Identification and Prediction of Large Pedestrian Flow in Urban Areas Based on Hybrid Detection Approach

Recently the density of population grows quickly with the accelerated process of urbanization. At the same time, overcrowded scenarios are more likely to take place in popular urban areas, which increase the risk of accidents. With the advent of this information and big data age, there are opportunities to identify and pre-control large pedestrian flow through real-time information interface from wireless network. This paper proposes a synthetic approach to identify and recognize the large pedestrian flow. In particular, a hybrid pedestrian flow detection model was constructed by analyzing real data from major operators in China, including information from smartphones and Base Stations (BS). With the hybrid model, we utilize Log Distance Path Loss (LDPL) model to find the pedestrian density from raw network data, and make data recovery with Gaussian Progress (GP) through supervised learning. Temporal-spatial prediction of the pedestrian data were carried out with Machine Learning (ML) approaches. Finally, we conduct a case study of a real Center Business District (CBD) scenario in Shanghai using records of millions of real users. Results show the effectiveness of the approach and give insights for building intelligent urban city.

• Supplemental Notes:
  • This paper was sponsored by TRB committee ABJ35 Standing Committee on Highway Traffic Monitoring.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Wang, Mei
  • Zhang, Kaisheng
  • Wei, Bangyang
  • Sun, Daniel Jian
• Conference:
  • Transportation Research Board 96th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2017-1-8 to 2017-1-12
• Date: 2017

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References;
• Pagination: 17p
• Monograph Title: TRB 96th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Crowds; Crowdsourcing; Learning; Location; Pedestrian density; Pedestrian flow; Pedestrian safety; Smartphones
• Geographic Terms: Shanghai (China)
• Subject Areas: Data and Information Technology; Pedestrians and Bicyclists;

Filing Info

• Accession Number: 01628200
• Record Type: Publication
• Report/Paper Numbers: 17-06607
• Files: TRIS, TRB, ATRI
• Created Date: Mar 7 2017 10:25AM