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

被引：846
作者：
Heikkilä, M [1 ]
Pietikäinen, M [1 ]
机构：
[1] Univ Oulu, Machine Vis Grp, Dept Elect & Informat Engn, Oulu 90014, Finland
来源：
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2006年 / 28卷 / 04期
基金：
芬兰科学院;
关键词：
motion; texture; background subtraction; local binary pattern;
D O I：
10.1109/TPAMI.2006.68
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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.
引用
收藏
页码：657 / 662
页数：6
相关论文
共 50 条
12345