MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202641123709 A) filed by J. J. College Of Engineering And Technology on October 15, 2026, for Ai Based Unreserved Coach Crowd Management.
Inventors include Dr. P. Balakrishnan; Dr. P. Mathiyalagan; Dr. G. Sundararajan; Mr. P. John Britto; Mr. S. Karthikeyan; Mr. S. Thomas Praveen Joseph; Mrs. R. Gayathri; Ms. P. Manimekala; Mrs. Ar. Manjuladevi; S. Dharshan; and A. Anash Mohamed.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: An unreserved coach management system using an AI function provided in estimating the number of passengers in the railway coach door is disclosed. The passengers are monitored using a dome-type CCTV camera and video data are processed locally by an edge computing device. YOLO11 detects persons and ByteTrack assigns persistent tracking identifiers. A virtual reference line with an intermediate margin zone is defined in the camera view. When tracked persons cross the line in a direction that differs from the previous, it is considered to be an entry/exit, and an inside passenger counter will be updated. Occupancy percentage calculated with a set of parameters (configurable coach capacity) and a crowd-status indication may be generated. Processed video and statistics are made available via a Flask-based dashboard and machine-readable occupancy data is provided through a REST/JSON interface. The prototype is based on Raspberry Pi 5, Hailo AI accelerator, Broadcom BCM2712 processor and core video processing is left on the edge device.
Disclaimer: Curated by HT Syndication.
