A data augmentation methodology for training machine/deep learning gait recognition algorithms
This addresses the challenge of limited high-quality training data for gait recognition systems, though it is incremental as it builds on existing simulation and data augmentation techniques.
The authors tackled the problem of confounding factors like clothing and lighting reducing gait recognition accuracy by introducing a simulation-based data augmentation methodology and a subject-specific dataset to generate synthetic video frames. Results show that synthetic examples retain identity information, enabling studies into fully-invariant recognition across more conditions.
There are several confounding factors that can reduce the accuracy of gait recognition systems. These factors can reduce the distinctiveness, or alter the features used to characterise gait, they include variations in clothing, lighting, pose and environment, such as the walking surface. Full invariance to all confounding factors is challenging in the absence of high-quality labelled training data. We introduce a simulation-based methodology and a subject-specific dataset which can be used for generating synthetic video frames and sequences for data augmentation. With this methodology, we generated a multi-modal dataset. In addition, we supply simulation files that provide the ability to simultaneously sample from several confounding variables. The basis of the data is real motion capture data of subjects walking and running on a treadmill at different speeds. Results from gait recognition experiments suggest that information about the identity of subjects is retained within synthetically generated examples. The dataset and methodology allow studies into fully-invariant identity recognition spanning a far greater number of observation conditions than would otherwise be possible.