Design of Analysis System for Driving Behaviour at Bus Stops

Abstract

Statistics indicate that many road accidents stem from driver negligence, such as collisions with parked cars, motorcyclists or pedestrians in blind spots. Although numerous studies address bus driver behaviour, most focus on freeways rather than urban streets. This paper introduces a safety assessment system (SAS) utilising existing onboard cameras on buses, eliminating the need for additional sensors. The SAS evaluates city bus drivers' behaviour when entering and exiting bus stops (ELBS), considering three key factors: entry velocity, head turn frequency to assess surroundings, and estimated distance from the road boundary upon arrival (DBR). Leveraging image and global positioning system (GPS) data, the system establishes risk levels for each scenario, aiding in identifying safe driving practices. To validate its feasibility, a professional survey was conducted, confirming alignment between the designed scoring scale and survey results.