Skip to content

An AI based mobile application aimed to help drivers not to fall asleep using Google's TFlite machine learning

Notifications You must be signed in to change notification settings

heyprincesingh/phantom-drive

Repository files navigation

PHANTOM DRIVE

Problem

It has been estimated that drowsiness causes between 10% to 20% of traffic accidents, causing both fatalities, deaths and injuries , whereas within the trucking industry 57% of fatal truck accidents are caused by this problem. In recent years, driver drowsiness has been one of the major causes of road accidents and can lead to severe physical injuries, deaths and significant losses. A driver who falls asleep at the wheel loses control of the vehicle, an action which often results in a crash with either another vehicle or stationary objects.

Application Work

Our app is a car safety , AI based technology which helps to prevent accidents by alerting the driver, when gets drowsy. It senses and monitors each and every body postures and eye movements while driving.If the driver is drowsy and fatigued it will sense the body posture and alert the driver by an alerting sound.If our driver falls asleep for more than 15 seconds it will send an automatic message to the sos conctacts with their live location.
We used Google teachable machine trains the computer to recognize image sound and pose of the driver and Tensorflow lite is used to fetch the data, also converts and optimizes tensor flow models to run on mobile and edge devices. Our app analyses and interprets visual data,if the driver is sleeping or not.

SCREENSHOTS



About

An AI based mobile application aimed to help drivers not to fall asleep using Google's TFlite machine learning

Resources

Stars

Watchers

Forks

Packages

No packages published