Advanced Driver Assistance System Using Computer Vision and IOT

Advanced driver assistance systems (ADAS) assist the driver by providing vital information and by automating some actions. We have proposed an advanced technique based on deep learning and IOT that can monitor the driver and surroundings of the car by providing a quantifiable increase in safety and security. The sensors are embedded in the steering of the car to monitor the heartbeat of the driver. The proposed technique is to detect and classify cars, bicycles, pedestrians as well as to inform the user if there is any abnormality in the driver's heartbeat by implementing deep learning techniques and the technology of internet of things. This paper provides a well-defined structure for live data analysis using firebase which is a real time database. The proposed method is mainly supported by the real time object detection and classification which is implemented using Mobile Net and Single shot detector. The sensor that is used for pulse rate detection is INVNT_11 and the further processing is done using Arduino. CC3200 is used for sending message to medical services when there is any anomaly or abnormality in the driver's BPM. The ESP8266 is used for sending the data to firebase, where the driver's state can be monitored and analysed.