Scholarlink

This study proposes a new approach to address the limitations of traditional elevator systems when handling a large number of passengers during peak hours in high-rise buildings. The study proposes integrating a modified LOOK SCAN algorithm with a simulated YOLOv5 model for real-time people counting. Based on the number of people waiting at each floor and the number of people inside each elevator car, the modified algorithm dynamically adjusts the elevator movement and priority. The simulation results show significant improvements in average waiting time, average travel time, and approximated energy usage over the conventional LOOK SCAN algorithm. This research helps in creating intelligent and efficient elevator systems for modern high-rise buildings.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Improving Elevator Control Algorithms by Integrating with Computer Vision

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Vu Thu Diep,
  • Nguyen Dang Phat,
  • Phan Duy Hung

摘要

This study proposes a new approach to address the limitations of traditional elevator systems when handling a large number of passengers during peak hours in high-rise buildings. The study proposes integrating a modified LOOK SCAN algorithm with a simulated YOLOv5 model for real-time people counting. Based on the number of people waiting at each floor and the number of people inside each elevator car, the modified algorithm dynamically adjusts the elevator movement and priority. The simulation results show significant improvements in average waiting time, average travel time, and approximated energy usage over the conventional LOOK SCAN algorithm. This research helps in creating intelligent and efficient elevator systems for modern high-rise buildings.