An adaptive learning rate GMM for background extraction
DOI:
Author:
Affiliation:

Clc Number:

TP39

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    The rapidness and stability of background extraction from image sequences are incompatible, that is, when a conventionalCraussian mixture models (GMM)is used to rebuild the background, if the background regions of the scene are changed, theextracted background becomes bad until the transition is over. A novel adaptive method is presented to adjust the learningrate of GMM in a Hilbert space. The background extraction is treated as a process of approaching to a certain point in theHilbert space, so the real-time learning rate can be obtained by calculating the distance between the two adjacent extractedbackground images, and a judgment method of the stability of background is got too. Compared with conventional GMM,the method has both high rapidness and good stability at the same time, and it can adjust the learning rate online. Theexperiment shows that it is better than conventional GMM, especially in the transition process of background extraction.

    Reference
    Related
    Cited by
Get Citation

Zun-bing Sheng, Xian-yu Cui. An adaptive learning rate GMM for background extraction[J]. Optoelectronics Letters,2008,4(6):460-463

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:December 11,2007
  • Revised:
  • Adopted:
  • Online:
  • Published: