Universiti Teknologi Malaysia Institutional Repository

Classification of moving objects using active vision

Osman, S. M. (2005) Classification of moving objects using active vision. In: Conference on Computers Communications and Signal Processing with Special Track on Biomedical Engineering (CCSP'05), 2005, Kuala Lumpur.

[img]
Preview
PDF
122Kb

Official URL: http://dx.doi.org/10.1109/CCSP.2005.4977170

Abstract

An offline system that is capable to detect the moving object and classify it into three classes: “Human, Vehicle and Animal” is presented. The detection of the target based on Background Subtraction technique. The classification makes use of both static and dynamic features of the moving objects. All features are sequentially arranged to improve the classification significantly.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:1-D Profile, background subtraction, base to abdomen ratio, features vector
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:Electrical Engineering
ID Code:21328
Deposited By: Liza Porijo
Last Modified:19 Jan 2012 08:55

Repository Staff Only: item control page