基于方向场的输电线路间隔棒匹配定位算法  

Spacer Matching and Localization Algorithm for Transmission Line Video Images Based on Directional Field

作　　者：孙凤杰[1] 赵孟丹[1] 刘威[1] 范杰清[1] 

机构地区：[1]华北电力大学电气与电子工程学院,北京市昌平区102206

出　　处：《中国电机工程学报》2014年第1期206-213,共8页Proceedings of the CSEE

摘　　要：输电线路视频图像中的间隔棒是获得导线状态信息的重要元素。为了实现对输电线路图像中间隔棒的快速、准确定位,提出了一种基于梯度方向场优化的快速模板匹配算法。该算法针对传统的相关匹配算法运算量大、直方图匹配结果不准确的缺陷,提出了直方图和归一化相关匹配结合的复合匹配方法。结合输电线路图像中导线方向明确的特点,应用梯度方向场对图像中输电线路目标区域进行锁定,减少模板的搜索空间。实验结果表明,该算法具有较强的鲁棒性,在保证匹配精度的同时,大幅提高了匹配速度,能够满足远程视频监控系统对电力设备图像识别实时性和准确性的需求,可为准确判定输电线路状态信息提供依据。The spacer is an important element to obtain the state of transmission lines. To accurately and quickly locate the spacer in transmission line images, this paper proposed a fast template matching algorithm based on the optimization of the gradient directional field. Since the traditional correlation matching algorithm is complex and the result of the histogram matching algorithm is inaccurate, a combination method of histogram and normalized correlation matching algorithm was put forward. In order to reduce the search space of the template, combined with the characteristics of transmission lines＇ specific directional information, gradient directional field was applied to lock the target area of transmission line images. Experimental results show that this algorithm has strong robustness and matching precision. At the same time, it both greatly improves matching speed, which can meet the demands of real-time and accuracy of the remote video monitoring system for power equipment, and provides references for accurate determination of transmission lines＇ state information.

关 键 词：间隔棒 方向场 模板匹配 平方梯度 区域定位 

分 类 号：TM76[电气工程—电力系统及自动化]