An object tracking method using modified galaxy-based search algorithm

作者：Sardari Faegheh; Moghaddam Mohsen Ebrahimi^*

来源：Swarm and Evolutionary Computation, 2016, 30: 27-38.

DOI：10.1016/j.swevo.2016.04.001

• Object tracking
• Galaxy-based search algorithm
• Particle filter
• Likelihood model

Object tracking is a dynamic optimization process based on the temporal information related to the previous frames. Proposing a method with higher precision in complex environments is a challenge for researchers in this field of study. In this paper, we have proposed an object tracking method based on a meta-heuristic approach. Although there are some meta-heuristic approaches in the literature, we have modified GbSA (galaxy based search algorithm) which is more precise than related works. The GbSA searches the state space by simulating the movement of the spiral galaxy to find the optimum object state. The proposed method searches each frame of video with particle filter and the MGSbA in a similar manner. It receives current frame and the temporal information that is related to previous frames as input and tries to find the optimum object state in each one. The experimental results show the efficiency of this algorithm in comparison with results of related methods.

• 出版日期2016-10