Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion

Infrared cameras form images by capturing the thermal radiation emitted by objects in the infrared spectrum, making them complex sensors widely used in maritime surveillance. However, the broad spectral range of the infrared band makes it susceptible to environmental interference, which can reduce t...

Full description

Saved in:
Bibliographic Details
Main Authors: Chun Liu, Yuanliang Zhang, Jingfu Shen, Feiyue Liu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/12/12/2130
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104140664537088
author Chun Liu
Yuanliang Zhang
Jingfu Shen
Feiyue Liu
author_facet Chun Liu
Yuanliang Zhang
Jingfu Shen
Feiyue Liu
author_sort Chun Liu
collection DOAJ
description Infrared cameras form images by capturing the thermal radiation emitted by objects in the infrared spectrum, making them complex sensors widely used in maritime surveillance. However, the broad spectral range of the infrared band makes it susceptible to environmental interference, which can reduce the contrast between the target and the background. As a result, detecting infrared targets in complex marine environments remains challenging. This paper presents a novel and enhanced detection model developed from the real-time detection transformer (RT-DETR), which is designated as MAFF-DETR. The model incorporates a novel backbone by integrating CSP and parallelized patch-aware attention to enhance sensitivity to infrared imagery. Additionally, a channel attention module is employed during feature selection, leveraging high-level features to filter low-level information and enabling efficient multi-level fusion. The model’s target detection performance on resource-constrained devices is further enhanced by incorporating advanced techniques such as group convolution and ShuffleNetV2. The experimental results show that, although the enhanced RT-DETR algorithm still experiences missed detections under severe object occlusion, it has significantly improved overall performance, including a 1.7% increase in mAP, a reduction in 4.3 M parameters, and a 5.8 GFLOPs decrease in computational complexity. It can be widely applied to tasks such as coastline monitoring and maritime search and rescue.
format Article
id doaj-art-58df9e53bc0140bbab36feb693e4523a
institution Kabale University
issn 2077-1312
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-58df9e53bc0140bbab36feb693e4523a2024-12-27T14:33:02ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-11-011212213010.3390/jmse12122130Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature FusionChun Liu0Yuanliang Zhang1Jingfu Shen2Feiyue Liu3College of Marine Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaCollege of Mechanical Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaCollege of Marine Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaCollege of Marine Engineering, Jiangsu Ocean University, Lianyungang 222005, ChinaInfrared cameras form images by capturing the thermal radiation emitted by objects in the infrared spectrum, making them complex sensors widely used in maritime surveillance. However, the broad spectral range of the infrared band makes it susceptible to environmental interference, which can reduce the contrast between the target and the background. As a result, detecting infrared targets in complex marine environments remains challenging. This paper presents a novel and enhanced detection model developed from the real-time detection transformer (RT-DETR), which is designated as MAFF-DETR. The model incorporates a novel backbone by integrating CSP and parallelized patch-aware attention to enhance sensitivity to infrared imagery. Additionally, a channel attention module is employed during feature selection, leveraging high-level features to filter low-level information and enabling efficient multi-level fusion. The model’s target detection performance on resource-constrained devices is further enhanced by incorporating advanced techniques such as group convolution and ShuffleNetV2. The experimental results show that, although the enhanced RT-DETR algorithm still experiences missed detections under severe object occlusion, it has significantly improved overall performance, including a 1.7% increase in mAP, a reduction in 4.3 M parameters, and a 5.8 GFLOPs decrease in computational complexity. It can be widely applied to tasks such as coastline monitoring and maritime search and rescue.https://www.mdpi.com/2077-1312/12/12/2130object detectioninfrared shipRT-DETR
spellingShingle Chun Liu
Yuanliang Zhang
Jingfu Shen
Feiyue Liu
Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion
Journal of Marine Science and Engineering
object detection
infrared ship
RT-DETR
title Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion
title_full Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion
title_fullStr Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion
title_full_unstemmed Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion
title_short Improved RT-DETR for Infrared Ship Detection Based on Multi-Attention and Feature Fusion
title_sort improved rt detr for infrared ship detection based on multi attention and feature fusion
topic object detection
infrared ship
RT-DETR
url https://www.mdpi.com/2077-1312/12/12/2130
work_keys_str_mv AT chunliu improvedrtdetrforinfraredshipdetectionbasedonmultiattentionandfeaturefusion
AT yuanliangzhang improvedrtdetrforinfraredshipdetectionbasedonmultiattentionandfeaturefusion
AT jingfushen improvedrtdetrforinfraredshipdetectionbasedonmultiattentionandfeaturefusion
AT feiyueliu improvedrtdetrforinfraredshipdetectionbasedonmultiattentionandfeaturefusion