Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 68 for “"cloud registration"”.
-
LEARNING POINT CLOUD REGISTRATION
Point cloud registration refers to the task of finding the spatial transformation that aligns two or more point clouds. It is an important problem with many applications in robotics and virtual or augmented reality. In this thesis comprising four works, we propose several ways to learn from data …
-
Cloud To Cloud Registration For 3d Point Data
… and has given rise to the popularity of point cloud data (PCD). 3D imaging sensors provide a means for quickly capturing dense and accurate geospatial information that represent the 3D geometry of objects in a digital environment. Due to spatial and temporal constraints, it is quite common that …
-
Rigid and Non-Rigid Point Cloud Registration with Applications
Accurate 3D point cloud registration is essential for a wide range of applications in robotics, computer vision, and graphics, where aligning partial shapes captured from different viewpoints or timeframes is often required. Traditional methods rely on computationally expensive global alignment …
-
Robust point-cloud registration based on dense point matching and probabilistic modeling
This thesis presents techniques for 3D point-cloud registration that are robust to outliers and missing regions. They tackle non-rigid and rigid registration and exploit the advan tages of deep learning for dense point matching. This is done by proposing a single new neural network to solve both …
-
Using Rock Bolts to Enhance Partially Overlapping Point Cloud Registration Accuracy in Mine Tunnels
… time-consuming. Recent advancements in partial registration algorithms allow for merging point cloud scans which is practical for combining them within the local coordinate system of the scanner. However, registering tunnel scans poses challenges due to the large amount of data and limited …
-
Cylindrical and Polygonal Object Modelling and its use in LiDAR Calibration and Point Cloud Registration
… sets of discrete points (known as point clouds) in a 3D coordinate system from which spatial information can be extracted to support many applications. The accuracy of the LiDAR measurements can be improved by performing appropriate calibration. In this thesis, two novel cylinder-based …
-
Unified 3D Understanding: 3D Generation And Registration
… object generation, UV map generation, and point cloud registration by dramatically improving accuracy, efficiency, and automation. Diffusion models, for instance, have significantly advanced 3D object generation, enabling the synthesis of complex geometries and realistic textures. Similarly, …
-
Virtual-Real Object Registration and Shape Completion for Stable and Accurate Augmented Reality Technology
… been widely used in many applications. 3D point cloud registration is one of the main processes to correctly align virtual 3D objects with real-world scenes in AR. The higher quality of the underlying 3D point clouds with fewer missing and noisy points, the more accurate the 3D point cloud …
-
Autonomous Aerial Drone Landing Site Selection on a Maritime Vessel
… the system integrates robust mapping, point cloud registration, and site selection algorithms to enable reliable performance in dynamic maritime conditions. A simulation environment was developed, utilizing Microsoft AirSim and ShipMo3D. This simulation incorporated a quadrotor equipped with …
-
Point Cloud Processing: Classification, Registration and Reconstruction
Point cloud processing methods have been an important task of 3D computer vision and graphics, with broad applications in robotic navigation, autonomous driving, 3D modeling, and medical imaging. This thesis introduces several new methods for point cloud classification, point-based surface …
-
Generalised Discriminative Optimisation Algorithms for Augmented Reality: Theory and Practice.
… Reality (AR) technology achieves the seamless registration between virtual scenes and the real world. Three-dimensional registration is a core method for integrat- ing virtual information and the real world. Registration has always been treated as an optimisation process, involving the design …
-
Mapping and Localization Using LiDAR Fiducial Markers
… of 3D assets and training data for point cloud registration, 3D map merging, Augmented Reality (AR), and many more. First, an Intensity Image-based LiDAR Fiducial Marker (IFM) system is introduced, using thin, letter-sized markers compatible with VFMs. A detection method locates 3D …
-
Dense RGB-D SLAM and object localisation for robotics and industrial applications
… local photometric alignment and global geometric registration. This study revealed the effectiveness and excellent performance of the proposed RSO-SLAM on both plastic and metallic objects. In addition, a case study involving the cover of a electric vehicle battery with metallic surface …
-
A 3D vision framework for generalized workpiece localization in robotic manufacturing
… workpiece localization through CAD-based Point Cloud Registration (PCR) plays a key role in enabling adaptive robotic tasks, e.g., mapping toolpaths from a CAD model to the current workpiece location. However, existing approaches often lack the robustness required for full autonomy and need …
-
Understanding Motion and Geometry of Point Cloud in Dynamic Environment
Point cloud offers a discrete yet meaningful representation of the 3D world, capturing object shapes, rigid poses, and the motion of dynamic scenes, etc.. Understanding dynamic environments through learning the geometry and motion is critical for robotic applications. However, the inherent …
Page 1 of 4