1 April 2008 Video background replacement using a genetic algorithm
Author Affiliations +
Abstract
Recent statistical methods of video background replacement are robust enough to operate in dynamic environments, but generally require very large computational resources and still have difficulty in clear segmentation of objects. We use a simpler running-average method to model a changing background, and a single global threshold vector, optimized by a genetic algorithm, instead of pixel-by-pixel thresholds. A fitness function is trained to evaluate segmentations by penalizing incorrectly recognized regions. Experimental results on real images show that our new approach outperforms an existing method based on a mixture of Gaussians.
© (2008) Society of Photo-Optical Instrumentation Engineers (SPIE)
Yangmi Lim, Yangmi Lim, Jinwan Park, Jinwan Park, } "Video background replacement using a genetic algorithm," Optical Engineering 47(4), 047402 (1 April 2008). https://doi.org/10.1117/1.2909664 . Submission:
JOURNAL ARTICLE
11 PAGES


SHARE
Back to Top