A Dynamic Cooperative Swarm Optimization Model for MRF-Based Early Vision Problem

Swarm optimization has been proved suitable to solve various combinatorial optimization problems. Markov random field (MRF) based MRF-based early vision problem has higher dimensions, more complicate structure of solution space, and dynamic constrain conditions. Based on a dynamic multi-colony ant scheme, this paper proposes a dynamic cooperative swarm optimization model to estimate the labels fields and minimize the MAP estimation in MRF-based early vision problem. Firstly, MRF-based early vision problems are divided into several sub-problems according to divide-and-conquer principle, and each colony optimizes one sub-problem independently. Then, a set of information exchange strategies are proposed for adaptive dynamic cooperation between neighboring colonies to implement the global optimization. Lastly, the proposed swarm optimization model is applied to solve stereo correspondence problem, and it can also solve the image segmentation problem. Experiments show this method can achieve good results.