In this paper, we present an automatic video segmentation algorithm for object-based coding, based on a k-medians clustering algorithm and 2D binary model. Firstly, the k-medians algorithm is employed to partition an image into a set of homogeneous regions. Then, a 2D binary model of the moving object is set up, which, combined with temporal and spatial information, guides the extraction process of the video object planes from the video sequence. The performance of the segmentation algorithm is illustrated by simulations carried out on standard video sequences.