Parallel spiral search algorithm applied to integer motion estimation

An efficient VLSI architecture for fast motion estimation by hybridizing parallel spiral and adaptive threshold star diamond search algorithm‐based search algorithm in HEVC

“…2. The parallel spiral search approach 18 utilizes the spiral pattern for searching from the center to the surroundings and the adaptive threshold star diamond search algorithm (SDA) 19 consists of two phases adaptive threshold and star diamond algorithm.…”

“…The main contributions of this article are summarized below: Here, hybrid parallel spiral and adaptive threshold star diamond search algorithm (Hyb PS‐ATSDSA) is proposed for fast ME in HEVC. The parallel spiral search approach 18 utilizes the spiral pattern for searching from the center to the surroundings and the adaptive threshold star diamond search algorithm (SDA) 19 consists of two phases adaptive threshold and star diamond algorithm. To lower the computational complexities in the HEVC architecture, the parallel spiral search algorithm uses several blocks matching schemes, such as scaling the SAD in parallel, early termination, and L and P value selection. Here, adaptive threshold and star diamond approach is used to reduce the matching errors and removes the null blocks early from ME procedure and finally predicts the final motion of the image. Therefore, the speed is increases while using this hybrid algorithm. The proposed method is carried out in Xilinx; ISE 14.5 design suit; experimental outcomes are analyzed with the existing ME strategies in FPGA devices. Here, the efficiency of the proposed Hyb‐PS‐ATSDSA‐ME‐HEVC method is calculated as low power, low area, low delay, and the speed. Then the efficiency of the proposed Hyb‐PS‐ATSDSA‐ME‐HEVC is analyzed to the existing FSA‐ME‐HEVC, 20 TZSA‐ME‐HEVC, 21 hyb TZSA‐IME‐HEVC, 22 and IBMSA‐ME‐HEVC methods 23 …”