESS, 2021, 9 : 18867 - 18875
  • [33] High-Resolution Self-attention with Fair Loss for Point Cloud Segmentation
    Liu, Qiyuan
    Lu, Jinzheng
    Li, Qiang
    Huang, Bingsen
    [J]. NEURAL INFORMATION PROCESSING, ICONIP 2023, PT V, 2024, 14451 : 344 - 356
  • [34] High-Resolution Remote Sensing Image Segmentation Algorithm Based on Improved Feature Extraction and Hybrid Attention Mechanism
    Huang, Min
    Dai, Wenhui
    Yan, Weihao
    Wang, Jingyang
    [J]. ELECTRONICS, 2023, 12 (17)
  • [35] Multiple Attention Siamese Network for High-Resolution Image Change Detection
    Huang, Jiru
    Shen, Qian
    Wang, Min
    Yang, Mengyuan
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [36] Image super -resolution via channel attention and spatial graph convolutional network
    Yang, Yue
    Qi, Yong
    [J]. PATTERN RECOGNITION, 2021, 112
  • [37] High-Resolution Remote Sensing Image Semantic Segmentation via Multiscale Context and Linear Self-Attention
    Yin, Peng
    Zhang, Dongmei
    Han, Wei
    Li, Jiang
    Cheng, Jianmei
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 9174 - 9185
  • [38] Spider-Net: High-resolution multi-scale attention network with full-attention decoder for tumor segmentation in kidney, liver and pancreas
    Peng, Yanjun
    Hu, Xiqing
    Hao, Xiaobo
    Liu, Pengcheng
    Deng, Yanhui
    Li, Zhengyu
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 93
  • [39] Siamese Network Tracker with Channel Attention Mechanism
    Zhang Sen
    Gao Yun
    [J]. THIRTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2021), 2022, 12083
  • [40] An Efficient Convolutional Neural Network Model Combined with Attention Mechanism for Inverse Halftoning
    Shao, Linhao
    Zhang, Erhu
    Li, Mei
    [J]. ELECTRONICS, 2021, 10 (13)