4 papers
Pixel Watch: Robust Heart Rate Sensing from Multipath PPG and On-Device Deep Learning Trained on 10,000 hours of Free-Living and Fitness Data
Daniel Roggen, Megan Walker, Yojan Patel +26
The Pixel Watch 2 (PW2) is the first Google smartwatch to combine multipath photoplethysmography (PPG) with deep learning-based heart rate inference, designed to significantly impr…
Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation
Nobuyuki Oishi, Philip Birch, Daniel Roggen +1
The scarcity of high-quality labeled data in sensor-based Human Activity Recognition (HAR) hinders model performance and limits generalization across real-world scenarios. Data aug…
GRASPTrack: Geometry-Reasoned Association via Segmentation and Projection for Multi-Object Tracking
Xudong Han, Pengcheng Fang, Yueying Tian +4
Multi-object tracking (MOT) in monocular videos is fundamentally challenged by occlusions and depth ambiguity, issues that conventional tracking-by-detection (TBD) methods struggle…
In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models against Variability
Azhar Ali Khaked, Nobuyuki Oishi, Daniel Roggen +1
Human Activity Recognition (HAR) using wearable inertial measurement unit (IMU) sensors can revolutionize healthcare by enabling continual health monitoring, disease prediction, an…