Monocular estimation of 3D poses from a distance

Véges, Márton and Varga, Viktor: Monocular estimation of 3D poses from a distance. Conference of PhD Students in Computer Science, (11). pp. 114-117. (2018)

[img] Cikk, tanulmány, mű
cscs_2018_127-130.pdf

Download (172kB)

Abstract

Most 3D pose estimators only estimate egocentric coordinates where the body is centred at the origin. This is suitable for scenes with a single person but for images with interacting persons it is insufficient. We propose a monocular depth estimator for telephoto lenses to estimate 3D coordinates centred at the camera. Our method fuses a depth map predictor and a relative 3D pose estimator by means of a 3-layer neural network. We compare the algorithm with the state-of-the-art method and show a 19% improvement.

Item Type: Article
Event Title: Conference of PhD students in computer science (11.) (2018) (Szeged)
Journal or Publication Title: Conference of PhD Students in Computer Science
Date: 2018
Volume: 11
Page Range: pp. 114-117
Uncontrolled Keywords: Számítástechnika
Additional Information: Bibliogr.: p. 116-117. ; összefoglalás angol nyelven
Date Deposited: 2019. Nov. 04. 12:53
Last Modified: 2019. Nov. 04. 12:53
URI: http://acta.bibl.u-szeged.hu/id/eprint/61780

Actions (login required)

View Item View Item