MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641042150 A) filed by Bgs College Of Engineering And Technology, Bengaluru, Karnataka, on April 2, for 'a method and system for adaptive intruder detection in a monitored environment.'
Inventor(s) include Ravikumar Guralamata Krishnegowda; Govindaiah Thimma Raju; Chaitra Naveen; Prajwal Dhananjaya; Shravan Mundukodu Sreenivas; Siddesh Sangenahalli Kumar; and Srujan Dalavaikodihalli Jayaramu.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "Existing surveillance solutions depend on continuous monitoring and static classification, leading to excessive computational load, delayed response, and inaccurate identification due to frequent false alarms. The present disclosure provides an adaptive intruder detection system and method that address these limitations through motion-triggered processing and threshold-based decision-making. Video frames are analysed to detect motion, upon which a facial recognition pipeline is selectively activated. Facial embeddings are generated and compared with stored authorized user data to compute similarity. A dedicated decision mechanism evaluates the similarity using dynamically adjustable threshold parameters to accurately classify individuals as authorized or intruders. Upon detecting an intruder, multi-channel alerts with associated visual evidence are generated, and event data is logged for analysis. The proposed approach improves computational efficiency, enhances detection accuracy, and enables real-time, reliable intrusion response."
Disclaimer: Curated by HT Syndication.
