中国邮电高校学报(英文) ›› 2015, Vol. 22 ›› Issue (3): 100-109.doi: 10.1016/S1005-8885(15)60658-6

• Others • 上一篇    下一篇

Neural network based method for background modeling and detecting moving objects

Bi Song, Han Cunwu, Sun Dehui   

  1. Beijing Key Laboratory of Fieldbus Technology and Automation, North China University of Technology
  • 收稿日期:2014-11-24 修回日期:2015-01-21 出版日期:2015-06-30 发布日期:2015-06-24
  • 通讯作者: Bi Song, E-mail: bisongo@163.com E-mail:bisongo@163.com
  • 基金资助:

Neural network based method for background modeling and detecting moving objects

Bi Song, Han Cunwu, Sun Dehui   

  1. Beijing Key Laboratory of Fieldbus Technology and Automation, North China University of Technology
  • Received:2014-11-24 Revised:2015-01-21 Online:2015-06-30 Published:2015-06-24
  • Contact: Bi Song, E-mail: bisongo@163.com E-mail:bisongo@163.com

摘要: This paper proposes a novel method, primarily based on the fuzzy adaptive resonance theory (ART) neural network with forgetting procedure, for moving object detection and background modeling in natural scenes. With the ability, inheriting from the ART neural network, of extracting patterns from arbitrary sequences, the background model based on the proposed method can learn new scenes quickly and accurately. To guarantee that a long-life model can derived from the proposed mothed, a forgetting procedure is employed to find the neuron that needs to be discarded and reconstructed, and the finding procedure is based on a neural network which can find the extreme value quickly. The results of a suite of quantitative and qualitative experiments conducted verify that for processes of modeling background and detecting moving objects our method is more effective than five other proven methods with which it is compared.

关键词: background modeling, forgetting procedure, fuzzy adaptive resonance theory, moving object detection

Abstract: This paper proposes a novel method, primarily based on the fuzzy adaptive resonance theory (ART) neural network with forgetting procedure, for moving object detection and background modeling in natural scenes. With the ability, inheriting from the ART neural network, of extracting patterns from arbitrary sequences, the background model based on the proposed method can learn new scenes quickly and accurately. To guarantee that a long-life model can derived from the proposed mothed, a forgetting procedure is employed to find the neuron that needs to be discarded and reconstructed, and the finding procedure is based on a neural network which can find the extreme value quickly. The results of a suite of quantitative and qualitative experiments conducted verify that for processes of modeling background and detecting moving objects our method is more effective than five other proven methods with which it is compared.

Key words: background modeling, forgetting procedure, fuzzy adaptive resonance theory, moving object detection