Sökning: "Point Cloud Registration"

Visar resultat 1 - 5 av 32 uppsatser innehållade orden Point Cloud Registration.

1. 1. Performance metrics and velocity influence for point cloud registration in autonomous vehicles

   Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

   Författare :Óscar Poveda Ruiz; [2023]
   Nyckelord :autonomous vehicle; localization; registration; metrics; error; classification; estimation; autonomt fordon; lokalisering; registrering; mätvärden; fel; klassificering; uppskattning;

   Sammanfattning : Autonomous vehicles are currently under study and one of the critical parts is the localization of the vehicle in the environment. Different localization methods have been studied over the years, such as the GPS sensor, commonly fused with other sensors such as the IMU. LÄS MER

3. 2. Evaluation of SLAM based mobile laser scanning and terrestrial laser scanning in the Kiruna mine : A comparison between the Emesent Hovermap HF1 mobile laser scanner and the Faro Laser Scanner Focus3D X 330 terrestrial laser scanner

   Kandidat-uppsats, Högskolan i Gävle/Samhällsbyggnad

   Författare :Claes Gustafsson; [2023]
   Nyckelord :Terrestrial laser scanning; mobile laser scanning; simultaneous localization and mapping; underground mapping; Kiruna mine.;

   Sammanfattning : The mining industry has over the last few decades seen a drastic increase in the usage of laser scanning technologies as a way of creating 3D maps of the mines being exploited. Underground mapping in places such as mines has become more prevalent as the technology has progressed and made it easier to generate highly detailed point clouds faster. LÄS MER

4. 3. 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

5. 4. Point clouds in the application of Bin Picking

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Abhijeet Anand; [2023]
   Nyckelord :Point clouds; Computer vision; 3D instance segmentation; Point cloud registration; Deep learning; Clustering;

   Sammanfattning : Automatic bin picking is a well-known problem in industrial automation and computer vision, where a robot picks an object from a bin and places it somewhere else. There is continuous ongoing research for many years to improve the contemporary solution. LÄS MER

7. 5. Feature-Aware Point Transformer for Point Cloud Alignment Classification : Pose your pose to FACT

   Master-uppsats, Linköpings universitet/Institutionen för systemteknik

   Författare :Ludvig Dillén; [2023]
   Nyckelord :point cloud alignment; point cloud alignment classification; alignment validation; point cloud; map validation; map quality; misalignment recognition; alignment quality; point transformer; Sinkhorn divergence; differential entropy; point cloud co-visibility; point cloud visibility; SLAM; point cloud registration; point cloud density;

   Sammanfattning : As the demand for 3D maps from LIDAR scanners increases, delivering high-quality maps becomes critical. One way to ensure the quality of such maps is through point cloud alignment classification, which aims to classify the alignment error between two registered point clouds. LÄS MER