Simple Head Trajectory Measurement for Deep Gait Recognition

Biometric-based person identification methods, such as fingerprint or face recognition, have been challenged due to cyberattacks using deep learning technology. Against cyberattacks, gait recognition has proven to be a promising alternative for robust person identification. However, compared to conventional biometric recognition systems, gait measurement systems are complicated, obstructing the collection of sufficient gait datasets and, consequently, limiting the reliability of person identification applications. In this article, we introduce a new method of gait recognition using the head trajectory segmented by head peaks on the human longitudinal axis during walking. We aim to simplify gait recognition systems and data processing to efficiently create larger databases for reliable individual identification based on gait patterns. Head trajectories were collected from 586 stride sequences of 12 participants walking on a flat and hard ground floor. We used a deep learning neural network model, requiring only 64 sampled 3-D head positions (64 × 3) as an input. This article displays different results with three covariates: sampling rate, the number of trained gait strides, and inclusion of body height, considering various measurement environments. The average performance was measured in ten repetitions with different training datasets to mitigate biased results due to the small number of samples. The average identification accuracy reached up to 94.4%, and the equal error rate (EER) ranged from 2.33% to 4.13% in the selected practical scenarios. Since various sensors, such as cameras and inertial sensors (ISs), can capture head trajectories, our proposed method is suitable for diverse environments across the physical and virtual worlds.