Multi-Scale Feature Fusion Enhancement for Underwater Object Detection

Underwater object detection (UOD) presents substantial challenges due to the complex visual conditions and the physical properties of light in underwater environments. Small aquatic creatures often congregate in large groups, further complicating the task. To address these challenges, we develop Aqu...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhanhao Xiao, Zhenpeng Li, Huihui Li, Mengting Li, Xiaoyong Liu, Yinying Kong
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152500135067648
author Zhanhao Xiao
Zhenpeng Li
Huihui Li
Mengting Li
Xiaoyong Liu
Yinying Kong
author_facet Zhanhao Xiao
Zhenpeng Li
Huihui Li
Mengting Li
Xiaoyong Liu
Yinying Kong
author_sort Zhanhao Xiao
collection DOAJ
description Underwater object detection (UOD) presents substantial challenges due to the complex visual conditions and the physical properties of light in underwater environments. Small aquatic creatures often congregate in large groups, further complicating the task. To address these challenges, we develop Aqua-DETR, a tailored end-to-end framework for UOD. Our method includes an align-split network to enhance multi-scale feature interaction and fusion for small object identification and a distinction enhancement module using various attention mechanisms to improve ambiguous object identification. Experimental results on four challenging datasets demonstrate that Aqua-DETR outperforms most existing state-of-the-art methods in the UOD task, validating its effectiveness and robustness.
format Article
id doaj-art-77d2cd18c6ae4b41b5b8cd359863f34c
institution Kabale University
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-77d2cd18c6ae4b41b5b8cd359863f34c2024-11-26T18:21:05ZengMDPI AGSensors1424-82202024-11-012422720110.3390/s24227201Multi-Scale Feature Fusion Enhancement for Underwater Object DetectionZhanhao Xiao0Zhenpeng Li1Huihui Li2Mengting Li3Xiaoyong Liu4Yinying Kong5School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, ChinaSchool of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, ChinaSchool of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, ChinaSchool of Data Science and Engineering, Guangdong Polytechnic Normal University, Heyuan 517583, ChinaSchool of Data Science and Engineering, Guangdong Polytechnic Normal University, Heyuan 517583, ChinaSchool of Statistics and Mathematics, Guangdong University of Finance & Economics, Guangzhou 510320, ChinaUnderwater object detection (UOD) presents substantial challenges due to the complex visual conditions and the physical properties of light in underwater environments. Small aquatic creatures often congregate in large groups, further complicating the task. To address these challenges, we develop Aqua-DETR, a tailored end-to-end framework for UOD. Our method includes an align-split network to enhance multi-scale feature interaction and fusion for small object identification and a distinction enhancement module using various attention mechanisms to improve ambiguous object identification. Experimental results on four challenging datasets demonstrate that Aqua-DETR outperforms most existing state-of-the-art methods in the UOD task, validating its effectiveness and robustness.https://www.mdpi.com/1424-8220/24/22/7201underwater object detectionDETRcross-scale feature fusion
spellingShingle Zhanhao Xiao
Zhenpeng Li
Huihui Li
Mengting Li
Xiaoyong Liu
Yinying Kong
Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
Sensors
underwater object detection
DETR
cross-scale feature fusion
title Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
title_full Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
title_fullStr Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
title_full_unstemmed Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
title_short Multi-Scale Feature Fusion Enhancement for Underwater Object Detection
title_sort multi scale feature fusion enhancement for underwater object detection
topic underwater object detection
DETR
cross-scale feature fusion
url https://www.mdpi.com/1424-8220/24/22/7201
work_keys_str_mv AT zhanhaoxiao multiscalefeaturefusionenhancementforunderwaterobjectdetection
AT zhenpengli multiscalefeaturefusionenhancementforunderwaterobjectdetection
AT huihuili multiscalefeaturefusionenhancementforunderwaterobjectdetection
AT mengtingli multiscalefeaturefusionenhancementforunderwaterobjectdetection
AT xiaoyongliu multiscalefeaturefusionenhancementforunderwaterobjectdetection
AT yinyingkong multiscalefeaturefusionenhancementforunderwaterobjectdetection