Pedestrian detection with an improved Adaboost

Yusuf Engin Tetik, Bulent Bolat

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

1 Citation (Scopus)

Abstract

This paper focuses on improving the performance of Adaboost (Adaptive Boosting) by using weak classifiers that make classification with a confidence score. Single thresholds and nearest neighbor classifiers are used as base classifiers. The proposed method is applied to the problem of pedestrian detection in still images. Haar-like basic features are used to construct weak classifiers.

Original languageEnglish
Title of host publication2013 IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA 2013
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA 2013 - Albena, Bulgaria
Duration: 19 Jun 201321 Jun 2013

Publication series

Name2013 IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA 2013

Conference

Conference2013 IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA 2013
Country/TerritoryBulgaria
CityAlbena
Period19/06/1321/06/13

Keywords

  • Adaboost
  • Confidence Score
  • Haar like basic features
  • Nearest Neighbour
  • Weak Classifiers

Fingerprint

Dive into the research topics of 'Pedestrian detection with an improved Adaboost'. Together they form a unique fingerprint.

Cite this