电力线点云精细提取与重建的模型残差实现

Precise extraction and reconstruction of power line by using model residual

针对分裂导线提取方法抗噪性差、建模精度低等问题,该文提出一种利用模型残差聚类的机载激光雷达单根电力线点云精确提取并建模方法。首先利用最小二乘原理最佳拟合二维直线和抛物线;然后通过改进后的K-均值聚类算法对拟合残差进行聚类并剔除噪声点,得到高精度的单根电力线点;最后采用抛物线方程实现三维模型精细重建。利用典型代表性的两组实验数据进行验证,结果表明:该方法能很好地顾及电力线类型、档距、高差、噪声和缺失等因素,单根电力线点提取精度99.75%以上,模型拟合最大误差为0.017 m。

In order to solve the problems of poor anti-noise performance and low precision for extracting bundle conductor,an accurate extraction and modeling method for single power line of airborne light detection and ranging(LiDAR)points based on model residual clustering was proposed.Firstly,the least square method was used to fit the two-dimensional straight line and parabola,secondly,the improved K-Means clustering algorithm was utilized to cluster the fitting residuals and eliminate noise points to obtain high-precision single power line points.Finally,a three-dimensional model was reconstructed using parabolic equation method.Two typical sets of experimental data were used to verify the method.The results show that the method can take into account the factors such as power line type,distance,height difference,noise and data missing.The extraction accuracy of single power line points was over 99.75%.The maximum error of this method was 0.017 m.