No abstract

Object reconstruction is an important task in many fields of application as it allows to generate digital representations of our physical world used as base for analysis, planning, construction, visualization or other aims. A reconstruction itself normally is based on reliable data (images, 3D point clouds for example) expressing the object in his complete extent. This data then has to be compiled and analyzed in order to extract all necessary geometrical elements, which represent the object and form a digital copy of it. Traditional strategies are largely based on manual interaction and interpretation, because with increasing complexity of objects human understanding is inevitable to achieve acceptable and reliable results. But human interaction is time consuming and expensive, why many researches has already been invested to use algorithmic support, what allows to speed up the process and to reduce manual work load. Presently most of such supporting algorithms are datadriven and concentrate on specific features of the objects, being accessible to numerical models. By means of these models, which normally will represent geometrical (flatness, roughness, for example) or physical features (color, texture), the data is classified and analyzed. This is successful for objects with low complexity, but gets to its limits with increasing complexness of objects. Then purely numerical strategies are not able to sufficiently model the reality. Therefore, the intention of our approach is to take human cognitive strategy as an example, and to simulate extraction processes based on available human defined knowledge for the objects of interest. Such processes will introduce a semantic structure for the objects and guide the algorithms used to detect and recognize objects, which will yield a higher effectiveness. Hence, our research proposes an approach using knowledge to guide the algorithms in 3D point cloud and image processing.

Due to the increasing availability of large unstructured point clouds from lasers canning and photogrammetry, there is a growing demand for automatic evaluation methods. Given the complexity of the underlying problems, several new methods resort to using semantic knowledge in particular for object detection and qualification support. In this paper, we present a novel approach which makes use of advanced algorithms, and benefits from intelligent knowledge management strategies for the processing of 3D point clouds and object qualification in a scanned scene. In particular, our method extends the use of semantic knowledge to all stages of the processing, including the guidance of the 3D processing algorithms. The complete solution consists of a multistage, iterative, concept based on three factors: the modeled knowledge, the package of algorithms, and the qualification engine. Zusammenfassung: Automatische Detektion und Qualifizierung von Objekten in Punktwolken unter Nutzung mehrschichtiger Semantik. Infolge der zunehmenden Verfügbarkeit großer unstrukturierter Punktwolken aus Laserscanning und Photogrammetrie entsteht wachsender Bedarf für automatisierte Auswerteverfahren. Angesichts der häufig hohen Komplexität der in den Punktwolken enthaltenen Objekte stoßen rein Daten-getriebene Ansätze an ihre Grenzen. Es entstehen vermehrt Konzepte, die auf verschiedene Weise auch Gebrauch von Semantik machen. Semantik und Algorithmik sind dabei oft eng miteinander verwoben und führen zu Limitationen in Art und Umfang der nutzbaren Semantik. Mit der vorgestellten Lösung werden Algorithmik und Semantik klar getrennt und mit den exakt auf diese Domänen zugeschnittenen Werkzeugen behandelt. Deren prozedurale Verknüpfung führt dann zu einem neuen Verarbeitungskonzept, das eine bislang nicht erreichte Flexibilität und Vielseitigkeit in der Nutzung unterschiedlichster Semantiken besitzt und auch die Steuerung der Algorithmen integriert. Die iterative Gesamtlösung fußt auf drei Säulen, die aus dem modellierten Wissen, dem Pool der Algorithmen und dem Identifikationsprozess bestehen.

No abstract