Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F23%3A00370713" target="_blank" >RIV/68407700:21730/23:00370713 - isvavai.cz</a>
Výsledek na webu
<a href="https://doi.org/10.1109/LRA.2023.3259735" target="_blank" >https://doi.org/10.1109/LRA.2023.3259735</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/LRA.2023.3259735" target="_blank" >10.1109/LRA.2023.3259735</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Popis výsledku v původním jazyce
This letter introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their performance is usually limited for heavily occluded objects, which is a common case in imitation learning, where the object is typically partially occluded by the manipulating hand. Currently, there is a lack of datasets that would enable the development of robust 6D pose estimation methods for these conditions. To overcome this problem, we collect a new dataset (Imitrob) aimed at 6D pose estimation in imitation learning and other applications where a human holds a tool and performs a task. The dataset contains image sequences of nine different tools and twelve manipulation tasks with two camera viewpoints, four human subjects, and left/right hand. Each image is accompanied by an accurate ground truth measurement of the 6D object pose obtained by the HTC Vive motion tracking device. The use of the dataset is demonstrated by training and evaluating a recent 6D object pose estimation method (DOPE) in various setups.
Název v anglickém jazyce
Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators
Popis výsledku anglicky
This letter introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their performance is usually limited for heavily occluded objects, which is a common case in imitation learning, where the object is typically partially occluded by the manipulating hand. Currently, there is a lack of datasets that would enable the development of robust 6D pose estimation methods for these conditions. To overcome this problem, we collect a new dataset (Imitrob) aimed at 6D pose estimation in imitation learning and other applications where a human holds a tool and performs a task. The dataset contains image sequences of nine different tools and twelve manipulation tasks with two camera viewpoints, four human subjects, and left/right hand. Each image is accompanied by an accurate ground truth measurement of the 6D object pose obtained by the HTC Vive motion tracking device. The use of the dataset is demonstrated by training and evaluating a recent 6D object pose estimation method (DOPE) in various setups.
Klasifikace
Druh
J<sub>imp</sub> - Článek v periodiku v databázi Web of Science
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
IEEE Robotics and Automation Letters
ISSN
2377-3766
e-ISSN
2377-3766
Svazek periodika
8
Číslo periodika v rámci svazku
5
Stát vydavatele periodika
US - Spojené státy americké
Počet stran výsledku
8
Strana od-do
2788-2795
Kód UT WoS článku
000964797800003
EID výsledku v databázi Scopus
2-s2.0-85151544096