Visual Data Simulation for Deep Learning in Robot Manipulation Tasks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00332335" target="_blank" >RIV/68407700:21230/19:00332335 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/19:00332335

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-14984-0_29" target="_blank" >https://doi.org/10.1007/978-3-030-14984-0_29</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-14984-0_29" target="_blank" >10.1007/978-3-030-14984-0_29</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Visual Data Simulation for Deep Learning in Robot Manipulation Tasks

Popis výsledku v původním jazyce

This paper introduces the usage of simulated images for training convolutional neural networks for object recognition and localization in the task of random bin picking. For machine learning applications, a limited amount of real world image data that can be captured and labeled for training and testing purposes is a big issue. In this paper, we focus on the use of realistic simulation of image data for training convolutional neural networks to be able to estimate the pose of an object. We can systematically generate varying camera viewpoint datasets with a various pose of an object and lighting conditions. After successful training and testing the neural network, we compare the performance of network trained on simulated images and images from a real camera capturing the physical object. The usage of the simulated data can speed up the complex and time-consuming task of gathering training data as well as increase robustness of object recognition by generating a bigger amount of data.

Název v anglickém jazyce

Visual Data Simulation for Deep Learning in Robot Manipulation Tasks

Popis výsledku anglicky

This paper introduces the usage of simulated images for training convolutional neural networks for object recognition and localization in the task of random bin picking. For machine learning applications, a limited amount of real world image data that can be captured and labeled for training and testing purposes is a big issue. In this paper, we focus on the use of realistic simulation of image data for training convolutional neural networks to be able to estimate the pose of an object. We can systematically generate varying camera viewpoint datasets with a various pose of an object and lighting conditions. After successful training and testing the neural network, we compare the performance of network trained on simulated images and images from a real camera capturing the physical object. The usage of the simulated data can speed up the complex and time-consuming task of gathering training data as well as increase robustness of object recognition by generating a bigger amount of data.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Modelling and Simulation for Autonomous Systems (MESAS 2018)

ISBN

978-3-030-14983-3

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

10

Strana od-do

402-411

Název nakladatele

Springer International Publishing AG

Místo vydání

Cham

Místo konání akce

Praha

Datum konání akce

17. 10. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—