基于高斯混合背景模型运动检测的研究

Research of Detection of Moving Objects Based on Gaussian Mixture Background Model

研究了运动对象自动检测方法,针对传统的光流法、时间差法存在的不足,采用一种经典的背景模型提取运动对象,即高斯混合背景模型。对于模型参数的更新,摈弃计算量大的EM算法,采用一种拟合方法,使得算法的计算开销大为降低,提高了运算效率。通过在不同分环境多次实验,证明算法具有很好的鲁棒性、准确性。

A study about auto detection of moving objects is made. Because of the insufficiency of traditional methods of optical flow and time difference, a classical method of background difference is taken for detection of moving objects-the Gaussian mixture background model for detecting moving objects. The updating of the parameters of the model using an approximate method instead of the EM algorithm which would be costly, and it improves the efficiency of the operation. Experiments are done for many times and lots of conditions, which verify that the algorithm is good at robustness and accuracy.