一种基于混沌粒子群的泥沙颗粒图像优化算法

RESEARCH ON SEDIMENT PARTICLE IMAGE OPTIMIZATION ALGORITHM BASED ON CHAOS PARTICLE SWARM OPTIMIZATION

针对泥沙颗粒图像与其它领域的颗粒图像的类同性,利用图像处理技术计算泥沙颗粒,提出了一种基于混沌粒子群的泥沙颗粒图像优化算法。该算法在运行的初期为了避免收敛早熟,增强了群体的多样性;通过设定的特定格式迭代产生混沌序列,有效的避免多样性的下降和早熟收敛的产生。在运行的中后期,能够在全局的最优区域进行更加精细的搜索,找到全局最优解的速度更快。实验结果表明,算法较好地解决了河流复杂泥沙颗粒图像的优化问题。

According to the similarity of the sediment particle image and its other fields, image processing technology is used to calculate the sediment particles. We proposed the sediment particle image optimization algorithm which is based on chaos particle swarm optimization. We also use the search capability of particle swarm optimization and the ergodic disturbance of chaos in order to enhance the ability to jump out of local optima and accelerate the algorithm convergence rate. Enhanced population diversity is used to avoid premature convergence in the early iteration. Chaotic sequence generated by a set specific format iterative is used to effectively avoid the decrease of diversity and premature convergence. In the late iteration, more precise search can be applied at the global optimal region and it is much faster to find the global optima solution. The experiment and analysis shows that that this algorithm is a good way to solve the river sediment complex optimization problems. The chaos particle swarm river sediment optimization algorithm is an important means of detection to identify the content of the river sediment in the image.