MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202611088402 A) filed by Uttaranchal University on July 20, 2026, for An Ai-Enabled Surveillance System For Automated Recognition Of Bullying And Violent Behavior In University Campus.
Inventors include Rahul Mahala; Sanya Singh; Rajesh Singh; Anita Gehlot; and Sumit Chaudhary.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: An AI-enabled surveillance system and associated automated process utilize a distributed multi-node network and cloud-hosted machine learning models to achieve non-invasive, real-time recognition and reporting of bullying and violent behaviors within university campus environments. The system architecture integrates a plurality of N sensor-based computing units configured to capture audio waves via microphone arrays, motion events via PIR sensors, and environmental profiles via sound level sensors to flag shouting or distress signals; and a smaller array of P vision-based computing units (P N) deploying single-board edge processors linked to RGB and night-vision cameras to capture high-resolution video streams across variable lighting conditions. Every node is sustained by an independent solar panels, a rechargeable battery stack, and a battery management system (BMS) running adaptive power-saving scripts, and uses built-in Wi-Fi modules to transmit data bound with spatial-temporal metadata from integrated GPS and real-time clock (RTC) modules. The vision nodes execute localized edge-level preprocessing comprising frame selection and video compression to minimize campus network bandwidth overhead. Telemetry packets are aggregated at a centralized cloud server that performs audio denoising, frame normalization, and timestamp synchronization prior to running deep pose estimation and spectral feature extraction models.
Disclaimer: Curated by HT Syndication.
