An Artificial Intelligence-based Proactive Blind Spot Warning System for Motorcycles

The goal of this research is to design a proactive bus blind spot warning (PBSW) system which will notify the motorcycle riders as soon as they enter the blind spot of a target vehicle, i.e., bus. The motorcycle side of this PBSW system, consisting of a Raspberry Pi 3B+ and a dual-lens stereo camera, will first transmit captured images to the Android phone using Wi-Fi and then to the cloud server through the cellular network. At the cloud server, the famous AI model, YOLOv4, is used to recognize the position of the rear-view mirror of the bus. By the principle of lens imaging, the distance between the bus and the motorcycle is estimated. Based on the estimated distance returned from the cloud server, the PBSW APP running in the Android phone illustrates the visible area/blind spot of the bus, the position of the rider and the estimated distance between the motorcycle and the bus. It further alarms the rider whenever the rider has entered the blind spot of the bus. According to performance evaluation on this implemented system, it recognizes the rear-view mirror with the average accuracy of 92.82%, the error rate of the estimated distance lower than 0.2% and the average round trip delay of 0.5 sec. It is concluded that this PBSW system keeps the motorcycle rider away from imminent dangers in real time.