Real-time multiclass object recognition system based on adaptive correlation filtering

Viridiana Contreras, Victor H. Diaz-Ramirez, Francisco J. Ramirez-Arias, Kenia Picos

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

Abstract

A real-time system for multiclass object recognition is proposed. The system is able to identify and correctly classify several moving targets from an input scene by using a bank of adaptive correlation filters with complex constraints implemented on a graphics processing unit. The bank of filters is synthesized with the help of an iterative algorithm based on complex synthetic discriminant functions. At each iteration, the algorithm optimizes the discrimination capability of each filter in the bank by using all available information about the known patterns to be recognized and unwanted patterns to be rejected such as false objects or a background. Computer simulation results obtained with the proposed system in real and synthetic scenes are presented and discussed in terms of pattern recognition performance and real-time operation speed.

Original languageEnglish
Title of host publicationOptics and Photonics for Information Processing VI
DOIs
StatePublished - 2012
EventOptics and Photonics for Information Processing VI - San Diego, CA, United States
Duration: 15 Aug 201216 Aug 2012

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8498
ISSN (Print)0277-786X

Conference

ConferenceOptics and Photonics for Information Processing VI
Country/TerritoryUnited States
CitySan Diego, CA
Period15/08/1216/08/12

Keywords

  • Adaptive correlation filters
  • Graphics processing unit
  • Multiclass pattern recognition
  • Real-time image processing

Fingerprint

Dive into the research topics of 'Real-time multiclass object recognition system based on adaptive correlation filtering'. Together they form a unique fingerprint.

Cite this