Sökning: "point cloud segmentation"

Visar resultat 6 - 10 av 34 uppsatser innehållade orden point cloud segmentation.

  1. 6. 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

  3. 7. SENSOR FUSION FOR AUTONOMOUS NAVIGATION

    Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Dan Österlund; [2023]
    Nyckelord :;

    Sammanfattning : This report describes the progress made in designing and constructing an unmanned surface vehicle. The focus is on the development of the vessel's perception system, which includes three LiDAR sensors and a camera. LÄS MER

  4. 8. Automatic processing of LiDAR point cloud data captured by drones

    Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Leon Li Persson; [2023]
    Nyckelord :machine learning; supervised learning; random forest; point cloud segmentation;

    Sammanfattning : As automation is on the rise in the world at large, the ability to automatically differentiate objects in datasets via machine learning is of growing interest. This report details an experimental evaluation of supervised learning on point cloud data using random forest with varying setups. LÄS MER

  5. 9. Maximizing the performance of point cloud 4D panoptic segmentation using AutoML technique

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Teng Ma; [2022]
    Nyckelord :LiDAR perception; 4D panoptic segmentation; Hyperparameter Optimization; Deep learning; Automated Machine Learning; LiDAR-uppfattning; 4D-panoptisk segmentering; hyperparameteroptimering; djupinlärning; automatiserad maskininlärning;

    Sammanfattning : Environment perception is crucial to autonomous driving. Panoptic segmentation and objects tracking are two challenging tasks, and the combination of both, namely 4D panoptic segmentation draws researchers’ attention recently. LÄS MER

  7. 10. A Deep Learning Based Approach to Object Recognition from LiDAR Data Along Swedish Railroads

    Master-uppsats, KTH/Fastigheter och byggande

    Författare :Egil Morast; [2022]
    Nyckelord :Deep learning; DGCNN; LiDAR; Object recognition; Railroad; Automatisation; Sweden; Point cloud; Djupinlärning; DGCNN; LiDAR; Objektigenkänning; Järnväg; Automatisering; Sverige; Punktmoln;

    Sammanfattning : Malfunction in the overhead contact line system is a common cause of disturbances in the train traffic in Sweden. Due to the preventive methods being inefficient, the Swedish Transport Administration has stated the need to develop the railroad maintenance services and has identified Artificial Intelligence (AI) as an important tool for this undertaking. LÄS MER