Open AccessAN ENERGY-BASED APPROACH FOR DETECTION AND CHARACTERIZATION OF SUBTLE ENTITIES WITHIN LASER SCANNING POINT-CLOUDS
Author(s) -
Reuma Arav,
Sagi Filin
Publication year - 2016
Publication title -
the international archives of the photogrammetry, remote sensing and spatial information sciences/international archives of the photogrammetry, remote sensing and spatial information sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.264
H-Index - 71
eISSN - 1682-1777
pISSN - 1682-1750
DOI - 10.5194/isprsarchives-xli-b3-167-2016
Subject(s) - point cloud , computer science , pipeline (software) , set (abstract data type) , domain (mathematical analysis) , characterization (materials science) , energy minimization , artificial intelligence , energy (signal processing) , minification , signature (topology) , laser scanning , interpretation (philosophy) , field (mathematics) , change detection , data set , point (geometry) , data mining , laser , mathematics , geometry , physics , optics , mathematical analysis , statistics , quantum mechanics , pure mathematics , programming language
Airborne laser scans present an optimal tool to describe geomorphological features in natural environments. However, a challenge arises in the detection of such phenomena, as they are embedded in the topography, tend to blend into their surroundings and leave only a subtle signature within the data. Most object-recognition studies address mainly urban environments and follow a general pipeline where the data are partitioned into segments with uniform properties. These approaches are restricted to man-made domain and are capable to handle limited features that answer a well-defined geometric form. As natural environments present a more complex set of features, the common interpretation of the data is still manual at large. In this paper, we propose a data-aware detection scheme, unbound to specific domains or shapes. We define the recognition question as an energy optimization problem, solved by variational means. Our approach, based on the level-set method, characterizes geometrically local surfaces within the data, and uses these characteristics as potential field for minimization. The main advantage here is that it allows topological changes of the evolving curves, such as merging and breaking. We demonstrate the proposed methodology on the detection of collapse sinkholes.