D
Dimitrios S. Alexiadis
Researcher at Information Technology Institute
Publications - 40
Citations - 1055
Dimitrios S. Alexiadis is an academic researcher from Information Technology Institute. The author has contributed to research in topics: Motion estimation & 3D reconstruction. The author has an hindex of 16, co-authored 40 publications receiving 946 citations. Previous affiliations of Dimitrios S. Alexiadis include Aristotle University of Thessaloniki.
Papers
More filters
Proceedings ArticleDOI
Evaluating a dancer's performance using kinect-based skeleton tracking
Dimitrios S. Alexiadis,Philip Kelly,Petros Daras,Noel E. O'Connor,Tamy Boubekeur,Maher Ben Moussa +5 more
TL;DR: A novel system that automatically evaluates dance performances against a gold-standard performance and provides visual feedback to the performer in a 3D virtual environment and is proposed for temporally aligning dance movements from two different users and quantitatively evaluating one performance against another.
Journal ArticleDOI
Real-Time, Full 3-D Reconstruction of Moving Foreground Objects From Multiple Consumer Depth Cameras
TL;DR: A multiple-Kinect capturing system and a novel methodology for the creation of accurate, realistic, full 3-D reconstructions of moving foreground objects, e.g., humans, to be exploited in real-time applications.
Proceedings ArticleDOI
Estimating human motion from multiple Kinect sensors
Stylianos Asteriadis,Anargyros Chatzitofis,Dimitrios Zarpalas,Dimitrios S. Alexiadis,Petros Daras +4 more
TL;DR: This work presents a methodology for fusing information from multiple sensors based on a series of factors that can alleviate from the problem of occlusion or noisy estimates of 3D joints' positions.
Journal ArticleDOI
An Integrated Platform for Live 3D Human Reconstruction and Motion Capturing
Dimitrios S. Alexiadis,Anargyros Chatzitofis,Nikolaos Zioulis,Olga Zoidi,Georgios Louizis,Dimitrios Zarpalas,Petros Daras +6 more
TL;DR: The main elements of an integrated platform, which target tele-immersion and future 3D applications, are described in this paper, addressing the tasks of real-time capturing, robust 3D human shape/appearance reconstruction, and skeleton-based motion tracking.
Journal ArticleDOI
Estimation of Motions in Color Image Sequences Using Hypercomplex Fourier Transforms
TL;DR: It is shown that translational motions are manifested as energy concentration along planes in the hypercomplex 3D Fourier domain and a methodology to estimate the motions is described, based on this property, which can be reduced by a factor of 1/3, using thehypercomplex Fourier transform.