Footstep patterns, captured using pressure or force-sensitive walkways during natural walking, offer a convenient and passive approach to biometric recognition. However, footwear variability poses a major challenge to practical deployment, as it impacts both the foot-sensor interface and the user's underlying gait mechanics. This study considers the particularly difficult scenario where users enroll under one fixed footwear condition but must later be recognized in arbitrary, unseen footwear. Using the StepUP-P150 dataset, we show that footwear-induced shift, while substantial and heterogeneous across individuals, contains shared structure that can be learned from a training population and transferred, zero-shot, to previously unseen users and footwear styles. We do this using BiStepNet, a novel architecture that decomposes spatial and temporal identity cues into independently trainable streams and outperforms compact 3D spatiotemporal baselines for cross-footwear recognition. We demonstrate that cross-footwear recognition performance scales systematically with the volume and diversity of footwear representation in the training set, with gains transferring to footwear styles not directly observed during training. Moreover, we show that auxiliary gait datasets with only partial modality overlap (incorporated through the architecture's decomposed design) can be leveraged to further improve robustness to unseen footwear conditions.
Ethan Eddy, Evan Campbell, Scott Bateman, Erik Scheme
The recognition of dynamic gestures via discrete myoelectric control is becoming an attractive input modality for event-based human-machine interaction. While recent work suggests that discrete cross-user models are possible (i.e., no calibration data is required from the end user), few have evaluated techniques to optimize these systems and their generalizability to new randomly prompted data simulating real-world discrete control is relatively unknown. Using the 612-user EMG-EPN dataset, this work benchmarks five temporal deep-learning approaches, evaluates the tradeoff between performance and model complexity, and compares hand-crafted and machine-learned feature extraction techniques. The CNN-GRU achieved the best accuracy of 93% when tested on 184 previously unseen users. These models were then evaluated on a different, more realistic, unsegmented dataset, wherein users were randomly prompted to elicit discrete gestures during a continuous data collection. This dataset was recorded five years apart and in a separate country from the data used to train the original model. Results show that the cross-user results scale to this new dataset (accuracies of 96%) even though no feedback was given to users during the elicitation of gestures. These findings highlight the exciting potential of discrete zero-shot cross-user myoelectric control and offer valuable insights for the continued advancement of this promising technology.