A Review of Deep Learning Approaches for Human Gait Recognition

Human gait identification is an expanding field with potential use-cases in fields such as security, human-machine communication, and biometrics. In last few years, deep learning-based system have become the leading method in gait identification. This research presents a summary of the most recent developments in deep learning-based human gait recognition models. We examine the various architectures, characteristics, evaluation metrics, and datasets employed in these models, as well as discussing the challenges and future possibilities in this field. These include the requirement for more extensive and diverse datasets, the integration of multimodal information, and the construction of models that can withstand variations in gait. Our research offers a comprehensive understanding of the current state of human gait recognition models and the direction for future research.