Multi-GPU based framework for real-time motion analysis and tracking in multi-user scenarios

Journal Title: EAI Endorsed Transactions on Creative Technologies - Year 2015, Vol 2, Issue 2

Abstract

Video processing algorithms present a necessary tool for various domains related to computer vision such as motion tracking, event detection and localization in multi-user scenarios (crowd videos, mobile camera, scenes with noise, etc.). However, the new video standards, especially those in high definitions require more computation since their treatment is applied on large video frames. As result, the current implementations, even running on modern hardware, cannot provide a real-time processing (25 frames per second, fps). Several solutions have been proposed to overcome this constraint, by exploiting graphic processing units (GPUs). Although they exploit GPU platforms, they are not able to provide a real-time processing of high definition video sequences. In this work, we propose a new framework that enables an efficient exploitation of single and multiple GPUs, in order to achieve real-time processing of Full HD or even 4K video standards. Moreover, the framework includes several GPU based primitive functions related to motion analysis and tracking methods, such as silhouette extraction, contours extraction, corners detection and tracking using optical flow estimation. Based on this framework, we developed several real-time and GPU based video processing applications such as motion detection using moving camera, event detection and event localization

Authors and Affiliations

Sidi Ahmed Mahmoudi

Keywords

Related Articles

Designing intelligent games adapting to children’s playing maturity

Play is a voluntary activity in which individuals involve for pleasure. It is very important for children because through playing they learn to explore, develop and master physical and social skills. Play development is...

Moving Collaborations: A Critical Inquiry Into Designing Creative Interactive Systems for Choreography

The use of technology in choreographic process has been encumbered by the richness of data in live human movement and the constraints of computation. While technology is often considered a tool in choreographic process,...

Towards a novel and LMS-free Pervasive Learning System exploiting the Experience API

Experience API (xAPI), the evolution of SCORM (Sharable Content Object Reference Model) in e-learning content specifications, stably gains ground in education, defense and training. In this paper we shortly describe the...

A novel approach to painting powered by Ambient Intelligence

Today, many forms of art are influenced by the emergence of interactive technologies, including the mixing of physical media with digital technology for forming new hybrid works of art and the usage of mobile phones to c...

Augmented Reality Meets Tangibility: A New Approach for Early Childhood Education

Augmented Reality (AR) has been recognised as one of the promising technologies for the gaming industry. In this study, the authors intend to apply AR technology to develop an interactive educational game. This paper pre...

Download PDF file
  • EP ID EP45826
  • DOI http://dx.doi.org/10.4108/ct.2.2.e5
  • Views 461
  • Downloads 0

How To Cite

Sidi Ahmed Mahmoudi (2015). Multi-GPU based framework for real-time motion analysis and tracking in multi-user scenarios. EAI Endorsed Transactions on Creative Technologies, 2(2), -. https://www.europub.co.uk/articles/-A-45826