Sökning: "datorseende"

Visar resultat 1 - 5 av 438 uppsatser innehållade ordet datorseende.

  1. 1. Planet-NeRF : Neural Radiance Fields for 3D Reconstruction on Satellite Imagery in Season Changing Environments

    Master-uppsats, Linköpings universitet/Datorseende

    Författare :Erica Ingerstad; Liv Kåreborn; [2024]
    Nyckelord :NeRF; Neural Radiance Field; Satellite Imagery; Machine Learning; Deep Learning;

    Sammanfattning : This thesis investigates the seasonal predictive capabilities of Neural Radiance Fields (NeRF) applied to satellite images. Focusing on the utilization of satellite data, the study explores how Sat-NeRF, a novel approach in computer vision, per- forms in predicting seasonal variations across different months. LÄS MER

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

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

    Författare :Kobe Moerman; [2023]
    Nyckelord :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;

    Sammanfattning : 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. LÄS MER

  4. 3. Analyzing the performance of active learning strategies on machine learning problems

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

    Författare :Vendela Werner; [2023]
    Nyckelord :computer science; bioinformatics; machine learning; active learning; artificial intelligence; supervised learning; Astrazeneca; maskininlärning; artificiell intelligens; datorvetenskap; active learning; bioinformatik; supervised learning;

    Sammanfattning : Digitalisation within industries is rapidly advancing and data possibilities are growing daily. Machine learning models need a large amount of data that are well-annotated for good performance. To get well-annotated data, an expert is needed, which is expensive, and the annotation itself could be very time-consuming. LÄS MER

  5. 4. Assessing the Efficiency of COLMAP, DROID-SLAM, and NeRF-SLAM in 3D Road Scene Reconstruction

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Marcus Ascard; Farjam Movahedi; [2023]
    Nyckelord :3D reconstruction; Visual SLAM; Pose evaluation; Point cloud evaluation; Road scenes; Technology and Engineering;

    Sammanfattning : 3D reconstruction is a field in computer vision which has evolved rapidly as a result of the recent advancements in deep learning. As 3D reconstruction pipelines now can run in real-time, this has opened up new possibilities for teams developing Advanced Driver Assistance Systems (ADAS), which rely on the camera system of the vehicle to enhance the safety and driving experience. LÄS MER

  7. 5. Deep Learning Model Deployment for Spaceborne Reconfigurable Hardware : A flexible acceleration approach

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

    Författare :Javier Ferre Martin; [2023]
    Nyckelord :Space Situational Awareness; Deep Learning; Convolutional Neural Networks; FieldProgrammable Gate Arrays; System-On-Chip; Computer Vision; Dynamic Partial Reconfiguration; High-Level Synthesis; Rymdsituationstänksamhet; Djupinlärning; Konvolutionsnätverk; Omkonfigurerbara Field-Programmable Gate Arrays FPGAs ; System-On-Chip SoC ; Datorseende; Dynamisk partiell omkonfigurering; Högnivåsyntes.;

    Sammanfattning : Space debris and space situational awareness (SSA) have become growing concerns for national security and the sustainability of space operations, where timely detection and tracking of space objects is critical in preventing collision events. Traditional computer-vision algorithms have been used extensively to solve detection and tracking problems in flight, but recently deep learning approaches have seen widespread adoption in non-space related applications for their high accuracy. LÄS MER