Transtrack: Online meta-transfer learning and Otsu segmentation enabled wireless gesture tracking

Individual diversity poses a cross-user performance variance challenge that stumbles the practicality, especially for the wireless gesture tracking systems. Since the difficulty of annotating low-semantic wireless data limits constructing a big dataset, the recognizer should quickly adjust to different individuals via small datasets. To this end, we present TransTrack, an accurate wireless indoor gesture tracking system that can adjust to different users quickly. The key insight is that each unlabeled gesture contains learnable individual features that can help the gesture tracking model learning how to adapt to different users. Specifically, TransTrack uses recursive Otsu segmentation to separate gesture-induced signals with the background noise inspired by image segmentation. It then augments training data to learn the transferable features by leveraging the redundant information. A datum-based alignment method is proposed to unlock the limitation of classifier selection without distortion. Finally, TransTrack proposes an online meta-transfer learning method that collects unlabeled data transparently to train the tracking model for different tasks. Extensive experiments show that TransTrack can quickly adapt to different users and conditions. (c) 2021 Elsevier Ltd. All rights reserved.