Sökning: "dynamic scenes"

Visar resultat 11 - 15 av 35 uppsatser innehållade orden dynamic scenes.

  1. 11. Self-supervised monocular depth estimation for dynamic scenes

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Jonathan Lindberg; [2021]
    Nyckelord :Mathematics and Statistics;

    Sammanfattning : Estimating depth from an image is an ill-fitted problem, since we project a three-dimensional space to a two-dimensional image. However, human can estimate a plausible depth from only a single eye and often are we relaying on this for quick estimation of moving objects. LÄS MER

  3. 12. Towards Next Best View Planning for Observation of Time-Variant Scenes

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

    Författare :Embla Morast; [2021]
    Nyckelord :;

    Sammanfattning : Despite the inherent dynamic nature of real world environments, much robotics research focus on applying new concepts and techniques in isolated, static contexts. To further advance the field, it could be useful to explore not only how to compensate for dynamic features, but also how such features could be exploited. LÄS MER

  4. 13. Object Tracking based on Eye Tracking Data : A comparison with a state-of-the-art video tracker

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Ida Ejnestrand; Linnéa Jakobsson; [2020]
    Nyckelord :Eye tracking; Object tracking; Hidden Markov model; The Viterbi algorithm;

    Sammanfattning : The process of locating moving objects through video sequences is a fundamental computer vision problem. This process is referred to as video tracking and has a broad range of applications. LÄS MER

  5. 14. Vehicle Collision Risk Prediction Using a Dynamic Bayesian Network

    Master-uppsats, KTH/Matematisk statistik

    Författare :Jonas Lindberg; Isak Wolfert Källman; [2020]
    Nyckelord :Collision risk prediction; dynamic Bayesian network; sequential importance resampling; autonomous vehicles; ADAS; intelligent driver model; Förutsägelse av kollisionsrisk; dynamiskt Bayesianskt nätverk; sekventiell vägd simulering; autonoma fordon; ADAS; intelligent förarmodell;

    Sammanfattning : This thesis tackles the problem of predicting the collision risk for vehicles driving in complex traffic scenes for a few seconds into the future. The method is based on previous research using dynamic Bayesian networks to represent the state of the system. LÄS MER

  7. 15. Real-time Raytracing and Screen-space Ambient Occlusion

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

    Författare :Pooria Ghavamian; [2019]
    Nyckelord :;

    Sammanfattning : This paper investigates the advances in real-time ambient occlusion (AO). Topics discussed are state-of-the-art screen-space techniques and raytraced ambient occlusion. LÄS MER