A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection

Underwater vision-based detection plays an increasingly important role in underwater security, ocean exploration and other fields. Due to the absorption and scattering effects of water on light, as well as the movement of the carrier, underwater images generally have problems such as noise pollution...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xueting Zhang, Xiaohai Fang, Mian Pan, Luhua Yuan, Yaxin Zhang, Mengyi Yuan, Shuaishuai Lv, Haibin Yu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	marine organism detection marine monitoring underwater image enhancement underwater object detection joint optimization generative adversarial mechanism Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/a0d1fce1ae7f471095e9a254a6d18d5f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a0d1fce1ae7f471095e9a254a6d18d5f
record_format	dspace
spelling	oai:doaj.org-article:a0d1fce1ae7f471095e9a254a6d18d5f2021-11-11T19:11:14ZA Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection10.3390/s212172051424-8220https://doaj.org/article/a0d1fce1ae7f471095e9a254a6d18d5f2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7205https://doaj.org/toc/1424-8220Underwater vision-based detection plays an increasingly important role in underwater security, ocean exploration and other fields. Due to the absorption and scattering effects of water on light, as well as the movement of the carrier, underwater images generally have problems such as noise pollution, color cast and motion blur, which seriously affect the performance of underwater vision-based detection. To address these problems, this study proposes an end-to-end marine organism detection framework that can jointly optimize the image enhancement and object detection. The framework uses a two-stage detection network with dynamic intersection over union (IoU) threshold as the backbone and adds an underwater image enhancement module (UIEM) composed of denoising, color correction and deblurring sub-modules to greatly improve the framework’s ability to deal with severely degraded underwater images. Meanwhile, a self-built dataset is introduced to pre-train the UIEM, so that the training of the entire framework can be performed end-to-end. The experimental results show that compared with the existing end-to-end models applied to marine organism detection, the detection precision of the proposed framework can improve by at least 6%, and the detection speed has not been significantly reduced, so that it can complete the high-precision real-time detection of marine organisms.Xueting ZhangXiaohai FangMian PanLuhua YuanYaxin ZhangMengyi YuanShuaishuai LvHaibin YuMDPI AGarticlemarine organism detectionmarine monitoringunderwater image enhancementunderwater object detectionjoint optimizationgenerative adversarial mechanismChemical technologyTP1-1185ENSensors, Vol 21, Iss 7205, p 7205 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	marine organism detection marine monitoring underwater image enhancement underwater object detection joint optimization generative adversarial mechanism Chemical technology TP1-1185
spellingShingle	marine organism detection marine monitoring underwater image enhancement underwater object detection joint optimization generative adversarial mechanism Chemical technology TP1-1185 Xueting Zhang Xiaohai Fang Mian Pan Luhua Yuan Yaxin Zhang Mengyi Yuan Shuaishuai Lv Haibin Yu A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection
description	Underwater vision-based detection plays an increasingly important role in underwater security, ocean exploration and other fields. Due to the absorption and scattering effects of water on light, as well as the movement of the carrier, underwater images generally have problems such as noise pollution, color cast and motion blur, which seriously affect the performance of underwater vision-based detection. To address these problems, this study proposes an end-to-end marine organism detection framework that can jointly optimize the image enhancement and object detection. The framework uses a two-stage detection network with dynamic intersection over union (IoU) threshold as the backbone and adds an underwater image enhancement module (UIEM) composed of denoising, color correction and deblurring sub-modules to greatly improve the framework’s ability to deal with severely degraded underwater images. Meanwhile, a self-built dataset is introduced to pre-train the UIEM, so that the training of the entire framework can be performed end-to-end. The experimental results show that compared with the existing end-to-end models applied to marine organism detection, the detection precision of the proposed framework can improve by at least 6%, and the detection speed has not been significantly reduced, so that it can complete the high-precision real-time detection of marine organisms.
format	article
author	Xueting Zhang Xiaohai Fang Mian Pan Luhua Yuan Yaxin Zhang Mengyi Yuan Shuaishuai Lv Haibin Yu
author_facet	Xueting Zhang Xiaohai Fang Mian Pan Luhua Yuan Yaxin Zhang Mengyi Yuan Shuaishuai Lv Haibin Yu
author_sort	Xueting Zhang
title	A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection
title_short	A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection
title_full	A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection
title_fullStr	A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection
title_full_unstemmed	A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection
title_sort	marine organism detection framework based on the joint optimization of image enhancement and object detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a0d1fce1ae7f471095e9a254a6d18d5f
work_keys_str_mv	AT xuetingzhang amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT xiaohaifang amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT mianpan amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT luhuayuan amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT yaxinzhang amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT mengyiyuan amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT shuaishuailv amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT haibinyu amarineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT xuetingzhang marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT xiaohaifang marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT mianpan marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT luhuayuan marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT yaxinzhang marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT mengyiyuan marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT shuaishuailv marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection AT haibinyu marineorganismdetectionframeworkbasedonthejointoptimizationofimageenhancementandobjectdetection
_version_	1718431601276223488

A Marine Organism Detection Framework Based on the Joint Optimization of Image Enhancement and Object Detection

Ejemplares similares