Sensors and Signal Processing For High Accuracy Passenger Counting Final Report

It is imperative for a transit system to track statistics about their ridership in order to plan bus routes. There exists a wide variety of methods for obtaining these statistics that range from relying on the driver to count people to utilizing cameras and sensors. Utah State University (USU) has undertaken the task of creating a high accuracy people counter using a texel camera. The project has two main objectives. The rst and most important is to develop a system that accurately counts the number of people entering and exiting a bus. The second is to associate each exiting passenger with a passenger that previously entered. This information will better allow a transit system to track usage of buses and stops. The project has been divided into two phases. This report covers the work done in phase I. Phase II would be carried out under additional funding. The primary goal of phase I is to develop a proof of concept system for the people counter with the software algorithms needed to perform accurately. Phase II will involve the optimization of the algorithms used and the design and manufacturing of a prototype system that can be installed a bus. The optimization will be performed at USU, while VPI Engineering (a third-party interested in commercial system production) will work to produce a prototype system.