Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source

Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine lit...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Brendan Chongzhi Corrigan [verfasserIn] Zhi Yung Tay [verfasserIn] Dimitrios Konovessis [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	underwater litter plastic litter computer vision litter detection instance segmentation YOLACT

Übergeordnetes Werk:	In: Journal of Marine Science and Engineering - MDPI AG, 2014, 11(2023), 8, p 1532
Übergeordnetes Werk:	volume:11 ; year:2023 ; number:8, p 1532

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/jmse11081532

Katalog-ID:	DOAJ09359657X

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ09359657X
003	DE-627
005	20240413013513.0
007	cr uuu---uuuuu
008	240413s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/jmse11081532 \|2 doi
035			\|a (DE-627)DOAJ09359657X
035			\|a (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a VM1-989
050		0	\|a GC1-1581
100	0		\|a Brendan Chongzhi Corrigan \|e verfasserin \|4 aut
245	1	0	\|a Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source
264		1	\|c 2023
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution.
650		4	\|a underwater litter
650		4	\|a plastic litter
650		4	\|a computer vision
650		4	\|a litter detection
650		4	\|a instance segmentation
650		4	\|a YOLACT
653		0	\|a Naval architecture. Shipbuilding. Marine engineering
653		0	\|a Oceanography
700	0		\|a Zhi Yung Tay \|e verfasserin \|4 aut
700	0		\|a Dimitrios Konovessis \|e verfasserin \|4 aut
773	0	8	\|i In \|t Journal of Marine Science and Engineering \|d MDPI AG, 2014 \|g 11(2023), 8, p 1532 \|w (DE-627)771274181 \|w (DE-600)2738390-8 \|x 20771312 \|7 nnns
773	1	8	\|g volume:11 \|g year:2023 \|g number:8, p 1532
856	4	0	\|u https://doi.org/10.3390/jmse11081532 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/2077-1312/11/8/1532 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2077-1312 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 11 \|j 2023 \|e 8, p 1532

Indexfelder

author_variant	b c c bcc z y t zyt d k dk
matchkey_str	article:20771312:2023----::elientneemnainodtcinfnewtri
hierarchy_sort_str	2023
callnumber-subject-code	VM
publishDate	2023
allfields	10.3390/jmse11081532 doi (DE-627)DOAJ09359657X (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0 DE-627 ger DE-627 rakwb eng VM1-989 GC1-1581 Brendan Chongzhi Corrigan verfasserin aut Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution. underwater litter plastic litter computer vision litter detection instance segmentation YOLACT Naval architecture. Shipbuilding. Marine engineering Oceanography Zhi Yung Tay verfasserin aut Dimitrios Konovessis verfasserin aut In Journal of Marine Science and Engineering MDPI AG, 2014 11(2023), 8, p 1532 (DE-627)771274181 (DE-600)2738390-8 20771312 nnns volume:11 year:2023 number:8, p 1532 https://doi.org/10.3390/jmse11081532 kostenfrei https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 kostenfrei https://www.mdpi.com/2077-1312/11/8/1532 kostenfrei https://doaj.org/toc/2077-1312 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 8, p 1532
spelling	10.3390/jmse11081532 doi (DE-627)DOAJ09359657X (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0 DE-627 ger DE-627 rakwb eng VM1-989 GC1-1581 Brendan Chongzhi Corrigan verfasserin aut Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution. underwater litter plastic litter computer vision litter detection instance segmentation YOLACT Naval architecture. Shipbuilding. Marine engineering Oceanography Zhi Yung Tay verfasserin aut Dimitrios Konovessis verfasserin aut In Journal of Marine Science and Engineering MDPI AG, 2014 11(2023), 8, p 1532 (DE-627)771274181 (DE-600)2738390-8 20771312 nnns volume:11 year:2023 number:8, p 1532 https://doi.org/10.3390/jmse11081532 kostenfrei https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 kostenfrei https://www.mdpi.com/2077-1312/11/8/1532 kostenfrei https://doaj.org/toc/2077-1312 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 8, p 1532
allfields_unstemmed	10.3390/jmse11081532 doi (DE-627)DOAJ09359657X (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0 DE-627 ger DE-627 rakwb eng VM1-989 GC1-1581 Brendan Chongzhi Corrigan verfasserin aut Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution. underwater litter plastic litter computer vision litter detection instance segmentation YOLACT Naval architecture. Shipbuilding. Marine engineering Oceanography Zhi Yung Tay verfasserin aut Dimitrios Konovessis verfasserin aut In Journal of Marine Science and Engineering MDPI AG, 2014 11(2023), 8, p 1532 (DE-627)771274181 (DE-600)2738390-8 20771312 nnns volume:11 year:2023 number:8, p 1532 https://doi.org/10.3390/jmse11081532 kostenfrei https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 kostenfrei https://www.mdpi.com/2077-1312/11/8/1532 kostenfrei https://doaj.org/toc/2077-1312 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 8, p 1532
allfieldsGer	10.3390/jmse11081532 doi (DE-627)DOAJ09359657X (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0 DE-627 ger DE-627 rakwb eng VM1-989 GC1-1581 Brendan Chongzhi Corrigan verfasserin aut Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution. underwater litter plastic litter computer vision litter detection instance segmentation YOLACT Naval architecture. Shipbuilding. Marine engineering Oceanography Zhi Yung Tay verfasserin aut Dimitrios Konovessis verfasserin aut In Journal of Marine Science and Engineering MDPI AG, 2014 11(2023), 8, p 1532 (DE-627)771274181 (DE-600)2738390-8 20771312 nnns volume:11 year:2023 number:8, p 1532 https://doi.org/10.3390/jmse11081532 kostenfrei https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 kostenfrei https://www.mdpi.com/2077-1312/11/8/1532 kostenfrei https://doaj.org/toc/2077-1312 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 8, p 1532
allfieldsSound	10.3390/jmse11081532 doi (DE-627)DOAJ09359657X (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0 DE-627 ger DE-627 rakwb eng VM1-989 GC1-1581 Brendan Chongzhi Corrigan verfasserin aut Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution. underwater litter plastic litter computer vision litter detection instance segmentation YOLACT Naval architecture. Shipbuilding. Marine engineering Oceanography Zhi Yung Tay verfasserin aut Dimitrios Konovessis verfasserin aut In Journal of Marine Science and Engineering MDPI AG, 2014 11(2023), 8, p 1532 (DE-627)771274181 (DE-600)2738390-8 20771312 nnns volume:11 year:2023 number:8, p 1532 https://doi.org/10.3390/jmse11081532 kostenfrei https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 kostenfrei https://www.mdpi.com/2077-1312/11/8/1532 kostenfrei https://doaj.org/toc/2077-1312 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 8, p 1532
language	English
source	In Journal of Marine Science and Engineering 11(2023), 8, p 1532 volume:11 year:2023 number:8, p 1532
sourceStr	In Journal of Marine Science and Engineering 11(2023), 8, p 1532 volume:11 year:2023 number:8, p 1532
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	underwater litter plastic litter computer vision litter detection instance segmentation YOLACT Naval architecture. Shipbuilding. Marine engineering Oceanography
isfreeaccess_bool	true
container_title	Journal of Marine Science and Engineering
authorswithroles_txt_mv	Brendan Chongzhi Corrigan @@aut@@ Zhi Yung Tay @@aut@@ Dimitrios Konovessis @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	771274181
id	DOAJ09359657X
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ09359657X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413013513.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240413s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/jmse11081532</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ09359657X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">VM1-989</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">GC1-1581</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Brendan Chongzhi Corrigan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">underwater litter</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">plastic litter</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">computer vision</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">litter detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">instance segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">YOLACT</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Naval architecture. Shipbuilding. Marine engineering</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Oceanography</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhi Yung Tay</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Dimitrios Konovessis</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Journal of Marine Science and Engineering</subfield><subfield code="d">MDPI AG, 2014</subfield><subfield code="g">11(2023), 8, p 1532</subfield><subfield code="w">(DE-627)771274181</subfield><subfield code="w">(DE-600)2738390-8</subfield><subfield code="x">20771312</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:8, p 1532</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/jmse11081532</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2077-1312/11/8/1532</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2077-1312</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2023</subfield><subfield code="e">8, p 1532</subfield></datafield></record></collection>
callnumber-first	V - Naval Science
author	Brendan Chongzhi Corrigan
spellingShingle	Brendan Chongzhi Corrigan misc VM1-989 misc GC1-1581 misc underwater litter misc plastic litter misc computer vision misc litter detection misc instance segmentation misc YOLACT misc Naval architecture. Shipbuilding. Marine engineering misc Oceanography Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source
authorStr	Brendan Chongzhi Corrigan
ppnlink_with_tag_str_mv	@@773@@(DE-627)771274181
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	VM1-989
illustrated	Not Illustrated
issn	20771312
topic_title	VM1-989 GC1-1581 Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source underwater litter plastic litter computer vision litter detection instance segmentation YOLACT
topic	misc VM1-989 misc GC1-1581 misc underwater litter misc plastic litter misc computer vision misc litter detection misc instance segmentation misc YOLACT misc Naval architecture. Shipbuilding. Marine engineering misc Oceanography
topic_unstemmed	misc VM1-989 misc GC1-1581 misc underwater litter misc plastic litter misc computer vision misc litter detection misc instance segmentation misc YOLACT misc Naval architecture. Shipbuilding. Marine engineering misc Oceanography
topic_browse	misc VM1-989 misc GC1-1581 misc underwater litter misc plastic litter misc computer vision misc litter detection misc instance segmentation misc YOLACT misc Naval architecture. Shipbuilding. Marine engineering misc Oceanography
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Journal of Marine Science and Engineering
hierarchy_parent_id	771274181
hierarchy_top_title	Journal of Marine Science and Engineering
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)771274181 (DE-600)2738390-8
title	Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source
ctrlnum	(DE-627)DOAJ09359657X (DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0
title_full	Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source
author_sort	Brendan Chongzhi Corrigan
journal	Journal of Marine Science and Engineering
journalStr	Journal of Marine Science and Engineering
callnumber-first-code	V
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
author_browse	Brendan Chongzhi Corrigan Zhi Yung Tay Dimitrios Konovessis
container_volume	11
class	VM1-989 GC1-1581
format_se	Elektronische Aufsätze
author-letter	Brendan Chongzhi Corrigan
doi_str_mv	10.3390/jmse11081532
author2-role	verfasserin
title_sort	real-time instance segmentation for detection of underwater litter as a plastic source
callnumber	VM1-989
title_auth	Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source
abstract	Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution.
abstractGer	Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution.
abstract_unstemmed	Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	8, p 1532
title_short	Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source
url	https://doi.org/10.3390/jmse11081532 https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0 https://www.mdpi.com/2077-1312/11/8/1532 https://doaj.org/toc/2077-1312
remote_bool	true
author2	Zhi Yung Tay Dimitrios Konovessis
author2Str	Zhi Yung Tay Dimitrios Konovessis
ppnlink	771274181
callnumber-subject	VM - Naval Architecture, Shipbuilding, Marine Engineering
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/jmse11081532
callnumber-a	VM1-989
up_date	2024-07-03T18:16:18.175Z
_version_	1803582783539380224
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ09359657X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413013513.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240413s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/jmse11081532</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ09359657X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ842e1ac77a6144eeaafdad8ce34092e0</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">VM1-989</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">GC1-1581</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Brendan Chongzhi Corrigan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Thousands of tonnes of litter enter the ocean every day, posing a significant threat to marine life and ecosystems. While floating and beach litter are often in the spotlight, about 70% of marine litter eventually sinks to the seafloor, making underwater litter the largest accumulation of marine litter that often goes undetected. Plastic debris makes up the majority of ocean litter and is a known source of microplastics in the ocean. This paper focuses on the detection of ocean plastic using neural network models. Two neural network models will be trained, i.e., YOLACT and the Mask R-CNN, for the instance segmentation of underwater litter in images. The models are trained on the TrashCAN dataset, using pre-trained model weights trained using COCO. The trained neural network could achieve a mean average precision (<inline-formula<<math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"<<semantics<<mrow<<mi<m</mi<<mi<A</mi<<mi<P</mi<</mrow<</semantics<</math<</inline-formula<) of 0.377 and 0.365 for the Mask R-CNN and YOLACT, respectively. The lightweight nature of YOLACT allows it to detect images at up to six times the speed of the Mask R-CNN, while only making a comparatively smaller trade-off in terms of performance. This allows for two separate applications: YOLACT for the collection of litter using autonomous underwater vehicles (AUVs) and the Mask R-CNN for surveying litter distribution.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">underwater litter</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">plastic litter</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">computer vision</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">litter detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">instance segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">YOLACT</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Naval architecture. Shipbuilding. Marine engineering</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Oceanography</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhi Yung Tay</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Dimitrios Konovessis</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Journal of Marine Science and Engineering</subfield><subfield code="d">MDPI AG, 2014</subfield><subfield code="g">11(2023), 8, p 1532</subfield><subfield code="w">(DE-627)771274181</subfield><subfield code="w">(DE-600)2738390-8</subfield><subfield code="x">20771312</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:8, p 1532</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/jmse11081532</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/842e1ac77a6144eeaafdad8ce34092e0</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2077-1312/11/8/1532</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2077-1312</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2023</subfield><subfield code="e">8, p 1532</subfield></datafield></record></collection>
score	7.3991175

Nicht das Richtige dabei?

Schreiben Sie uns!

Real-Time Instance Segmentation for Detection of Underwater Litter as a Plastic Source

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?