MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202411090521 A) filed by Amity University on November 21, 2024, for Intelligent Surveillance System With Real-Time Intrusion Detection And Target Tracking.
Inventors include Vinayak Majhi; and Sujata Pandey.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention relates to an AI-based intrusion detection and target acquisition system designed to enhance the capabilities of traditional surveillance technologies. The system integrates advanced artificial intelligence (AI) algorithms, edge computing, and multi-sensor data fusion to provide accurate, real-time detection and tracking of intrusions. The surveillance setup includes high- definition optical cameras and high-resolution thermal cameras, which capture video feeds continuously. An AI Processing Unit employs convolutional neural networks (CNNs), specifically the YOLOv5 algorithm, for object detection and background subtraction using Gaussian Mixture Models (GMM) for motion detection. Edge computing devices, are strategically deployed to perform real- time inference and motion analysis using optical flow algorithms, reducing latency and minimizing bandwidth usage. A Data Fusion Module integrates data from multiple sensors, including radar and LIDAR, using a Kalman Filter to enhance detection accuracy by reducing noise and measurement errors.
Disclaimer: Curated by HT Syndication.
