Jagriti via Mudra: A pose based surveillance anomaly detection system
Anirudhan Kasthuri, Arvind Balamurali, Ajay Krishna Srinivasan, P Shanmuga Priya · 2024
Anomaly detection using Closed-Circuit Television (CCTV) has become increasingly crucial for enhancing security and surveillance systems. This study explores the application of advanced computer vision techniques to analyze CCTV footage and identify anomalous activities in real-time. By employing machine learning algorithms, the system learns normal behavioral patterns within the monitored environment and can subsequently flag deviations from these norms as potential anomalies. The proposed approach aims to mitigate security threats by detecting unusual events such as intrusions, unattended objects, or abnormal behavior, thereby enabling timely responses. This research contributes to the evolving field of video analytics, fostering the development of more intelligent and efficient surveillance systems that can adapt to dynamic scenarios and enhance overall safety and security in various settings.