Spatio-temporal volume-based shape modelling for video event detection

Jing Wang, Zhijie Xu, Ying Liu

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

In a typical computer vision application, such as video event detection, the 'meaningful' information is fundamentally represented by pre-defined features, which determine the appropriate analytical methodologies in the following processing phases. Based on the uncompressed low-level image characteristics, such as colour, intensity and spatial positions, the features used for event detection in this research are predominantly based on 3D shapes, regional textures, and sudden colour/intensity. In this research, a spatio-temporal volume-based shape feature extraction and modelling approach has been proposed. This method starts from defining video data as 3D volumetric shapes by using active contour (AC) segmentation techniques. Based on the nature of its 3D distribution, a dynamic windowing mechanism has been developed for improving the segmentation performance when deploying the AC algorithm. The runtime performance of the prototype system has been evaluated which validated the design and its potential in improving volume-based event recognition.

Original languageEnglish
Title of host publicationICAC 2013 - Proceedings of the 19th International Conference on Automation and Computing
Subtitle of host publicationFuture Energy and Automation
PublisherIEEE Computer Society
Pages185-190
Number of pages6
ISBN (Print)9781908549082
Publication statusPublished - 2013
Externally publishedYes
Event19th International Conference on Automation and Computing, ICAC 2013 - London, United Kingdom
Duration: 13 Sept 201314 Sept 2013

Publication series

NameICAC 2013 - Proceedings of the 19th International Conference on Automation and Computing: Future Energy and Automation

Conference

Conference19th International Conference on Automation and Computing, ICAC 2013
Country/TerritoryUnited Kingdom
CityLondon
Period13/09/1314/09/13

Keywords

  • event detection
  • feature extraction
  • shape
  • spatio-temporal volume

Fingerprint

Dive into the research topics of 'Spatio-temporal volume-based shape modelling for video event detection'. Together they form a unique fingerprint.

Cite this