Cargando…

UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection

Underwater video object detection is a challenging task due to the poor quality of underwater videos, including blurriness and low contrast. In recent years, Yolo series models have been widely applied to underwater video object detection. However, these models perform poorly for blurry and low-cont...

Descripción completa

Detalles Bibliográficos
Autores principales: Pan, Haixia, Lan, Jiahua, Wang, Hongqiang, Li, Yanan, Zhang, Meng, Ma, Mojie, Zhang, Dongdong, Zhao, Xiaoran
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10221615/
https://www.ncbi.nlm.nih.gov/pubmed/37430773
http://dx.doi.org/10.3390/s23104859
_version_ 1785049498720927744
author Pan, Haixia
Lan, Jiahua
Wang, Hongqiang
Li, Yanan
Zhang, Meng
Ma, Mojie
Zhang, Dongdong
Zhao, Xiaoran
author_facet Pan, Haixia
Lan, Jiahua
Wang, Hongqiang
Li, Yanan
Zhang, Meng
Ma, Mojie
Zhang, Dongdong
Zhao, Xiaoran
author_sort Pan, Haixia
collection PubMed
description Underwater video object detection is a challenging task due to the poor quality of underwater videos, including blurriness and low contrast. In recent years, Yolo series models have been widely applied to underwater video object detection. However, these models perform poorly for blurry and low-contrast underwater videos. Additionally, they fail to account for the contextual relationships between the frame-level results. To address these challenges, we propose a video object detection model named UWV-Yolox. First, the Contrast Limited Adaptive Histogram Equalization method is used to augment the underwater videos. Then, a new CSP_CA module is proposed by adding Coordinate Attention to the backbone of the model to augment the representations of objects of interest. Next, a new loss function is proposed, including regression and jitter loss. Finally, a frame-level optimization module is proposed to optimize the detection results by utilizing the relationship between neighboring frames in videos, improving the video detection performance. To evaluate the performance of our model, We construct experiments on the UVODD dataset built in the paper, and select mAP@0.5 as the evaluation metric. The mAP@0.5 of the UWV-Yolox model reaches 89.0%, which is 3.2% better than the original Yolox model. Furthermore, compared with other object detection models, the UWV-Yolox model has more stable predictions for objects, and our improvements can be flexibly applied to other models.
format Online
Article
Text
id pubmed-10221615
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102216152023-05-28 UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection Pan, Haixia Lan, Jiahua Wang, Hongqiang Li, Yanan Zhang, Meng Ma, Mojie Zhang, Dongdong Zhao, Xiaoran Sensors (Basel) Article Underwater video object detection is a challenging task due to the poor quality of underwater videos, including blurriness and low contrast. In recent years, Yolo series models have been widely applied to underwater video object detection. However, these models perform poorly for blurry and low-contrast underwater videos. Additionally, they fail to account for the contextual relationships between the frame-level results. To address these challenges, we propose a video object detection model named UWV-Yolox. First, the Contrast Limited Adaptive Histogram Equalization method is used to augment the underwater videos. Then, a new CSP_CA module is proposed by adding Coordinate Attention to the backbone of the model to augment the representations of objects of interest. Next, a new loss function is proposed, including regression and jitter loss. Finally, a frame-level optimization module is proposed to optimize the detection results by utilizing the relationship between neighboring frames in videos, improving the video detection performance. To evaluate the performance of our model, We construct experiments on the UVODD dataset built in the paper, and select mAP@0.5 as the evaluation metric. The mAP@0.5 of the UWV-Yolox model reaches 89.0%, which is 3.2% better than the original Yolox model. Furthermore, compared with other object detection models, the UWV-Yolox model has more stable predictions for objects, and our improvements can be flexibly applied to other models. MDPI 2023-05-18 /pmc/articles/PMC10221615/ /pubmed/37430773 http://dx.doi.org/10.3390/s23104859 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Pan, Haixia
Lan, Jiahua
Wang, Hongqiang
Li, Yanan
Zhang, Meng
Ma, Mojie
Zhang, Dongdong
Zhao, Xiaoran
UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection
title UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection
title_full UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection
title_fullStr UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection
title_full_unstemmed UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection
title_short UWV-Yolox: A Deep Learning Model for Underwater Video Object Detection
title_sort uwv-yolox: a deep learning model for underwater video object detection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10221615/
https://www.ncbi.nlm.nih.gov/pubmed/37430773
http://dx.doi.org/10.3390/s23104859
work_keys_str_mv AT panhaixia uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT lanjiahua uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT wanghongqiang uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT liyanan uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT zhangmeng uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT mamojie uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT zhangdongdong uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection
AT zhaoxiaoran uwvyoloxadeeplearningmodelforunderwatervideoobjectdetection