Accurate Object Detection System on HoloLens Using YOLO Algorithm

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24620%2F19%3A00007887" target="_blank" >RIV/46747885:24620/19:00007887 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9057151" target="_blank" >https://ieeexplore.ieee.org/document/9057151</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCAIRO47923.2019.00042" target="_blank" >10.1109/ICCAIRO47923.2019.00042</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Accurate Object Detection System on HoloLens Using YOLO Algorithm

Popis výsledku v původním jazyce

We demonstrate in our paper, an implementation on Microsoft HoloLens, deep learning supported in the context of object detection. The main aim of this system is to create the more accurate object detection model for Augmented Reality using communication between the deep learning processing and the Microsoft HoloLens as Input/Output device. This system aims to help the wearable device user to detect and to recognize between objects in real world. For the object detection approach, a deep learning model has been used for the implementation of this system called YOLO. This model is near to real-time and it supports to detect more than 9000 objects. Our system provides the annotation of augmented object detected and its limitation area or bounding box via HoloLens. It allows to detect the new position of moving object in a few milliseconds. Preliminary results show a great rate of object detection with a detection time comparable.

Název v anglickém jazyce

Accurate Object Detection System on HoloLens Using YOLO Algorithm

Popis výsledku anglicky

We demonstrate in our paper, an implementation on Microsoft HoloLens, deep learning supported in the context of object detection. The main aim of this system is to create the more accurate object detection model for Augmented Reality using communication between the deep learning processing and the Microsoft HoloLens as Input/Output device. This system aims to help the wearable device user to detect and to recognize between objects in real world. For the object detection approach, a deep learning model has been used for the implementation of this system called YOLO. This model is near to real-time and it supports to detect more than 9000 objects. Our system provides the annotation of augmented object detected and its limitation area or bounding box via HoloLens. It allows to detect the new position of moving object in a few milliseconds. Preliminary results show a great rate of object detection with a detection time comparable.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20201 - Electrical and electronic engineering

Projekt

<a href="/cs/project/EF16_025%2F0007293" target="_blank" >EF16_025/0007293: Modulární platforma pro autonomní podvozky specializovaných elektrovozidel pro dopravu nákladu a zařízení</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings - 2019 3rd International Conference on Control, Artificial Intelligence, Robotics and Optimization, ICCAIRO 2019

ISBN

978-1-72813-572-4

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

219-224

Název nakladatele

Institute of Electrical and Electronics Engineers Inc.

Místo vydání

—

Místo konání akce

Athens; Greece

Datum konání akce

1. 1. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—