基于色彩模型和纹理特征的输电线路绝缘子串航拍图像识别

Transmission line aerial image recognition of insulator strings based oncolor model and texture features

随着智能电网的建设,电网公司逐渐采用无人机(UAV)代替人工去巡视输电线路。提出一种对UAV拍摄到的输电线路绝缘子串航拍图像进行处理的方法。首先,利用色彩模型中RGB各分量阈值和范围分割出目标和背景区域;然后,用数学形态学和不重叠窗口纹理特征的方法粗略标记目标区域;最后,生成最小外接水平矩形框,并对所有最小外接水平矩形框内的图案进行纹理特征识别,定位出绝缘子串航拍图像的最小水平矩形区域。该文用2幅图像进行算法验证,并与文献算法进行对比,结果显示该文算法能更好地识别出绝缘子串位置。

With the construction of smart grid,power companies gradually use unmanned aerial vehicles(UAV)to replace manual inspection of transmission lines.This paper proposes a method for processing aerial images of transmission line insulators captured by UAV.Firstly,the threshold and range of RGB components in the color model are used to segment the target and background areas.Secondly,mathematical morphology and non-overlapping window texture features are applied to roughly mark the target area.Finally,a minimum circumscribed horizontal rectangular frame is generated.Then the texture features of all the patterns within the minimum circumscribed horizontal rectangular frame are identified to locate the minimum horizontal rectangular area of the aerial image of the insulator string.In the end,we use two images to verify the algorithm and compare with the algorithms in the literature.The results show that the algorithm proposed in this paper can better identify the position of insulator strings.