Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images

Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Mohamed Barakat A. Gibril [verfasserIn] Helmi Zulhaidi Mohd Shafri [verfasserIn] Abdallah Shanableh [verfasserIn] Rami Al-Ruzouq [verfasserIn] Aimrun Wayayok [verfasserIn] Shaiful Jahari bin Hashim [verfasserIn] Mourtadha Sarhan Sachit [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation

Übergeordnetes Werk:	In: Geocarto International - Taylor & Francis Group, 2023, 37(2022), 27, Seite 18569-18599
Übergeordnetes Werk:	volume:37 ; year:2022 ; number:27 ; pages:18569-18599

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc Journal toc

DOI / URN:	10.1080/10106049.2022.2142966

Katalog-ID:	DOAJ099486849

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ099486849
003	DE-627
005	20240414035017.0
007	cr uuu---uuuuu
008	240414s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1080/10106049.2022.2142966 \|2 doi
035			\|a (DE-627)DOAJ099486849
035			\|a (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a GB3-5030
100	0		\|a Mohamed Barakat A. Gibril \|e verfasserin \|4 aut
245	1	0	\|a Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images
264		1	\|c 2022
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.
650		4	\|a instance segmentation
650		4	\|a mask r-cnn
650		4	\|a swin transformer
650		4	\|a mask scoring r-cnn
650		4	\|a solov2
650		4	\|a yolact
650		4	\|a pointrend
650		4	\|a individual tree crown delineation
653		0	\|a Physical geography
700	0		\|a Helmi Zulhaidi Mohd Shafri \|e verfasserin \|4 aut
700	0		\|a Abdallah Shanableh \|e verfasserin \|4 aut
700	0		\|a Rami Al-Ruzouq \|e verfasserin \|4 aut
700	0		\|a Aimrun Wayayok \|e verfasserin \|4 aut
700	0		\|a Shaiful Jahari bin Hashim \|e verfasserin \|4 aut
700	0		\|a Mourtadha Sarhan Sachit \|e verfasserin \|4 aut
773	0	8	\|i In \|t Geocarto International \|d Taylor & Francis Group, 2023 \|g 37(2022), 27, Seite 18569-18599 \|w (DE-627)364462809 \|w (DE-600)2109550-4 \|x 17520762 \|7 nnns
773	1	8	\|g volume:37 \|g year:2022 \|g number:27 \|g pages:18569-18599
856	4	0	\|u https://doi.org/10.1080/10106049.2022.2142966 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 \|z kostenfrei
856	4	0	\|u http://dx.doi.org/10.1080/10106049.2022.2142966 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1010-6049 \|y Journal toc \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1752-0762 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_63
912			\|a GBV_ILN_70
912			\|a GBV_ILN_100
912			\|a GBV_ILN_224
912			\|a GBV_ILN_285
912			\|a GBV_ILN_370
912			\|a GBV_ILN_702
912			\|a GBV_ILN_2001
912			\|a GBV_ILN_2006
912			\|a GBV_ILN_2007
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2015
912			\|a GBV_ILN_2026
912			\|a GBV_ILN_2034
912			\|a GBV_ILN_2111
912			\|a GBV_ILN_2129
912			\|a GBV_ILN_2507
912			\|a GBV_ILN_4046
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4393
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 37 \|j 2022 \|e 27 \|h 18569-18599

Indexfelder

author_variant	m b a g mbag h z m s hzms a s as r a r rar a w aw s j b h sjbh m s s mss
matchkey_str	article:17520762:2022----::epovltoanuantokadwnrnfrebsdrmwrsoidvdadtpltedtci
hierarchy_sort_str	2022
callnumber-subject-code	GB
publishDate	2022
allfields	10.1080/10106049.2022.2142966 doi (DE-627)DOAJ099486849 (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819 DE-627 ger DE-627 rakwb eng GB3-5030 Mohamed Barakat A. Gibril verfasserin aut Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications. instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation Physical geography Helmi Zulhaidi Mohd Shafri verfasserin aut Abdallah Shanableh verfasserin aut Rami Al-Ruzouq verfasserin aut Aimrun Wayayok verfasserin aut Shaiful Jahari bin Hashim verfasserin aut Mourtadha Sarhan Sachit verfasserin aut In Geocarto International Taylor & Francis Group, 2023 37(2022), 27, Seite 18569-18599 (DE-627)364462809 (DE-600)2109550-4 17520762 nnns volume:37 year:2022 number:27 pages:18569-18599 https://doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 kostenfrei http://dx.doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/toc/1010-6049 Journal toc kostenfrei https://doaj.org/toc/1752-0762 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_63 GBV_ILN_70 GBV_ILN_100 GBV_ILN_224 GBV_ILN_285 GBV_ILN_370 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2026 GBV_ILN_2034 GBV_ILN_2111 GBV_ILN_2129 GBV_ILN_2507 GBV_ILN_4046 GBV_ILN_4313 GBV_ILN_4393 GBV_ILN_4700 AR 37 2022 27 18569-18599
spelling	10.1080/10106049.2022.2142966 doi (DE-627)DOAJ099486849 (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819 DE-627 ger DE-627 rakwb eng GB3-5030 Mohamed Barakat A. Gibril verfasserin aut Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications. instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation Physical geography Helmi Zulhaidi Mohd Shafri verfasserin aut Abdallah Shanableh verfasserin aut Rami Al-Ruzouq verfasserin aut Aimrun Wayayok verfasserin aut Shaiful Jahari bin Hashim verfasserin aut Mourtadha Sarhan Sachit verfasserin aut In Geocarto International Taylor & Francis Group, 2023 37(2022), 27, Seite 18569-18599 (DE-627)364462809 (DE-600)2109550-4 17520762 nnns volume:37 year:2022 number:27 pages:18569-18599 https://doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 kostenfrei http://dx.doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/toc/1010-6049 Journal toc kostenfrei https://doaj.org/toc/1752-0762 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_63 GBV_ILN_70 GBV_ILN_100 GBV_ILN_224 GBV_ILN_285 GBV_ILN_370 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2026 GBV_ILN_2034 GBV_ILN_2111 GBV_ILN_2129 GBV_ILN_2507 GBV_ILN_4046 GBV_ILN_4313 GBV_ILN_4393 GBV_ILN_4700 AR 37 2022 27 18569-18599
allfields_unstemmed	10.1080/10106049.2022.2142966 doi (DE-627)DOAJ099486849 (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819 DE-627 ger DE-627 rakwb eng GB3-5030 Mohamed Barakat A. Gibril verfasserin aut Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications. instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation Physical geography Helmi Zulhaidi Mohd Shafri verfasserin aut Abdallah Shanableh verfasserin aut Rami Al-Ruzouq verfasserin aut Aimrun Wayayok verfasserin aut Shaiful Jahari bin Hashim verfasserin aut Mourtadha Sarhan Sachit verfasserin aut In Geocarto International Taylor & Francis Group, 2023 37(2022), 27, Seite 18569-18599 (DE-627)364462809 (DE-600)2109550-4 17520762 nnns volume:37 year:2022 number:27 pages:18569-18599 https://doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 kostenfrei http://dx.doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/toc/1010-6049 Journal toc kostenfrei https://doaj.org/toc/1752-0762 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_63 GBV_ILN_70 GBV_ILN_100 GBV_ILN_224 GBV_ILN_285 GBV_ILN_370 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2026 GBV_ILN_2034 GBV_ILN_2111 GBV_ILN_2129 GBV_ILN_2507 GBV_ILN_4046 GBV_ILN_4313 GBV_ILN_4393 GBV_ILN_4700 AR 37 2022 27 18569-18599
allfieldsGer	10.1080/10106049.2022.2142966 doi (DE-627)DOAJ099486849 (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819 DE-627 ger DE-627 rakwb eng GB3-5030 Mohamed Barakat A. Gibril verfasserin aut Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications. instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation Physical geography Helmi Zulhaidi Mohd Shafri verfasserin aut Abdallah Shanableh verfasserin aut Rami Al-Ruzouq verfasserin aut Aimrun Wayayok verfasserin aut Shaiful Jahari bin Hashim verfasserin aut Mourtadha Sarhan Sachit verfasserin aut In Geocarto International Taylor & Francis Group, 2023 37(2022), 27, Seite 18569-18599 (DE-627)364462809 (DE-600)2109550-4 17520762 nnns volume:37 year:2022 number:27 pages:18569-18599 https://doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 kostenfrei http://dx.doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/toc/1010-6049 Journal toc kostenfrei https://doaj.org/toc/1752-0762 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_63 GBV_ILN_70 GBV_ILN_100 GBV_ILN_224 GBV_ILN_285 GBV_ILN_370 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2026 GBV_ILN_2034 GBV_ILN_2111 GBV_ILN_2129 GBV_ILN_2507 GBV_ILN_4046 GBV_ILN_4313 GBV_ILN_4393 GBV_ILN_4700 AR 37 2022 27 18569-18599
allfieldsSound	10.1080/10106049.2022.2142966 doi (DE-627)DOAJ099486849 (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819 DE-627 ger DE-627 rakwb eng GB3-5030 Mohamed Barakat A. Gibril verfasserin aut Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications. instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation Physical geography Helmi Zulhaidi Mohd Shafri verfasserin aut Abdallah Shanableh verfasserin aut Rami Al-Ruzouq verfasserin aut Aimrun Wayayok verfasserin aut Shaiful Jahari bin Hashim verfasserin aut Mourtadha Sarhan Sachit verfasserin aut In Geocarto International Taylor & Francis Group, 2023 37(2022), 27, Seite 18569-18599 (DE-627)364462809 (DE-600)2109550-4 17520762 nnns volume:37 year:2022 number:27 pages:18569-18599 https://doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 kostenfrei http://dx.doi.org/10.1080/10106049.2022.2142966 kostenfrei https://doaj.org/toc/1010-6049 Journal toc kostenfrei https://doaj.org/toc/1752-0762 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_63 GBV_ILN_70 GBV_ILN_100 GBV_ILN_224 GBV_ILN_285 GBV_ILN_370 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2026 GBV_ILN_2034 GBV_ILN_2111 GBV_ILN_2129 GBV_ILN_2507 GBV_ILN_4046 GBV_ILN_4313 GBV_ILN_4393 GBV_ILN_4700 AR 37 2022 27 18569-18599
language	English
source	In Geocarto International 37(2022), 27, Seite 18569-18599 volume:37 year:2022 number:27 pages:18569-18599
sourceStr	In Geocarto International 37(2022), 27, Seite 18569-18599 volume:37 year:2022 number:27 pages:18569-18599
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation Physical geography
isfreeaccess_bool	true
container_title	Geocarto International
authorswithroles_txt_mv	Mohamed Barakat A. Gibril @@aut@@ Helmi Zulhaidi Mohd Shafri @@aut@@ Abdallah Shanableh @@aut@@ Rami Al-Ruzouq @@aut@@ Aimrun Wayayok @@aut@@ Shaiful Jahari bin Hashim @@aut@@ Mourtadha Sarhan Sachit @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	364462809
id	DOAJ099486849
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">DOAJ099486849</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240414035017.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240414s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1080/10106049.2022.2142966</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ099486849</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ878dcc3a346843478247a7c8a3dae819</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">GB3-5030</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Mohamed Barakat A. Gibril</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">instance segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">mask r-cnn</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">swin transformer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">mask scoring r-cnn</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">solov2</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">yolact</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pointrend</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">individual tree crown delineation</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Physical geography</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Helmi Zulhaidi Mohd Shafri</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Abdallah Shanableh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Rami Al-Ruzouq</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Aimrun Wayayok</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Shaiful Jahari bin Hashim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mourtadha Sarhan Sachit</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">Geocarto International</subfield><subfield code="d">Taylor & Francis Group, 2023</subfield><subfield code="g">37(2022), 27, Seite 18569-18599</subfield><subfield code="w">(DE-627)364462809</subfield><subfield code="w">(DE-600)2109550-4</subfield><subfield code="x">17520762</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:37</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:27</subfield><subfield code="g">pages:18569-18599</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1080/10106049.2022.2142966</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/878dcc3a346843478247a7c8a3dae819</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://dx.doi.org/10.1080/10106049.2022.2142966</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1010-6049</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1752-0762</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_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_63</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_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</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_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2006</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</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_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</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_4393</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">37</subfield><subfield code="j">2022</subfield><subfield code="e">27</subfield><subfield code="h">18569-18599</subfield></datafield></record></collection>
callnumber-first	G - Geography, Anthropology, Recreation
author	Mohamed Barakat A. Gibril
spellingShingle	Mohamed Barakat A. Gibril misc GB3-5030 misc instance segmentation misc mask r-cnn misc swin transformer misc mask scoring r-cnn misc solov2 misc yolact misc pointrend misc individual tree crown delineation misc Physical geography Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images
authorStr	Mohamed Barakat A. Gibril
ppnlink_with_tag_str_mv	@@773@@(DE-627)364462809
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	GB3-5030
illustrated	Not Illustrated
issn	17520762
topic_title	GB3-5030 Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images instance segmentation mask r-cnn swin transformer mask scoring r-cnn solov2 yolact pointrend individual tree crown delineation
topic	misc GB3-5030 misc instance segmentation misc mask r-cnn misc swin transformer misc mask scoring r-cnn misc solov2 misc yolact misc pointrend misc individual tree crown delineation misc Physical geography
topic_unstemmed	misc GB3-5030 misc instance segmentation misc mask r-cnn misc swin transformer misc mask scoring r-cnn misc solov2 misc yolact misc pointrend misc individual tree crown delineation misc Physical geography
topic_browse	misc GB3-5030 misc instance segmentation misc mask r-cnn misc swin transformer misc mask scoring r-cnn misc solov2 misc yolact misc pointrend misc individual tree crown delineation misc Physical geography
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Geocarto International
hierarchy_parent_id	364462809
hierarchy_top_title	Geocarto International
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)364462809 (DE-600)2109550-4
title	Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images
ctrlnum	(DE-627)DOAJ099486849 (DE-599)DOAJ878dcc3a346843478247a7c8a3dae819
title_full	Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images
author_sort	Mohamed Barakat A. Gibril
journal	Geocarto International
journalStr	Geocarto International
callnumber-first-code	G
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2022
contenttype_str_mv	txt
container_start_page	18569
author_browse	Mohamed Barakat A. Gibril Helmi Zulhaidi Mohd Shafri Abdallah Shanableh Rami Al-Ruzouq Aimrun Wayayok Shaiful Jahari bin Hashim Mourtadha Sarhan Sachit
container_volume	37
class	GB3-5030
format_se	Elektronische Aufsätze
author-letter	Mohamed Barakat A. Gibril
doi_str_mv	10.1080/10106049.2022.2142966
author2-role	verfasserin
title_sort	deep convolutional neural networks and swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale uav images
callnumber	GB3-5030
title_auth	Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images
abstract	Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.
abstractGer	Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.
abstract_unstemmed	Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_63 GBV_ILN_70 GBV_ILN_100 GBV_ILN_224 GBV_ILN_285 GBV_ILN_370 GBV_ILN_702 GBV_ILN_2001 GBV_ILN_2006 GBV_ILN_2007 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2026 GBV_ILN_2034 GBV_ILN_2111 GBV_ILN_2129 GBV_ILN_2507 GBV_ILN_4046 GBV_ILN_4313 GBV_ILN_4393 GBV_ILN_4700
container_issue	27
title_short	Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images
url	https://doi.org/10.1080/10106049.2022.2142966 https://doaj.org/article/878dcc3a346843478247a7c8a3dae819 http://dx.doi.org/10.1080/10106049.2022.2142966 https://doaj.org/toc/1010-6049 https://doaj.org/toc/1752-0762
remote_bool	true
author2	Helmi Zulhaidi Mohd Shafri Abdallah Shanableh Rami Al-Ruzouq Aimrun Wayayok Shaiful Jahari bin Hashim Mourtadha Sarhan Sachit
author2Str	Helmi Zulhaidi Mohd Shafri Abdallah Shanableh Rami Al-Ruzouq Aimrun Wayayok Shaiful Jahari bin Hashim Mourtadha Sarhan Sachit
ppnlink	364462809
callnumber-subject	GB - Physical Geography
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.1080/10106049.2022.2142966
callnumber-a	GB3-5030
up_date	2024-07-03T23:01:28.691Z
_version_	1803600725226291200
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">DOAJ099486849</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240414035017.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240414s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1080/10106049.2022.2142966</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ099486849</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ878dcc3a346843478247a7c8a3dae819</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">GB3-5030</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Mohamed Barakat A. Gibril</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">Timely and reliable mapping of individual date palm trees is essential for their monitoring, health and risk assessment, pest control, and sustainable management of the date palm industry. This study presents an instance segmentation framework for large-scale detection and mapping of date palm trees using unmanned aerial vehicle (UAV)-based images. First, a data conversion framework is created to convert UAV image tiles and ground-truth vector data into annotation format of Common Objects in Context. Second, this study examines the efficacy of various instance segmentation models, namely, mask region convolutional neural network (Mask R-CNN), Mask Scoring R-CNN, You Only Look At CoefficientTs, Point-based Rendering, Segmenting Objects by Locations (SOLO), and SOLOv2) with varying residual learning networks (ResNets) in detecting and delineating individual date palm trees. Furthermore, the performance of two variants of Swin Transformer networks with a feature pyramid network (FPN) (Swin-small-FPN and Swin-tiny-FPN) as Mask R-CNN network backbones was also evaluated. Third, we assess the generalizability of the evaluated instance segmentation models and backbones on different testing datasets with varying spatial resolutions. Results show that Mask R-CNN models based on Swin Transformers backbones outperform those with ResNets in the detection and segmentation of date palm trees with mAP50 of 92% and 91% and F-measures of 94% and 93%. Moreover, the Mask scoring R-CNN-based ResNet-50 and Mask R-CNN with a Swin-small-FPN backbone outperform the evaluated models and demonstrate great generalizability in different datasets with diverse spatial resolutions. The proposed instance segmentation framework provides an efficient tool for date palm tree mapping from multi-scale UAV-based images and is valuable and suitable for individual tree crown delineations and other earth-related applications.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">instance segmentation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">mask r-cnn</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">swin transformer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">mask scoring r-cnn</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">solov2</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">yolact</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pointrend</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">individual tree crown delineation</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Physical geography</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Helmi Zulhaidi Mohd Shafri</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Abdallah Shanableh</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Rami Al-Ruzouq</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Aimrun Wayayok</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Shaiful Jahari bin Hashim</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Mourtadha Sarhan Sachit</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">Geocarto International</subfield><subfield code="d">Taylor & Francis Group, 2023</subfield><subfield code="g">37(2022), 27, Seite 18569-18599</subfield><subfield code="w">(DE-627)364462809</subfield><subfield code="w">(DE-600)2109550-4</subfield><subfield code="x">17520762</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:37</subfield><subfield code="g">year:2022</subfield><subfield code="g">number:27</subfield><subfield code="g">pages:18569-18599</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1080/10106049.2022.2142966</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/878dcc3a346843478247a7c8a3dae819</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://dx.doi.org/10.1080/10106049.2022.2142966</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1010-6049</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1752-0762</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_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_63</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_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</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_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2001</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2006</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2007</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_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2026</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4046</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_4393</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">37</subfield><subfield code="j">2022</subfield><subfield code="e">27</subfield><subfield code="h">18569-18599</subfield></datafield></record></collection>
score	7.398777

Nicht das Richtige dabei?

Schreiben Sie uns!

Deep convolutional neural networks and Swin transformer-based frameworks for individual date palm tree detection and mapping from large-scale UAV images

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?