Wi-Fi based passenger counting - Using Indoor localization methods to classify detected devices as being inside vehicle or outside.
keywords AUTOMATED PASSENGER COUNTING, IOT AND SENSORS, LOCALISATION METHODS, WI-FI
Reference persons CRISTINA PRONELLO
Research Groups Transport Research for Innovation and Sustainability (TRIS)
Thesis type EXPERIMENTAL - DESIGN
Description Passenger counting within public transport systems uses various methods. There are several devices on the market, which mainly use optical systems such as stroboscopic cameras or video cameras. Market analysis shows that these systems are claimed to be highly accurate in laboratory tests, but this is not the case in the field. Analysing the pros and cons and the accuracy in the field - by obtaining data from the transport companies - will make it possible to understand whether or not Wi-Fi-based systems can be a viable alternative, also in terms of cost for the company compared to video cameras. The end result will be a simple prototype that incorporates an algorithm that provides sufficiently good accuracy and that could possibly also work in conjunction with other systems based on an optical approach. The need is to find a compromise between cost and accuracy, in an environment that can accommodate more than one passenger counting device.
Required skills Programming knowledge especially in Python, some knowledge of C will be beneficial but not mandatory. Some knowledge of IoT and of systems based on Wi-Fi.
Deadline 05/11/2023 PROPONI LA TUA CANDIDATURA