Naslov
A Review of 3D Human Pose Estimation from 2D Images

Autori
Bartol, Kristijan ; Bojanić, David ; Petković, Tomislav ; D'Apuzzo, Nicola ; Pribanić, Tomislav

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of 3DBODY.TECH 2020 11th International Conference and Exhibition on 3D Body Scanning and Processing Technologies Online/Virtual, 17-18 November 2020 / D’Apuzzo , Nicola - : Hometrica Consulting - Dr. Nicola D'Apuzzo, 2020

ISBN
978-3-033-08209-0

Skup
11th International Conference and Exhibition on 3D Body Scanning and Processing Technologies (3DBODY.TECH 2020)

Mjesto i datum
Online, 17.11.2020. - 18.11.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
3d computer vision ; human pose estimation ; review

Sažetak
Human pose estimation task takes images as input and extracts a set of locations representing the predefined body joints and the sparse connections between the joints, called the body parts. A pose can be estimated from single or multiple frames, in a single (monocular) or multi-view (stereo) setup and for a single person or multiple people in the scene. In this work, we provide an overview of the classic and deep learning-based 3D pose estimation approaches. We also point out relevant evaluation metrics, pose parametrizations, body models, and 3D human pose datasets. Finally, we review state-of-the-art pose estimation results, briefly discuss open problems, and propose possible future research directions.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA