Sökning: "Pose Fusion"

Visar resultat 1 - 5 av 15 uppsatser innehållade orden Pose Fusion.

  1. 1. Movement Estimation with SLAM through Multimodal Sensor Fusion

    Master-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakulteten

    Författare :Jimmy Cedervall Lamin; [2024]
    Nyckelord :slam; discrete-slam; continuous-slam; synchronous; asynchronous; computer vision; BRISK; opencv; ceres; visual; inertial; sensor fusion; multimodal; Simultaneous Localization and Mapping; time offset; pose estimation; quaternions; movement estimation;

    Sammanfattning : In the field of robotics and self-navigation, Simultaneous Localization and Mapping (SLAM) is a technique crucial for estimating poses while concurrently creating a map of the environment. Robotics applications often rely on various sensors for pose estimation, including cameras, inertial measurement units (IMUs), and more. LÄS MER

  3. 2. Spot the Pain: Exploring the Application of Skeleton Pose Estimation for Automated Pain Assessment

    Master-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

    Författare :Angelica Hjelm Gardner; [2022]
    Nyckelord :automated pain assessment; pain recognition; body movements; skeleton pose estimation; deep learning; neural networks;

    Sammanfattning : Automated pain assessment is emerging as an essential part of pain management in areas such as healthcare, rehabilitation, sports and fitness. These automated systems are based on machine learning applications and can provide reliable, objective and cost-effective benefits. LÄS MER

  4. 3. Applying Deep Learning To Improve Optimization- Based Approaches For Robust Sensor Fusion

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

    Författare :Pernilla Wikström; [2021]
    Nyckelord :Inertial Measurement Unit; Zero Velocity UPdaTes; Temporal Convolutional Network; PoseGraph Optimization; Inertial Measurement Unit; Zero Velocity UPdaTes; Temporal Convolutional Network; Optimering av GrafBaserad Positionering;

    Sammanfattning : Recent studies show that deep learning can be employed to learn from sensor data to improve accuracy and robustness of sensor fusion algorithms. In the same vein, in this thesis we use a state-of-the-art temporal convolution network to predict zero velocity updates (ZUPT) from raw inertial measurement unit (IMU) signals, and use the network output to improve the performance of an optimization-based pose estimator. LÄS MER

  5. 4. Localisation and Mapping for an Autonomous Lawn Mower : Implementation of localisation and mapping features for an autonomous lawn mower using heterogeneous sensors

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

    Författare :Marco Boffo; [2021]
    Nyckelord :Autonomous Mobile Robot; Sensor Fusion; Localisation; Mapping; Robot mobili autonomi; fusione di sensori; localizzazione; mappatura; Autonom mobil robot; sensorfusion; lokalisering; kartläggning;

    Sammanfattning : Autonomous lawn mowers have been available to consumers for more than 20 years. During this period, advancements in embedded device computations and sensor performance have led to improvements in the reliability of these robots. Despite recent improvements, the opportunity for further innovation of such systems remains significant. LÄS MER

  7. 5. A Case Study of Save The Children’s Cross-sector Value Creation

    Master-uppsats, Göteborgs universitet/Graduate School

    Författare :Martin Wramsby; [2020-09-04]
    Nyckelord :Cross-sector Collaboration; Collaborative Value Creation; Shared Value; Value Frame Fusion; Save the Children Sweden;

    Sammanfattning : The expanding view of how to deal with societal issues have grown more complex than ever before which have forced, what previously was viewed as unlikely collaborators, to innovate what it means to partner in value creation in support of social progress. The private sectors partnerships with non-governmental organisations (NGOs) have previously largely been limited to philanthropy and simple trade-offs. LÄS MER