01627726

Component

The phenomenon of large pedestrian flow is common in shopping malls, tourist attractions and transportation hubs during holidays. Obtaining real time pedestrian data has become increasingly important to business strategy adjustment and guiding measures. Taking advantage of the wide use of smartphones and wireless technology, WIFI based system has been applied to detecting the pedestrian flow volume, which can capture the unique Media Access Control addresses of devices through WIFI probes. But often with low detection rate and precision. This paper mainly proposes an enhanced method to increase detection rate and precision under WIFI based system. Two data screening criteria were firstly identified to process original data. Based on the theoretical analysis on the influences of probes’ relative locations, four probe layout schemes were compared and the optimal one with the highest detection rate was identified experimentally. Using the optimal layout scheme, a data processing of direction distinguished detection is proposed. In order to improve the detection precision, this paper proposes an estimation model between detected pedestrian flow and actual pedestrian flow by establishing a cubic spline interpolation function. The model was verified experimentally at Tongji University, showing a high estimation precision (average error -11.21%). The results of experiments proved that the proposed method can effectively improve the detection rate and precision of pedestrian flow volume and help increase the reliability and application value of WIFI based detection.

This paper was sponsored by TRB committee ABJ35 Standing Committee on Highway Traffic Monitoring.

01618707

17-03017

English

15p

2017

Transportation Research Board 96th Annual Meeting

Digital/other

Figures; References; Tables

Data quality; Detection and identification systems; Methodology; Pedestrian flow; Reliability (Statistics)

IEEE 802.11 (Standard)

Data and Information Technology; Pedestrians and Bicyclists

Transportation Research Board Annual Meeting 2017 Paper #17-03017

TRIS, TRB, ATRI

Dec 8 2016 11:08AM