Search:
Computing and Library Services - delivering an inspiring information environment

Volume-based Video analysis using 3D Segmentation Techniques

Wang, Jing, Xu, Zhijie and Pickering, Jonathan (2009) Volume-based Video analysis using 3D Segmentation Techniques. In: 15th International Conference on Automation & Computing, 19th September 2009, Luton, UK. (Unpublished)

[img]
Preview
PDF
Volume_Segmentation_for_Video_Event_Detection.pdf - Accepted Version

Download (542kB) | Preview

Abstract

Video content understanding for surveillance and security applications such as smart CCTV cameras has become a research hotspot in the last decade. This paper presents applications of volume construction and volume-based cluster segmentation approaches to video event detection. It starts with a description of the translation between original video frames and 3D volume structures denoted by spatial and temporal features. It then highlights the volume array structure, a so called “pre-suspicion” mechanism. The focus of the work is on devising an effective and efficient voxel-based segmentation technique suitable to the volumetric nature of video events through deploying innovative 3D clustering methods. It is supported by the design and experiment on the 3D data compression techniques for accelerating the pre-processing of the original video data. An evaluation on the performance of the developed methods is presented at the end.

Item Type: Conference or Workshop Item (Paper)
Subjects: T Technology > T Technology (General)
Schools: School of Computing and Engineering
School of Computing and Engineering > High-Performance Intelligent Computing > Visualisation, Interaction and Vision
Related URLs:
Depositing User: Jing Wang
Date Deposited: 11 May 2010 10:21
Last Modified: 24 Jun 2011 08:56
URI: http://eprints.hud.ac.uk/id/eprint/7602

Downloads

Downloads per month over past year

Repository Staff Only: item control page

View Item View Item

University of Huddersfield, Queensgate, Huddersfield, HD1 3DH Copyright and Disclaimer All rights reserved ©