Ship detection based on semantic aggregation for video surveillance images with complex backgrounds

Background Ship detection in video surveillance images holds significant practical value. However, the background in these images is often complex, complicating the achievement of an optimal balance between detection precision and speed. Method This study proposes a ship detection method that levera...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongmei Ren, Haibo Liu, Jie Yang, Xiaohu Wang, Wei He, Dongrui Xiao
Format: Article
Language:English
Published: PeerJ Inc. 2024-12-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2624.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846109163779784704
author Yongmei Ren
Haibo Liu
Jie Yang
Xiaohu Wang
Wei He
Dongrui Xiao
author_facet Yongmei Ren
Haibo Liu
Jie Yang
Xiaohu Wang
Wei He
Dongrui Xiao
author_sort Yongmei Ren
collection DOAJ
description Background Ship detection in video surveillance images holds significant practical value. However, the background in these images is often complex, complicating the achievement of an optimal balance between detection precision and speed. Method This study proposes a ship detection method that leverages semantic aggregation in complex backgrounds. Initially, a semantic aggregation module merges deep features, rich in semantic information, with shallow features abundant in location details, extracted via the front-end network. Concurrently, these shallow features are reshaped through the reorg layer to extract richer feature information, and then these reshaped shallow features are integrated with deep features within the feature fusion module, thereby enhancing the capability for feature fusion and improving classification and positioning capability. Subsequently, a multiscale object detection layer is implemented to enhance feature expression and effectively identify ship objects across various scales. Moreover, the distance intersection over union (DIoU) metric is utilized to refine the loss function, enhancing the detection precision for ship objects. Results The experimental results on the SeaShips dataset and SeaShips_enlarge dataset demonstrate that the mean average precision@0.5 (mAP@0.5) of this proposed method reaches 89.30% and 89.10%, respectively. Conclusions The proposed method surpasses other existing ship detection techniques in terms of detection effect and meets real-time detection requirements, underscoring its engineering relevance.
format Article
id doaj-art-aa09537c3aca4e9f81b02e417346938d
institution Kabale University
issn 2376-5992
language English
publishDate 2024-12-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-aa09537c3aca4e9f81b02e417346938d2024-12-25T15:05:40ZengPeerJ Inc.PeerJ Computer Science2376-59922024-12-0110e262410.7717/peerj-cs.2624Ship detection based on semantic aggregation for video surveillance images with complex backgroundsYongmei Ren0Haibo Liu1Jie Yang2Xiaohu Wang3Wei He4Dongrui Xiao5School of Electrical and Information Engineering, Hunan Institute of Technology, Hengyang, ChinaSchool of Electrical and Information Engineering, Hunan Institute of Technology, Hengyang, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan, ChinaCollege of Intelligent Manufacturing and Mechanical Engineering, Hunan Institute of Technology, Hengyang, ChinaSchool of Electrical and Information Engineering, Hunan Institute of Technology, Hengyang, ChinaSchool of Electrical and Information Engineering, Hunan Institute of Technology, Hengyang, ChinaBackground Ship detection in video surveillance images holds significant practical value. However, the background in these images is often complex, complicating the achievement of an optimal balance between detection precision and speed. Method This study proposes a ship detection method that leverages semantic aggregation in complex backgrounds. Initially, a semantic aggregation module merges deep features, rich in semantic information, with shallow features abundant in location details, extracted via the front-end network. Concurrently, these shallow features are reshaped through the reorg layer to extract richer feature information, and then these reshaped shallow features are integrated with deep features within the feature fusion module, thereby enhancing the capability for feature fusion and improving classification and positioning capability. Subsequently, a multiscale object detection layer is implemented to enhance feature expression and effectively identify ship objects across various scales. Moreover, the distance intersection over union (DIoU) metric is utilized to refine the loss function, enhancing the detection precision for ship objects. Results The experimental results on the SeaShips dataset and SeaShips_enlarge dataset demonstrate that the mean average precision@0.5 (mAP@0.5) of this proposed method reaches 89.30% and 89.10%, respectively. Conclusions The proposed method surpasses other existing ship detection techniques in terms of detection effect and meets real-time detection requirements, underscoring its engineering relevance.https://peerj.com/articles/cs-2624.pdfImage processingShip detectionSemantic aggregationFeature fusionVideo surveillance images
spellingShingle Yongmei Ren
Haibo Liu
Jie Yang
Xiaohu Wang
Wei He
Dongrui Xiao
Ship detection based on semantic aggregation for video surveillance images with complex backgrounds
PeerJ Computer Science
Image processing
Ship detection
Semantic aggregation
Feature fusion
Video surveillance images
title Ship detection based on semantic aggregation for video surveillance images with complex backgrounds
title_full Ship detection based on semantic aggregation for video surveillance images with complex backgrounds
title_fullStr Ship detection based on semantic aggregation for video surveillance images with complex backgrounds
title_full_unstemmed Ship detection based on semantic aggregation for video surveillance images with complex backgrounds
title_short Ship detection based on semantic aggregation for video surveillance images with complex backgrounds
title_sort ship detection based on semantic aggregation for video surveillance images with complex backgrounds
topic Image processing
Ship detection
Semantic aggregation
Feature fusion
Video surveillance images
url https://peerj.com/articles/cs-2624.pdf
work_keys_str_mv AT yongmeiren shipdetectionbasedonsemanticaggregationforvideosurveillanceimageswithcomplexbackgrounds
AT haiboliu shipdetectionbasedonsemanticaggregationforvideosurveillanceimageswithcomplexbackgrounds
AT jieyang shipdetectionbasedonsemanticaggregationforvideosurveillanceimageswithcomplexbackgrounds
AT xiaohuwang shipdetectionbasedonsemanticaggregationforvideosurveillanceimageswithcomplexbackgrounds
AT weihe shipdetectionbasedonsemanticaggregationforvideosurveillanceimageswithcomplexbackgrounds
AT dongruixiao shipdetectionbasedonsemanticaggregationforvideosurveillanceimageswithcomplexbackgrounds