Detection of moving individuals in cluttered scenes

Christogiannopoulos, G, Young, R C and Chatwin, C R (2006) Detection of moving individuals in cluttered scenes. In: Optical Pattern Recognition XVII, April 17, 2006, Orlando (Kissimmee), FL.

Full text not available from this repository.

Abstract

This paper describes a system for the detection of people moving in a video scene. The system is ultimately intended to allow tracking of the major parts of the human body. Objects are detected utilising a background subtraction method which is based on the movements of objects within the scene. The background removal algorithm is designed in a way that allows the background be to constantly up-dated automatically, allowing it to be used over a long period of time. Several methods for improving the outcome from the background removal algorithm are used which include addressing problems caused by variable shading. Mathematical morphology techniques are subsequently employed in order to improve the segmentation achieved in each frame.

Item Type: Conference or Workshop Item (Paper)
Keywords: Background subtraction; Color space; Pose estimation; Scene segmentation; Scene understanding; Temporal differencing, Algorithms; Clutter (information theory); Image segmentation; Motion pictures; Object recognition; Tracking (position), Image analysis
Schools and Departments: School of Engineering and Informatics > Engineering and Design
Subjects: T Technology
Depositing User: Chris Chatwin
Date Deposited: 24 May 2013 06:59
Last Modified: 24 May 2013 06:59
URI: http://srodev.sussex.ac.uk/id/eprint/44980
📧 Request an update