Cargando…

YOLOv7-CSAW for maritime target detection

INTRODUCTION: The issue of low detection rates and high false negative rates in maritime search and rescue operations has been a critical problem in current target detection algorithms. This is mainly due to the complex maritime environment and the small size of most targets. These challenges affect...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Qiang, Ma, Ke, Wang, Zhong, Shi, Peibei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10352484/
https://www.ncbi.nlm.nih.gov/pubmed/37469573
http://dx.doi.org/10.3389/fnbot.2023.1210470
_version_ 1785074520071077888
author Zhu, Qiang
Ma, Ke
Wang, Zhong
Shi, Peibei
author_facet Zhu, Qiang
Ma, Ke
Wang, Zhong
Shi, Peibei
author_sort Zhu, Qiang
collection PubMed
description INTRODUCTION: The issue of low detection rates and high false negative rates in maritime search and rescue operations has been a critical problem in current target detection algorithms. This is mainly due to the complex maritime environment and the small size of most targets. These challenges affect the algorithms' robustness and generalization. METHODS: We proposed YOLOv7-CSAW, an improved maritime search and rescue target detection algorithm based on YOLOv7. We used the K-means++ algorithm for the optimal size determination of prior anchor boxes, ensuring an accurate match with actual objects. The C2f module was incorporated for a lightweight model capable of obtaining richer gradient flow information. The model's perception of small target features was increased with the non-parameter simple attention module (SimAM). We further upgraded the feature fusion network to an adaptive feature fusion network (ASFF) to address the lack of high-level semantic features in small targets. Lastly, we implemented the wise intersection over union (WIoU) loss function to tackle large positioning errors and missed detections. RESULTS: Our algorithm was extensively tested on a maritime search and rescue dataset with YOLOv7 as the baseline model. We observed a significant improvement in the detection performance compared to traditional deep learning algorithms, with a mean average precision (mAP) improvement of 10.73% over the baseline model. DISCUSSION: YOLOv7-CSAW significantly enhances the accuracy and robustness of small target detection in complex scenes. This algorithm effectively addresses the common issues experienced in maritime search and rescue operations, specifically improving the detection rates and reducing false negatives, proving to be a superior alternative to current target detection algorithms.
format Online
Article
Text
id pubmed-10352484
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103524842023-07-19 YOLOv7-CSAW for maritime target detection Zhu, Qiang Ma, Ke Wang, Zhong Shi, Peibei Front Neurorobot Neuroscience INTRODUCTION: The issue of low detection rates and high false negative rates in maritime search and rescue operations has been a critical problem in current target detection algorithms. This is mainly due to the complex maritime environment and the small size of most targets. These challenges affect the algorithms' robustness and generalization. METHODS: We proposed YOLOv7-CSAW, an improved maritime search and rescue target detection algorithm based on YOLOv7. We used the K-means++ algorithm for the optimal size determination of prior anchor boxes, ensuring an accurate match with actual objects. The C2f module was incorporated for a lightweight model capable of obtaining richer gradient flow information. The model's perception of small target features was increased with the non-parameter simple attention module (SimAM). We further upgraded the feature fusion network to an adaptive feature fusion network (ASFF) to address the lack of high-level semantic features in small targets. Lastly, we implemented the wise intersection over union (WIoU) loss function to tackle large positioning errors and missed detections. RESULTS: Our algorithm was extensively tested on a maritime search and rescue dataset with YOLOv7 as the baseline model. We observed a significant improvement in the detection performance compared to traditional deep learning algorithms, with a mean average precision (mAP) improvement of 10.73% over the baseline model. DISCUSSION: YOLOv7-CSAW significantly enhances the accuracy and robustness of small target detection in complex scenes. This algorithm effectively addresses the common issues experienced in maritime search and rescue operations, specifically improving the detection rates and reducing false negatives, proving to be a superior alternative to current target detection algorithms. Frontiers Media S.A. 2023-07-03 /pmc/articles/PMC10352484/ /pubmed/37469573 http://dx.doi.org/10.3389/fnbot.2023.1210470 Text en Copyright © 2023 Zhu, Ma, Wang and Shi. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Zhu, Qiang
Ma, Ke
Wang, Zhong
Shi, Peibei
YOLOv7-CSAW for maritime target detection
title YOLOv7-CSAW for maritime target detection
title_full YOLOv7-CSAW for maritime target detection
title_fullStr YOLOv7-CSAW for maritime target detection
title_full_unstemmed YOLOv7-CSAW for maritime target detection
title_short YOLOv7-CSAW for maritime target detection
title_sort yolov7-csaw for maritime target detection
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10352484/
https://www.ncbi.nlm.nih.gov/pubmed/37469573
http://dx.doi.org/10.3389/fnbot.2023.1210470
work_keys_str_mv AT zhuqiang yolov7csawformaritimetargetdetection
AT make yolov7csawformaritimetargetdetection
AT wangzhong yolov7csawformaritimetargetdetection
AT shipeibei yolov7csawformaritimetargetdetection