Cargando…

Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n

Deep-sea biological detection is essential for deep-sea resource research and conservation. However, due to the poor image quality and insufficient image samples in the complex deep-sea imaging environment, resulting in poor detection results. Furthermore, most existing detection models accomplish h...

Descripción completa

Detalles Bibliográficos
Autores principales: Ding, Zhongjun, Liu, Chen, Li, Dewei, Yi, Guangrui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611201/
https://www.ncbi.nlm.nih.gov/pubmed/37896693
http://dx.doi.org/10.3390/s23208600
_version_ 1785128435772817408
author Ding, Zhongjun
Liu, Chen
Li, Dewei
Yi, Guangrui
author_facet Ding, Zhongjun
Liu, Chen
Li, Dewei
Yi, Guangrui
author_sort Ding, Zhongjun
collection PubMed
description Deep-sea biological detection is essential for deep-sea resource research and conservation. However, due to the poor image quality and insufficient image samples in the complex deep-sea imaging environment, resulting in poor detection results. Furthermore, most existing detection models accomplish high precision at the expense of increased complexity, and leading cannot be well deployed in the deep-sea environment. To alleviate these problems, a detection method for deep-sea organisms based on lightweight YOLOv5n is proposed. First, a lightweight YOLOv5n is created. The proposed image enhancement method based on global and local contrast fusion (GLCF) is introduced into the input layer of YOLOv5n to address the problem of color deviation and low contrast in the image. At the same time, a Bottleneck based on the Ghost module and simAM (GS-Bottleneck) is developed to achieve a lightweight model while ensuring sure detection performance. Second, a transfer learning strategy combined with knowledge distillation (TLKD) is designed, which can reduce the dependence of the model on the amount of data and improve the generalization ability to enhance detection accuracy. Experimental results on the deep-sea biological dataset show that the proposed method achieves good detection accuracy and speed, outperforming existing methods.
format Online
Article
Text
id pubmed-10611201
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106112012023-10-28 Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n Ding, Zhongjun Liu, Chen Li, Dewei Yi, Guangrui Sensors (Basel) Article Deep-sea biological detection is essential for deep-sea resource research and conservation. However, due to the poor image quality and insufficient image samples in the complex deep-sea imaging environment, resulting in poor detection results. Furthermore, most existing detection models accomplish high precision at the expense of increased complexity, and leading cannot be well deployed in the deep-sea environment. To alleviate these problems, a detection method for deep-sea organisms based on lightweight YOLOv5n is proposed. First, a lightweight YOLOv5n is created. The proposed image enhancement method based on global and local contrast fusion (GLCF) is introduced into the input layer of YOLOv5n to address the problem of color deviation and low contrast in the image. At the same time, a Bottleneck based on the Ghost module and simAM (GS-Bottleneck) is developed to achieve a lightweight model while ensuring sure detection performance. Second, a transfer learning strategy combined with knowledge distillation (TLKD) is designed, which can reduce the dependence of the model on the amount of data and improve the generalization ability to enhance detection accuracy. Experimental results on the deep-sea biological dataset show that the proposed method achieves good detection accuracy and speed, outperforming existing methods. MDPI 2023-10-20 /pmc/articles/PMC10611201/ /pubmed/37896693 http://dx.doi.org/10.3390/s23208600 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
Ding, Zhongjun
Liu, Chen
Li, Dewei
Yi, Guangrui
Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n
title Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n
title_full Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n
title_fullStr Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n
title_full_unstemmed Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n
title_short Deep-Sea Biological Detection Method Based on Lightweight YOLOv5n
title_sort deep-sea biological detection method based on lightweight yolov5n
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611201/
https://www.ncbi.nlm.nih.gov/pubmed/37896693
http://dx.doi.org/10.3390/s23208600
work_keys_str_mv AT dingzhongjun deepseabiologicaldetectionmethodbasedonlightweightyolov5n
AT liuchen deepseabiologicaldetectionmethodbasedonlightweightyolov5n
AT lidewei deepseabiologicaldetectionmethodbasedonlightweightyolov5n
AT yiguangrui deepseabiologicaldetectionmethodbasedonlightweightyolov5n