EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments
Correct detection of floating objects in complex water environments is a challenge because of the problems of obscuration and dense floating objects. In view of the above issues, this article proposed a network called EC-YOLOX by introducing the coordinate attention (CA) and efficient channel attent...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10449338/ |
_version_ | 1797222058834264064 |
---|---|
author | Jiaxin He Yong Cheng Wei Wang Yakang Gu Yixuan Wang Wenjie Zhang Achyut Shankar Shitharth Selvarajan Sathish A. P. Kumar |
author_facet | Jiaxin He Yong Cheng Wei Wang Yakang Gu Yixuan Wang Wenjie Zhang Achyut Shankar Shitharth Selvarajan Sathish A. P. Kumar |
author_sort | Jiaxin He |
collection | DOAJ |
description | Correct detection of floating objects in complex water environments is a challenge because of the problems of obscuration and dense floating objects. In view of the above issues, this article proposed a network called EC-YOLOX by introducing the coordinate attention (CA) and efficient channel attention (ECA) mechanism and improving the loss function to further the multifeature extraction and detection accuracy of floating objects. In this article, ablation experiments and comparison experiments were conducted on the river floating objects dataset. The ablation experiments showed that the ECA and CA mechanism played a great role in EC-YOLOX, which can reduce the missed detection rate by 5.86% and increase the mean average precision (mAP) by 5.53% compared with YOLOX. The EC-YOLOX was also applicable to different types of floating objects; the mAP of the ball, plastic garbage, plastic bag, leaf, milk box, grass, and branches were, respectively, improved by 4%, 4%, 4%, 6%, 4%, 18%, and 5%. The mAP of the comparison experiments was improved by 15.13%, 9.30%, and 8.03% compared to faster R-CNN, YOLOv5, and YOLOv3, respectively. This method facilitates the precise extraction of floating objects from images, which holds paramount importance for monitoring and safeguarding water environments. It offers significant contributions to water environment monitoring and protection. |
first_indexed | 2024-04-24T13:15:18Z |
format | Article |
id | doaj.art-b6067f0250ff46e9af53237092abad8d |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-24T13:15:18Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-b6067f0250ff46e9af53237092abad8d2024-04-04T23:00:13ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01177359737010.1109/JSTARS.2024.336771310449338EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water EnvironmentsJiaxin He0https://orcid.org/0009-0002-0876-4227Yong Cheng1https://orcid.org/0009-0001-2287-2809Wei Wang2https://orcid.org/0009-0008-5436-1721Yakang Gu3https://orcid.org/0009-0005-3847-8709Yixuan Wang4https://orcid.org/0009-0007-8209-2541Wenjie Zhang5https://orcid.org/0000-0002-4463-6014Achyut Shankar6https://orcid.org/0000-0003-3165-3293Shitharth Selvarajan7Sathish A. P. Kumar8https://orcid.org/0000-0002-3162-2211School of Automation, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Software, Nanjing University of Information Science & Technology, Nanjing, ChinaSchool of Automation, Nanjing University of Information Science and Technology, Nanjing, ChinaSchool of Software, Nanjing University of Information Science & Technology, Nanjing, ChinaSchool of Software, Nanjing University of Information Science & Technology, Nanjing, ChinaSchool of Geographical Sciences, Nanjing University of Information Science & Technology, Nanjing, ChinaDepartment of Cyber Systems Engineering, WMG, University of Warwick, Coventry, U.K.School of Built Environment, Engineering and Computing, Leeds Beckett University, Leeds, U.K.Department of Computer Science, Cleveland State University, Cleveland, OH, USACorrect detection of floating objects in complex water environments is a challenge because of the problems of obscuration and dense floating objects. In view of the above issues, this article proposed a network called EC-YOLOX by introducing the coordinate attention (CA) and efficient channel attention (ECA) mechanism and improving the loss function to further the multifeature extraction and detection accuracy of floating objects. In this article, ablation experiments and comparison experiments were conducted on the river floating objects dataset. The ablation experiments showed that the ECA and CA mechanism played a great role in EC-YOLOX, which can reduce the missed detection rate by 5.86% and increase the mean average precision (mAP) by 5.53% compared with YOLOX. The EC-YOLOX was also applicable to different types of floating objects; the mAP of the ball, plastic garbage, plastic bag, leaf, milk box, grass, and branches were, respectively, improved by 4%, 4%, 4%, 6%, 4%, 18%, and 5%. The mAP of the comparison experiments was improved by 15.13%, 9.30%, and 8.03% compared to faster R-CNN, YOLOv5, and YOLOv3, respectively. This method facilitates the precise extraction of floating objects from images, which holds paramount importance for monitoring and safeguarding water environments. It offers significant contributions to water environment monitoring and protection.https://ieeexplore.ieee.org/document/10449338/Attention mechanismfloating objectsloss functionmissed detection rateYOLOX |
spellingShingle | Jiaxin He Yong Cheng Wei Wang Yakang Gu Yixuan Wang Wenjie Zhang Achyut Shankar Shitharth Selvarajan Sathish A. P. Kumar EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism floating objects loss function missed detection rate YOLOX |
title | EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments |
title_full | EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments |
title_fullStr | EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments |
title_full_unstemmed | EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments |
title_short | EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments |
title_sort | ec yolox a deep learning algorithm for floating objects detection in ground images of complex water environments |
topic | Attention mechanism floating objects loss function missed detection rate YOLOX |
url | https://ieeexplore.ieee.org/document/10449338/ |
work_keys_str_mv | AT jiaxinhe ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT yongcheng ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT weiwang ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT yakanggu ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT yixuanwang ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT wenjiezhang ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT achyutshankar ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT shitharthselvarajan ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments AT sathishapkumar ecyoloxadeeplearningalgorithmforfloatingobjectsdetectioningroundimagesofcomplexwaterenvironments |