Sökning: "Semantisk SLAM"

Hittade 4 uppsatser innehållade orden Semantisk SLAM.

  1. 1. The V-SLAM Hurdler : A Faster V-SLAM System using Online Semantic Dynamic-and-Hardness-aware Approximation

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

    Författare :Liu Mingxuan; [2022]
    Nyckelord :Approximate Computing; Deep Learning; Dynamic Environments; Object Detection; Online Controller; Semantic SLAM; Ungefärlig Beräkning; Djup Lärning; Dynamiska miljöer; Objektdetektion; Online Kontroller; Semantisk SLAM;

    Sammanfattning : Visual Simultaneous Localization And Mapping (V-SLAM) and object detection algorithms are two critical prerequisites for modern XR applications. V-SLAM allows XR devices to geometrically map the environment and localize itself within the environment, simultaneously. LÄS MER

  2. 2. Towards Visual-Inertial SLAM for Dynamic Environments Using Instance Segmentation and Dense Optical Flow

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

    Författare :Luis Alejandro Sarmiento Gonzalez; [2021]
    Nyckelord :Semantic SLAM; Stereo Vision; VisualInertial SLAM; Motion likelihood; Stereo disparity; Dense optical flow; Dynamic objects.; Semantisk SLAM; Stereo Vision; Visual-Inertial SLAM; Sannolikhet för rörelse; Stereoskillnader; Tätt optiskt flöde; Dynamiska objekt.;

    Sammanfattning : Dynamic environments pose an open problem for the performance of visual SLAM systems in real-life scenarios. Such environments involve dynamic objects that can cause pose estimation errors. LÄS MER

  3. 3. Visual Simultaneous Localization and Mapping with Deep Learning

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

    Författare :Ferran Montraveta Roca; [2020]
    Nyckelord :;

    Sammanfattning : One of the biggest challenges of the automotive industry at the moment is the idea of autonomous vehicles and the huge amount of data that they require due to the main technology they use, Deep Learning. Often, collecting enough data is very expensive and time-consuming, causing the industry to start adopting technologies such as Scenario Cloning, where previously recorded sequences are used to digitally reconstruct the scenario. LÄS MER

  4. 4. Design and analysis of different semantic SLAM algorithms

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

    Författare :Magdalini Papaioannou; [2019]
    Nyckelord :;

    Sammanfattning : The goal of this thesis project was to improve trajectory estimation of a traditional SLAM framework using semantic information generated by a deep neural network. The first part of the project involved designing and implementing a semantic integration method, in order to semantically classify keypoints and 3D map points within the pipeline. LÄS MER