3. Vehicle Health Monitoring and Diagnostics Quality assurance in manufacturing department
of 2-wheeler automobiles using machine vision
It consists of a client micro-computer device within the
vehicle coupled to sensors as well as with
communication system for managing and transmitting
the vehicle’s health data to remote Hero service
center, where this data is analysed and is then
forwarded to user’s mobile providing the information
regarding client vehicle’s health.
In regards to 2-wheeler vehicle driver assistance
using Proposed Secure Helmet, a large and public
real-life dataset of subjects, with video segments
labeled as low vigilant, drowsy and yowining.
A small range night vision camera is attached on the
glass shield of our helmet with a connectivity to
Raspberry Pi3 Module and a Speaker.
Driver Assistance and Monitoring using AI &
Embedded Systems
Low Vigilant Yawning Drowsiness
It is used in quality assurance sector where in the
parts of the automobile are tested and analysed
according to the requirements of the manufacturer.
This is very important area where quality of end-
product is decided and is visualised with utmost
care.
Parts manufacturers can capture images of each
component as it comes off the assembly line, and
automatically run those images through a machine
learning model to identify any flaws.
Muffler 3D constructionDeep Learning Model
4. Vehicle Health Monitoring and Diagnostics Quality assurance in manufacturing department
of 2-wheeler automobiles using machine vision
Sensors are placed in near by brakes, tyres, clutch,
fuel & oil tank and at the end of muffler to collect data
required for the analysis of vehicle’s health by the
remote Hero service center which they incorporates
parameters such as mileage, pollution concentrated
emission control etc.
During real time evaluation, camera will capture the
video continuously, our deep learning model will
detect and track the movements of eyes, mouth and
face of driver. This will send a signal to Raspberry Pi3
module and alert the user about his condition in the
form of voice signals similar to Google Assistant.
Further, we are using a GPS connectivity to alert the
user regarding the crowd/traffic near him/her. In
addition, we can also make user aware of nearby
hospitals, restaurants, hotels, dormitories etc.
Maintaining adequate tyre pressures, information
related to loosening of brake,overriding of clutch,
leaking oil from oil tank and rate of consumption of
fuel, will help in improving the overall performance
and fuel efficiency of bike as the feedback of proper
maintenance and timely servicing information will be
shared to client’s mobile from remote service center
using our novel embedded system.
Driver Assistance and Monitoring using AI &
Embedded Systems
The driver assistance is taken care using real time
machine learning models which looks after the
customer safety. The prolonged yawning or
drowsiness may lead to accidents and this tool will
pervade the user to be alert during the ride.
Highly-accurate anomaly detection algorithms can
detect issues down to a fraction of a millimeter.
Predictive analytics can be used to evaluate whether
a flawed part can be reworked or needs to be
scrapped.
This feature of machine vision having high speed
algorithms just require milliseconds to detect and
process image information. Eliminating or re-
working faulty parts at quality testing stage is far
less costly than discovering and having to fix them
later. It saves on more expensive issues down the
line in manufacturing and reduces the risk of
costly recalls. It also helps ensure customer
safety, satisfaction and retention.