Wireless Speed Control of Vehicles with Detection of Person & Zebra Crossing

Abstract

Pedestrians crossing zebra lines are one of the major concerns for road accidents. Nowadays, the number of road accidents increases due to careless driving and pedestrian motions at crosswalks. It is necessary to detect both person and zebra crossings properly and control vehicle speed accordingly. Here in this paper, a suitable solution that improves both detections can be introducing. Here used the TensorFlow Single Shot Detection (SSD) model is the best and most convenient trained model for Zebra line and person detection. A database is taking for the analysis. The input image could process as a crosswalk detection, which has more used for zebra crossing identification via the SSD model. Suppose detected the person and zebra crossings were at the same time. In that case, it will perform commands such as run, slow down, stop, horn, etc., with the help of wireless serial communication Universal Asynchronous Receiver-Transmitter. A Bluetooth command signal matches UART, which provides the vehicle with the necessary control inputs to execute the prescribed topology properly. Simultaneous detection of pedestrians at zebra crossings is a critical factor. It results most efficiently and to identify the person detection.