改进樽海鞘群算法增强电力巡检图像的研究  

Research on Image Enhancement of Power Patrol Inspection Based on Improved Slap Swarm Algorithm

作　　者：成贵学 郑晓楠 CHENG Gui-xue;ZHENG Xiao-nan(College of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学计算机科学与技术学院,上海200090

出　　处：《计算机仿真》2022年第6期373-379,共7页Computer Simulation

摘　　要：针对传统樽海鞘群算法处理图像问题时收敛速度慢和精度低的问题,提出引入高斯变异、自适应惯性权重和早熟判别机制的樽海鞘群算法,并将其有效地运用在电力巡检图像增强中。改进的樽海鞘群算法(Improved Salp Swarm Aalgorith, ISSA)增强了种群多样性,扩大了种群搜索范围,克服了算法陷入局部最优解的缺陷,稳定快速地收敛于全局最优解。为了验证算法的有效性,在5个标准函数上进行测试,与其它元启发式算法进行比较,同时在电力巡检图像上进行实验。结果表明,算法寻优效率提高,对比于其它图像增强方法,上述算法使图像增强效果得到有效提升,具有较强的实用性。In order to solve the problems of slow convergence speed and low accuracy of salp Swarm Algorithm in image processing, an improved salp swarm algorithm(ISSA) with gaussian mutation, adaptive inertia weight and precocious discrimination mechanism is proposed and effectively applied to image enhancement in the power inspection. The improved salp swarm algorithm can enhance the diversity of the population, expand the search range of population, overcome the defect that the algorithm falls into local optimal solution, and converge to the global optimal solution stably and quickly. In order to verify the effectiveness of the algorithm, it was tested on five standard functions and compared with other meta heuristic algorithms. At the same time, the experiments were carried out on power inspection images. The results show that the algorithm can effectively improve the image enhancement effect and the optimization efficiency of the algorithm, and has strong practicability.

关 键 词：樽海鞘群算法 图像增强 脉冲耦合神经网络 高斯变异 自适应惯性权重 早熟判别机制 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]