3-1 0 Adaptive Background Estimation for Object Tracking

Adaptive Background Model Tracking people has received considerable attention by computer vision researchers. Interest is motivated by the broad range of potential applications such as per- sonal identification, human-machine interaction, and au- tomated surveillance. We previously proposed a method for extracting moving region by subtraction from back- ground images. Background images were estimated by using UD factorized Kalman Filter. In order to use a Kalman Filter, good initial parameters are needed for es- timation and were manually given in the previous work. In this paper we propose an improved method for esti- mation of background image and for automatic parame- ter initialization. We also show experimental results us- ing real images to test the performance of our proposed method.