A texture-based method for modeling the background and detecting moving objects

Author

Heikkilä, Marko ; Pietikäinen, Matti

Author_Institution

Dept. of Electr. & Inf. Eng., Oulu Univ., Finland

Volume

28

Issue

4

fYear

2006

fDate

4/1/2006 12:00:00 AM

Firstpage

657

Lastpage

662

Abstract

This paper presents a novel and efficient texture-based method for modeling the background and detecting moving objects from a video sequence. Each pixel is modeled as a group of adaptive local binary pattern histograms that are calculated over a circular region around the pixel. The approach provides us with many advantages compared to the state-of-the-art. Experimental results clearly justify our model.

Keywords

image sequences; image texture; motion estimation; object detection; video signal processing; adaptive local binary pattern histograms; background modeling; moving object detection; texture-based method; video sequence; Cameras; Gaussian distribution; Histograms; Jitter; Layout; Lighting; Object detection; Statistics; Vegetation; Video sequences; Motion; background subtraction; local binary pattern.; texture; Algorithms; Artificial Intelligence; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Models, Biological; Movement; Pattern Recognition, Automated; Photography; Reproducibility of Results; Sensitivity and Specificity; Subtraction Technique; Video Recording;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/TPAMI.2006.68

Filename

1597122