Advanced Pedestrian Dataset Augmentation for Autonomous Driving

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F19%3A00335023" target="_blank" >RIV/68407700:21730/19:00335023 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCVW.2019.00290" target="_blank" >https://doi.org/10.1109/ICCVW.2019.00290</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCVW.2019.00290" target="_blank" >10.1109/ICCVW.2019.00290</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Advanced Pedestrian Dataset Augmentation for Autonomous Driving

Popis výsledku v původním jazyce

Having the ability of generating people images in arbitrary, yet admissible, pose is a crucial prerequisite for Autonomous Driving applications. Firstly, because the existing datasets are quite limited in the human pose variation and appearance. Secondly, because the strict safety requirements call for the ability of validation on rare situations. Generating realistically looking people images is very challenging problem due to various transformations of individual body parts self occlusions etc. We propose a novel approach for person image generation. Our approach allows generating people images in a required pose, indicated by specific pose keypoints and deals with occlusions. We build on top of the recent prevailing success of Generative Adversarial Networks. Our contributions comprise of the networks architecture, as well as the novel loss terms specically designed to generate visually appealing pedestrians tting the surrounding environment well.

Název v anglickém jazyce

Advanced Pedestrian Dataset Augmentation for Autonomous Driving

Popis výsledku anglicky

Having the ability of generating people images in arbitrary, yet admissible, pose is a crucial prerequisite for Autonomous Driving applications. Firstly, because the existing datasets are quite limited in the human pose variation and appearance. Secondly, because the strict safety requirements call for the ability of validation on rare situations. Generating realistically looking people images is very challenging problem due to various transformations of individual body parts self occlusions etc. We propose a novel approach for person image generation. Our approach allows generating people images in a required pose, indicated by specific pose keypoints and deals with occlusions. We build on top of the recent prevailing success of Generative Adversarial Networks. Our contributions comprise of the networks architecture, as well as the novel loss terms specically designed to generate visually appealing pedestrians tting the surrounding environment well.

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

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)

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

2019 IEEE International Conference on Computer Vision Workshops (ICCVW 2019)

ISBN

—

ISSN

2473-9944

e-ISSN

2473-9944

Počet stran výsledku

6

Strana od-do

2367-2372

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Seoul

Datum konání akce

27. 10. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—