Tracking fast changing non-stationary distributions with a topologically adaptive neural network: Application to video tracking

Abstract : In this paper, an original method named GNG-T, extended from GNG-U algorithm by Fritzke is presented. The method performs continuously vector quantization over a distribution that changes over time. It deals with both sudden changes and continuous ones, and is thus suited for video tracking framework, where continuous tracking is required as well as fast adaptation to incoming and outgoing people. The central mechanism relies on the management of quantization resolution, that cope with stopping condition problems of usual Growing Neural Gas inspired methods. Application to video tracking is briefly presented.
Document type :
Conference papers
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal-supelec.archives-ouvertes.fr/hal-00250981
Contributor : Sébastien van Luchene <>
Submitted on : Tuesday, February 12, 2008 - 12:03:19 PM
Last modification on : Thursday, March 29, 2018 - 11:06:04 AM
Long-term archiving on : Monday, May 17, 2010 - 9:10:45 PM

File

es2007-89.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00250981, version 1

Collections

Citation

Georges Drumea, Hervé Frezza-Buet. Tracking fast changing non-stationary distributions with a topologically adaptive neural network: Application to video tracking. 15th European Symposium on Artificial Neural Networks (ESANN2007), Apr 2007, Bruges, Belgium. pp.43-48. ⟨hal-00250981⟩

Share

Metrics

Record views

158

Files downloads

78