How AI would save more than 100,000 crashes and injuries caused by distracted driving.

22/12/2019

Distracted driving is a serious and growing threat to road safety.

According to the National Highway Traffic Safety Administration (NHTSA), about 25% of police-reported crashes involve some form of driver inattention.

Driving while being inattentive (drowsy or distracted) is dangerous, there are different types of driver distraction, Human drivers may be inattentive, under the influence of alcohol or other substances, drowsy, or otherwise impaired.

According to experts, many drivers fail to recognize they are fatigued. In consequence, developing technologies to detect and alert inattentive drivers is essential to avoid vehicle accidents and to stimulate safe driving practices in drivers.

The rapid growth in the possession and use of mobile phones is the most common reason for distracted driving. Evidence shows that the distraction caused by talking on mobile phones can impair driving performance in several ways, e.g. longer reaction times (notably braking reaction time), impaired ability to keep in the correct lane, and shorter following distances. Texting also results in considerably reduced driving performance, with young drivers at particular risk.

Lizmotors is developing a driving behavior monitoring system that applies computer vision and pattern recognition techniques. This system monitors Facial expression, eye movement, drowsiness, head pose, and many more feature sets.

In-vehicle driving behavior monitoring system detects inattentive driving behaviors and gives corresponding feedback to drivers, scoring their driving and alerting them in case their behaviors are unsafe. It uses computer vision and pattern recognition techniques to assess whether the driver is drowsy or distracted using the image sensors, the microphone, the inertial sensors, and the GPS.

In addition to it, the device calculates the driving scores, driving as a function of the frequency and level of these dangerous behaviors. In case they get over a certain threshold an alarm is generated and alerted to the back office as well as a sound alert in the cabin and force the driver to pull over until the driver is fully able to operate the vehicle successfully.

Although the cost of vehicle safety technology is dropping, most safety technologies are not available in economy vehicles.

Lizmotor's vehicle driving behavior monitoring system can be installed in all vehicles and represent a cheap and disruptive safety technology powered by Artificial Intelligence, Edge Computing, and Connectivity.