Incremental nonnegative matrix factorization for background modeling in surveillance video


Bucak S. S., Guensel B., Guersoy O.

IEEE 15th Signal Processing and Communications Applications Conference, Eskişehir, Türkiye, 11 - 13 Haziran 2007, ss.838-841 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Eskişehir
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.838-841
  • İstanbul Teknik Üniversitesi Adresli: Hayır

Özet

In this paper, we propose an Incremental Non-negative Matrix Factorization (INMF) method which can be effectively used for dynamic background modeling in surveillance applications. The proposed factorization method is derived from Non-negative Matrix Factorization (NW), and models the dynamic content of the video by controlling contribution of the subsequent observations to the existing model adaptively. Unlike the batch nature of NMF, INMF is an on-line content representation scheme which is capable of extracting moving foreground objects. Test results are reported in order to compare background modeling performances of INMF, NMF and Incremental Principal Components Analysis (IPCA). It is concluded that INMF outperforms both NMF and IPCA and its robustness to illumination changes makes it as a powerful representation tool in surveillance applications.