/AIroadGuard

Let Our AI handle it.

Primary LanguageJupyter NotebookMIT LicenseMIT

AI roadGuard

Road accidents continue to be a leading cause of death, disabilities and hospitalization in the country despite our commitment and efforts. India ranks first in the number of road accident deaths across the 199 countries and accounts for almost 11% of the accident related deaths in the World. We aim to make emergency services work easier and efficient with the use of Machine Learning and technology.

About AI.roadGuard

AI.roadGuard can be deployed as a smart system of devices, It uses Machine Learning and Deep Learning models like convolutional neural networks to detect accidents using CCTV footage and notify the emergency services about the situation.

Important Links

Dataset Credit -

Accident Detection From CCTV Footage (by - Mr.Charan Kumar)

License : Open Data Commons Open Database License (ODbL) v1.0

The Machine Learning Algorithm

Model Diagram The model has test accuracy of 98.8% and validation accuracy of 92.8%. Further to reduce false calls to the portal we have deviced some measures.

Technologies Used -

OpenCV Python TensorFlow Keras NodeJS Express.js Next JS Git MongoDB

Scope of Improvement -

  • Increasing Accuracy of Machine Learning Model with the avalability of better dataset.
  • Deploying on real world devices.




AIRoadGuard is under MIT License, Please Read the LICENSE


Authors -

Aryan Raj

Aryan Raj

ML and CV Developer

Harsh Srivastava

Aryan Raj

MERN Stack Developer

Nikhil I

Aryan Raj

Competitve Programmer

Avya Rathod

Avya Rathod

ML and CV Developer

Mohd Zaid

MERN Stack Developer