Distributed subway station safety detection system based on Raspberry Pi

• Published in: 2022 5th International Conference on Data Science and Information Technology (DSIT) pp. 1 - 5
• Main Authors: Wang, Yang, Jiang, Shenggang, Zeng, Zhao, Xiong, Hanyue, Fang, Qiubao, Li, Yazhuo
• Format: Conference Proceeding
• Language: English
• Published: IEEE 22.07.2022
• Subjects: Air quality; Distributed databases; distributions; environmental detection; passenger detection; Performance evaluation; Raspberry Pi; Real-time systems; Wireless communication; Wireless LAN; Wireless sensor networks
• DOI: 10.1109/DSIT55514.2022.9943833

To ensure the safety of subway and maintain a good operating environment is the primary task of station operating units. Therefore, the environmental and passenger detection of the key locations in the subway station is necessary, to obtain real-time information such as the air quality status in the station and the density of passenger at the station hall layer and the platform layer. Station operation management department can adjust the station operation and emergency plan in real time according to the various data and information inside the station to improve the security of passengers and property in the station. The traditional detection system performs data processing on the server and has too high requirements for the server. The raspberry Pi as an embedded device have abilities of environment detection, data processing and information transmission on the local area. Multiple Raspberry Pi can be distributed at the key locations in the subway station, sending processed detection data to the server through wireless ways, which can greatly reduce the requirements of the server performance of the station monitoring system. In order to realize air quality detection and passenger detection in station, this paper designs a distributed detection system based on Raspberry Pi 4 platform. Real-time detection and upload of air quality parameters such as temperature, humidity, CO and smoke in station and passenger detection parameters such as passenger number and passenger flow density. The system has the characteristics of low cost, high accuracy and strong real-time.