Cascaded change detection for foreground segmentation

• Type: Article in International Conference Proceedings Book
• Date: 2007

Authors

Teixeira, LF (Author) Other; Corte Real, L (Author) FEUP

Conference proceedings International

Title: 2007 IEEE Workshop on Motion and Video Computing, WMVC 2007

2007 IEEE Workshop on Motion and Video Computing, WMVC 2007

Austin, TX, 23 February 2007 through 24 February 2007

Indexing

ISI Web of Knowledge

Scopus - 2 Citations

Scientific classification

CORDIS: Technological sciences > Technology > Computer technology > Image processing

Other information

Authenticus ID: P-007-J4G

DOI: 10.1109/wmvc.2007.11

Abstract (EN): The extraction of relevant objects (foreground) from a background is an important first step in many applications. We propose a technique that tackles this problem using a cascade of change detection tests, including noise-induced, illumination variation and structural changes. An objective comparison of pixel-wise modelling methods is first presented. Given its best relation performance/complexity, the mixture of Gaussians was chosen to be used in the proposed method to detect structural changes. Experimental results show that the cascade technique consistently outperforms the commonly used mixture of Gaussians, without additional post-processing and without the expense of processing overheads. ©2007 IEEE.

Language: English

Type (Professor's evaluation): Scientific