Classification of airborne laser scanning (ALS) point clouds of power lines is of great importance to their reconstruction. However, it is still a difficult task to efficiently and accurately classify the ground, vegetation, power lines and power pylons from ALS point clouds. Therefore, in this paper, a method is proposed to improve the accuracy and efficiency of the classification of point clouds of transmission lines, which is based on improved Random Forest and multi-scale features. The point clouds are filtered by the optimized progressive TIN densification filtering algorithm, then the elevations of the filtered point cloud are normalized. The features of the point cloud at different scales are calculated according to the basic features of the point cloud and the characteristics of transmission lines. The Relief F and Sequential Backward Selection algorithm are used to select the best subset of features to estimate the parameters of the learning model, then an Improved Random Forest classification model is built to classify the point clouds. The proposed method is verified by using three different samples from the study area and the results show that, compared with the methods based on Support Vector Machines, AdaBoost or Random Forest, our method can reduce feature redundancy and has higher classification accuracy and efficiency.

Urban components are the important part of the city, and the rapid and efficient survey of urban components is a key requirement of urban digitization. In this paper, a method of the collaborative survey and storage of urban components is proposed. The national standard code for urban components survey is optimized to accelerate the survey and storage of urban components, and the time cost of error discovery is shorten by using AutoCAD to check the spatial location and employing a VBA macro programme to search for the attribute data errors. At the same time, a collaborative processing flow of components data is constructed through ArcPy to further speed up the storage of urban components. The experiment of urban components survey in Wanxiu District of Wuzhou City shows that this method can effectively reduce the complexity of urban component data storage procedure and the error rate. Compared with the traditional method, the proposed method is about 2 times more efficient to input the urban component data into the database.