Phys-3D: Physics-Constrained Real-Time Crowd Tracking and Counting on Railway Platforms

TL;DR

This paper introduces Phys-3D, a real-time crowd tracking and counting system for railway platforms that uses physics-based motion modeling and deep learning to improve accuracy under occlusions and dynamic conditions.

Contribution

The paper presents a novel physics-constrained Kalman filter integrated with deep learning detection and appearance models for improved crowd counting during train arrivals.

Findings

Achieved a counting error of 2.97% on the MOT-RPCH dataset.

Demonstrated robustness under occlusions and dynamic camera motion.

Enabled reliable crowd monitoring for safety and capacity management.

Abstract

Accurate, real-time crowd counting on railway platforms is essential for safety and capacity management. We propose to use a single camera mounted in a train, scanning the platform while arriving. While hardware constraints are simple, counting remains challenging due to dense occlusions, camera motion, and perspective distortions during train arrivals. Most existing tracking-by-detection approaches assume static cameras or ignore physical consistency in motion modeling, leading to unreliable counting under dynamic conditions. We propose a physics-constrained tracking framework that unifies detection, appearance, and 3D motion reasoning in a real-time pipeline. Our approach integrates a transfer-learned YOLOv11m detector with EfficientNet-B0 appearance encoding within DeepSORT, while introducing a physics-constrained Kalman model (Phys-3D) that enforces physically plausible 3D motion dynamics through pinhole geometry. To address counting brittleness under occlusions, we implement a virtual counting band with persistence. On our platform benchmark, MOT-RailwayPlatformCrowdHead Dataset(MOT-RPCH), our method reduces counting error to 2.97%, demonstrating robust performance despite motion and occlusions. Our results show that incorporating first-principles geometry and motion priors enables reliable crowd counting in safety-critical transportation scenarios, facilitating effective train scheduling and platform safety management.