Multi-Contextual and Multi-Aspect Analysis for Road Surface Type Classification Through Inertial Sensors and Deep Learning
This project contains the Artificial Intelligence models and experiments developed for the paper Multi-Contextual and Multi-Aspect Analysis for Road Surface Type Classification Through Inertial Sensors and Deep Learning. In this research, we developed models for the road surface type classification, classifying between segments of dirt, cobblestone, and asphalt roads. We applied Deep Learning techniques based on Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), and Long Short-Term Memory Network (LSTM). We analyzed various aspects, such as the influence of the vehicle data collection placement, the analysis domain, the model input features, and the data window size. We also evaluate the generability of model learning for unknown contexts, such as an unknown car, driver, or environment. The contents of each folder are described below.
The jupyter notebooks present in the folders correspond to the applied techniques. To run the models, just change the folders where the datasets are located (datasets_folder) and the work folder that has the experiments (work_folder). These parameters are in the file Deep Learning - Processing.ipynb. Other instructions are documented in the source code.
This folder contains all the experiments performed. Each folder stores the experiments of a technique, among the generated models and execution logs.
You can request a full text for free at:
Or in scientific databases:
To cite this paper use:
J. Menegazzo and A. von Wangenheim, "Multi-Contextual and Multi-Aspect Analysis for Road Surface Type Classification Through Inertial Sensors and Deep Learning," 2020 X Brazilian Symposium on Computing Systems Engineering (SBESC), Florianopolis, 2020, pp. 1-8, doi: 10.1109/SBESC51047.2020.9277846.
@inproceedings{menegazzo_multi_contextual_2020,
title = {Multi-{Contextual} and {Multi}-{Aspect} {Analysis} for {Road} {Surface} {Type} {Classification} {Through} {Inertial} {Sensors} and {Deep} {Learning}},
doi = {10.1109/SBESC51047.2020.9277846},
booktitle = {2020 {X} {Brazilian} {Symposium} on {Computing} {Systems} {Engineering} ({SBESC})},
author = {Menegazzo, J. and Wangenheim, A. von},
month = nov,
year = {2020},
note = {ISSN: 2324-7894},
pages = {1--8}
}This project is under Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0). Please see License File for more information.