Publication detail

A methods for recognition and separation human body

ŠMIRG, O. SMÉKAL, Z. ČÍKA, P. MÍČA, I.

Original Title

A methods for recognition and separation human body

English Title

A methods for recognition and separation human body

Type

journal article - other

Language

en

Original Abstract

This article discuss about separation moving objects from video scene by Mixture of Gaussian method. The object recognition can be executed using Active Shape Models. We show several practical examples where we have built such models and used them to partially occluded objects, which are in the environment with noise and local moving objects. The article compare Mixture of Gaussian and Running Gaussian Average methods.

English abstract

This article discuss about separation moving objects from video scene by Mixture of Gaussian method. The object recognition can be executed using Active Shape Models. We show several practical examples where we have built such models and used them to partially occluded objects, which are in the environment with noise and local moving objects. The article compare Mixture of Gaussian and Running Gaussian Average methods.

Keywords

ASM, Mixture of Gaussians, Segmentation, Human recognition

RIV year

2010

Released

17.11.2010

Pages from

1

Pages to

6

Pages count

6

BibTex 


@article{BUT50532,
  author="Ondřej {Šmirg} and Zdeněk {Smékal} and Petr {Číka} and Ivan {Míča}",
  title="A methods for recognition and separation human body",
  annote="This article discuss about separation moving objects from video scene by Mixture of Gaussian method. The object recognition can be executed using Active Shape
Models. We show several practical examples where we have built such models and used them to partially occluded objects, which are in the environment with noise and local moving
objects. The article compare Mixture of Gaussian and
Running Gaussian Average methods.",
  chapter="50532",
  journal="Elektrorevue - Internetový časopis (http://www.elektrorevue.cz)",
  number="11",
  volume="2010",
  year="2010",
  month="november",
  pages="1--6",
  type="journal article - other"
}