基于多模块集成系统的自动扶梯相关伤害识别与预防以保障公共卫生
计算机视觉与模式识别
2022-02-04 v2
摘要
随着自动扶梯的广泛使用，扶梯相关伤害威胁着公共卫生。现有研究倾向于关注事后统计，反思原始设计与使用缺陷以降低扶梯相关伤害的影响，但极少关注进行中与迫近的伤害。本研究设计并提出一种基于计算机视觉的多模块扶梯安全监控系统，以同时监测并处理三大伤害诱因，包括失去平衡、未握扶手及携带大件物品。扶梯识别模块用于确定扶梯区域即感兴趣区域。乘客监测模块用于估计乘客姿态以识别扶梯上的不安全行为。危险物体检测模块检测可能进入扶梯的大件物品并报警。上述三模块的处理结果在安全评估模块中汇总，作为系统智能决策的依据。实验结果表明，所提系统具有良好的性能与巨大的应用潜力。
引用
@article{arxiv.2103.07620,
title = {Potential Escalator-related Injury Identification and Prevention Based on Multi-module Integrated System for Public Health},
author = {Zeyu Jiao and Huan Lei and Hengshan Zong and Yingjie Cai and Zhenyu Zhong},
journal= {arXiv preprint arXiv:2103.07620},
year = {2022}
}
备注
Please excuse me for taking some of your time. But that we have not yet studied our work completely and some new great results are discovered. So after carefully thinking, we are going to rearrange this manuscript and try to give more precise model. Thus, we decided to withdraw this manuscript with great pity