Color Video Segmentation by Temporal Linking of Irregular Pyramids

C. Valencia, J.A. Rodríguez, C. Urdiales, and F. Sandoval (Spain)


Hierarchical segmentation, motion estimation, irregularpyramids


This paper presents a new spatiotemporal segmentation and motion estimation technique for color video sequences. It relies on building irregular pyramids over consecutive frames. The pyramids are built and pruned in a non iterative bottom-up way to split the image into homoge neous regions. After that, a hierarchical merging stage is performed and the resulting regions are easy to match be tween consecutive pyramids. Also, to overcome the prob lem derived from the presence of fast moving objects, a pre diction motion model is introduced. The main advantages of the proposed algorithm are that it is computationally fast and it preserves region connectivity.

Important Links:

Go Back