Tracking objects with level sets

Mark C. Moelich, Tony Chan

Research output: Contribution to conferencePaperpeer-review

Abstract

Tracking objects in video sequences is a challenging problem for which many techniques and algorithms have been developed. This paper focuses on using region-based segmentation and level sets as the basis of a tracking algorithm. This approach is relatively new and has much promise. The main ideas behind this approach are explained and then demonstrated with two algorithms. The first algorithm is capable of tracking a selected object in the presence of a moving camera. The second algorithm assumes a fixed camera, but is able to detect and isolate multiple moving objects in low-resolution video, without user input.

Original languageEnglish (US)
StatePublished - Dec 1 2004
EventEuropean Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2004 - Jyvaskyla, Finland
Duration: Jul 24 2004Jul 28 2004

Other

OtherEuropean Congress on Computational Methods in Applied Sciences and Engineering, ECCOMAS 2004
CountryFinland
CityJyvaskyla
Period07/24/0407/28/04

Keywords

  • Level sets
  • Region-based
  • Segmentation
  • Tracking
  • Video

ASJC Scopus subject areas

  • Artificial Intelligence
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Tracking objects with level sets'. Together they form a unique fingerprint.

Cite this