An improved block matching algorithm for motion estimation in video sequences and application in robotics

Abstract

Block Matching is one of the most efficient techniques for motion estimation for video sequences. Metaheuristic algorithms have been used effectively for motion estimation. In this paper, we propose two hybrid algorithms: Artificial Bee Colony with Differential Evolution and Harmony Search with Differential Evolution based motion estimation algorithms. Extensive experiments are conducted using four standard video sequences. The video sequences utilized for experimentation have all essential features such as different formats, resolutions and number of frames which are generally required in input video sequences. We compare the performance of the proposed algorithms with other algorithms considering various parameters such as Structural Similarity, Peak Signal to Noise Ratio, Average Number of Search Points etc. The comparative results demonstrate that the proposed algorithms outperformed other algorithms.