Recognising structure in laser scanning point clouds

TLDR

Airborne and terrestrial laser scanners generate large point clouds, and while direct measurements may suffice for some applications, most require automatic processing to extract shape information, often involving recognition of specific geometric shapes or smooth surfaces, which is valuable in industry, urban planning, water management, and forestry. The study aims to review techniques for recognizing such structures in point clouds. The authors review several methods for detecting geometric shapes and smooth surfaces within point clouds. The paper was written while the first author was at Delft University of Technology.

Abstract

Both airborne and terrestrial laser scanners are used to capture large point clouds of the objects under study. Although for some applications, direct measurements in the point clouds may already suffice, most applications require an automatic processing of the point clouds to extract information on the shape of the recorded objects. This processing often involves the recognition of specific geometric shapes or more general smooth surfaces. This paper reviews several techniques that can be used to recognise such structures in point clouds. Applications in industry, urban planning, water management and forestry document the usefulness of these techniques. 1 This paper was written while the first author was with the Delft University of Technology.