Public Transport Crowd Estimation via Bus Stop Images Using AI

: Urban areas are rapidly expanding, increasing pressure on public transportation systems. Bus stops often become overcrowded, causing inconvenience, safety risks, and service delays. Traditional methods of monitoring passenger density, such as manual counting and ticket-based estimation, are often slow and inaccurate, and lack real-time insights.This research proposes an Artificial Intelligence-based crowd estimation system using images captured from cameras installed at bus stops. The system applies computer vision and deep learning techniques to automatically detect and count passengers. Models such as Convolutional Neural Networks (CNNs) and object detection algorithms like YOLO or Faster R-CNN are used to identify individuals under varying conditions such as lighting, occlusion, and weather.The system continuously monitors passenger density and provides real-time data to transportation authorities. This helps identify peak hours, optimize bus schedules, reduce congestion, and improve passenger safety, contributing to more efficient public transport management.