Advanced search

Showing result 1 - 5 of 246 essays matching the above criteria.

  1. 1. Modulating Depth Map Features to Estimate 3D Human Pose via Multi-Task Variational Autoencoders

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Kobe Moerman; [2023]
    Keywords : 3D pose estimation; Joint landmarks; Variational autoencoder; Multi-task model; Loss discrimination; Latent-space modulation; Depth map; 3D-positionsuppskattning; Gemensamma landmärken; Variationell autoencoder; Multitask-modell; Förlustdiskriminering; Latent-space-modulering; Djupkarta;

    Abstract : Human pose estimation (HPE) constitutes a fundamental problem within the domain of computer vision, finding applications in diverse fields like motion analysis and human-computer interaction. This paper introduces innovative methodologies aimed at enhancing the accuracy and robustness of 3D joint estimation. READ MORE

  3. 2. Towards Adaptive Image Resolution for Visual SLAM on Resource-constrained Devices

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Herman Blenneros; [2023]
    Keywords : Visual localization and mapping; Runtime-control; Resource-constrained devices; Bildbaserad lokalisering och kartläggning; Realtidsreglering; Resursbegränsade enheter;

    Abstract : Today, a large number of devices with small form factors and limited resources are being integrated with processes to perform complex tasks such as localization and mapping. One example of this are headsets used for Extended Reality. READ MORE

  4. 3. Dynamic Object Removal for Point Cloud Map Creation in Autonomous Driving : Enhancing Map Accuracy via Two-Stage Offline Model

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Weikai Zhou; [2023]
    Keywords : Autonomous driving; Dynamic object removal; Map creation; 3D point cloud; Autonom körning; Dynamiska objekt borttagning; Skapande av kartor; 3D-punktmoln;

    Abstract : Autonomous driving is an emerging area that has been receiving an increasing amount of interest from different companies and researchers. 3D point cloud map is a significant foundation of autonomous driving as it provides essential information for localization and environment perception. READ MORE

  5. 4. Deep Learning-Based Depth Estimation Models with Monocular SLAM : Impacts of Pure Rotational Movements on Scale Drift and Robustness

    University essay from Linköpings universitet/Datorseende

    Author : Daniel Bladh; [2023]
    Keywords : Deep Learning; Computer Vision; Monocular; SLAM; Depth Estimation;

    Abstract : This thesis explores the integration of deep learning-based depth estimation models with the ORB-SLAM3 framework to address challenges in monocular Simultaneous Localization and Mapping (SLAM), particularly focusing on pure rotational movements. The study investigates the viability of using pre-trained generic depth estimation networks, and hybrid combinations of these networks, to replace traditional depth sensors and improve scale accuracy in SLAM systems. READ MORE

  6. 5. Localized and extended states in finite-sized mosaic Wannier-Stark lattices

    University essay from KTH/Tillämpad fysik

    Author : Emrah Tortumlu; [2023]
    Keywords : Applied Physics; Condensed matter physics; quantum technology; quantum nanophotonics; localization; mobility edge; phase transition; Tillämpad Fysik; Kondenserade materiens fysik; kvantteknologi; kvantnanofotonik; lokalisering; fasövergång;

    Abstract : Anderson localization occurs when an otherwise conductive solid becomes insulatingdue to a sufficiently large degree of disorder in the medium. The electron band energy(as a function of disorder) at which this transition between extended and localizedelectron states occur is called the mobility edge (ME) and is energy-dependent only in3-dimensional systems. READ MORE