Generating Synthetic Depth Image Dataset for Industrial Applications of Hand Localization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27230%2F22%3A10250425" target="_blank" >RIV/61989100:27230/22:10250425 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9893133/authors#authors" target="_blank" >https://ieeexplore.ieee.org/document/9893133/authors#authors</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ACCESS.2022.3206948" target="_blank" >10.1109/ACCESS.2022.3206948</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Generating Synthetic Depth Image Dataset for Industrial Applications of Hand Localization

Popis výsledku v původním jazyce

In this paper, we focus on the problem of applying domain randomization to produce synthetic datasets for training depth image segmentation models for the task of hand localization. We provide new synthetic datasets for industrial environments suitable for various hand tracking applications, as well as ready-to-use pre-trained models. The presented datasets are analyzed to evaluate the characteristics of these datasets that affect the generalizability of the trained models, and recommendations are given for adapting the simulation environment to achieve satisfactory results when creating datasets for specialized applications. Our approach is not limited by the shortcomings of standard analytical methods, such as color, specific gestures, or hand orientation. The models in this paper were trained solely on a synthetic dataset and were never trained on real camera images; nevertheless, we demonstrate that our most diverse datasets allow the models to achieve up to 90% accuracy. The proposed hand localization system is designed for industrial applications where the operator shares the workspace with the robot.

Název v anglickém jazyce

Generating Synthetic Depth Image Dataset for Industrial Applications of Hand Localization

Popis výsledku anglicky

In this paper, we focus on the problem of applying domain randomization to produce synthetic datasets for training depth image segmentation models for the task of hand localization. We provide new synthetic datasets for industrial environments suitable for various hand tracking applications, as well as ready-to-use pre-trained models. The presented datasets are analyzed to evaluate the characteristics of these datasets that affect the generalizability of the trained models, and recommendations are given for adapting the simulation environment to achieve satisfactory results when creating datasets for specialized applications. Our approach is not limited by the shortcomings of standard analytical methods, such as color, specific gestures, or hand orientation. The models in this paper were trained solely on a synthetic dataset and were never trained on real camera images; nevertheless, we demonstrate that our most diverse datasets allow the models to achieve up to 90% accuracy. The proposed hand localization system is designed for industrial applications where the operator shares the workspace with the robot.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

<a href="/cs/project/EF17_049%2F0008425" target="_blank" >EF17_049/0008425: Platforma pro výzkum orientovaný na Průmysl 4.0 a robotiku v ostravské aglomeraci</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název periodika

IEEE Access

ISSN

2169-3536

e-ISSN

2169-3536

Svazek periodika

10

Číslo periodika v rámci svazku

10/2022

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

11

Strana od-do

99734-99744

Kód UT WoS článku

000861358100001

EID výsledku v databázi Scopus

2-s2.0-85139396288