MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049851 A) filed by Dr. S. V. Divya; M. Rajasekar; Dr. P. Venkadesh; and I. Mohammed Thahir, Coimbatore, Tamil Nadu, on April 19, for 'ai based real-time anomaly detection in video surveillance.'
Inventor(s) include M. Rajasekar; Dr. S. V. Divya; Dr. P. Venkadesh; and I Mohammed Thahir.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The increasing use of surveillance cameras in public and private spaces has made it difficult to monitor them manually on a real-time basis. Security personnel face difficulties in monitoring multiple video feeds simultaneously, which may cause delays or missed responses to critical situations. To overcome this issue, the proposed project aims to develop an AI-based real-time anomaly detection system for video surveillance. The proposed system applies advanced deep learning algorithms to analyze live video feeds and automatically identify unusual activities such as unauthorized access, suspicious movement, violence, loitering, or abandoned objects. Rather than relying on rule-based systems, the system learns normal activity patterns from past video feeds and detects anomalies that may signal potential threats. The system continuously processes video frames and, upon detecting unusual activity, automatically sends alerts through a centralized dashboard or mobile alerting system. The system is scalable and can be easily integrated with multiple cameras installed in various locations. The proposed system automatically detects anomalies in surveillance feeds, which reduces human effort, increases accuracy, and enables faster responses to critical events, thus improving the efficiency of surveillance and overall public safety."
Disclaimer: Curated by HT Syndication.
