基于相关滤波的绝缘子跟踪与测距算法  

Tracing and Ranging Algorithm for Insulators Based on Correlation Filtering

作　　者：刘永姣 闫斌[1] 叶润[1] 

机构地区：[1]电子科技大学自动化工程学院,成都611731

出　　处：《科学技术与工程》2017年第26期262-267,共6页Science Technology and Engineering

摘　　要：针对旋翼无人机进行输电线路巡检的应用场景,通过基于相关滤波的跟踪算法,实现绝缘子的跟踪并适应尺度的变化。在滤波器的训练过程引入核函数,构建出更加鲁棒的滤波模板。通过gabor滤波器,在HSV颜色空间提取绝缘子的纹理特征。采用两个并行的相关滤波器,分别用于位置和尺度的定位。在此基础上,通过最大类间方差法,对图像中绝缘子进行分割,按照相机成像原理,计算绝缘子与无人机之间的相对距离。算法能够实现绝缘子的实时跟踪并适应尺度变化,以及计算无人机与绝缘子之间的相对距离,为无人机智能化巡线提供技术支持。Aiming at the application scenes of rotor unmanned aerial vehicle for transmission line inspection,the tracking algorithm based on correlation filtering is adopted to achieve the tracking of insulators and adaptation of changes of the scale. The kernel function is introduced in the training process of the filter to construct a more robust filter template. The texture features of insulators are extracted in HSV color space by gabor filter. Two parallel correlation filters are used respectively for the positioning of location and size. On this basis,the maximum interclass variance method is used to segment the insulators in the image and calculate the distance between insulators and the unmanned aerial vehicle according to the principle of camera imaging. This algorithm can realize the multi-scale tracking of insulators and calculate the relative position information between UAV and insulators,which will provide technical support for the intelligent inspection by unmanned aerial vehicles.

关 键 词：绝缘子 相关滤波 纹理特征 跟踪 测距 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]