Efficient segment-based ground filtering and adaptive road detection from mobile light detection and ranging (LiDAR) data.

Mobile light detection and ranging (LiDAR) has been widely applied to support a variety of tasks because it captures detailed three-dimensional data of a scene with high accuracy with reduced costs and time compared with many other techniques. Given the large volume of data within a mobile LiDAR point cloud, automation of processing and analysis is critical to improve the efficiency of the entire workflow, particularly for common tasks of ground filtering (separating points representing the ground from non-ground objects) and road detection (identifying and extracting the road surface). This paper proposes a novel and highly efficient method of segment-based ground filtering and adaptive road detection from mobile LiDAR data. The proposed method includes four principal steps: (1) preprocessing of the mobile LiDAR point cloud with data merging and splitting, (2) an improved Mo-norvana trajectory reconstruction and segmentation, (3) segment-based ground filtering via a segment analysis followed by a scanline analysis, and (4) road detection including an adaptive rasterization and vehicle access analysis. The proposed method is demonstrated to be robust, effective, and efficient by testing on representative datasets collected with different speeds in a rural/highway and an urban/suburban scene. The performance of our method is further evaluated quantitatively through a model-based accuracy assessment by comparison to a model generated from manually extracted ground points where the F₁ score and Root Mean Square Error of the elevation model are 98.14% and 0.0027 m, and 99.16% and 0.0004 m for the rural and suburban datasets, respectively. [ABSTRACT FROM AUTHOR]