Bus Headcount Analysis App Using Deep Learning

Public transport is crowded, and with increasing demand, we must find a balance between space and allocated resources to meet the needs of residents. The BEST is the second largest mass transit system in Mumbai along the network of suburban trains and ferries, However, problems such as an irregular bus schedule and overcrowding are still faced.With the rapid development of technology such as informat ion, AI/ ML, and communication in recent years, it is becoming increasingly possible to improve the efficiency of conventional transportation systems through the application of advanced technologies. In general, most of the available passenger counting systems consist of sensors and counters to count the number of passengers on public transport but this system might give inaccurate counting. To overcome the highlighted issues, this paper proposes an automatic passenger counting system by using a deep-learning algorithm to count the number of passengers in the bus. The proposed system provides accurate and up-to-date headcount estimates. This headcount is further reflected in the android application along with several other features like Bus number, the route, and location of the bus. The passenger gets information whether the bus is crowded or not, making the journey comfortable. This approach has the potential to revolutionize the way that bus headcount data is analyzed, providing insights into passenger behavior, and enabling optimized resource allocation for bus operators.