Systematic Comparison of Power Corridor Classification Methods from ALS Point Clouds

Abstract

Power corridor classification using LiDAR (light detection and ranging) point clouds is an important means for power line inspection. Many supervised classification methods have been used for classifying power corridor scenes, such as using random forest (RF) and JointBoost. However, these studies did not systematically analyze all the relevant factors that affect the classification, including the class distribution, feature selection, classifier type and neighborhood radius for classification feature extraction. In this study, we examine these factors using point clouds collected by an airborne laser scanning system (ALS). Random forest shows strong robustness to various pylon types. When classifying complex scenes, the gradient boosting decision tree (GBDT) shows good generalization. Synthetically, considering performance and efficiency, RF is very suitable for power corridor classification. This study shows that balanced learning leads to poor classification performance in the current scene. Data resampling for the original unbalanced dataset may not be necessary. The sensitivity analysis shows that the optimal neighborhood radius for feature extraction of different objects may be different. Scale invariance and automatic scale selection methods should be further studied. Finally, it is suggested that RF, original unbalanced class distribution, and complete feature set should be considered for power corridor classification in most cases.