Object kinematic model: A novel approach of adaptive background mixture models for video segmentation
Jin Shou Yu, Xuan Wu Zhou, Feng Qian · 2010
In the field of video surveillance, adaptive Gaussian mixture model (GMM) is widely used as the background-pixel dynamic modeling approach. GMM produced each pixel Gaussian distribution corresponds to the respective, but this ignores the impact of the movement of the object itself. The ideas of object kinematic model is presented to guide the number of distribution in the process of iterative, which can speed up the process of clustering, and the results indicate that this method can improve the efficiency and stability of background modeling.