Recognizing Human Actions by Local Space Time and LS-TSVM over CUDA

Abstract

Local space-time features can be used to make the events adapted to the velocity of moving patterns, size of the object and the frequency in captured video. This paper purposed the new implementation approach of Human Action Reorganization (HAR) using Compute Unified Device Architecture (CUDA). Initially, local space-time features extracted from the customized dataset of videos. The video features are extracted by utilizing the Histogram of Optical Flow (HOF) and Harris detector algorithm descriptor. A new extended version of SVM classifier which is four time faster and has better precision than classical SVM known as the Least Square Twin SVM (LS-TSVM); a binary classifier which use two non-parallel hyperplanes, is applied on extracted video features. Paper evaluates the LS-TSVM performance on the customized data and experimental result showed the significant improvements.

Authors and Affiliations

Mohsin Raza Siyal, Muhammad Saeed, Jibran R. Khan, Farhan A. Siddiqui, Kamran Ahsan

Keywords

Related Articles

Performance Comparison of Detection, Recognition and Tracking Rates of the different Algorithms

This article discusses the approach of human detection and tracking in a homogeneous domain using surveillance cameras. This is a vast area in which significant research has been taking place from more than a decade and...

Adaptive Cache Replacement:A Novel Approach

Cache replacement policies are developed to help insure optimal use of limited resources. Varieties of such algorithms exist with relatively few that dynamically adapt to traffic patterns. Algorithms that are tunable typ...

A Modified Heuristic-Block Protocol Model for Privacy and Concurrency in Cloud

With boost in the figure of cloud users and the magnitude of sensitive data on cloud, shielding of cloud has become more important. Competent methods are consistently desirable to ensure the information privacy and load...

Software Migration Frameworks for Software System Solutions: A Systematic Literature Review

This study examines and review the current software migration frameworks. With the quick technological enhancement, companies need to move their software’s from one platform to another platform like cloud-based migration...

Comparative Study for Software Project Management Approaches and Change Management in the Project Monitoring & Controlling

A software project encounters many changes during the software development life cycle. The key challenge is to control these changes and manage their impact on the project plan, budget, and implementation schedules. A we...

Download PDF file
  • EP ID EP240660
  • DOI 10.14569/IJACSA.2017.081124
  • Views 92
  • Downloads 0

How To Cite

Mohsin Raza Siyal, Muhammad Saeed, Jibran R. Khan, Farhan A. Siddiqui, Kamran Ahsan (2017). Recognizing Human Actions by Local Space Time and LS-TSVM over CUDA. International Journal of Advanced Computer Science & Applications, 8(11), 183-186. https://europub.co.uk/articles/-A-240660