This paper presents a new method for background subtraction which takes advantages of using the color invariants combined with gray color. The proposed method works robustly reducing misclassified foreground objects. Gaussian mixtures are exploited for each pixel through two channels: the color invariants, which are derived from a physical model, and the gray colors obtained as a descriptor of the image. The background models update is performed using a random process selected considering that in many practical situations it is not necessary to update each background pixel model for each new frame. The novel algorithm has been compared to three state-of-the-art methods. Experimental results demonstrate the proposed method achieves a higher robustness, is less sensitive to noise and increases the number of pixel correctly classified as foreground for both indoor and outdoor video sequences.

A novel background subtraction method based on color invariants and grayscale levels

COCORULLO, Giuseppe;CORSONELLO, Pasquale;Frustaci F;PERRI, Stefania
2014-01-01

Abstract

This paper presents a new method for background subtraction which takes advantages of using the color invariants combined with gray color. The proposed method works robustly reducing misclassified foreground objects. Gaussian mixtures are exploited for each pixel through two channels: the color invariants, which are derived from a physical model, and the gray colors obtained as a descriptor of the image. The background models update is performed using a random process selected considering that in many practical situations it is not necessary to update each background pixel model for each new frame. The novel algorithm has been compared to three state-of-the-art methods. Experimental results demonstrate the proposed method achieves a higher robustness, is less sensitive to noise and increases the number of pixel correctly classified as foreground for both indoor and outdoor video sequences.
2014
978-1-4799-3530-7
background subtraction method; video signal processing; Video sequences
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/169139
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? ND
social impact