Sökning: "PointCloud"

Visar resultat 1 - 5 av 13 uppsatser innehållade ordet PointCloud.

1. 1. Replacing Objects in Point Cloud stream with Real-time Meshes using Semantic Segmentation

   Master-uppsats, Blekinge Tekniska Högskola

   Författare :Abhinav Chitta; [2024]
   Nyckelord :;

   Sammanfattning : Background: The evolving landscape of 3D data processing, particularly pointcloud manipulation, is pivotal in numerous applications ranging from architecturaldesign to spatial analysis. Traditional methods, primarily mesh generation from point clouds, face challenges in adapting to complex real-world scenarios. LÄS MER

3. 2. Point Cloud Registration using both Machine Learning and Non-learning Methods : with Data from a Photon-counting LIDAR Sensor

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Maja Boström; [2023]
   Nyckelord :Point Cloud Registration; Machine Learning; Photon-counting LIDAR; Iterative Closest Point;

   Sammanfattning : Point Cloud Registration with data measured from a photon-counting LIDAR sensor from a large distance (500 m - 1.5 km) is an expanding field. Data measuredfrom far is sparse and have low detail, which can make the registration processdifficult, and registering this type of data is fairly unexplored. LÄS MER

4. 3. Jämförelseanalys av höjdmodeller skapade med LiDAR-data från UAV och flygplan för projektering av kraftledningsgator

   Kandidat-uppsats, Karlstads universitet

   Författare :Hanna Edlund; [2023]
   Nyckelord :LiDAR; UAV; Airborne laser-scanning; Digital Elevation Model DEM ; Powerline; LiDAR; UAV; Flygburen laser-skanning; Höjdmodell; Kraftledning;

   Sammanfattning : I dagsläget står det svenska kraftnätet inför en stor utmaning om det ska kunna klara av att tillgodose Sveriges växande elbehov. Stora delar av kraftnätet måste förnyas samtidigt som det byggs ut. LÄS MER

5. 4. Estimating Forest Variables from LiDAR Pointcloud Data Using a Deep Learning Approach

   Master-uppsats, Linköpings universitet/Kommunikationssystem

   Författare :Ella Grundin; Rasmus Kozak Åslöv; [2022]
   Nyckelord :Deep Learning; Forest Management; Machine Learning; Measuring Forests; Neural Networks; Data Analysis; Digital Edge; Djupinlärning; Skogsbruk; Maskininlärning; Skogsmätning; Neurala nätverk; Dataanalys; Digital Edge;

   Sammanfattning : Knowledge about forest measurements is essential for efficient and sustainableforestry. One important measurement is wood volume, both from an economicand an environmental perspective. Therefore it is crucial to measure wood vol-ume accurately and reliably. LÄS MER

7. 5. 3D Context of Objects : A prior for Object Detection and Place Classification

   Master-uppsats, Örebro universitet/Institutionen för naturvetenskap och teknik

   Författare :Nima Behzad; [2021]
   Nyckelord :;

   Sammanfattning : Contextual information is helpful for object detection and object-based placerepresentation. 3D data significantly helps to capture geometrical informationabout scenes. In this work, a feature descriptor for object context in full 3Dpointclouds of places is introduced together with a method to extract featuresand build the context model. LÄS MER