Efficient hierarchical method for background subtraction
Journal
Pattern Recognition
Journal Volume
40
Journal Issue
10
Pages
2706-2715
Date Issued
2007
Date
2007
Author(s)
Abstract
Detecting moving objects by using an adaptive background model is a critical component for many vision-based applications. Most background models were maintained in pixel-based forms, while some approaches began to study block-based representations which are more robust to non-stationary backgrounds. In this paper, we propose a method that combines pixel-based and block-based approaches into a single framework. We show that efficient hierarchical backgrounds can be built by considering that these two approaches are complementary to each other. In addition, a novel descriptor is proposed for block-based background modeling in the coarse level of the hierarchy. Quantitative evaluations show that the proposed hierarchical method can provide better results than existing single-level approaches. © 2006 Pattern Recognition Society.
Subjects
Background subtraction; Contrast histogram; Hierarchical background modeling; Non-stationary background; Object detection; Video surveillance
Other Subjects
Block codes; Mathematical models; Object recognition; Pixels; Tracking (position); Background subtraction; Contrast histograms; Hierarchical background modeling; Non-stationary background; Object detection; Video surveillance; Hierarchical systems
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
23.pdf
Size
830.28 KB
Format
Adobe PDF
Checksum
(MD5):a2bcc7a08e9a9704e5d8f073c8b25515