Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing

In the current work, an approach to implement AI-based techniques in real-time focusing mainly on the detection, tracking, and landing on the target object is presented. For an object detection, CNN algorithm is utilized. For object tracking and stabilizing, a novel algorithm is developed that can e...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohamed Rabah, Eero Immonen
Formato:	article
Lenguaje:	EN
Publicado:	FRUCT 2021
Materias:	quadcopter object detection object tracking safe-landing Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/a8405e325b864be49e00243967fcfdec
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a8405e325b864be49e00243967fcfdec
record_format	dspace
spelling	oai:doaj.org-article:a8405e325b864be49e00243967fcfdec2021-11-20T15:59:33ZDevelopment of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing2305-72542343-073710.5281/zenodo.5639776https://doaj.org/article/a8405e325b864be49e00243967fcfdec2021-10-01T00:00:00Zhttps://www.fruct.org/publications/acm30/files/Rab.pdfhttps://doaj.org/toc/2305-7254https://doaj.org/toc/2343-0737In the current work, an approach to implement AI-based techniques in real-time focusing mainly on the detection, tracking, and landing on the target object is presented. For an object detection, CNN algorithm is utilized. For object tracking and stabilizing, a novel algorithm is developed that can execute along with object detection via sequential stream data. For landing, a vision-based algorithm is used to estimate the distance between the UAV and the detected object. For UAV control, a Fuzzy-PID controller is designed to steer the UAV by a continuously manipulation of the actuators based on the stream data from the tracking unit and dynamics of the UAV. For UAV landing, a new type of fuzzy logic controller is developed to compensate for the nonlinear ground effect that affects the safe landing of the UAV. All the developed algorithms are executed on an NVIDIA Jetson TX2 embedded artificial intelligence device, and an ARM Cortex M4. Experimental results show that the tracking algorithm responds faster than conventionally used approaches, and the safe landing algorithm minimized the landing time of the UAV and provided the safety assurance as compared to conventional controllers. Furthermore, a farming monitoring and automated wireless charging is considered as an application example.Mohamed RabahEero ImmonenFRUCTarticlequadcopterobject detectionobject trackingsafe-landingTelecommunicationTK5101-6720ENProceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 30, Iss 2, Pp 373-377 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	quadcopter object detection object tracking safe-landing Telecommunication TK5101-6720
spellingShingle	quadcopter object detection object tracking safe-landing Telecommunication TK5101-6720 Mohamed Rabah Eero Immonen Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing
description	In the current work, an approach to implement AI-based techniques in real-time focusing mainly on the detection, tracking, and landing on the target object is presented. For an object detection, CNN algorithm is utilized. For object tracking and stabilizing, a novel algorithm is developed that can execute along with object detection via sequential stream data. For landing, a vision-based algorithm is used to estimate the distance between the UAV and the detected object. For UAV control, a Fuzzy-PID controller is designed to steer the UAV by a continuously manipulation of the actuators based on the stream data from the tracking unit and dynamics of the UAV. For UAV landing, a new type of fuzzy logic controller is developed to compensate for the nonlinear ground effect that affects the safe landing of the UAV. All the developed algorithms are executed on an NVIDIA Jetson TX2 embedded artificial intelligence device, and an ARM Cortex M4. Experimental results show that the tracking algorithm responds faster than conventionally used approaches, and the safe landing algorithm minimized the landing time of the UAV and provided the safety assurance as compared to conventional controllers. Furthermore, a farming monitoring and automated wireless charging is considered as an application example.
format	article
author	Mohamed Rabah Eero Immonen
author_facet	Mohamed Rabah Eero Immonen
author_sort	Mohamed Rabah
title	Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing
title_short	Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing
title_full	Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing
title_fullStr	Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing
title_full_unstemmed	Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing
title_sort	development of real-time control system based on deep learning for uavs object detection, tracking and safe-landing
publisher	FRUCT
publishDate	2021
url	https://doaj.org/article/a8405e325b864be49e00243967fcfdec
work_keys_str_mv	AT mohamedrabah developmentofrealtimecontrolsystembasedondeeplearningforuavsobjectdetectiontrackingandsafelanding AT eeroimmonen developmentofrealtimecontrolsystembasedondeeplearningforuavsobjectdetectiontrackingandsafelanding
_version_	1718419442251071488

Development of Real-Time Control System based on Deep Learning for UAVs Object Detection, Tracking and Safe-Landing

Ejemplares similares