Directional Cross Diamond Search Algorithm for Fast Block Motion Estimation

In block-matching motion estimation (BMME), the search patterns have a significant impact on the algorithm’s performance, both the search speed and the search quality. The search pattern should be designed to fit the motion vector probability (MVP) distribution characteristics of the real-world sequences. In this paper, we build a directional model of MVP distribution to describe the directional-center-biased characteristic of the MVP distribution and the directional characteristics of the conditional MVP distribution more exactly based on the detailed statistical data of motion vectors of eighteen popular sequences. Three directional search patterns are firstly designed by utilizing the directional characteristics and they are the smallest search patterns among the popular ones. A new algorithm is proposed using the horizontal cross search pattern as the initial step and the horizontal/vertical diamond search pattern as the subsequent step for the fast BMME, which is called the directional cross diamond search (DCDS) algorithm. The DCDS algorithm can obtain the motion vector with fewer search points than CDS, DS or HEXBS while maintaining the similar or even better search quality. The gain on speedup of DCDS over CDS or DS can be up to 54.9%. The simulation results show that DCDS is efficient, effective and robust, and it can always give the faster search speed on different sequences than other fast block-matching algorithm in common use.