Co-evolution based feature selection for pedestrian detection

  • Y. P. Guo
  • , X. B. Cao
  • , Y. W. Xu
  • , Q. Hong

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

6 Scopus citations

Abstract

In a pedestrian detection system, the most critical requirement is to quickly and reliably determine whether a candidate region contains a pedestrian. The detection ability of whole system determines directly upon quality of chosen features. However, due to the large number and various types of available features, it is difficult to find an optimal feature subset and acquire the proper feature proportion at the same time for most traditional methods including AdaBoost Algorithm. This paper presents a co-evolutionary method with sub-population size adjusting strategy for the feature selection problem in pedestrian detection system. Our method is able to find an optimal feature subset and adjust feature proportion to a proper state in the mean time. Experiments show that our method performs better than AdaBoost Algorithm.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Control and Automation, ICCA
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2797-2801
Number of pages5
ISBN (Print)1424408180, 9781424408184
DOIs
StatePublished - 2007
Externally publishedYes
Event2007 IEEE International Conference on Control and Automation, ICCA - Guangzhou, China
Duration: 30 May 20071 Jun 2007

Publication series

Name2007 IEEE International Conference on Control and Automation, ICCA

Conference

Conference2007 IEEE International Conference on Control and Automation, ICCA
Country/TerritoryChina
CityGuangzhou
Period30/05/071/06/07

Fingerprint

Dive into the research topics of 'Co-evolution based feature selection for pedestrian detection'. Together they form a unique fingerprint.

Cite this