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

IntroductionMaritime 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 porti...

Full description

Saved in:
Bibliographic Details
Main Authors: Guokang Xu, Jianchuan Yin, Jinfeng Zhang, Nini Wang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Marine Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmars.2025.1547747/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434741798862848
author Guokang Xu
Jianchuan Yin
Jianchuan Yin
Jinfeng Zhang
Nini Wang
author_facet Guokang Xu
Jianchuan Yin
Jianchuan Yin
Jinfeng Zhang
Nini Wang
author_sort Guokang Xu
collection DOAJ
description IntroductionMaritime 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.MethodsTo 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.ResultsExperimental 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.DiscussionIn 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.
format Article
id doaj-art-19e382098d6b4375baaeff75c71c2f13
institution Kabale University
issn 2296-7745
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Marine Science
spelling doaj-art-19e382098d6b4375baaeff75c71c2f132025-08-20T03:26:33ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-06-011210.3389/fmars.2025.15477471547747Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion networkGuokang Xu0Jianchuan Yin1Jianchuan Yin2Jinfeng Zhang3Nini Wang4Naval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaNaval Architecture and Shipping College, Guangdong Ocean University, Zhanjiang, ChinaGuangdong Provincial Key Laboratory of Intelligent Equipment for South China Sea Marine Ranching, Zhanjiang, ChinaSchool of Navigation, Wuhan University of Technology, Wuhan, ChinaCollege of Mathematics and Computer, Guangdong Ocean University, Zhanjiang, ChinaIntroductionMaritime 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.MethodsTo 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.ResultsExperimental 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.DiscussionIn 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.https://www.frontiersin.org/articles/10.3389/fmars.2025.1547747/fullman-overboardmodulated deformable convolutionbi-directional feature fusion networkanchor-free detectormaritime search and rescuesmall object detection
spellingShingle Guokang Xu
Jianchuan Yin
Jianchuan Yin
Jinfeng Zhang
Nini Wang
Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network
Frontiers in Marine Science
man-overboard
modulated deformable convolution
bi-directional feature fusion network
anchor-free detector
maritime search and rescue
small object detection
title Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network
title_full Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network
title_fullStr Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network
title_full_unstemmed Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network
title_short Maritime man-overboard search based on MOB-Detector with modulated deformable convolution and bi-directional feature fusion network
title_sort maritime man overboard search based on mob detector with modulated deformable convolution and bi directional feature fusion network
topic man-overboard
modulated deformable convolution
bi-directional feature fusion network
anchor-free detector
maritime search and rescue
small object detection
url https://www.frontiersin.org/articles/10.3389/fmars.2025.1547747/full
work_keys_str_mv AT guokangxu maritimemanoverboardsearchbasedonmobdetectorwithmodulateddeformableconvolutionandbidirectionalfeaturefusionnetwork
AT jianchuanyin maritimemanoverboardsearchbasedonmobdetectorwithmodulateddeformableconvolutionandbidirectionalfeaturefusionnetwork
AT jianchuanyin maritimemanoverboardsearchbasedonmobdetectorwithmodulateddeformableconvolutionandbidirectionalfeaturefusionnetwork
AT jinfengzhang maritimemanoverboardsearchbasedonmobdetectorwithmodulateddeformableconvolutionandbidirectionalfeaturefusionnetwork
AT niniwang maritimemanoverboardsearchbasedonmobdetectorwithmodulateddeformableconvolutionandbidirectionalfeaturefusionnetwork