StepNet—Deep Learning Approaches for Step Length Estimation
Itzik Klein, Omri Asraf
Abstract
The case of a user walking with a smartphone in an indoor environment is considered. Instead of using traditional pedestrian dead reckoning approaches to estimate the user step-length, we define a deep learning based framework with an activity recognition model to regress the user change in distance and step-length. We propose StepNet - a family of deep-learning based approaches to regress the step-length or change in distance. In addition, we propose regressing a time-varying gain instead of a constant one used for traditional step-length estimation. A comparison is made between the proposed approaches and different network architectures. Experimental results show that the proposed deep-learning approaches outperform traditional ones for the examined trajectories.