Image Segmentation Algorithm Research for Sport Graphics Based on Multi-Layer Background Subtraction

Autor:	Zhan Ping Li, Ming Jing Lu
Rok vydání:	2013
Předmět:	Background subtraction Pixel Computer science Local binary patterns business.industry Scale-space segmentation Image processing General Medicine Image segmentation RGB color space Computer Science::Computer Vision and Pattern Recognition Segmentation Computer vision Artificial intelligence business
Zdroj:	Applied Mechanics and Materials. 339:265-268
ISSN:	1662-7482
DOI:	10.4028/www.scientific.net/amm.339.265
Popis:	Segmentation of motion in an image sequence is one of the most challenging problems in image processing, while at the same time one that finds numerous applications. In this paper, we propose a robust multi-layer background subtraction technique which takes advantages of local texture features represented by local binary patterns (LBP) and photometric invariant color measurements in RGB color space. Due to the use of a simple layer-based strategy, the approach can model moving background pixels with quasiperiodic flickering as well as background scenes which may vary over time due to the addition and removal of long-time stationary objects. The use of a cross-bilateral filter allows to implicitly smooth detection results over regions of similar intensity and preserve object boundaries.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::8d542c75d04156187566a2b4cfe8cf6e https://doi.org/10.4028/www.scientific.net/amm.339.265 Zobrazit plný text záznamu