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 14 of 14 for “"Pointclouds"”.

  1. Stereo-Based Three-Dimensional Model Acquisition and Motion Detection

    … intensity distribution difference. Multiple MVS pointclouds from different reference views are fused with two new fusion strategies to generate a better final reconstruction. To characterize the performance of our matching method and fusion strategies, an evaluation based on the quality of …

    ottawa-retro Repository record for Stereo-Based Three-Dimensional Model Acquisition and Motion Detection (opens in a new tab)

  2. Automated creation of labeled pointcloud datasets in support of machine learning-based perception

    … synchronized 2D camera images and 3D LIDAR pointclouds, depth clusters each LIDAR frame to spatially segment a scene, correlates each resultant pointcloud segment to a cropped 2D image, and processes each crop through a 2D image classifier to assign a segment label. Our automated …

    nps Repository record for Automated creation of labeled pointcloud datasets in support of machine learning-based perception (opens in a new tab)

  3. Deep Learning Based Perception on Radar Data for Autonomous Driving

    … rather than the commonly used sparse radar pointclouds. The thesis investigates how range-beam-doppler tensors can be processed by neural networks through the exemplary task of scene classification and evaluates the effectiveness of complex-valued convolutions in processing radar data. Our …

    cau-kiel Repository record for Deep Learning Based Perception on Radar Data for Autonomous Driving (opens in a new tab)

  4. Loosely coupled LiDAR-Visual/Thermal-Inertial Odometry and Mapping

    … of the system as well as globally registered pointclouds. A set of evaluation studies is presented showing the outperformance of our approach against the LiDAR only odometry and mapping method in a tunnel environment and the field-verification in an autonomous mission in an underground mine.

    unr Repository record for Loosely coupled LiDAR-Visual/Thermal-Inertial Odometry and Mapping (opens in a new tab)

  5. Three-Dimensional Accuracy Analysis of a Mapping-Grade Mobile Laser Scanning System

    … algorithms. The resulting geo-referenced pointclouds, collected in backpack mode, are compared to high-accuracy terrestrial laser scanning data. Several analysis methods are used, including planar investigations and feature extraction approaches. These techniques provide multiple …

    houston Repository record for Three-Dimensional Accuracy Analysis of a Mapping-Grade Mobile Laser Scanning System (opens in a new tab)

  6. Point Cloud Initialization Techniques For Gaussian Splatting

    … that efficiently registers the necessary pointclouds and camera poses. However, these features require a surplus number of images that are often unavailable. In this thesis, we investigate and compare other types of SfM and Multi-View-Stereo (MVS) technologies that use both traditional and …

    calpoly Repository record for Point Cloud Initialization Techniques For Gaussian Splatting (opens in a new tab)

  7. Weakly-supervised geometry-aware novel view synthesis

    … consistent novel views by rendering the pointclouds from different perspectives. Using a much simpler model and far fewer training examples than costly state-of-the-art diffusion models, we can recover 3D structure from single images of objects and quickly reconstruct them from unseen …

    ubc Repository record for Weakly-supervised geometry-aware novel view synthesis (opens in a new tab) Download PDF for Weakly-supervised geometry-aware novel view synthesis (opens in a new tab)

  8. On Landmarks for Introducing 3D SLAM Structure to VPR

    … well with the inherent sparsity of accumulated pointclouds from traversal by visual SLAM, due to differences in route, incomplete coverage, and the inherent sparsity of SLAM feature tracking in general. What is needed is an approach based on matching sub-regions which are common between …

    waterloo Repository record for On Landmarks for Introducing 3D SLAM Structure to VPR (opens in a new tab)

  9. Semantic-Weighted LiDAR–Camera SLAM for Robust Mapping in Vegetation-Rich Environments

    … end outputs RGB-colored and semantic-colored pointclouds to a factor-graph SLAM backend that performs global optimization. This proposed system aims to enhance odometry stability and improve overall map consistency in complex natural and agricultural environments where purely geometric methods …

    wvu Repository record for Semantic-Weighted LiDAR–Camera SLAM for Robust Mapping in Vegetation-Rich Environments (opens in a new tab)

  10. Model-Based Knowledge-Driven Machine Learning for Automotive Radar Imaging and Perception

    … in angular resolution, reliance on sparse pointclouds in commercial systems, and the scarcity of publicly available high-resolutionautomotive radar datasets.To address these challenges, this thesis focuses on three key enhancements. First, wepropose novel deep learning frameworks for …

    alabama Repository record for Model-Based Knowledge-Driven Machine Learning for Automotive Radar Imaging and Perception (opens in a new tab)

  11. Measuring and modelling soil erosion in agricultural systems: Evaluating the application of UAVs and SfM-MVS for soil erosion research

    … application, the vertical accuracy (RMSE) of pointclouds converges on 2–3× the ground-sampling-distance of the optical imagery with a practical upper limit of 0.01 m. Our nadir aerial surveys had ground-sampling-distances of between 0.011 – 0.018 m, which resulted in pointclouds with a range …

    waterloo Repository record for Measuring and modelling soil erosion in agricultural systems: Evaluating the application of UAVs and SfM-MVS for soil erosion research (opens in a new tab)

  12. The Resilient Micro Flyer: a New Collision-tolerant Autonomous Robot

    … to project into a 2D bird-eye view a series of N pointclouds stitched together based on the odometry of the robot. On this newly generated image we then find and isolate the best set of parallel lines based on length, orientation and relative distance between each other. The algorithm is able to …

    unr Repository record for The Resilient Micro Flyer: a New Collision-tolerant Autonomous Robot (opens in a new tab)

  13. Toward Interpretable, Data-Driven Frameworks for 3D Point-Cloud Analysis in Forest Ecology

    Three-dimensional point clouds have transformed our ability to capture natural environments at scale, offering detailed representations of forest structure, canopy architecture, and understory composition. Yet despite this promise, the use of deep learning on ecological point clouds remains limited …

    unr Repository record for Toward Interpretable, Data-Driven Frameworks for 3D Point-Cloud Analysis in Forest Ecology (opens in a new tab)

  14. Spatiotemporal coherent semantic maps with mobile robots

    … geometrical information of the environment, i.e. pointclouds registered in a graph of nodes; (iii) the labeled sparse topological oneestablishes the spatiotemporal coherence by associating the respective nodes inthe topometric maps via place labels and geometrical transformations, …

    greece Repository record for Spatiotemporal coherent semantic maps with mobile robots (opens in a new tab)