An online background subtraction algorithm using a contiguously weighted linear regression model

Y. Hu, K. Sirlantzis, G. Howells, N. Ragot, P. Rodriguez

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

6 Citas (Scopus)

Resumen

In this paper, we propose a fast online background subtraction algorithm detecting a contiguous foreground. The proposed algorithm consists of a background model and a foreground model. The background model is a regression based low rank model. It seeks a low rank background subspace and represents the background as the linear combination of the basis spanning the subspace. The foreground model promotes the contiguity in the foreground detection. It encourages the foreground to be detected as whole regions rather than separated pixels. We formulate the background and foreground model into a contiguously weighted linear regression problem. This problem can be solved efficiently and it achieves an online scheme. The experimental comparison with most recent algorithms on the benchmark dataset demonstrates the high effectiveness of the proposed algorithm.

Idioma originalInglés
Título de la publicación alojada2015 23rd European Signal Processing Conference, EUSIPCO 2015
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1845-1849
Número de páginas5
ISBN (versión digital)9780992862633
DOI
EstadoPublicada - 22 dic. 2015
Evento23rd European Signal Processing Conference, EUSIPCO 2015 - Nice, Francia
Duración: 31 ago. 20154 set. 2015

Serie de la publicación

Nombre2015 23rd European Signal Processing Conference, EUSIPCO 2015

Conferencia

Conferencia23rd European Signal Processing Conference, EUSIPCO 2015
País/TerritorioFrancia
CiudadNice
Período31/08/154/09/15

Huella

Profundice en los temas de investigación de 'An online background subtraction algorithm using a contiguously weighted linear regression model'. En conjunto forman una huella única.

Citar esto