Potential Escalator-related Injury Identification and Prevention Based on Multi-module Integrated System for Public Health

TL;DR

This paper presents a multi-module computer vision system for real-time escalator injury prevention by monitoring unsafe behaviors, objects, and escalator identification to enhance public safety.

Contribution

The study introduces an integrated safety monitoring system combining escalator identification, passenger pose estimation, and object detection for proactive injury prevention.

Findings

System demonstrates high accuracy in detecting unsafe behaviors.

Effective identification of large objects entering escalators.

Potential for real-world application in public safety enhancement.

Abstract

Escalator-related injuries threaten public health with the widespread use of escalators. The existing studies tend to focus on after-the-fact statistics, reflecting on the original design and use of defects to reduce the impact of escalator-related injuries, but few attention has been paid to ongoing and impending injuries. In this study, a multi-module escalator safety monitoring system based on computer vision is designed and proposed to simultaneously monitor and deal with three major injury triggers, including losing balance, not holding on to handrails and carrying large items. The escalator identification module is utilized to determine the escalator region, namely the region of interest. The passenger monitoring module is leveraged to estimate the passengers' pose to recognize unsafe behaviors on the escalator. The dangerous object detection module detects large items that may enter the escalator and raises alarms. The processing results of the above three modules are summarized in the safety assessment module as the basis for the intelligent decision of the system. The experimental results demonstrate that the proposed system has good performance and great application potential.