Animal Detection and Counting from UAV Images Using Convolutional Neural Networks

In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Kristina Rančić [verfasserIn] Boško Blagojević [verfasserIn] Atila Bezdan [verfasserIn] Bojana Ivošević [verfasserIn] Bojan Tubić [verfasserIn] Milica Vranešević [verfasserIn] Branislav Pejak [verfasserIn] Vladimir Crnojević [verfasserIn] Oskar Marko [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2023

Schlagwörter:	convolutional neural networks deer animal counting deep learning YOLO SSD

Übergeordnetes Werk:	In: Drones - MDPI AG, 2018, 7(2023), 3, p 179
Übergeordnetes Werk:	volume:7 ; year:2023 ; number:3, p 179

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3390/drones7030179

Katalog-ID:	DOAJ087388995

Internformat


LEADER	01000caa a22002652 4500
001	DOAJ087388995
003	DE-627
005	20240413052020.0
007	cr uuu---uuuuu
008	230331s2023 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3390/drones7030179 \|2 doi
035			\|a (DE-627)DOAJ087388995
035			\|a (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a TL1-4050
100	0		\|a Kristina Rančić \|e verfasserin \|4 aut
245	1	0	\|a Animal Detection and Counting from UAV Images Using Convolutional Neural Networks
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 In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%.
650		4	\|a convolutional neural networks
650		4	\|a deer
650		4	\|a animal counting
650		4	\|a deep learning
650		4	\|a YOLO
650		4	\|a SSD
653		0	\|a Motor vehicles. Aeronautics. Astronautics
700	0		\|a Boško Blagojević \|e verfasserin \|4 aut
700	0		\|a Atila Bezdan \|e verfasserin \|4 aut
700	0		\|a Bojana Ivošević \|e verfasserin \|4 aut
700	0		\|a Bojan Tubić \|e verfasserin \|4 aut
700	0		\|a Milica Vranešević \|e verfasserin \|4 aut
700	0		\|a Branislav Pejak \|e verfasserin \|4 aut
700	0		\|a Vladimir Crnojević \|e verfasserin \|4 aut
700	0		\|a Oskar Marko \|e verfasserin \|4 aut
773	0	8	\|i In \|t Drones \|d MDPI AG, 2018 \|g 7(2023), 3, p 179 \|w (DE-627)1025498356 \|x 2504446X \|7 nnns
773	1	8	\|g volume:7 \|g year:2023 \|g number:3, p 179
856	4	0	\|u https://doi.org/10.3390/drones7030179 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 \|z kostenfrei
856	4	0	\|u https://www.mdpi.com/2504-446X/7/3/179 \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2504-446X \|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_170
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 7 \|j 2023 \|e 3, p 179

Indexfelder

author_variant	k r kr b b bb a b ab b i bi b t bt m v mv b p bp v c vc o m om
matchkey_str	article:2504446X:2023----::nmleetoadonigrmaiaeuigovl
hierarchy_sort_str	2023
callnumber-subject-code	TL
publishDate	2023
allfields	10.3390/drones7030179 doi (DE-627)DOAJ087388995 (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4 DE-627 ger DE-627 rakwb eng TL1-4050 Kristina Rančić verfasserin aut Animal Detection and Counting from UAV Images Using Convolutional Neural Networks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%. convolutional neural networks deer animal counting deep learning YOLO SSD Motor vehicles. Aeronautics. Astronautics Boško Blagojević verfasserin aut Atila Bezdan verfasserin aut Bojana Ivošević verfasserin aut Bojan Tubić verfasserin aut Milica Vranešević verfasserin aut Branislav Pejak verfasserin aut Vladimir Crnojević verfasserin aut Oskar Marko verfasserin aut In Drones MDPI AG, 2018 7(2023), 3, p 179 (DE-627)1025498356 2504446X nnns volume:7 year:2023 number:3, p 179 https://doi.org/10.3390/drones7030179 kostenfrei https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 kostenfrei https://www.mdpi.com/2504-446X/7/3/179 kostenfrei https://doaj.org/toc/2504-446X 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_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 7 2023 3, p 179
spelling	10.3390/drones7030179 doi (DE-627)DOAJ087388995 (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4 DE-627 ger DE-627 rakwb eng TL1-4050 Kristina Rančić verfasserin aut Animal Detection and Counting from UAV Images Using Convolutional Neural Networks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%. convolutional neural networks deer animal counting deep learning YOLO SSD Motor vehicles. Aeronautics. Astronautics Boško Blagojević verfasserin aut Atila Bezdan verfasserin aut Bojana Ivošević verfasserin aut Bojan Tubić verfasserin aut Milica Vranešević verfasserin aut Branislav Pejak verfasserin aut Vladimir Crnojević verfasserin aut Oskar Marko verfasserin aut In Drones MDPI AG, 2018 7(2023), 3, p 179 (DE-627)1025498356 2504446X nnns volume:7 year:2023 number:3, p 179 https://doi.org/10.3390/drones7030179 kostenfrei https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 kostenfrei https://www.mdpi.com/2504-446X/7/3/179 kostenfrei https://doaj.org/toc/2504-446X 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_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 7 2023 3, p 179
allfields_unstemmed	10.3390/drones7030179 doi (DE-627)DOAJ087388995 (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4 DE-627 ger DE-627 rakwb eng TL1-4050 Kristina Rančić verfasserin aut Animal Detection and Counting from UAV Images Using Convolutional Neural Networks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%. convolutional neural networks deer animal counting deep learning YOLO SSD Motor vehicles. Aeronautics. Astronautics Boško Blagojević verfasserin aut Atila Bezdan verfasserin aut Bojana Ivošević verfasserin aut Bojan Tubić verfasserin aut Milica Vranešević verfasserin aut Branislav Pejak verfasserin aut Vladimir Crnojević verfasserin aut Oskar Marko verfasserin aut In Drones MDPI AG, 2018 7(2023), 3, p 179 (DE-627)1025498356 2504446X nnns volume:7 year:2023 number:3, p 179 https://doi.org/10.3390/drones7030179 kostenfrei https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 kostenfrei https://www.mdpi.com/2504-446X/7/3/179 kostenfrei https://doaj.org/toc/2504-446X 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_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 7 2023 3, p 179
allfieldsGer	10.3390/drones7030179 doi (DE-627)DOAJ087388995 (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4 DE-627 ger DE-627 rakwb eng TL1-4050 Kristina Rančić verfasserin aut Animal Detection and Counting from UAV Images Using Convolutional Neural Networks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%. convolutional neural networks deer animal counting deep learning YOLO SSD Motor vehicles. Aeronautics. Astronautics Boško Blagojević verfasserin aut Atila Bezdan verfasserin aut Bojana Ivošević verfasserin aut Bojan Tubić verfasserin aut Milica Vranešević verfasserin aut Branislav Pejak verfasserin aut Vladimir Crnojević verfasserin aut Oskar Marko verfasserin aut In Drones MDPI AG, 2018 7(2023), 3, p 179 (DE-627)1025498356 2504446X nnns volume:7 year:2023 number:3, p 179 https://doi.org/10.3390/drones7030179 kostenfrei https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 kostenfrei https://www.mdpi.com/2504-446X/7/3/179 kostenfrei https://doaj.org/toc/2504-446X 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_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 7 2023 3, p 179
allfieldsSound	10.3390/drones7030179 doi (DE-627)DOAJ087388995 (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4 DE-627 ger DE-627 rakwb eng TL1-4050 Kristina Rančić verfasserin aut Animal Detection and Counting from UAV Images Using Convolutional Neural Networks 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%. convolutional neural networks deer animal counting deep learning YOLO SSD Motor vehicles. Aeronautics. Astronautics Boško Blagojević verfasserin aut Atila Bezdan verfasserin aut Bojana Ivošević verfasserin aut Bojan Tubić verfasserin aut Milica Vranešević verfasserin aut Branislav Pejak verfasserin aut Vladimir Crnojević verfasserin aut Oskar Marko verfasserin aut In Drones MDPI AG, 2018 7(2023), 3, p 179 (DE-627)1025498356 2504446X nnns volume:7 year:2023 number:3, p 179 https://doi.org/10.3390/drones7030179 kostenfrei https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 kostenfrei https://www.mdpi.com/2504-446X/7/3/179 kostenfrei https://doaj.org/toc/2504-446X 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_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 7 2023 3, p 179
language	English
source	In Drones 7(2023), 3, p 179 volume:7 year:2023 number:3, p 179
sourceStr	In Drones 7(2023), 3, p 179 volume:7 year:2023 number:3, p 179
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	convolutional neural networks deer animal counting deep learning YOLO SSD Motor vehicles. Aeronautics. Astronautics
isfreeaccess_bool	true
container_title	Drones
authorswithroles_txt_mv	Kristina Rančić @@aut@@ Boško Blagojević @@aut@@ Atila Bezdan @@aut@@ Bojana Ivošević @@aut@@ Bojan Tubić @@aut@@ Milica Vranešević @@aut@@ Branislav Pejak @@aut@@ Vladimir Crnojević @@aut@@ Oskar Marko @@aut@@
publishDateDaySort_date	2023-01-01T00:00:00Z
hierarchy_top_id	1025498356
id	DOAJ087388995
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ087388995</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413052020.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230331s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/drones7030179</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ087388995</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4</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">TL1-4050</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Kristina Rančić</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Animal Detection and Counting from UAV Images Using Convolutional Neural Networks</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">In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">animal counting</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">YOLO</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">SSD</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Motor vehicles. Aeronautics. Astronautics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Boško Blagojević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Atila Bezdan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Bojana Ivošević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Bojan Tubić</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Milica Vranešević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Branislav Pejak</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Vladimir Crnojević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Oskar Marko</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">Drones</subfield><subfield code="d">MDPI AG, 2018</subfield><subfield code="g">7(2023), 3, p 179</subfield><subfield code="w">(DE-627)1025498356</subfield><subfield code="x">2504446X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:7</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:3, p 179</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/drones7030179</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2504-446X/7/3/179</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2504-446X</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_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">7</subfield><subfield code="j">2023</subfield><subfield code="e">3, p 179</subfield></datafield></record></collection>
callnumber-first	T - Technology
author	Kristina Rančić
spellingShingle	Kristina Rančić misc TL1-4050 misc convolutional neural networks misc deer misc animal counting misc deep learning misc YOLO misc SSD misc Motor vehicles. Aeronautics. Astronautics Animal Detection and Counting from UAV Images Using Convolutional Neural Networks
authorStr	Kristina Rančić
ppnlink_with_tag_str_mv	@@773@@(DE-627)1025498356
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	TL1-4050
illustrated	Not Illustrated
issn	2504446X
topic_title	TL1-4050 Animal Detection and Counting from UAV Images Using Convolutional Neural Networks convolutional neural networks deer animal counting deep learning YOLO SSD
topic	misc TL1-4050 misc convolutional neural networks misc deer misc animal counting misc deep learning misc YOLO misc SSD misc Motor vehicles. Aeronautics. Astronautics
topic_unstemmed	misc TL1-4050 misc convolutional neural networks misc deer misc animal counting misc deep learning misc YOLO misc SSD misc Motor vehicles. Aeronautics. Astronautics
topic_browse	misc TL1-4050 misc convolutional neural networks misc deer misc animal counting misc deep learning misc YOLO misc SSD misc Motor vehicles. Aeronautics. Astronautics
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Drones
hierarchy_parent_id	1025498356
hierarchy_top_title	Drones
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)1025498356
title	Animal Detection and Counting from UAV Images Using Convolutional Neural Networks
ctrlnum	(DE-627)DOAJ087388995 (DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4
title_full	Animal Detection and Counting from UAV Images Using Convolutional Neural Networks
author_sort	Kristina Rančić
journal	Drones
journalStr	Drones
callnumber-first-code	T
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2023
contenttype_str_mv	txt
author_browse	Kristina Rančić Boško Blagojević Atila Bezdan Bojana Ivošević Bojan Tubić Milica Vranešević Branislav Pejak Vladimir Crnojević Oskar Marko
container_volume	7
class	TL1-4050
format_se	Elektronische Aufsätze
author-letter	Kristina Rančić
doi_str_mv	10.3390/drones7030179
author2-role	verfasserin
title_sort	animal detection and counting from uav images using convolutional neural networks
callnumber	TL1-4050
title_auth	Animal Detection and Counting from UAV Images Using Convolutional Neural Networks
abstract	In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%.
abstractGer	In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%.
abstract_unstemmed	In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%.
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_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
container_issue	3, p 179
title_short	Animal Detection and Counting from UAV Images Using Convolutional Neural Networks
url	https://doi.org/10.3390/drones7030179 https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4 https://www.mdpi.com/2504-446X/7/3/179 https://doaj.org/toc/2504-446X
remote_bool	true
author2	Boško Blagojević Atila Bezdan Bojana Ivošević Bojan Tubić Milica Vranešević Branislav Pejak Vladimir Crnojević Oskar Marko
author2Str	Boško Blagojević Atila Bezdan Bojana Ivošević Bojan Tubić Milica Vranešević Branislav Pejak Vladimir Crnojević Oskar Marko
ppnlink	1025498356
callnumber-subject	TL - Motor Vehicles and Aeronautics
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3390/drones7030179
callnumber-a	TL1-4050
up_date	2024-07-04T01:28:44.950Z
_version_	1803609990713311232
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">DOAJ087388995</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240413052020.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230331s2023 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3390/drones7030179</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ087388995</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ9021cf399fc9421db5f7cc9ae50808d4</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">TL1-4050</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Kristina Rančić</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Animal Detection and Counting from UAV Images Using Convolutional Neural Networks</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">In the last decade, small unmanned aerial vehicles (UAVs/drones) have become increasingly popular in the airborne observation of large areas for many purposes, such as the monitoring of agricultural areas, the tracking of wild animals in their natural habitats, and the counting of livestock. Coupled with deep learning, they allow for automatic image processing and recognition. The aim of this work was to detect and count the deer population in northwestern Serbia from such images using deep neural networks, a tedious process that otherwise requires a lot of time and effort. In this paper, we present and compare the performance of several state-of-the-art network architectures, trained on a manually annotated set of images, and use it to predict the presence of objects in the rest of the dataset. We implemented three versions of the You Only Look Once (YOLO) architecture and a Single Shot Multibox Detector (SSD) to detect deer in a dense forest environment and measured their performance based on mean average precision (mAP), precision, recall, and F1 score. Moreover, we also evaluated the models based on their real-time performance. The results showed that the selected models were able to detect deer with a mean average precision of up to 70.45% and a confidence score of up to a 99%. The highest precision was achieved by the fourth version of YOLO with 86%, as well as the highest recall value of 75%. Its compressed version achieved slightly lower results, with 83% mAP in its best case, but it demonstrated four times better real-time performance. The counting function was applied on the best-performing models, providing us with the exact distribution of deer over all images. Yolov4 obtained an error of 8.3% in counting, while Yolov4-tiny mistook 12 deer, which accounted for an error of 7.1%.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">convolutional neural networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deer</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">animal counting</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">YOLO</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">SSD</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Motor vehicles. Aeronautics. Astronautics</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Boško Blagojević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Atila Bezdan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Bojana Ivošević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Bojan Tubić</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Milica Vranešević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Branislav Pejak</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Vladimir Crnojević</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Oskar Marko</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">Drones</subfield><subfield code="d">MDPI AG, 2018</subfield><subfield code="g">7(2023), 3, p 179</subfield><subfield code="w">(DE-627)1025498356</subfield><subfield code="x">2504446X</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:7</subfield><subfield code="g">year:2023</subfield><subfield code="g">number:3, p 179</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3390/drones7030179</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/9021cf399fc9421db5f7cc9ae50808d4</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.mdpi.com/2504-446X/7/3/179</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2504-446X</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_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">7</subfield><subfield code="j">2023</subfield><subfield code="e">3, p 179</subfield></datafield></record></collection>
score	7.400923

Nicht das Richtige dabei?

Schreiben Sie uns!

Animal Detection and Counting from UAV Images Using Convolutional Neural Networks

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?