3D hand reconstruction from RGB-D/RGB video frames in real-time
View/Open
Cita com:
hdl:2117/133121
CovenanteeÉcole polytechnique fédérale de Lausanne
Document typeMaster thesis
Date2019-04-30
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
We present a pipeline able to extract 3D real-world measurements from RGB-D images with high accuracy in real-time. A new method bottom-up multi-person for hand-body pose detection evolved from OpenPifPaf has been presented. Two novel training strategies using multiple datasets are presented.
SubjectsMachine learning, Computer vision, Artificial intelligence, Video recording, Aprenentatge automàtic, Visió per ordinador, Intel·ligència artificial, Vídeo
DegreeMÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2017)
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
137377.pdf | 13,09Mb | View/Open |