Full Series Algorithm of Automatic Building Extraction and Modelling From LiDAR Data

This paper suggests an algorithm that automatically links the automatic building classification and modelling algorithms. To make this connection, the suggested algorithm applies two filters to the building classification results that enable processing of the failed cases of the classification algorithm. In this context, it filters the noisy terrain class and analyses the remaining points to detect missing buildings. Moreover, it filters the detected building to eliminate all undesirable points such as those associated with trees overhanging the building roof, the surrounding terrain and the façade points. In the modelling algorithm, the error map matrix is analysed to recognize the failed cases of the building modelling algorithm with these buildings being modelled with flat roofs. Finally, the region growing algorithm is applied on the building mask to detect each building and pass it to the modelling algorithm. The accuracy analysis of the classification and modelling algorithm within the global algorithm shows it to be highly effective. Hence, the total error of the building classification algorithm is 0.01% and only one building in the sample dataset is rejected by the modelling algorithm and even that is modelled, but with a flat roof. Most of the buildings have Segmentation Accuracy and Quality factor less than 5% (error less than 5%) which means that the resulting evaluation is excellent.