Fast Algorithm for Video Tracking Based on Adaptive Hybrid Difference
Han Pang Huang · 2008
Background modeling is an important technique for video tracking.Recently,there have been two popular methods of Background modeling:statistical model and image difference.However,the computational effort of model is too large,and the method cannot be used to analyze fast-moving rigid objects.Image difference easily causes shadow of the overlapped objects so that the shape of tracking objects cannot be clear.Furthermore,a manual threshold parameter is necessary to image difference.Adaptive hybrid difference(AHD) algorithm is proposed as an improvement of the methods.AHD algorithm uses a hybrid difference strategy to optimize the image partition and runs with an adaptive threshold setting based on Gaussian distribution.The experimental results indicate that AHD algorithm performs better and more steadily than the popular methods in the background modeling of fast-moving rigid objects.