RMG Visual Anti-Collision System

It is an Intelligent Active Safety Protection System custom-developed for large Rail-Mounted Gantry Cranes (RMGs) in railway container stack yards. The system employs multi-sensor fusion perception and AI-powered visual analysis technologies to achieve real-time detection, classification, motion trend prediction, and intelligent anti-collision response for various obstacles within the RMG’s operating area, thereby effectively ensuring operational safety and continuous equipment operation in railway stack yards.

Vision-first recognition and classification

Wide-angle HD industrial cameras deployed at the RMG door legs and saddle beams, based on a self-developed lightweight deep neural network model, are the first to perform real-time semantic segmentation and object detection in a 15-meter range, quickly identifying obstacle categories (such as personnel, straddle carriers, and adjacent RMGs) and making a preliminary judgment of their motion intentions.

Lidar-assisted

Combined with LiDAR point cloud data, it achieves high-precision 3D modeling and verification of obstacle contours and distances.

Centimeter-Level Electronic Fencing and Adaptive Protection

Leveraging laser and vision fusion perception, a virtual electronic fence with centimeter-level accuracy is delineated along the RMG’s travel path; it supports flexible configuration across multiple areas and angles; the fence status is updated in real time and the protection range can be dynamically adjusted according to the operation plan and scenarios.

Intelligent Deceleration and Smooth Control

The system automatically adjusts the RMG trolley speed based on the collision risk level, achieving a smooth transition from “early warning to deceleration and then to stopping.”