Object tracking using color correlogram

Qi Zhao, Hai Tao

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

63 Scopus citations

Abstract

Color histogram based representations have been widely used far blob tracking. In this paper, a new color histogram based approach for object representation is proposed. By using a simplified version of color correlogram as object feature, spatial information is incorporated into object representation, which allows variations of rotation to be detected throughout the tracking therefore rotational objects can be more accurately tracked. The gradient decent method mean shift algorithm is adopted as the central computational module and further extended to a 3D domain to find the most probable target position and orientation simultaneously. The capability of the tracker to tolerate appearance changes like orientation changes, small scale changes, partial occlusions and background scene changes is demonstrated using real image sequences.

Original languageEnglish (US)
Title of host publicationProceedings - 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS
Pages263-270
Number of pages8
DOIs
StatePublished - 2005
Event2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS - Beijing, China
Duration: Oct 15 2005Oct 16 2005

Publication series

NameProceedings - 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS
Volume2005

Other

Other2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS
Country/TerritoryChina
CityBeijing
Period10/15/0510/16/05

Fingerprint

Dive into the research topics of 'Object tracking using color correlogram'. Together they form a unique fingerprint.

Cite this