Login | Register

Universal Gesture Tracking Framework in OpenISS and ROS and its Applications

Title:

Universal Gesture Tracking Framework in OpenISS and ROS and its Applications

Singh, Jashanjot (2020) Universal Gesture Tracking Framework in OpenISS and ROS and its Applications. Masters thesis, Concordia University.

[thumbnail of Singh_MCompSc_S2020.pdf]
Preview
Text (application/pdf)
Singh_MCompSc_S2020.pdf - Accepted Version
Available under License Spectrum Terms of Access.
23MB

Abstract

In this research work, we present a common and extensible framework that abstracts different vision-based gesture recognition middleware and provides uniform gesture recognition data obtained from those via its simpler API to enable hand gesture interaction in different kinds of applications. We demonstrate various aspects of our framework via instrumentation and enable gesture interaction for our two specific yet different needs.
Firstly, we alleviate limited gesture tracking functionality in ISSv2 aka. (Illimitable Space System v2), an interactive and configurable artists' toolbox that is used to create music visualizations, visual effects and interactive documentary film based on the inputs from users such as gestures, voice, motion, etc.
Secondly, we provide a proof-of-concept solution to enhance and demonstrate limited language usability of the FORENSIC LUCID language's composition and compiler interactivity by enabling a forensic investigator to create partial FORENSIC LUCID encoded programs which require manipulation of preloaded digital evidence objects in a 3D warehouse-like application (DigiEVISS) via hand gesture interaction.
We also leverage Robot Operating System (ROS), an open source set of tools and libraries for its communication middleware to broadcast our framework data over the network. We provide this framework as a specialization of the OpenISS core framework and evaluate our framework on various aspects. We employ metrics such as effective frame rate and delay to evaluate our exemplified scenarios that represent our needs.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Singh, Jashanjot
Institution:Concordia University
Degree Name:M. Comp. Sc.
Program:Computer Science
Date:22 January 2020
Thesis Supervisor(s):Paquet, Joey and Mokhov, Serguei A.
Keywords:OpenISS, Computer Vision, Human-Computer Interaction, Gesture Recognition, Frameworks, Natural User Interfaces, Gesture Tracking
ID Code:986429
Deposited By: Jashanjot Singh
Deposited On:26 Jun 2020 13:39
Last Modified:26 Jun 2020 13:39
Related URLs:
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top