3D point cloud edge detection

Feature extraction in 2D-images, is one of the most important topics in the fields of image analysis and computer vision and has been studied for years. Edges and feature lines are considered as important features in various urban scenes covering a vast number of man-made objects. Generally, once edges are detected, a further step will be done for tracing feature lines from the detected edges. An extensive review of the established edge detection methods can be found in the sources bellow.
In recent years, benefiting from the advances in sensor technology for both airborne and ground-based laser scanning, dense 3D-point clouds have become increasingly common. Therefore, edge detection and feature line extraction in 3D-point clouds have become a novel research topic.

Sources:
- http://www.mdpi.com/2072-4292/8/9/710
- http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=825756
- http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=977560