5 May 2014 Graph-based filtering of urban LiDAR data
Author Affiliations +
A graph-based approach for modeling and solving the LiDAR filtering problem in urban areas is established. Our method consists of three steps. In the first step we construct a graph-based representation of the LiDAR data, Delaunay triangulation or the KNN graph can be used in this step. An algorithm is introduced to label the edges of this graph. In this second step, we defined criteria to eliminate some of the graph edges, then we used a connected components algorithm to separate the graph representation into different components. Finally, these components are classified into terrain or objects. Different datasets with different characteristics have been used to analyze the performance of our method.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yassine Belkhouche, Yassine Belkhouche, Bill Buckles, Bill Buckles, Prakash Duraisamy, Prakash Duraisamy, Mohammad S. Alam, Mohammad S. Alam, "Graph-based filtering of urban LiDAR data", Proc. SPIE 9094, Optical Pattern Recognition XXV, 90940I (5 May 2014); doi: 10.1117/12.2053188; https://doi.org/10.1117/12.2053188

Back to Top