Intelligent Traffic Light System Using Computer Vision with Android Monitoring and Control

One of the predominant cause of the diminishing productivity of the Philippines that affects its residents and industry sectors alike is no other than the unresolved traffic. Numerous efforts have been implemented in the country to regulate traffic including road expansion, highway development and application of several traffic schemes. One of the research thrust being studied is the solution to the limitation of traditional traffic light systems. Existing literatures in traffic light system embarked on intelligent transportation system (ITS) that is typically based its operation on real-time traffic density data, however implemented in limited control. This paper discussed an approach in developing traffic signaling system capable of prioritizing congested lanes based on real-time traffic density data and integrated with an automated and manual control ported in a mobile android-based application. The system worked with CCTV cameras positioned at every lane of the intersection for the acquisition of traffic images transmitted to the Raspberry Pi 3 microcontroller for traffic density calculation using image processing. It utilized a traffic monitoring system and traffic lights operation control via a mobile android-based application. The system was tested and yielded an average of 92.83% and 85.77% vehicle detection rate for daytime and nighttime respectively. Moreover, an overall system reliability of 92.82% and 85.77% were obtained during daytime and nighttime testing based on the android GUI, lane prioritization and traffic light response. Future work involved integrating the Internet of Things (IoT) on the traffic light system for a wider scope interconnected implementation.