Avancerad sökning

Hittade 5 uppsatser som matchar ovanstående sökkriterier.

  1. 1. RGB-D Deep Learning keypoints and descriptors extraction Network for feature-based Visual Odometry systems

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

    Författare :Federico Bennasciutti; [2022]
    Nyckelord :DeepLearning; Visual Odometry; Computer Vision; RGB-D Camera; Feature Extraction; Interest Point Extraction; Djupinlärning; Visuell Odometri; Datorseende; RGB-D-kamera; Nyckelpunkter; Detektion;

    Sammanfattning : Feature extractors in Visual Odometry pipelines rarely exploit depth signals, even though depth sensors and RGB-D cameras are commonly used in later stages of Visual Odometry systems. Nonetheless, depth sensors from RGB-D cameras function even with no external light and can provide feature extractors with additional structural information otherwise invisible in RGB images. LÄS MER

  3. 2. Robust Registration of ToF and RGB-D Camera Point Clouds

    Master-uppsats, KTH/Fastigheter och byggande

    Författare :Shuo Chen; [2021]
    Nyckelord :Robustness; Estimator; Feature extraction; RANSAC; BLAVE; M-estimator; ToF; RGB-D; Robusthet; Uppskattare; Särdragsextraktion; RANSAC; BLAVE; M-uppskattare; ToF; RGB-D;

    Sammanfattning : This thesis presents a comparison of M-estimator, BLAVE, and RANSAC method in point clouds registration. The comparison is performed empirically by applying all the estimators on a simulated data added with noise plus gross errors, ToF data and RGB-D data. The RANSAC method is the fastest and most robust estimator from the comparison. LÄS MER

  4. 3. Extracting contact surfaces from point-cloud data for autonomous placing of rigid objects

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

    Författare :Carolina Bianchi; [2020]
    Nyckelord :;

    Sammanfattning : Nowadays, thousands of humanworkers engage daily in non-creative and physically demanding tasks such as order-picking-and-placing. This task consists of collecting different goods from warehouse shelves and placing them in a container to fulfill an order. LÄS MER

  5. 4. Visual Odometry for Autonomous MAV with On-Board Processing

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Jacob Greenberg; [2015]
    Nyckelord :MAV; Visual Odometry; AICK;

    Sammanfattning : A new visual registration algorithm (Adaptive Iterative Closest Keypoint, AICK) is tested and evaluated as a positioning tool on a Micro Aerial Vehicle (MAV). Captured frames from a Kinect like RGB-D camera are analyzed and an estimated position of the MAV is extracted. The hope is to find a positioning solution for GPS-denied environments. LÄS MER

  7. 5. Multiple Session 3D Reconstruction using RGB-D Cameras

    Master-uppsats, Linköpings universitet/Datorseende; Linköpings universitet/Tekniska högskolan

    Författare :Nikolaus Widebäck West; [2014]
    Nyckelord :3D-Reconstruction; SLAM; RGB-D; 3D-Keypoints; Registration;

    Sammanfattning : In this thesis we study the problem of multi-session dense rgb-d slam for 3D reconstruc- tion. Multi-session reconstruction can allow users to capture parts of an object that could not easily be captured in one session, due for instance to poor accessibility or user mistakes. LÄS MER