Gait-Motion: A Smartphone Sensor-based Gait Recognition Dataset

In the domain of gait recognition, the scarcity of non-simulated, real-world data significantly hampers the performance and applicability of recognition systems. To address this limitation, we present a comprehensive gait recognition dataset - GaitMotion- collected using built-in sensors of Android smartphones in an uncontrolled, real-world environment. This dataset captures the walking activity of 24 subjects (14 females and 10 males) above 18 years old and weighing at least 50 kg. The data was gathered using three smartphones mounted in the front pockets of the subjects with a vertical orientation during a 3-minute walking activity over various terrains, including roads with slopes and flat surfaces. The dataset incorporates raw sensor data from accelerometers and gyroscopes, capturing acceleration due to gravity, linear acceleration, gravity, rotational rate, and rotational vector, all sampled at 100 Hz.
Post-collection, the data underwent preprocessing to ensure quality and reliability. This involved encoding user labels, omitting initial and final instances to reduce noise, and handling missing values.

Further, the dataset serves as a valuable resource for developing and evaluating gait recognition systems, fostering advancements in this domain by providing authentic, real-world data for robust algorithmic training and testing.