Fast human/car classification methods in the computer vision tasks

Boris V. Vishnyakov, Ivan K. Malin, Yuri V. Vizilter, Shih Chia Huang, Sy Yen Kuo

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

1 Scopus citations

Abstract

In this paper we propose a method for classification of moving objects of human and car types in computer vision systems using statistical hypotheses and integration of the results using two different decision rules. FAR-FRR graphs for all criteria and the decision rule are plotted. Confusion matrix for both ways of integration is presented. The example of the method application to the public video databases is provided. Ways of accuracy improvement are proposed.

Original languageEnglish
Title of host publicationVideometrics, Range Imaging, and Applications XII; and Automated Visual Inspection
DOIs
StatePublished - 2013
Externally publishedYes
EventVideometrics, Range Imaging, and Applications XII; and Automated Visual Inspection - Munich, Germany
Duration: 14 05 201316 05 2013

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8791
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceVideometrics, Range Imaging, and Applications XII; and Automated Visual Inspection
Country/TerritoryGermany
CityMunich
Period14/05/1316/05/13

Keywords

  • Bayesian integration
  • Classification
  • Human/car
  • Logistic regression
  • Statistical criterion
  • Video surveillance

Fingerprint

Dive into the research topics of 'Fast human/car classification methods in the computer vision tasks'. Together they form a unique fingerprint.

Cite this