Video Foreground Detection Based on Symmetric Alpha-Stable Mixture Models

Background subtraction (BS) is an efficient technique for detecting moving objects in video sequences. A simple BS process involves building a model of the background and extracting regions of the foreground (moving objects) with the assumptions that the camera remains stationary and there exist no movements in the background. However, these assumptions restrict the applicability of BS methods for real-time object detection in video. In this paper, we propose an extended cluster BS technique with symmetric alpha stable distributions. An iterative self-adaptive mechanism is presented that allows automated estimation of the model parameters using the log moment method. Comparative results over real video sequences from both indoor and outdoor environments, as well as with data from static and moving video cameras are performed, using SS mixture models. Our results demonstrate improvements of detection performance compared to a cluster BS method using a Gaussian mixture model and the meth...

• Type: Journal
• Year: 2010
• Where: TCSV
• Authors: Harish Bhaskar, Lyudmila Mihaylova, Alin Achim
• Keywords: Bs Method, Computational Biology, Mixture Model, TCSV 2010, Video Sequences