MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202641094268 A) filed by Karpagam College Of Engineering; Karpagam Academy Of Higher Education; Ms. B Lakshmi; and Mr. Amarjith P T on August 04, 2026, for Location-Based Collision Analysis To Detect Accident Blackspot Zones And Its Alternative Measures For Coimbatore City.
Inventors include Ms. B Lakshmi; and Mr. Amarjith P T.
The application for the patent was published on August 07, 2026, under issue no. 32/2026.
Abstract: Urban traffic congestion and road safety have become significant challenges in developing smart cities, where traditional traffic management systems rely on manual monitoring and lack real-time responsiveness. These limitations make it difficult to track overspeeding vehicles, analyze traffic flow accurately, and enforce rules consistently. To address these issues, this project proposes a Smart City Traffic Management System that leverages artificial intelligence, computer vision, and web technologies to automate traffic surveillance and improve operational efficiency. The system is designed using Python, the Flask web framework, and the YOLOv8 deep learning model for real-time vehicle detection and tracking. By processing live camera feeds or recorded traffic footage, it identifies individual vehicles, calculates their speed using pixel displacement and real-world calibration, and determines compliance with speed limits. In cases of violations, the system generates instant alerts and logs the incident with relevant details. Additionally, it performs vehicle counting to assess traffic density and flow patterns, storing this information in a structured database for future analysis and planning. The Flask-based web interface allows traffic officials to monitor streams, view alerts, track vehicle counts, and access analytics dashboards, facilitating efficient management and quick response. By automating surveillance and leveraging YOLOv8’s high accuracy in detecting cars, buses, and bikes under diverse conditions, the system reduces human error, minimizes labor, and provides 24/7 monitoring. Its lightweight implementation allows deployment on edge devices, making it scalable across multiple traffic junctions. Overall, the proposed solution enhances road safety, ensures consistent rule enforcement, and supports the smart city vision by enabling safer, more efficient, and data-driven traffic management.
Disclaimer: Curated by HT Syndication.
