基于自适应混合高斯模型的运动目标检测

研究视频监控系统中序列图像的运动目标检测问题。传统的目标检测方法无法克服背景图像变化、场景光线突变等问题。采用混合高斯分布对背景进行建模,并根据输入的当前帧图像的像素信息进行背景模型更新,能够准确地检测出运动目标。通过相关仿真实验,验证该方法具有一定的可靠性。

Objects Detection Approach Based on Adaptive Mixture Gaussian Model

This paper studies the detection of moving targets in sequence images in the video monitoring system. Traditional detection methods can not overcome problems such as changing background images and illusion mutation,and so on . This paper constructs background model with mixture Guassian distribution. The background model updating is applied for pixel information of the current input frames. So this method can detect the moving targets precisely. The experimental results verify the reliability of the method.