Comparative Analysis of Anpr and TIRTL Systems Using Artificial Neural Networks for Traffic Speed Management

Transportation networks are struggling with increased traffic due to mixed flows and the unregulated growth of private vehicles. Over-speeding and congestion are critical issues for urban planners. Effective speed management and enforcement are essential to mitigate excessive speed, which is a major cause of traffic accidents. This study aims to develop efficient traffic speed management measures by evaluating the performance of Automatic Number Plate Recognition (ANPR) and The Infra-Red Traffic Logger (TIRTL) in data collection and the detection of excessive speeding. The results show ANPR detected only 51% of the vehicle classes, while TIRTL detected 96% of them. A maximum speed reduction of 20 km/h was observed in the vehicles, with an average reduction of 8 km/h. The ANN model developed can help urban planners devise new speed management techniques by accurately estimating their effectiveness in an urban setting.