A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television

Vessel recognition plays important role in ensuring navigation safety. However, existing methods are mainly based on a single sensor, such as automatic identification system (AIS), marine radar, closed-circuit television (CCTV), etc. To this end, this paper proposes a coarse-to-fine recognition meth...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xinglong Liu, Yicheng Li, Yong Wu, Zhiyuan Wang, Wei He, Zhixiong Li
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	marine vessel recognition multi-scale matching convolutional neural network (CNN) radar-camera calibration vessel net (VesNet) Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581
Acceso en línea:	https://doaj.org/article/f94c6f295dab416783c4423c5ac235b1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f94c6f295dab416783c4423c5ac235b1
record_format	dspace
spelling	oai:doaj.org-article:f94c6f295dab416783c4423c5ac235b12021-11-25T18:04:15ZA Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television10.3390/jmse91111992077-1312https://doaj.org/article/f94c6f295dab416783c4423c5ac235b12021-10-01T00:00:00Zhttps://www.mdpi.com/2077-1312/9/11/1199https://doaj.org/toc/2077-1312Vessel recognition plays important role in ensuring navigation safety. However, existing methods are mainly based on a single sensor, such as automatic identification system (AIS), marine radar, closed-circuit television (CCTV), etc. To this end, this paper proposes a coarse-to-fine recognition method by fusing CCTV and marine radar, called multi-scale matching vessel recognition (MSM-VR). This method first proposes a novel calibration method that does not use any additional calibration target. The calibration is transformed to solve an N point registration model. Furthermore, marine radar image is used for coarse detection. A region of interest (ROI) area is computed for coarse detection results. Lastly, we design a novel convolutional neural network (CNN) called VesNet and transform the recognition into feature extraction. The VesNet is used to extract the vessel features. As a result, the MVM-VR method has been validated by using actual datasets collected along different waterways such as Nanjing waterway and Wuhan waterway, China, covering different times and weather conditions. Experimental results show that the MSM-VR method can adapt to different times, different weather conditions, and different waterways with good detection stability. The recognition accuracy is no less than 96%. Compared to other methods, the proposed method has high accuracy and great robustness.Xinglong LiuYicheng LiYong WuZhiyuan WangWei HeZhixiong LiMDPI AGarticlemarine vessel recognitionmulti-scale matchingconvolutional neural network (CNN)radar-camera calibrationvessel net (VesNet)Naval architecture. Shipbuilding. Marine engineeringVM1-989OceanographyGC1-1581ENJournal of Marine Science and Engineering, Vol 9, Iss 1199, p 1199 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	marine vessel recognition multi-scale matching convolutional neural network (CNN) radar-camera calibration vessel net (VesNet) Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581
spellingShingle	marine vessel recognition multi-scale matching convolutional neural network (CNN) radar-camera calibration vessel net (VesNet) Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 Xinglong Liu Yicheng Li Yong Wu Zhiyuan Wang Wei He Zhixiong Li A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television
description	Vessel recognition plays important role in ensuring navigation safety. However, existing methods are mainly based on a single sensor, such as automatic identification system (AIS), marine radar, closed-circuit television (CCTV), etc. To this end, this paper proposes a coarse-to-fine recognition method by fusing CCTV and marine radar, called multi-scale matching vessel recognition (MSM-VR). This method first proposes a novel calibration method that does not use any additional calibration target. The calibration is transformed to solve an N point registration model. Furthermore, marine radar image is used for coarse detection. A region of interest (ROI) area is computed for coarse detection results. Lastly, we design a novel convolutional neural network (CNN) called VesNet and transform the recognition into feature extraction. The VesNet is used to extract the vessel features. As a result, the MVM-VR method has been validated by using actual datasets collected along different waterways such as Nanjing waterway and Wuhan waterway, China, covering different times and weather conditions. Experimental results show that the MSM-VR method can adapt to different times, different weather conditions, and different waterways with good detection stability. The recognition accuracy is no less than 96%. Compared to other methods, the proposed method has high accuracy and great robustness.
format	article
author	Xinglong Liu Yicheng Li Yong Wu Zhiyuan Wang Wei He Zhixiong Li
author_facet	Xinglong Liu Yicheng Li Yong Wu Zhiyuan Wang Wei He Zhixiong Li
author_sort	Xinglong Liu
title	A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television
title_short	A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television
title_full	A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television
title_fullStr	A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television
title_full_unstemmed	A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television
title_sort	hybrid method for inland ship recognition using marine radar and closed-circuit television
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f94c6f295dab416783c4423c5ac235b1
work_keys_str_mv	AT xinglongliu ahybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT yichengli ahybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT yongwu ahybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT zhiyuanwang ahybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT weihe ahybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT zhixiongli ahybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT xinglongliu hybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT yichengli hybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT yongwu hybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT zhiyuanwang hybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT weihe hybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision AT zhixiongli hybridmethodforinlandshiprecognitionusingmarineradarandclosedcircuittelevision
_version_	1718411719434305536

A Hybrid Method for Inland Ship Recognition Using Marine Radar and Closed-Circuit Television

Ejemplares similares