While many technological solutions have been implemented for accident detection, not many have focused on accident prevention. Accidents have been an everlasting concern as they have caused heavy injuries and death tolls on a large scale. There has been an everlasting increase in the rate of accidents and violation of traffic laws and wrongdoers managing to escape from the legal ramifications of predominantly Hit-and-Run cases. This entails a system to alleviate the occurrence of accidents and deaths caused. Focusing on this, a viable solution that focuses on preventing such circumstances by detecting accident-causing behaviour has been proposed. If accidents take place, it ensures the victim gets their rightful compensation. The research encompasses two modules, Prevention and Recovery. The prevention module uses Deep Learning and Computer Vision to detect whether the driver is drowsy and issues an alert employing CNN. The recovery module focuses on detecting occurrences of accidents and acquiring information about the parties involved in the same. Moreover, the prototype detects drowsiness, and detects and saves the accident footage in real-time enabling information acquisition.

Vehicular Safety Hit-and-Run Information Acquisition CNN Driver Attention Behavioral Detection Deep Learning Computer Vision