Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 4 of 4 for “"Virtual IMU"”.

  1. Deriving Sensor-based Complex Human Activity Recognition Models Using Videos

    … well. My research develops a framework, namely IMUTube, that can potentially alleviate the limitations of large-scale labeled data collection in sensor-based HAR, which is the most pressing issue to limit the model performance in HAR systems. I aim to harvest existing video data from large-scale …

    gatech Repository record for Deriving Sensor-based Complex Human Activity Recognition Models Using Videos (opens in a new tab)

  2. A personal inertial-navigation system based on multiple distributed, nine-degrees-of-freedom, inertial measurement units

    The use of inertial-measurement units (IMUs) for personal navigation is investigated in this thesis. IMUs lack a position-finding algorithm that optimally blends sensor data to achieve high accuracy in a GPS-denied environment. In this research, software and a methodology for tracking position …

    nps Repository record for A personal inertial-navigation system based on multiple distributed, nine-degrees-of-freedom, inertial measurement units (opens in a new tab)

  3. Sign Language Recognition Using Wearable Motion Sensing and Video Co-Training

    … overcomes these limitations by combining real IMU sensing with virtual IMU (v-IMU) data generated from publicly available videos. We construct large-scale v-IMU datasets using two-view video analysis, 3D joint reconstruction, and triangulation algorithms, enabling wearable models to be trained …

    buffalo Repository record for Sign Language Recognition Using Wearable Motion Sensing and Video Co-Training (opens in a new tab)

  4. Overcoming Data Scarcity in IMU-based Human Motion Analysis

    … from older adults. Inertial measurement units (IMU) datasets collected in naturalistic settings are often fraught with labeling noise due to misaligned onsets, the presence of concurrent activities, unpredictable terrains or human errors. However, state-of-the-art learning with label noise (LNL) …

    mcmaster Repository record for Overcoming Data Scarcity in IMU-based Human Motion Analysis (opens in a new tab)