Skip to content

Fast Object Detection with Occlusions

by Yen-Yu Lin, Tyng-Luh Liu, Chiou-Shann Fuh
Methods ()
  • ISSN: 03029743

Abstract

We describe a new framework, based on boosting algorithms and cascade structures, to efficiently detect objects/faces with occlusions. While our approach is motivated by the work of Viola and Jones, several techniques have been developed for establishing a more general system, including (i) a robust boosting scheme, to select useful weak learners and to avoid overfitting; (ii) reinforcement training, to reduce false-positive rates via a more effective training procedure for boosted cascades; and (iii) cascading with evidence, to extend the system to handle occlusions, without compromising in detection speed. Experimental results on de- tecting faces under various situations are provided to demonstrate the performances of the proposed method.

Cite this document (BETA)

Readership Statistics

27 Readers on Mendeley
by Discipline
 
70% Computer Science
 
22% Engineering
 
4% Mathematics
by Academic Status
 
41% Student > Master
 
37% Student > Ph. D. Student
 
11% Researcher
by Country
 
7% Germany
 
4% Chile
 
4% Taiwan

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Sign up & Download

Already have an account? Sign in