Intellectual Property India Publishes Patent Application for 'Mobilenet-Convlstm Based Low-Power Spatio-Temporal Surveillance For Border Security With Gpu Accelerated Resnet-Based Secondary Verification' Filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering And Technology

MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017439 A) filed by Vallurupalli Nageswara Rao Vignana Jyothi Institute Of Engineering And Technology, Hyderabad, Telangana, on Feb. 17, for 'mobilenet-convlstm based low-power spatio-temporal surveillance for border security with gpu accelerated resnet-based secondary verification.'

Inventor(s) include Dr. A. Pramod Kumar; K. Vishweshwar Reddy; K. Hitesh Varma; M. Ganesh; A. Anshul; and Mr. B. Sangameshwar.

The application for the patent was published on Feb. 27, under issue no. 09/2026.

According to the abstract released by the Intellectual Property India: "The present invention relates to an AI-based border surveillance system integrating edge-level spatio-temporal video analysis with centralized GPU-accelerated verification. A camera module (110) captures video that is processed by preprocessing unit (112). Spatial features are extracted using module (114), and temporal motion patterns are analyzed using module (116) deployed on a single board computer (118). An adaptive inference controller (119) optimizes execution based on motion activity. Suspicious frames are transmitted through wireless module (120) to a server (122). A GPU module (124) performs super-resolution enhancement, followed by intrusion verification using module (126). A confidence-fusion module (127) produces final intrusion confirmation. Verified events are stored in database (128) and alerts are generated via interface (130). The invention provides low-power, scalable, and reliable surveillance for remote border environments."

Disclaimer: Curated by HT Syndication.