文献类型：期刊文献

英文题名：Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network

作者：Xu, Guokang[1];Yin, Jianchuan[1,2];Zhang, Jinfeng[3];Wang, Nini[4]

机构：[1]Guangdong Ocean Univ, Naval Architecture & Shipping Coll, Zhanjiang, Peoples R China;[2]Guangdong Prov Key Lab Intelligent Equipment South, Zhanjiang, Peoples R China;[3]Wuhan Univ Technol, Sch Nav, Wuhan, Peoples R China;[4]Guangdong Ocean Univ, Coll Math & Comp, Zhanjiang, Peoples R China

年份：2025

卷号：12

外文期刊名：FRONTIERS IN MARINE SCIENCE

收录：SCI-EXPANDED(收录号：WOS:001525052000001)、、Scopus(收录号：2-s2.0-105010942216)、WOS

基金：The author(s) declare that financial support was received for the research and/or publication of this article. This work was supported by the National Natural Science Foundation of China under Grants 52231014 and 52271361; the Special Projects of Key Areas for Colleges and Universities in Guangdong Province under Grant 2021ZDZX1008; the Natural Science Foundation of Guangdong Province under Grant 2023A1515010684; the Technology Breakthrough Plan Project of Zhanjiang under Grant 2023B01024; the Postgraduate Education Innovation Project of Guangdong Ocean University (202546); and the Program for Scientific Research Start-Up Funds of Guangdong Ocean University.

语种：英文

外文关键词：man-overboard; modulated deformable convolution; bi-directional feature fusion network; anchor-free detector; maritime search and rescue; small object detection

外文摘要：Introduction Maritime transport is vital for global trade and cultural exchange, yet it carries inherent risks, particularly accidents at sea. Drones are increasingly valuable in marine search missions. However, Unmanned Aerial Vehicles (UAV) operating at high altitudes often leave only a small portion of a person overboard visible above the water, posing challenges for traditional detection algorithms.Methods To tackle this issue, we present the Man-Overboard Detector (MOB-Detector), an anchor-free detector that enhances the accuracy of man-overboard detection. MOB-Detector utilizes the bi-directional feature fusion network to integrate location and semantic features effectively. Additionally, it employs modulated deformable convolution (MDConv), allowing the model to adapt to various geometric variations of individuals in distress.Results Experimental validation shows that the MOB-Detector outperformed its nearest competitor by 8.6% in [Metric 1 AP50] and 5.2% in [Metric 2 APsmall], demonstrating its effectiveness for maritime search tasks. Furthermore, we introduce the ManOverboard Benchmark to evaluate algorithms for detecting small objects in maritime environments.Discussion In the discussion, the challenge faced by the MOB-Detector in low-visibility environments is discussed, and two future research directions are proposed: optimizing the detector based on the Transformer architecture and developing targeted data augmentation strategies.