Extraction of the moving foreground object from a given video shot is an important task for spatiotemporal analysis and content representation in many computer vision and digital video processing applications. We propose an iterative framework based on energy minimization, for segmenting the prominent moving foreground object efficiently from moving camera video (MCV) shots. The solution obtained using graph-cut for figure-ground classification is enhanced using features extracted over a set of neighboring frames. This is used to iteratively update the foreground and background probability (tri-) maps and hence the graph weights. The segmentation results from neighboring frames are integrated as constraints to iteratively guide the energy minimization process, for an efficient solution. The proposed framework is automatic and does not require any human interaction (neither initialization nor refinement). Our method outperforms recent state-of-the-art moving object segmentation techniques on benchmark datasets with MCV shots. © 2014, Springer-Verlag London.