Share Email Print
cover

Proceedings Paper

Optimization of background subtraction for image enhancement
Author(s): Larry Venetsky; Ross Boczar; Robert Lee-Own
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Analysis of foreground objects in scenery via image processing often involves a background subtraction process. This process aims to improve blob (connected component) content in the image. Quality blob content is often needed for defining regions of interest for object recognition and tracking. Three techniques are examined which optimize the background to be subtracted - genetic algorithm, an analytic solution based on convex optimization, and a related application of the CVX solver toolbox. These techniques are applied to a set of images and the results are compared. Additionally, a possible implementation architecture that uses multiple optimization techniques with subsequent arbitration to produce the best background subtraction is considered.

Paper Details

Date Published: 28 May 2013
PDF: 13 pages
Proc. SPIE 8751, Machine Intelligence and Bio-inspired Computation: Theory and Applications VII, 875102 (28 May 2013); doi: 10.1117/12.2014319
Show Author Affiliations
Larry Venetsky, Naval Air Engineering Ctr. (United States)
Ross Boczar, Naval Air Engineering Ctr. (United States)
Robert Lee-Own, Naval Air Engineering Ctr. (United States)


Published in SPIE Proceedings Vol. 8751:
Machine Intelligence and Bio-inspired Computation: Theory and Applications VII
Misty Blowers; Olga Mendoza-Schrock, Editor(s)

© SPIE. Terms of Use
Back to Top