Image-based 3D reconstruction refers to the capture and virtual reconstruction of real scenes, through the use of ordinary camera sensors. A common approach is the use of the algorithms Structure from Motion, Multi-view Stereo and Poisson Surface Reconstruction, that fares well for many types of scenes. However, a problem that this pipeline suffers from is that it often falters when it comes to texture-less surfaces and areas, such as those found in man-made environments. Building facades, roads and walls often lack detail and easily trackable feature points, making this approach less than ideal for such scenes. To remedy this weakness, this thesis investigates an expanded approach, incorporating line segment detection and line cloud generation into the already existing point cloud-based pipeline. Texture-less objects such as building facades, windows and roofs are well-suited for line segment detection, and line clouds are fitting for encoding 3D positional data in scenes consisting mostly of objects featuring many straight lines. A number of approaches have been explored in order to determine the usefulness of line clouds in this context, each of them addressing different aspects of the reconstruction procedure.

Au cours des dernières années, la capacité de la technologie LiDAR à capturer des informations détaillées sur la structure des forêts a attiré une attention croissante de la part de la communauté des écologues et des forestiers. Le LiDAR terrestre, notamment, apparaît comme un outil prometteur pour recueillir les caractéristiques géométriques des arbres à une précision millimétrique.Cette thèse étudie la reconstruction de surface à partir de nuages de points épars et non structurés, capturés en environnement forestier par un LiDAR terrestre. Nous proposons une suite d’algorithmes dédiés à la reconstruction de modèles d’attributs de placettes forestières : le sol etla structure ligneuse des arbres (i.e. troncs et branches principales). En pratique, nos approches modélisent le problème par des surfaces implicites construites à partir de fonctions à base radiale pour faire face à la forte hétérogénéité spatiale du nuage de points Lidar terrestre. / In recent years, the capacity of LiDAR technology to capture detailed information about forests structure has attracted increasing attention in the field of forest science. In particular, the terrestrial LiDAR arises as a promising tool to retrieve geometrical characteristics of trees at a millimeter level.This thesis studies the surface reconstruction problem from scattered and unorganized point clouds, captured in forested environment by a terrestrial LiDAR. We propose a sequence of algorithms dedicated to the reconstruction of forests plot attributes model: the ground and the woody structure of trees (i.e. the trunk and the main branches). In practice, our approaches model the surface with implicit function build with radial basis functions to manage the homogeneity and handle the noise of the sample data points.

This thesis describes methods of reconstruction of 3D scenes from photographs and videos using the Structure from motion approach. A new software capable of automatic reconstruction of point clouds and polygonal models from common images and videos was implemented based on these methods. The software uses variety of existing and custom solutions and clearly links them into one easily executable application. The reconstruction consists of feature point detection, pairwise matching, Bundle adjustment, stereoscopic algorithms and polygon model creation from point cloud using PCL library. Program is based on Bundler and PMVS. Poisson surface reconstruction algorithm, as well as simple triangulation and own reconstruction method based on plane segmentation were used for polygonal model creation.