MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202631073520 A) filed by National Institute Of Technology Jamshedpur on June 12, 2026, for A System And Method For Real-Time Vehicle Identification Using Deep Learning And Temporal Aggregation.
Inventors include Premdeep; Vijay Kumar Dalla; Nidhi Dua; and Kawal Lal Kurre.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: [0051] The method and system for real-time vehicle identification involve capturing video frames, detecting vehicles using an object detection model, and tracking them with a multi-object tracking algorithm. License plates are detected and optical character recognition is performed to generate candidate text readings with confidence scores. Multiple readings are collected and clustered based on string similarity, with a cumulative confidence score calculated for each cluster. The cluster with the highest score is selected, and the final license plate number is determined from this cluster. The system includes modules for video input, vehicle detection, tracking, license plate detection, and optical character recognition, along with a temporal aggregation module for processing candidate text readings.
Disclaimer: Curated by HT Syndication.
