基于混沌粒子群优化算法的电力线检测  

Detection of Power Lines Based on Chaotic Particle Swarm Optimization

作　　者：徐胜舟[1] 胡怀飞[2] 

机构地区：[1]中南民族大学计算机科学学院,武汉430074 [2]中南民族大学生物医学工程学院,武汉430074

出　　处：《中南民族大学学报（自然科学版）》2014年第3期100-104,共5页Journal of South-Central University for Nationalities：Natural Science Edition

基　　金：国家自然科学基金资助项目(61302192);中南民族大学自然科学基金资助项目(CZQ11027)

摘　　要：提出了一种基于混沌粒子群的直线检测算法,并将其应用于电力线自动检测.首先利用Sobel算子对图像进行边缘检测得到候选边缘点;然后从中随机选择若干点对作为初始粒子,每个粒子代表一条直线,并以与其共线的候选边缘点的数目作为其适应度值,迭代过程中用混沌粒子替代最差粒子;最后选择适应度值最高的粒子作为所要检测的直线.实验结果表明:与Hough变换等算法相比,该算法可以有效减少重复计算,提高检测效率和准确率.A line detection algorithm based on Chaotic Particle Swarm Optimization （ CPSO ） has been proposed and applied to the detection of power lines .First, the candidates for edge points are detected by Sobel operator .Then, a number of pairs of points are selected from the candidates for edge points as the initial particles .Each particle represents a line, and its fitness value is the number of candidate edge points collinear the line .In the iterative process , the worst particle is replaced with a new chaotic particle .Finally, the particle with the highest fitness is chose to be the line to be detected.The algorithm is applied to the power line detection , and the experimental results verify its effectiveness . Comparing with other algorithms such as Hough transform , the algorithm proposed in this paper can effectively reduce the problem of double counting and improve the accuracy and efficiency .

关 键 词：粒子群优化算法 适应度 检测 HOUGH变换 电力线 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]