Configurable Hardware Core for IoT Object Detection

Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pedro R. Miranda, Daniel Pestana, João D. Lopes, Rui Policarpo Duarte, Mário P. Véstias, Horácio C. Neto, José T. de Sousa
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	Internet of Things object detection YOLO FPGA Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/bd055852bd1d4233ad824b714ad595ad
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bd055852bd1d4233ad824b714ad595ad
record_format	dspace
spelling	oai:doaj.org-article:bd055852bd1d4233ad824b714ad595ad2021-11-25T17:39:46ZConfigurable Hardware Core for IoT Object Detection10.3390/fi131102801999-5903https://doaj.org/article/bd055852bd1d4233ad824b714ad595ad2021-10-01T00:00:00Zhttps://www.mdpi.com/1999-5903/13/11/280https://doaj.org/toc/1999-5903Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes a configurable hardware core on a field-programmable gate array (FPGA) for object detection. The configurability of the core allows its deployment on target devices with diverse hardware resources. The object detection accelerator is based on YOLO, for its good accuracy at moderate computational complexity. The solution was applied to the design of a core to accelerate the Tiny-YOLOv3, based on a CNN developed for constrained environments. However, it can be applied to other YOLO versions. The core was integrated into a full system-on-chip solution and tested with the COCO dataset. It achieved a performance from 7 to 14 FPS in a low-cost ZYNQ7020 FPGA, depending on the quantization, with an accuracy reduction from 2.1 to 1.4 points of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">A</mi><msub><mi mathvariant="normal">P</mi><mn>50</mn></msub></mrow></semantics></math></inline-formula>.Pedro R. MirandaDaniel PestanaJoão D. LopesRui Policarpo DuarteMário P. VéstiasHorácio C. NetoJosé T. de SousaMDPI AGarticleInternet of Thingsobject detectionYOLOFPGAInformation technologyT58.5-58.64ENFuture Internet, Vol 13, Iss 280, p 280 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Internet of Things object detection YOLO FPGA Information technology T58.5-58.64
spellingShingle	Internet of Things object detection YOLO FPGA Information technology T58.5-58.64 Pedro R. Miranda Daniel Pestana João D. Lopes Rui Policarpo Duarte Mário P. Véstias Horácio C. Neto José T. de Sousa Configurable Hardware Core for IoT Object Detection
description	Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes a configurable hardware core on a field-programmable gate array (FPGA) for object detection. The configurability of the core allows its deployment on target devices with diverse hardware resources. The object detection accelerator is based on YOLO, for its good accuracy at moderate computational complexity. The solution was applied to the design of a core to accelerate the Tiny-YOLOv3, based on a CNN developed for constrained environments. However, it can be applied to other YOLO versions. The core was integrated into a full system-on-chip solution and tested with the COCO dataset. It achieved a performance from 7 to 14 FPS in a low-cost ZYNQ7020 FPGA, depending on the quantization, with an accuracy reduction from 2.1 to 1.4 points of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">A</mi><msub><mi mathvariant="normal">P</mi><mn>50</mn></msub></mrow></semantics></math></inline-formula>.
format	article
author	Pedro R. Miranda Daniel Pestana João D. Lopes Rui Policarpo Duarte Mário P. Véstias Horácio C. Neto José T. de Sousa
author_facet	Pedro R. Miranda Daniel Pestana João D. Lopes Rui Policarpo Duarte Mário P. Véstias Horácio C. Neto José T. de Sousa
author_sort	Pedro R. Miranda
title	Configurable Hardware Core for IoT Object Detection
title_short	Configurable Hardware Core for IoT Object Detection
title_full	Configurable Hardware Core for IoT Object Detection
title_fullStr	Configurable Hardware Core for IoT Object Detection
title_full_unstemmed	Configurable Hardware Core for IoT Object Detection
title_sort	configurable hardware core for iot object detection
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/bd055852bd1d4233ad824b714ad595ad
work_keys_str_mv	AT pedrormiranda configurablehardwarecoreforiotobjectdetection AT danielpestana configurablehardwarecoreforiotobjectdetection AT joaodlopes configurablehardwarecoreforiotobjectdetection AT ruipolicarpoduarte configurablehardwarecoreforiotobjectdetection AT mariopvestias configurablehardwarecoreforiotobjectdetection AT horaciocneto configurablehardwarecoreforiotobjectdetection AT josetdesousa configurablehardwarecoreforiotobjectdetection
_version_	1718412128970342400

Configurable Hardware Core for IoT Object Detection

Ejemplares similares