Ship Detection in Maritime Scenes under Adverse Weather Conditions

被引:4
|
作者
Zhang, Qiuyu [1 ]
Wang, Lipeng [1 ]
Meng, Hao [1 ]
Zhang, Zhi [1 ]
Yang, Chunsheng [2 ]
机构
[1] Harbin Engn Univ, Coll Intelligent Syst Sci & Engn, Harbin 150001, Peoples R China
[2] Natl Res Council Canada, Ottawa, ON K1A 0R6, Canada
基金
中国国家自然科学基金;
关键词
object detection; LiDAR; autonomous driving; data simulation;
D O I
10.3390/rs16091567
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Point cloud-based detection focuses on land traffic, rarely marine, facing issues with ships: it struggles in bad weather due to reliance on adverse weather data and fails to detect ships effectively due to overlooking size and appearance differences. Addressing the above challenges, our work introduces point cloud data of marine scenarios under realistically simulated adverse weather conditions and a dedicated Ship Detector tailored for marine environments. To adapt to various maritime weather conditions, we simulate realistic rain and fog in collected marine scene point cloud data. Additionally, addressing the issue of losing geometric and height information during feature extraction for large objects, we propose a Ship Detector. It employs a dual-branch sparse convolution layer for extracting multi-scale 3D feature maps, effectively minimizing height information loss. Additionally, a multi-scale 2D convolution module is utilized, which encodes and decodes feature maps and directly employs 3D feature maps for target prediction. To reduce dependency on existing data and enhance model robustness, our training dataset includes simulated point cloud data representing adverse weather conditions. In maritime point cloud ship detection, our Ship Detector, compared to adjusted small object detectors, demonstrates the best performance.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Adverse weather conditions for ship manoeuvrability
    Bitner-Gregerse, Elzbieta M.
    Guedes Soares, Carlos
    Vantorre, Marc
    TRANSPORT RESEARCH ARENA TRA2016, 2016, 14 : 1631 - 1640
  • [2] Rendering Scenes for Simulating Adverse Weather Conditions
    Sen, Prithwish
    Das, Anindita
    Sahu, Nilkanta
    ADVANCES IN COMPUTATIONAL INTELLIGENCE, IWANN 2021, PT I, 2021, 12861 : 347 - 358
  • [3] PODB: A learning-based polarimetric object detection benchmark for road scenes in adverse weather conditions
    Zhu, Zhen
    Li, Xiaobo
    Zhai, Jingsheng
    Hu, Haofeng
    INFORMATION FUSION, 2024, 108
  • [4] Learning degradation-aware visual prompt for maritime image restoration under adverse weather conditions
    He, Xin
    Jia, Tong
    Li, Junjie
    FRONTIERS IN MARINE SCIENCE, 2024, 11
  • [5] Joint Image and Feature Enhancement for Object Detection under Adverse Weather Conditions
    Yin, Mengyu
    Ling, Mingyang
    Chang, Kan
    Yuan, Zijian
    Qin, Qingpao
    Chen, Boning
    2024 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN 2024, 2024,
  • [6] Saturation Flow Under Adverse Weather Conditions
    Asamer, Johannes
    Van Zuylen, Henk J.
    TRANSPORTATION RESEARCH RECORD, 2011, (2258) : 103 - 109
  • [7] PAINTING OF TIMBER UNDER ADVERSE WEATHER CONDITIONS
    BOXALL, J
    JOURNAL OF THE OIL & COLOUR CHEMISTS ASSOCIATION, 1977, 60 (02): : 43 - 52
  • [8] DENet: Detection-driven Enhancement Network for Object Detection Under Adverse Weather Conditions
    Qin, Qingpao
    Chang, Kan
    Huang, Mengyuan
    Li, Guiqing
    COMPUTER VISION - ACCV 2022, PT III, 2023, 13843 : 491 - 507
  • [9] Roll motions analysis to improve ship responses in adverse weather conditions
    Andrei, Cristian
    Acomi, Nicoleta
    Ancuta, Cristian
    ADVANCED TOPICS IN OPTOELECTRONICS, MICROELECTRONICS, AND NANOTECHNOLOGIES IX, 2018, 10977
  • [10] Photonic Sensor for Multiple Targets Detection under Adverse Weather Conditions in Autonomous Vehicles
    Sharma, Abhishek
    Chaudhary, Sushank
    Malhotra, Jyoteesh
    Khichar, Sunita
    Wuttisittikulkij, Lunchakorn
    JOURNAL OF SENSOR AND ACTUATOR NETWORKS, 2022, 11 (04)