• Version
• Download 0
• File Size 148.00 KB
• File Count 1
• Create Date 30 April 2025
• Last Updated 30 April 2025

A Review of Ai-Powered Human Posture Detection for Multi-Context Recognition

Authors:

Samruddhi Bhamre¹, Aarti Pawara², Bhumika Suryawanshi³ , Sambhaji Watpade⁴ , Archana Gaikwad⁵

¹²³⁴⁵ Computer Department Loknete Gopinathji Munde Institute of Engineering Education & Research Nashik.

ABSTRACT - This project introduces a real-time abnormal activity detection system that leverages pose estimation and K-Nearest Neighbors (KNN) classification to enhance security monitoring and ensure public safety. Conventional surveillance systems often rely heavily on manual monitoring, leading to delayed responses and potential oversight, particularly in crowded and dynamic environments. Our approach uses pose estimation techniques to capture human skeletal structures and extract key joint coordinates, enabling the accurate analysis of movement patterns. These pose-based features are normalized and classified using the KNN algorithm to distinguish between normal and abnormal activities. An intelligent alert system is integrated to notify relevant authorities immediately upon detecting suspicious behavior, ensuring timely intervention. Additionally, a user-friendly interface provides real-time visualization, system logs, and analytical insights for enhanced situational awareness. This solution not only improves the accuracy and efficiency of behavior recognition but also automates security in diverse environments such as public spaces, transportation hubs, and restricted areas, addressing challenges related to scalability, response time, and minimizing human effort.

Key Words: Abnormal Activity Detection, Feature Extraction, KNN, Normalization, Pose Estimation, Skeleton Tracking