In this paper, we propose a Bayesian approach to video object segmentation, which consists of two stages. In the first stage, we partition the video data into a set of 3D watershed volumes, where each watershed volume is a series of corresponding 2D image regions. These 2D image regions are obtained by applying to each image frame the marker-controlled watershed segmentation. In the second stage, we use a Markov random field to model the spatio-temporal relationship among the 3D watershed volume. Then, the desired video objects can be extracted by merging watershed volumes having similar motion characteristics within a Bayeysian framework. Our experiments have shown that the proposed method has great potential in extracting moving objects from a video sequence.