In this repository are found the best Machine Learning models produced in the project Intelligent Vehicle Perception Based on Inertial Sensing and Artificial Intelligence. You can run them on Google Colab, Kaggle or Binder.
In this notebook, we detail the Passive Vehicular Sensors Datasets (PVS) 1-9 in the form of interactive maps illustrating the data classes and tables with the data distribution. These datasets contain data from accelerometer, gyroscope, magnetometer, temperature, GPS and camera sampled in vehicles.
In this notebook, we present a road surface type classification model using inertial sensors data and deep learning approach. The best model consists of a Convolutional Neural Network (CNN) that has as input: accelerometer data (X, Y, Z), gyroscope data (X, Y, Z) and speed; and as output: the road surface type between dirty, cobblestone and asphalt segments.
TODO
TODO
This project is under Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0). Please see License File for more information.