基于混合高斯模型的运动目标检测改进算法

Improved Moving Object Detection Algorithm Based on Gaussian Mixture Model

针对传统混合高斯模型法的不足,提出一种基于混合高斯模型的运动目标检测改进算法。首先对模型的参数更新机制进行了改进,不同阶段采用不同的更新率,并选择性地更新背景模型;其次,将改进后的混合高斯模型法与和帧差法结合,进行两次与运算和一次形态学膨胀处理,得到最后的运动目标。实验结果表明,该方法能够有效地消除复杂环境中的噪声,并对阴影有一定的抑制作用,提高了运动目标检测的准确性。

An improved algorithm for moving objects detection based on Gaussian mixture model is proposed to make up the deficiencies of original method. Firstly, model updating mechanism is improved by using different learning rate in different period and updating the background model selectively. Secondly, improved Gaussian mixture model and frames substraction are combined by using twice and operation and once morphological dilation. Finally, the moving objects are got after the above-mentioned process. The experimental results indicate that the proposed method can effectively eliminate noise and shadow in a complex environment and improve the accuracy of moving objects detection.