基于粒子群优化法的Niblack电力设备红外图像分割-红外技术.PDFVIP

第40 卷 第 8 期 红 外 技 术 Vol.40 No.8 2018 年 8 月 Infrared Technology Aug. 2018 基于粒子群优化法的 Niblack 电力设备红外图像分割 李 鑫，崔昊杨，霍思佳，束 江，刘晨斐，李 亚，李高芳 （上海电力学院电子与信息工程学院，上海 200090 ） 摘要：针对电力设备红外图像分割效果受非均匀背景和噪声干扰等因素影响的问题，提出了一种基于 粒子群优化方法的Niblack 设备红外图像分割算法。采用类间方差作为粒子群算法的适应度函数，自 动搜寻Niblack 法中图像不重叠矩形邻域的最优分割阈值，并将其用于图像的二值化分割，从红外图 像中提取出设备的目标区域。实验结果表明：该分割算法与传统的 Otsu 等算法相比效率更高，且误 分率（ME ）减少了 14%～78%。鲁棒性分析表明，本算法对含较大噪声密度的红外图像分割性能优 于其他传统算法，从而有效提高了电力设备红外图像分割精度与效率。 关键词：红外图像分割；电力设备；Niblack 法；粒子群算法；鲁棒性分析 中图分类号：TN219 文献标识码：A 文章编号：1001-8891(2018)08-0780-06 Niblack’s Method for Infrared Image Segmentation of Electrical Equipment Improved by Particle Swarm Optimization LI Xin ，CUI Haoyang，HUO Sijia ，SU Jiang，LIU Chenfei ，LI Ya ，LI Gaofang (School of Electronics and Information Engineering,Shanghai University of Electric Power, Shanghai 200090, China) Abstract ：The infrared (IR) image segmentation effect of power equipment is affected by non-uniform backgrounds, noise interference, among others. To solve this problem, a method of Niblack segmentation algorithm based on particle swarm optimization for infrared images of power equipment is presented. An inter-class variance is adopted as the fitness function of the particle swarm optimization algorithm to automatically search the optimal segmentation threshold value from the non-overlapping rectangular sub-block in Niblack’s method. The device is extracted from the IR image target area. The experiment results indicate that the misclassification rate (ME) of the proposed method is reduce