A real time 1080P 30FPS Gaussian Mixture Modeling design for background subtraction and object extraction

Autor:	Tian-Sheuan Chang, Shuo-Wen Hsu
Rok vydání:	2014
Předmět:	Background subtraction business.industry Computer science Gaussian Feature extraction Pattern recognition Mixture model Object detection symbols.namesake symbols Algorithm design Artificial intelligence business Connected-component labeling Gaussian process Algorithm
Zdroj:	ICCE-TW
DOI:	10.1109/icce-tw.2014.6904050
Popis:	The Gaussian Mixture Modeling (GMM) algorithm with connected component labeling as object extraction provide robust background subtraction but suffer from complexity, and large buffer or high bandwidth due to the frame level operations. For real time application needs, this paper proposed a block based GMM design for background subtraction with message passing between blocks to avoid performance drop. The corresponding parallel hardware design can reach real time 1080P@30fps and cost 164.82K gate-counts at 125MHz with 90nm process.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::3bede960ee38ee6a6f53265f3b54a5d2 https://doi.org/10.1109/icce-tw.2014.6904050 Zobrazit plný text záznamu