One of the most challenging problems in computer vision is the ability of understanding video sequences to automatically detect and recognize moving objects. This work presents the development and the inexpensive implementation of an efficient algorithm based on the background subtraction technique adequate for low-cost embedded video surveillance systems. The proposed algorithm exploits the combination of few historical frames with the use of two channels based on the invariant color H and the grayscale level information to achieve high performance and good quality also within the Raspberry-Pi platform. Experimental results show that the implemented algorithm is robust against noises typically occurring in both indoor and outdoor environments.

Embedded surveillance system using background subtraction and Raspberry Pi

COCORULLO, Giuseppe;CORSONELLO, Pasquale;Frustaci F;PERRI, Stefania
2015-01-01

Abstract

One of the most challenging problems in computer vision is the ability of understanding video sequences to automatically detect and recognize moving objects. This work presents the development and the inexpensive implementation of an efficient algorithm based on the background subtraction technique adequate for low-cost embedded video surveillance systems. The proposed algorithm exploits the combination of few historical frames with the use of two channels based on the invariant color H and the grayscale level information to achieve high performance and good quality also within the Raspberry-Pi platform. Experimental results show that the implemented algorithm is robust against noises typically occurring in both indoor and outdoor environments.
2015
computer vision; embedded systems; Image processing
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/20.500.11770/164897
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 4
social impact