In recent years, automated human presence detection systems have gained significant attention in various fields, including surveillance, healthcare, and sports performance analysis. These systems aim to detect human movements and behaviors accurately and efficiently, which can be used for various purposes, such as security monitoring and health diagnosis.

This research presents an idea for detecting human presence, body posture, and walking style (gait cycle) using computer vision techniques. The system utilizes a machine learning-based object detection algorithm to detect human bodies in real-time. Subsequently, the system analyses the body posture and walking style and notifies about their abnormalities. The system is evaluated on a public dataset, and the results show that it achieves high accuracy in detecting human presence, body posture, and walking style. The system has potential applications in various fields, including surveillance, healthcare, and sports performance analysis.