1 基于全变分模型的输电导线图像去噪 - 中国图象图形学报.doc

中图法分类号: TP911.73 文献标识码:A 文章编号:1006-8961(年) - 文章索引信息： 输电导线图像目标识别方法研究 孙凤杰，杨镇澴，李媛媛，范杰清 (华北电力大学电气与电子工程学院,北京市,102206) 摘 要 ：为了准确识别出背景复杂、对比度低时的输电导线目标，在对图像进行全变分模型去噪的基础上，采用本文提出的一种基于模拟退火微粒群算法的二维最大类间方差法进行图像分割，然后采用改进的Freeman链码表示法进行输电导线目标提取，并应用基于最小二乘法的直线拟合法复原输电导线的基本骨架中的缺失部分。实验结果表明：基于模拟退火微粒群算法的二维最大类间方差法具有较好的分割效果，且在最佳分割阈值的有哪些信誉好的足球投注网站中有着较好的收敛性和计算速度；基于改进的Freeman链码表示法的输电导线提取算法可以很好地滤除背景并将输电导线完整地提取出来。 关键词 ： 输电导线；图像去噪；图像分割；直线拟合 Study on the methods of transmission line target recognition SUN Feng-jie，YANG Zhen-huan，LI Yuan-yuan，FAN Jie-qing (School of Electrical and Electronic Engineering, North China Electric Power University,Beijing,102206) Abstract： In order to identify transmission lines accurately from the low-contrast images with complex background, this paper applies the total variation denoising model firstly. And a two-dimension OTSU based on the Simulated Annealing and Particle Swarm Optimization Algorithm is proposed and used for image segmenting. Besides, the traditional Freeman Chain Code Representation Method is improved to extract the transmission line target, and a line fitting method based on the Least Square Method is used to recover missing parts of the basic skeleton of transmission lines. The experimental results indicate that the two-dimension OTSU based on the Simulated Annealing and Particle Swarm Optimization Algorithm has better segmentation effect with better convergence and computing speed in the search of the best segmentation threshold. The transmission lines extraction algorithm based on the improved traditional Freeman Chain Code Representation Method can remove the complex image background well and extract transmission lines completely. Key words： transmission lines; image denoising; image segmentation; line fitting 0 引 言 高压输电线路所处的地理环境、气候条件比较[1]。因此，研究输电线路的监测、预警技术，帮助电力企业预防和减少事故的发生是十分必要的。 早期的输电线路监测主要依靠人工巡线，受地形环境、天气状况等因素的影响较大，存在效率低、工作量大、复巡周期长等缺点[2]。随着电网建设和通信技术的不断发展，国内外先后研制、开发出了多种输电线路远程监测装置[3]。现有监测技术可大致分为两种：一种是基于数字图像处理的方法，另一种是以输电线路状态方程为基础理论的方法。由于后者需要依赖各种