Tracking-optimal pre- and post-processing for H.264 compression in traffic video surveillance applications

E. Soyak*, S. A. Tsaftaris, Aggelos K Katsaggelos

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

The compression of video can reduce the accuracy of automated tracking algorithms. This is problematic for centralized applications such as transportation surveillance systems, where remotely captured and compressed video is transmitted to a central location for tracking. In typical systems, the majority of communications bandwidth is spent on representing events such as capture noise or local changes to lighting. We propose a pre- and post-processing algorithm that identifies and removes such events of low tracking interest, significantly reducing the bitrate required to transmit remotely captured video while maintaining comparable tracking accuracy. Using the H.264/AVC video coding standard and a commonly used state-of-the-art tracker we show that our algorithm allows for up to 90% bitrate savings while maintaining comparable tracking accuracy.

Original languageEnglish (US)
Title of host publication2010 IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2010 - Proceedings
Pages375-378
Number of pages4
DOIs
StatePublished - Dec 1 2010
Event2010 IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2010 - Athens, Greece
Duration: Dec 12 2010Dec 15 2010

Publication series

Name2010 IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2010 - Proceedings

Other

Other2010 IEEE International Conference on Electronics, Circuits, and Systems, ICECS 2010
CountryGreece
CityAthens
Period12/12/1012/15/10

Keywords

  • Postprocessing
  • Preprocessing
  • Transportation
  • Urban traffic video tracking
  • Video compression

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Tracking-optimal pre- and post-processing for H.264 compression in traffic video surveillance applications'. Together they form a unique fingerprint.

Cite this