Idioma:

A dynamic conditional random field model for foreground and shadow segmentation

Wang, Yang ; Loe, Kia-Fock ; Wu, Jian-Kang

IEEE transactions on pattern analysis and machine intelligence, 2006-02, Vol.28 (2), p.279-289 [Periódico revisado por pares]

Los Alamitos, CA: IEEE

Texto completo disponível

Citações Citado por

Enviar para

Título:
A dynamic conditional random field model for foreground and shadow segmentation
Autor: Wang, Yang ; Loe, Kia-Fock ; Wu, Jian-Kang
Assuntos: Algorithms ; Applied sciences ; Approximation ; Artificial Intelligence ; Colorimetry - methods ; Computer science; control theory; systems ; Computer Simulation ; dynamic models ; Dynamics ; Exact sciences and technology ; Filtering ; foreground segmentation ; Gaussian processes ; Hidden Markov models ; History ; Image edge detection ; Image Enhancement - methods ; Image Interpretation, Computer-Assisted - methods ; Image segmentation ; Index Terms- Conditional random fields ; Indoor ; Information Storage and Retrieval - methods ; Layout ; Lighting ; Models, Biological ; Models, Statistical ; Nonlinear Dynamics ; Object detection ; Pattern analysis ; Pattern Recognition, Automated - methods ; Pattern recognition. Digital image processing. Computational geometry ; Segmentation ; shadow detection ; Shadows ; Surveillance ; Video sequences
É parte de: IEEE transactions on pattern analysis and machine intelligence, 2006-02, Vol.28 (2), p.279-289
Notas: ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
Descrição: This paper proposes a dynamic conditional random field (DCRF) model for foreground object and moving shadow segmentation in indoor video scenes. Given an image sequence, temporal dependencies of consecutive segmentation fields and spatial dependencies within each segmentation field are unified by a dynamic probabilistic framework based on the conditional random field (CRF). An efficient approximate filtering algorithm is derived for the DCRF model to recursively estimate the segmentation field from the history of observed images. The foreground and shadow segmentation method integrates both intensity and gradient features. Moreover, models of background, shadow, and gradient information are updated adaptively for nonstationary background processes. Experimental results show that the proposed approach can accurately detect moving objects and their cast shadows even in monocular grayscale video sequences.
Editor: Los Alamitos, CA: IEEE
Idioma: Inglês

Links

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

A dynamic conditional random field model for foreground and shadow segmentation

Wang, Yang ; Loe, Kia-Fock ; Wu, Jian-Kang

Los Alamitos, CA: IEEE

Buscando em bases de dados remotas. Favor aguardar.