Detail publikace

Visual Surveillance Metadata Management

CHMELAŘ, P. ZENDULKA, J.

Originální název

Visual Surveillance Metadata Management

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

The paper deals with a solution for visual surveillance metadata management. Data coming from many cameras is annotated using computer vision units to produce metadata representing moving objects in their states. It is assumed that the data is often uncertain, noisy and some states are missing. The solution consists of the following three layers: (a) data cleaning layer - improves quality of the data by smoothing it and by filling in missing states in short sequences referred to as tracks that represent a composite state of a moving object in a spatiotemporal subspace followed by one camera. (b) Data integration layer - assigns a global identity to tracks that represent the same object. (c) Persistence layer - manages the metadata in a database so that it can be used for online identification and offline querying, analyzing and mining. A Kalman filter technique is used to solve (a) and a classification based on the moving object's state and its visual properties is used in (b). An object model for layer (c) is presented too.

Klíčová slova

Visual surveillance, metadata management, cameras, vision units, moving objects, data cleaning, integration, persistence, Kalman filter, classification, object model.

Autoři

CHMELAŘ, P.; ZENDULKA, J.

Rok RIV

2007

Vydáno

2. 9. 2007

Nakladatel

IEEE Computer Society Press

Místo

Regensburg

ISBN

978-0-7695-2932-5

Kniha

Eighteenth International Workshop on Database and Expert Systems Applications

Edice

IEEE CPS

Strany od

79

Strany do

83

Strany počet

5

BibTex

@inproceedings{BUT28830,
  author="Petr {Chmelař} and Jaroslav {Zendulka}",
  title="Visual Surveillance Metadata Management",
  booktitle="Eighteenth International Workshop on Database and Expert Systems Applications",
  year="2007",
  series="IEEE CPS",
  pages="79--83",
  publisher="IEEE Computer Society Press",
  address="Regensburg",
  isbn="978-0-7695-2932-5"
}