TO–YOLOX: a pure CNN tiny object detection model for remote sensing images

Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Zhe Chen [verfasserIn] Yuan Liang [verfasserIn] Zhengbo Yu [verfasserIn] Ke Xu [verfasserIn] Qingyun Ji [verfasserIn] Xueqi Zhang [verfasserIn] Quanping Zhang [verfasserIn] Zijia Cui [verfasserIn] Ziqiong He [verfasserIn] Ruichun Chang [verfasserIn] Zhongchang Sun [verfasserIn] Keyan Xiao [verfasserIn] Huadong Guo [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	tiny object detection to-yolox remote sensing image deep learning attention mechanism

Übergeordnetes Werk:	In: International Journal of Digital Earth - Taylor & Francis Group, 2022, 16(2023), 1, Seite 3882-3904
Übergeordnetes Werk:	volume:16 ; year:2023 ; number:1 ; pages:3882-3904

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

DOI / URN:	10.1080/17538947.2023.2261901

Katalog-ID:	DOAJ098347489

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ098347489
003	DE-627
005	20240413220750.0
007	cr uuu---uuuuu
008	240413s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1080/17538947.2023.2261901 \|2 doi
035			\|a (DE-627)DOAJ098347489
035			\|a (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a GA1-1776
100	0		\|a Zhe Chen \|e verfasserin \|4 aut
245	1	0	\|a TO–YOLOX: a pure CNN tiny object detection model for remote sensing images
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 Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation.
650		4	\|a tiny object detection
650		4	\|a to-yolox
650		4	\|a remote sensing image
650		4	\|a deep learning
650		4	\|a attention mechanism
653		0	\|a Mathematical geography. Cartography
700	0		\|a Yuan Liang \|e verfasserin \|4 aut
700	0		\|a Zhengbo Yu \|e verfasserin \|4 aut
700	0		\|a Ke Xu \|e verfasserin \|4 aut
700	0		\|a Qingyun Ji \|e verfasserin \|4 aut
700	0		\|a Xueqi Zhang \|e verfasserin \|4 aut
700	0		\|a Quanping Zhang \|e verfasserin \|4 aut
700	0		\|a Zijia Cui \|e verfasserin \|4 aut
700	0		\|a Ziqiong He \|e verfasserin \|4 aut
700	0		\|a Ruichun Chang \|e verfasserin \|4 aut
700	0		\|a Zhongchang Sun \|e verfasserin \|4 aut
700	0		\|a Keyan Xiao \|e verfasserin \|4 aut
700	0		\|a Huadong Guo \|e verfasserin \|4 aut
773	0	8	\|i In \|t International Journal of Digital Earth \|d Taylor & Francis Group, 2022 \|g 16(2023), 1, Seite 3882-3904 \|w (DE-627)558695884 \|w (DE-600)2410527-2 \|x 17538955 \|7 nnns
773	1	8	\|g volume:16 \|g year:2023 \|g number:1 \|g pages:3882-3904
856	4	0	\|u https://doi.org/10.1080/17538947.2023.2261901 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c \|z kostenfrei
856	4	0	\|u http://dx.doi.org/10.1080/17538947.2023.2261901 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1753-8947 \|y Journal toc \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/1753-8955 \|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_24
912			\|a GBV_ILN_31
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_206
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_2005
912			\|a GBV_ILN_2009
912			\|a GBV_ILN_2011
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2055
912			\|a GBV_ILN_2111
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 16 \|j 2023 \|e 1 \|h 3882-3904

Indexfelder

author_variant	z c zc y l yl z y zy k x kx q j qj x z xz q z qz z c zc z h zh r c rc z s zs k x kx h g hg
matchkey_str	article:17538955:2023----::oooauentnojcdtcinoefre
hierarchy_sort_str	2023
callnumber-subject-code	GA
publishDate	2023
allfields	10.1080/17538947.2023.2261901 doi (DE-627)DOAJ098347489 (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c DE-627 ger DE-627 rakwb eng GA1-1776 Zhe Chen verfasserin aut TO–YOLOX: a pure CNN tiny object detection model for remote sensing images 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation. tiny object detection to-yolox remote sensing image deep learning attention mechanism Mathematical geography. Cartography Yuan Liang verfasserin aut Zhengbo Yu verfasserin aut Ke Xu verfasserin aut Qingyun Ji verfasserin aut Xueqi Zhang verfasserin aut Quanping Zhang verfasserin aut Zijia Cui verfasserin aut Ziqiong He verfasserin aut Ruichun Chang verfasserin aut Zhongchang Sun verfasserin aut Keyan Xiao verfasserin aut Huadong Guo verfasserin aut In International Journal of Digital Earth Taylor & Francis Group, 2022 16(2023), 1, Seite 3882-3904 (DE-627)558695884 (DE-600)2410527-2 17538955 nnns volume:16 year:2023 number:1 pages:3882-3904 https://doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c kostenfrei http://dx.doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/toc/1753-8947 Journal toc kostenfrei https://doaj.org/toc/1753-8955 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_2111 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 16 2023 1 3882-3904
spelling	10.1080/17538947.2023.2261901 doi (DE-627)DOAJ098347489 (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c DE-627 ger DE-627 rakwb eng GA1-1776 Zhe Chen verfasserin aut TO–YOLOX: a pure CNN tiny object detection model for remote sensing images 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation. tiny object detection to-yolox remote sensing image deep learning attention mechanism Mathematical geography. Cartography Yuan Liang verfasserin aut Zhengbo Yu verfasserin aut Ke Xu verfasserin aut Qingyun Ji verfasserin aut Xueqi Zhang verfasserin aut Quanping Zhang verfasserin aut Zijia Cui verfasserin aut Ziqiong He verfasserin aut Ruichun Chang verfasserin aut Zhongchang Sun verfasserin aut Keyan Xiao verfasserin aut Huadong Guo verfasserin aut In International Journal of Digital Earth Taylor & Francis Group, 2022 16(2023), 1, Seite 3882-3904 (DE-627)558695884 (DE-600)2410527-2 17538955 nnns volume:16 year:2023 number:1 pages:3882-3904 https://doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c kostenfrei http://dx.doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/toc/1753-8947 Journal toc kostenfrei https://doaj.org/toc/1753-8955 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_2111 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 16 2023 1 3882-3904
allfields_unstemmed	10.1080/17538947.2023.2261901 doi (DE-627)DOAJ098347489 (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c DE-627 ger DE-627 rakwb eng GA1-1776 Zhe Chen verfasserin aut TO–YOLOX: a pure CNN tiny object detection model for remote sensing images 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation. tiny object detection to-yolox remote sensing image deep learning attention mechanism Mathematical geography. Cartography Yuan Liang verfasserin aut Zhengbo Yu verfasserin aut Ke Xu verfasserin aut Qingyun Ji verfasserin aut Xueqi Zhang verfasserin aut Quanping Zhang verfasserin aut Zijia Cui verfasserin aut Ziqiong He verfasserin aut Ruichun Chang verfasserin aut Zhongchang Sun verfasserin aut Keyan Xiao verfasserin aut Huadong Guo verfasserin aut In International Journal of Digital Earth Taylor & Francis Group, 2022 16(2023), 1, Seite 3882-3904 (DE-627)558695884 (DE-600)2410527-2 17538955 nnns volume:16 year:2023 number:1 pages:3882-3904 https://doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c kostenfrei http://dx.doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/toc/1753-8947 Journal toc kostenfrei https://doaj.org/toc/1753-8955 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_2111 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 16 2023 1 3882-3904
allfieldsGer	10.1080/17538947.2023.2261901 doi (DE-627)DOAJ098347489 (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c DE-627 ger DE-627 rakwb eng GA1-1776 Zhe Chen verfasserin aut TO–YOLOX: a pure CNN tiny object detection model for remote sensing images 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation. tiny object detection to-yolox remote sensing image deep learning attention mechanism Mathematical geography. Cartography Yuan Liang verfasserin aut Zhengbo Yu verfasserin aut Ke Xu verfasserin aut Qingyun Ji verfasserin aut Xueqi Zhang verfasserin aut Quanping Zhang verfasserin aut Zijia Cui verfasserin aut Ziqiong He verfasserin aut Ruichun Chang verfasserin aut Zhongchang Sun verfasserin aut Keyan Xiao verfasserin aut Huadong Guo verfasserin aut In International Journal of Digital Earth Taylor & Francis Group, 2022 16(2023), 1, Seite 3882-3904 (DE-627)558695884 (DE-600)2410527-2 17538955 nnns volume:16 year:2023 number:1 pages:3882-3904 https://doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c kostenfrei http://dx.doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/toc/1753-8947 Journal toc kostenfrei https://doaj.org/toc/1753-8955 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_2111 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 16 2023 1 3882-3904
allfieldsSound	10.1080/17538947.2023.2261901 doi (DE-627)DOAJ098347489 (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c DE-627 ger DE-627 rakwb eng GA1-1776 Zhe Chen verfasserin aut TO–YOLOX: a pure CNN tiny object detection model for remote sensing images 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation. tiny object detection to-yolox remote sensing image deep learning attention mechanism Mathematical geography. Cartography Yuan Liang verfasserin aut Zhengbo Yu verfasserin aut Ke Xu verfasserin aut Qingyun Ji verfasserin aut Xueqi Zhang verfasserin aut Quanping Zhang verfasserin aut Zijia Cui verfasserin aut Ziqiong He verfasserin aut Ruichun Chang verfasserin aut Zhongchang Sun verfasserin aut Keyan Xiao verfasserin aut Huadong Guo verfasserin aut In International Journal of Digital Earth Taylor & Francis Group, 2022 16(2023), 1, Seite 3882-3904 (DE-627)558695884 (DE-600)2410527-2 17538955 nnns volume:16 year:2023 number:1 pages:3882-3904 https://doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c kostenfrei http://dx.doi.org/10.1080/17538947.2023.2261901 kostenfrei https://doaj.org/toc/1753-8947 Journal toc kostenfrei https://doaj.org/toc/1753-8955 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_2111 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 16 2023 1 3882-3904
language	English
source	In International Journal of Digital Earth 16(2023), 1, Seite 3882-3904 volume:16 year:2023 number:1 pages:3882-3904
sourceStr	In International Journal of Digital Earth 16(2023), 1, Seite 3882-3904 volume:16 year:2023 number:1 pages:3882-3904
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	tiny object detection to-yolox remote sensing image deep learning attention mechanism Mathematical geography. Cartography
isfreeaccess_bool	true
container_title	International Journal of Digital Earth
authorswithroles_txt_mv	Zhe Chen @@aut@@ Yuan Liang @@aut@@ Zhengbo Yu @@aut@@ Ke Xu @@aut@@ Qingyun Ji @@aut@@ Xueqi Zhang @@aut@@ Quanping Zhang @@aut@@ Zijia Cui @@aut@@ Ziqiong He @@aut@@ Ruichun Chang @@aut@@ Zhongchang Sun @@aut@@ Keyan Xiao @@aut@@ Huadong Guo @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	558695884
id	DOAJ098347489
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">DOAJ098347489</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413220750.0</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">10.1080/17538947.2023.2261901</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ098347489</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c</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">GA1-1776</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Zhe Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">TO–YOLOX: a pure CNN tiny object detection model for remote sensing images</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">Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">tiny object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">to-yolox</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">remote sensing image</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">attention mechanism</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Mathematical geography. Cartography</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yuan Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhengbo Yu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ke Xu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Qingyun Ji</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Xueqi Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Quanping Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zijia Cui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ziqiong He</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ruichun Chang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhongchang Sun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Keyan Xiao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Huadong Guo</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">International Journal of Digital Earth</subfield><subfield code="d">Taylor & Francis Group, 2022</subfield><subfield code="g">16(2023), 1, Seite 3882-3904</subfield><subfield code="w">(DE-627)558695884</subfield><subfield code="w">(DE-600)2410527-2</subfield><subfield code="x">17538955</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:16</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:3882-3904</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1080/17538947.2023.2261901</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://dx.doi.org/10.1080/17538947.2023.2261901</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1753-8947</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/1753-8955</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_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</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_206</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_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</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_2055</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_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">16</subfield><subfield code="j">2023</subfield><subfield code="e">1</subfield><subfield code="h">3882-3904</subfield></datafield></record></collection>
callnumber-first	G - Geography, Anthropology, Recreation
author	Zhe Chen
spellingShingle	Zhe Chen misc GA1-1776 misc tiny object detection misc to-yolox misc remote sensing image misc deep learning misc attention mechanism misc Mathematical geography. Cartography TO–YOLOX: a pure CNN tiny object detection model for remote sensing images
authorStr	Zhe Chen
ppnlink_with_tag_str_mv	@@773@@(DE-627)558695884
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut aut aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	GA1-1776
illustrated	Not Illustrated
issn	17538955
topic_title	GA1-1776 TO–YOLOX: a pure CNN tiny object detection model for remote sensing images tiny object detection to-yolox remote sensing image deep learning attention mechanism
topic	misc GA1-1776 misc tiny object detection misc to-yolox misc remote sensing image misc deep learning misc attention mechanism misc Mathematical geography. Cartography
topic_unstemmed	misc GA1-1776 misc tiny object detection misc to-yolox misc remote sensing image misc deep learning misc attention mechanism misc Mathematical geography. Cartography
topic_browse	misc GA1-1776 misc tiny object detection misc to-yolox misc remote sensing image misc deep learning misc attention mechanism misc Mathematical geography. Cartography
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	International Journal of Digital Earth
hierarchy_parent_id	558695884
hierarchy_top_title	International Journal of Digital Earth
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)558695884 (DE-600)2410527-2
title	TO–YOLOX: a pure CNN tiny object detection model for remote sensing images
ctrlnum	(DE-627)DOAJ098347489 (DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c
title_full	TO–YOLOX: a pure CNN tiny object detection model for remote sensing images
author_sort	Zhe Chen
journal	International Journal of Digital Earth
journalStr	International Journal of Digital Earth
callnumber-first-code	G
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
container_start_page	3882
author_browse	Zhe Chen Yuan Liang Zhengbo Yu Ke Xu Qingyun Ji Xueqi Zhang Quanping Zhang Zijia Cui Ziqiong He Ruichun Chang Zhongchang Sun Keyan Xiao Huadong Guo
container_volume	16
class	GA1-1776
format_se	Elektronische Aufsätze
author-letter	Zhe Chen
doi_str_mv	10.1080/17538947.2023.2261901
author2-role	verfasserin
title_sort	to–yolox: a pure cnn tiny object detection model for remote sensing images
callnumber	GA1-1776
title_auth	TO–YOLOX: a pure CNN tiny object detection model for remote sensing images
abstract	Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation.
abstractGer	Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation.
abstract_unstemmed	Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 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_206 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2005 GBV_ILN_2009 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2055 GBV_ILN_2111 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	1
title_short	TO–YOLOX: a pure CNN tiny object detection model for remote sensing images
url	https://doi.org/10.1080/17538947.2023.2261901 https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c http://dx.doi.org/10.1080/17538947.2023.2261901 https://doaj.org/toc/1753-8947 https://doaj.org/toc/1753-8955
remote_bool	true
author2	Yuan Liang Zhengbo Yu Ke Xu Qingyun Ji Xueqi Zhang Quanping Zhang Zijia Cui Ziqiong He Ruichun Chang Zhongchang Sun Keyan Xiao Huadong Guo
author2Str	Yuan Liang Zhengbo Yu Ke Xu Qingyun Ji Xueqi Zhang Quanping Zhang Zijia Cui Ziqiong He Ruichun Chang Zhongchang Sun Keyan Xiao Huadong Guo
ppnlink	558695884
callnumber-subject	GA - Mathematical Geography and Cartography
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.1080/17538947.2023.2261901
callnumber-a	GA1-1776
up_date	2024-07-03T16:46:37.600Z
_version_	1803577141600714752
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">DOAJ098347489</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413220750.0</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">10.1080/17538947.2023.2261901</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ098347489</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ1d36b1364e3c44bfb892403168220d8c</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">GA1-1776</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Zhe Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">TO–YOLOX: a pure CNN tiny object detection model for remote sensing images</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">Remote sensing and deep learning are being widely combined in tasks such as urban planning and disaster prevention. However, due to interference occasioned by density, overlap, and coverage, the tiny object detection in remote sensing images has always been a difficult problem. Therefore, we propose a novel TO–YOLOX(Tiny Object–You Only Look Once) model. TO–YOLOX possesses a MiSo(Multiple-in-Single-out) feature fusion structure, which exhibits a spatial-shift structure, and the model balances positive and negative samples and enhances the information interaction pertaining to the local patch of remote sensing images. TO–YOLOX utilizes an adaptive IOU-T (Intersection Over Uni-Tiny) loss to enhance the localization accuracy of tiny objects, and it applies attention mechanism Group-CBAM (group-convolutional block attention module) to enhance the perception of tiny objects in remote sensing images. To verify the effectiveness and efficiency of TO–YOLOX, we utilized three aerial-photography tiny object detection datasets, namely VisDrone2021, Tiny Person, and DOTA–HBB, and the following mean average precision (mAP) values were recorded, respectively: 45.31% (+10.03%), 28.9% (+9.36%), and 63.02% (+9.62%). With respect to recognizing tiny objects, TO–YOLOX exhibits a stronger ability compared with Faster R-CNN, RetinaNet, YOLOv5, YOLOv6, YOLOv7, and YOLOX, and the proposed model exhibits fast computation.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">tiny object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">to-yolox</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">remote sensing image</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">attention mechanism</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Mathematical geography. Cartography</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Yuan Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhengbo Yu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ke Xu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Qingyun Ji</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Xueqi Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Quanping Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zijia Cui</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ziqiong He</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Ruichun Chang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhongchang Sun</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Keyan Xiao</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Huadong Guo</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">International Journal of Digital Earth</subfield><subfield code="d">Taylor & Francis Group, 2022</subfield><subfield code="g">16(2023), 1, Seite 3882-3904</subfield><subfield code="w">(DE-627)558695884</subfield><subfield code="w">(DE-600)2410527-2</subfield><subfield code="x">17538955</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:16</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:1</subfield><subfield code="g">pages:3882-3904</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1080/17538947.2023.2261901</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/1d36b1364e3c44bfb892403168220d8c</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">http://dx.doi.org/10.1080/17538947.2023.2261901</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/1753-8947</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/1753-8955</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_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</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_206</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_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2009</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</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_2055</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_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">16</subfield><subfield code="j">2023</subfield><subfield code="e">1</subfield><subfield code="h">3882-3904</subfield></datafield></record></collection>
score	7.4005537

Nicht das Richtige dabei?

Schreiben Sie uns!

TO–YOLOX: a pure CNN tiny object detection model for remote sensing images

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?