作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (23): 205-207,. doi: 10.3969/j.issn.1000-3428.2008.23.073

• 人工智能及识别技术 • 上一篇    下一篇

基于像素分类的运动目标检测算法

徐以美1,郭宝龙1,张 晋2   

  1. (1. 西安电子科技大学机电工程学院ICIE研究所,西安 710071;2. 北方工业大学机电工程学院,北京 100041)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-12-05 发布日期:2008-12-05

Moving Objects Detection Algorithm Based on Pixel Classification

XU Yi-mei1, GUO Bao-long1, ZHANG Jin2   

  1. (1. ICIE Institute, School of Electromechanical Engineering, Xidian University, Xi’an 710071; 2. School of Electromechanical Engineering, North China University of Technology, Beijing 100041)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-12-05 Published:2008-12-05

摘要: 针对复杂环境下运动目标检测提出一种基于像素分类的运动目标检测算法。该算法通过亮度归一化对图像序列进行预处理,用以降低光照变化造成的误检,根据场景中不同像素点的特点,对图像进行分类处理,单模态类的像素用中值法进行背景建模,多模态类的像素用混合高斯模型建模。实验结果表明,该算法与传统的高斯建模法相比,减少了运算量,更易于应用在实时系统中。

关键词: 背景差分, 高斯混合模型, 中值法, 运动目标检测, 像素分类

Abstract: A novel algorithm for moving objects detection based on pixel classification is proposed. This algorithm preprocesses the images with illuminate standard in order to decline detection mistakes caused by illuminant changes. The pixels are classified by its characteristics into the single-model and the multi-model. The former uses median method for background modeling while the later uses GMM. The experiments show that this algorithm, compared with GMM, is computational efficient and can be used for real-time systems easily.

Key words: background subtraction, GMM, median method, moving objects detection, pixel classification

中图分类号: