Identification and classification of objects in 3D point clouds based on a semantic concept
conference contributionposted on 06.12.2019 by Jean-Jacques PONCIANO, Frank Boochs, Alain Tremeau
Any type of content contributed to an academic conference, such as papers, presentations, lectures or proceedings.
Our real world is increasingly subject to digitization processes producing huge unstructured
3D data sets. In order to extract objects contained in these data sets subsequent analysis
steps are necessary. The most efficient but also the most expensive and time-consuming
analysis is based on manual editing, which allows integrating human knowledge and
intelligence. Computer based methods are less effective, as they mainly use implicit
knowledge allowing to parametrize algorithms, which are part of a defined processing
chain. We want to overcome these limitations through a more general and more flexible
integration of any kind of useful knowledge into the processing. This paper presents an
approach fully driven by semantic technologies and uses expert knowledge. This expert
knowledge is modeled into an ontology and describes objects, data, and algorithms. This
ontology guides an iterative reasoning process using the semantic technologies (e.g. OWL2,
SPARQL, an engine reasoner) to provide a prime flexibility. This process firstly identifies
relevant algorithms to parametrize and combine them. Secondly, it interprets the result
provided by algorithms to enrich the knowledge base. Thirdly, a semantic reasoning uses
added information to classify objects and determine, if needed, other relevant algorithms.
This process is thus, dynamically and iteratively adapted to the results of executed
algorithms. Its efficiency is presented through the result comparison of its results according
to other possible approaches.