Dataset for gait-based authentication

This dataset can be used for identifying and authenticating people according to their way of walking. Information contained in the dataset is especially suitable as train and test data for machine learning models. 

The data for this dataset has been gathered in a corridor with a RGB (Red, Blue and Green) camera at 30 FPS (Frames Per Second). The dataset is composed by videos of 14 people walking through a 4 meter distance in the most natural way. This dataset contains 10523 JSON files composed by 2D coordinates for each point of the body provided by OpenPose. 14 people were recorded walking These keypoints are: nose, neck, right shoulder, right elbow, right wrist, left shoulder, left elbow, left wrist, right hip, right knee, right ankle, left hip, left knee, left ankle, right eye, left eye, right ear, left ear, left big toe, left small toe, left heel, right big toe, right small toe and right heel.

JSON files are named as follows: Subject_XX_YY_ZZZZZZZZZZZZ_keypoints.json

XX: Person ID

YY: Video ID

ZZZZZZZZZZZZ: Frame ID