GPU accelerated stereo vision system to capture handwriting information

Stereo vision systems that capture 3D space data are of great use as computer interface systems for emerging technologies such as VR and Robotics. They are inexpensive, yet practical implementation is challenged by high CPU processing power requirement. Thus, in this paper a scheme is developed to e...

Full description

Bibliographic Details
Main Authors: Fadi Imad, Syed Ahmad, Sharifah Mumtazah, Hashim, Shaiful Jahari, Samsudin, Khairulmizam
Format: Article
Published: World Academy of Research in Science and Engineering 2019
Online Access:http://psasir.upm.edu.my/id/eprint/80004/
_version_ 1848858806574907392
author Fadi Imad
Syed Ahmad, Sharifah Mumtazah
Hashim, Shaiful Jahari
Samsudin, Khairulmizam
author_facet Fadi Imad
Syed Ahmad, Sharifah Mumtazah
Hashim, Shaiful Jahari
Samsudin, Khairulmizam
author_sort Fadi Imad
building UPM Institutional Repository
collection Online Access
description Stereo vision systems that capture 3D space data are of great use as computer interface systems for emerging technologies such as VR and Robotics. They are inexpensive, yet practical implementation is challenged by high CPU processing power requirement. Thus, in this paper a scheme is developed to exploit GPUs in the processing of high definition images required to track an object position and orientation in 3D space in real-time. This is done by porting and optimizing essential processing algorithms to operate efficiently in parallel on a GPU. The object detected is a pen, with the position of the tip and it's orientation tracked in real-time. The writing captured by the system is than compared to the one from commercial digitizing tablet. The results achieved indicated that pen tip can be tracked in 3D space with a percentage error below 1.7% within a distance of 40cm from the stereo camera shooting at a frame rate of 30 frames per second.
first_indexed 2025-11-15T12:19:18Z
format Article
id upm-80004
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T12:19:18Z
publishDate 2019
publisher World Academy of Research in Science and Engineering
recordtype eprints
repository_type Digital Repository
spelling upm-800042023-05-31T01:52:08Z http://psasir.upm.edu.my/id/eprint/80004/ GPU accelerated stereo vision system to capture handwriting information Fadi Imad Syed Ahmad, Sharifah Mumtazah Hashim, Shaiful Jahari Samsudin, Khairulmizam Stereo vision systems that capture 3D space data are of great use as computer interface systems for emerging technologies such as VR and Robotics. They are inexpensive, yet practical implementation is challenged by high CPU processing power requirement. Thus, in this paper a scheme is developed to exploit GPUs in the processing of high definition images required to track an object position and orientation in 3D space in real-time. This is done by porting and optimizing essential processing algorithms to operate efficiently in parallel on a GPU. The object detected is a pen, with the position of the tip and it's orientation tracked in real-time. The writing captured by the system is than compared to the one from commercial digitizing tablet. The results achieved indicated that pen tip can be tracked in 3D space with a percentage error below 1.7% within a distance of 40cm from the stereo camera shooting at a frame rate of 30 frames per second. World Academy of Research in Science and Engineering 2019 Article PeerReviewed Fadi Imad and Syed Ahmad, Sharifah Mumtazah and Hashim, Shaiful Jahari and Samsudin, Khairulmizam (2019) GPU accelerated stereo vision system to capture handwriting information. International Journal of Advanced Trends in Computer Science and Engineering, 8 (4). pp. 1186-1193. ISSN 2278-3091 https://www.warse.org/IJATCSE/years/archivesDetiles/?heading=Volume%208%20No.%204%20(2019) 10.30534/ijatcse/2019/29842019
spellingShingle Fadi Imad
Syed Ahmad, Sharifah Mumtazah
Hashim, Shaiful Jahari
Samsudin, Khairulmizam
GPU accelerated stereo vision system to capture handwriting information
title GPU accelerated stereo vision system to capture handwriting information
title_full GPU accelerated stereo vision system to capture handwriting information
title_fullStr GPU accelerated stereo vision system to capture handwriting information
title_full_unstemmed GPU accelerated stereo vision system to capture handwriting information
title_short GPU accelerated stereo vision system to capture handwriting information
title_sort gpu accelerated stereo vision system to capture handwriting information
url http://psasir.upm.edu.my/id/eprint/80004/
http://psasir.upm.edu.my/id/eprint/80004/
http://psasir.upm.edu.my/id/eprint/80004/