Switching Kalman filter-based approach for tracking and event detection at traffic intersections

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

18 Scopus citations

Abstract

Automatic event detection from video sequences has applications in several areas such as automatic visual surveillance, traffic monitoring for Intelligent Transportation Systems, key frame detection for video compression, and virtual reality applications. In this work, we present a computer vision-based approach for event detection and data collection at traffic intersections. Specifically, we make the following two contributions: (i) a robust tracking algorithm for targets through combination of multiple cues and multiple motion models, and (ii) a simple event detection system using the results of a switching Kalman filter in combination with some simple rules. We show the results of tracking and event detection, such as, turning, stopped or stalling vehicles, as well as motion statistics (average speeds and accelerations), collected for some outdoor traffic scenes.

Original languageEnglish (US)
Title of host publicationProceedings of the 20th IEEE International Symposium on Intelligent Control, ISIC '05 and the 13th Mediterranean Conference on Control and Automation, MED '05
PublisherIEEE Computer Society
Pages1167-1172
Number of pages6
ISBN (Print)0780389360, 9780780389366
DOIs
StatePublished - 2005
Event20th IEEE International Symposium on Intelligent Control, ISIC '05 and the13th Mediterranean Conference on Control and Automation, MED '05 - Limassol, Cyprus
Duration: Jun 27 2005Jun 29 2005

Publication series

NameProceedings of the 20th IEEE International Symposium on Intelligent Control, ISIC '05 and the 13th Mediterranean Conference on Control and Automation, MED '05
Volume2005

Other

Other20th IEEE International Symposium on Intelligent Control, ISIC '05 and the13th Mediterranean Conference on Control and Automation, MED '05
CountryCyprus
CityLimassol
Period6/27/056/29/05

Keywords

  • Cue combination
  • Event detection
  • Multiple cue-based tracking
  • Switching Kalman filter

Fingerprint Dive into the research topics of 'Switching Kalman filter-based approach for tracking and event detection at traffic intersections'. Together they form a unique fingerprint.

Cite this