Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
This addresses data scarcity in HAR for wearable device applications, but it is incremental as it builds on existing sensor and pose-based methods.
The paper tackled the problem of insufficient labeled data for Human Activity Recognition (HAR) by proposing a pose-to-sensor network that generates sensor data from 3D skeleton pose sequences, resulting in significant performance improvements over baseline methods on the MM-Fit dataset.
The proliferation of deep learning has significantly advanced various fields, yet Human Activity Recognition (HAR) has not fully capitalized on these developments, primarily due to the scarcity of labeled datasets. Despite the integration of advanced Inertial Measurement Units (IMUs) in ubiquitous wearable devices like smartwatches and fitness trackers, which offer self-labeled activity data from users, the volume of labeled data remains insufficient compared to domains where deep learning has achieved remarkable success. Addressing this gap, in this paper, we propose a novel approach to improve wearable sensor-based HAR by introducing a pose-to-sensor network model that generates sensor data directly from 3D skeleton pose sequences. our method simultaneously trains the pose-to-sensor network and a human activity classifier, optimizing both data reconstruction and activity recognition. Our contributions include the integration of simultaneous training, direct pose-to-sensor generation, and a comprehensive evaluation on the MM-Fit dataset. Experimental results demonstrate the superiority of our framework with significant performance improvements over baseline methods.