Segmentation-based Classification of Laser Scanning Data

Over the past few years, laser scanning has been established as a leading technology for the acquisition of high density 3D spatial information. Digital Terrain Models (DTMs), which can be used for different engineering applications, are obtained by classification of laser data and removing the points that do not belong to terrain surface. The commonly used methods for the classification of laser scanning data are point-based. The major drawback of these methods is focusing on the discontinuities between neighbouring points regardless of the nature of the objects they belong to, which might lead to unreliable classification results. A segmentation-based approach for the classification of both airborne and terrestrial point clouds is presented in this paper. This approach is designed to overcome the drawbacks of point-based classification methods. As the first step, the laser point cloud is segmented by clustering the points with common attributes. To compute precise attributes, an adaptive neighbourhood of each point is firstly defined while considering the proximity of the points in 3D space, surface trend, and noise level in datasets. Then, the coordinates of the origin’s projection on the best fitted plane to each point’s neighbourhood are computed and used as segmentation attributes. Finally, the laser points with similar attributes are aggregated in the attribute space using a new clustering approach. After segmentation, a heuristic approach is used to classify the segmentation results. The boundaries of segmented surfaces are utilized to determine the adjacency relationship among derived segments. Then, different measures such as the slope and area of each segment, the height difference, and planimetric distance between adjacent segments are checked to classify them into terrain and off-terrain surfaces. The classification of non-segmented points is carried out by comparing the height difference between them and their nearest classified terrain-segments. Experimental results from real data have demonstrated the feasibility of the proposed approach for the classification of airborne and terrestrial laser data.