A Moving Object Detection Method Based on Sliding Window Gaussian Mixture Model

Zhou  Jian-Ying; Wu  Xiao-Pei; Zhang  Chao; Lv Zhao

doi:10.3724/SP.J.1146.2012.01449

Volume 35 Issue 7

Jul. 2013

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2013 > 35(7): 1650-1656

Zhou Jian-Ying, Wu Xiao-Pei, Zhang Chao, Lv Zhao . A Moving Object Detection Method Based on Sliding Window Gaussian Mixture Model[J]. Journal of Electronics & Information Technology, 2013, 35(7): 1650-1656. doi: 10.3724/SP.J.1146.2012.01449

Citation:

Zhou Jian-Ying, Wu Xiao-Pei, Zhang Chao, Lv Zhao . A Moving Object Detection Method Based on Sliding Window Gaussian Mixture Model[J]. Journal of Electronics & Information Technology, 2013, 35(7): 1650-1656. doi: 10.3724/SP.J.1146.2012.01449

Citation:

PDF( 605 KB)

A Moving Object Detection Method Based on Sliding Window Gaussian Mixture Model

doi: 10.3724/SP.J.1146.2012.01449

Received Date: 2012-11-12
Rev Recd Date: 2013-02-18
Publish Date: 2013-07-19

Abstract

Abstract

在复杂场景下，传统混合高斯模型能较好地检测出运动目标，但随着时间的推移，模型参数收敛缓慢且难以适应场景中真实背景的实时变化，从而导致运动目标的错误检测率增加。该文利用滑动窗技术的短时历史记忆特性，提出一种新颖的基于滑动窗的混合高斯模型运动目标检测方法，该方法弥补了传统混合高斯背景模型不能及时形成新背景的缺点，提高了运动检测的完整性，并进一步降低了算法对场景光照变化的敏感性。多场景下的对比实验结果表明，该方法能更准确、完整地检测出运动目标并具有更好的环境适应性。
- 运动目标检测,
- 滑动窗,
- 混合高斯模型,
- 背景模型