A preliminary implementation of convolutional neural network in embedded system for road pavement quality classification

Alessio Gagliardi; Vanessa Staderini; Sergio Saponara

doi:10.1117/12.2618466

27 May 2022 A preliminary implementation of convolutional neural network in embedded system for road pavement quality classification

Alessio Gagliardi, Vanessa Staderini, Sergio Saponara

Author Affiliations +

Proceedings Volume 12102, Real-Time Image Processing and Deep Learning 2022; 121020I (2022) https://doi.org/10.1117/12.2618466
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

This paper proposes an embedded implementation able to evaluate the pavement quality of road infrastructure by using a low-cost microcontroller board, an analog microphone placed inside the tyre cavity and a Convolutional Neural Network for real-time classification. To train the neural network, tracks audio were collected employing a vehicle moving at different cruise speeds (30, 40, 50 km/h) in the area of Pisa. The raw audio signals were split, labelled and converted into images by calculating the MFCC spectrogram. Finally, the author designed a tiny CNN with a size of 18KB able to classify five different classes: good quality road, bad quality road, pothole-bad road, silence and unknown. The CNN model achieved an accuracy equal to 93.8 % on the original model and about 90 % on the quantized model. The finale embedded system is equipped with BLE communication for the transmission of information to a smartphone equipped with GPS and obtain real-time maps of road quality.

Conference Presentation

Citation Download Citation

Alessio Gagliardi, Vanessa Staderini, and Sergio Saponara "A preliminary implementation of convolutional neural network in embedded system for road pavement quality classification", Proc. SPIE 12102, Real-Time Image Processing and Deep Learning 2022, 121020I (27 May 2022); https://doi.org/10.1117/12.2618466

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available