MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641049946 A) filed by Prasad V. Potluri Siddhartha Institute Of Technology on April 20, 2026, for Automatic Door Unlock System Using Face Recognition.
Inventors include D. Kavitha; A. Veera; Lavanya; Ch. Chakravardhan Reddy; B. Sathvik Sai; and K. Phani Sreeja.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: ABSTRACT OF THE INVENTION The increasing number of road accidents caused by unexpected animal crossings and obstacles on highways has created the need for intelligent and automated detection systems to enhance road safety and reduce accident rates. This invention presents a Monocular Vision-Based Low-Cost Real- Time Highway Hazard Detection and Dynamic Risk Assessment System that integrates computer vision, deep learning-based object detection, and real-time processing for efficient highway monitoring. The system utilizes a YOLOv8 model to analyze continuous video streams and detect objects such as animals, humans, and vehicles under varying environmental and low-light conditions. The detected objects are further processed using a monocular distance estimation module, which approximates object distance based on geometric relationships, enabling spatial awareness without the need for expensive sensors. A dynamic risk assessment mechanism evaluates the severity of detected hazards by considering object type and proximity, classifying them into multiple risk levels. The system operates through an optimized real-time pipeline, ensuring fast and accurate detection suitable for practical deployment. Additionally, the system incorporates a web-based interface that provides realtime visualization, annotated outputs, and alert notifications for drivers or ~ monitoring authorities. The overall framework improves situational awareness, E -LoL. reduces manual monitoring effort, and supports scalable deployment in rural (0 e~n and wildlife-prone highway environments.
Disclaimer: Curated by HT Syndication.
