Thèse : Knowledge-based 3D point cloud processing

Soutenance de thèse de doctorat : Quoc Hung TRUONG

Équipe : AVR

Title: Knowledge-based 3D point cloud processing

Abstract: The modeling of real-world scenes through capturing 3D digital data has proven to be both useful and applicable in a variety of industrial and surveying applications. Entire scenes are generally captured by laser scanners and represented by large unorganized point clouds possibly along with additional photogrammetric data. A typical challenge in processing such point clouds and data lies in detecting and classifying objects that are present in the scene. In addition to the presence of noise, occlusions and missing data, such tasks are often hindered by the irregularity of the capturing conditions both within the same dataset and from one data set to another. Given the complexity of the underlying problems, recent processing approaches attempt to exploit semantic knowledge for identifying and classifying objects. In the present thesis, we propose a novel approach that makes
use of intelligent knowledge management strategies for processing 3D point clouds as well as identifying and classifying objects in digitized scenes. Our approach extends the use of semantic knowledge to all stages of the processing, including the guidance of the individual data-driven processing algorithms. The complete solution consists in a multi-stage iterative concept based on three factors: the modeled knowledge, the package of algorithms, and a classification engine. The goal of the present work is to select and guide algorithms following an adaptive and intelligent strategy for detecting objects in point clouds. Experiments with two case studies demonstrate the applicability of our approach. The studies were carried out on scans of the waiting area of an airport and along the tracks of a railway. In both cases the goal was to detect and identify objects within a defined area. Results show that our approach succeeded in identifying the objects of interest while using various data types.

La présentation aura lieu le vendredi 15 novembre 2013 à 10h00 dans l'amphithéâtre A302 du Pôle API à Illkirch.