In practical applications

many video sequences have moving background

and then the extraction of video object becomes complicated. An algorithm is proposed in the paper to extract video object from dynamic scene based on motion estimation and the graph pyramid. Phase correlation is first used to obtain the motion vector with high efficiency and robustness

and to weaken the impacts of illumination in the video sequence. Then global motion estimation with parameter-model is used to find the final motion template. Finally

to extract the semantic video object

spatial segmentation using the graph pyramid is applied to the image region in the current motion template. Compared with some prevailing methods

in the case of extraction of moving object from video sequences of dynamic scene

our algorithm avoids precise background compensation and is very computationally efficient

while the extracted semantic object is of high precision. The experimental results show that both rigid and non-rigid moving objects in dynamic scene are well extracted by this algorithm.