MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122278 A) filed by Kg Reddy College Of Engineering And Technology, Hyderabad, Telangana, on Dec. 5, 2025, for 'suspicious activity detection using computer vision and deep learning.'
Inventor(s) include Bapu Sreenivas; Sangyam Soundarya; Mudusu Rambabu; Medari Vishnu Vardhan; K. Prathima; Yanamadni Venkata Rao; and Ankam Sai Gowtam.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "Suspicious activity detection using computer vision and deep learning is the proposed invention. The increasing need for enhanced security and public safety, intelligent surveillance systems have become essential in monitoring public and private spaces. Traditional surveillance methods, which rely on human supervision, are inefficient and prone to human error due to the vast amount of recorded video footage. To address this challenge, this research presents a deep learning-based Suspicious Activity Detection System that automates the identification of abnormal behaviours in real-time surveillance footage. The proposed system leverages Convolutional Neural Networks (CNNs) to analyse video frames and detect suspicious activities such as fighting, theft, arson, shooting, and accidents with remarkable accuracy. The system is trained using a labelled dataset, where 80% of the data is used for training and 20% for testing, achieving an impressive 99.91% accuracy in activity classification."
Disclaimer: Curated by HT Syndication.
