Pedestrian detection from still images

Yusuf Engin Tetik*, Bülent Bolat

*Corresponding author for this work

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

6 Citations (Scopus)

Abstract

In this work, a pedestrian detection method based on adaptive boosting is proposed. The proposed method works on still images. The features utilized in the work are derived from Haar-like templates. An Adaboost classifier is utilized for both feature selection and classification. To show the effectiveness of the proposed algorithm, the system is trained by using Nicta Pedestrian Dataset and tested by using Penn Fudan Pedestrian Dataset. The experimental result shows the proposed method's effectiveness.

Original languageEnglish
Title of host publicationINISTA 2011 - 2011 International Symposium on INnovations in Intelligent SysTems and Applications
Pages540-544
Number of pages5
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2011 - Istanbul-Kadikoy, Turkey
Duration: 15 Jun 201118 Jun 2011

Publication series

NameINISTA 2011 - 2011 International Symposium on INnovations in Intelligent SysTems and Applications

Conference

Conference2011 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2011
Country/TerritoryTurkey
CityIstanbul-Kadikoy
Period15/06/1118/06/11

Keywords

  • Adaboost
  • Haar-like features
  • pedestrian detection
  • rectangular features

Fingerprint

Dive into the research topics of 'Pedestrian detection from still images'. Together they form a unique fingerprint.

Cite this