MobiSense

The project

The MobiSense imec.icon project, which ran from October 1, 2017 until September 30, 2019, aimed at efficiently creating spatio-temporal information on road surfaces and their wear, based on opportunistic sensing on-board of ordinary vehicles. The project was funded under grant HBC.2017.0155 by imec and Vlaio (ICON scheme), and was coordinated by ASAsense. Ghent University, the University of Antwerp, and KU Leuven collaborate as scientific partners, wheras ASAsense, Be-Mobile and Qweriu develop the application-oriented part.

The project solves several important challenges:

Data collection
Collecting data from large numbers of vehicles and efficient big data processing;
Data analytics
Removing confounders and modifiers such as vehicle speed, differences in vehicle transfer functions, music and speech inside the vehicle, sound from other vehicles etc.;
Information extraction
Converting measured quantities to applicable knowledge for road administrators and environmental agencies;
Action planning
Embedding this knowledge in environmental assessment and road maintenance assessment.

Technology

Noise and vibration data is collected using proprietary hardware and software from a large number of cars that or on the road anyhow: we work with stakeholder fleets, car sharing, etc. On the server, trips are mapped to road segments and lanes and the abundancy of data is used to derive useful information about road segments such as rolling noise category, macrostructure, and waviness. Dedicated expert systems further process the information to knowledge on indicators of wear, pothole proficiency, or basic information on road pavement and speed bumps.

Outcomes

Within the proof-of-concept of the project, a large part of Flanders was covered. Below, a small part of the results are available online, for a selected region of the South of Ghent, Belgium.

Pavement noise label. As engine noise is being reduced by improved engine and muffler design stimulated by European vehicle noise policy, and as the market share of hybrid and electric vehicles will increase over the coming years, the contribution of rolling noise in environmental noise is prone to significantly increase. Tires and road pavement both contribute to rolling noise, hence tire noise labeling and road pavement labeling have been proposed. Road pavement choice and maintenance could become an important tool for environmental agencies in their noise action plans developed according to the European Noise Directive 2002/49/EC. The graph below uses colors to indicate the noise label. When clicking on a road segment, the spectrum on the right shows the spectral deviation dL (in dB) of the road segment compared to the standard surface.

Macrotexture spectrum. Macrotexture refers to spatial irregularities in the road pavement with characteristic lengths between a couple of cm and 1m. Macrotexture can be indicative for road surface wear and degradation. By carefully tuning the indicator, joints on bridges and concrete plates can be included or not. The figure below shows the macrotexture spectrum (in dB) for every clicked road segment.

Waviness. Waviness of the road is important for passenger comfort and cargo safety. It is also indicative for the state of the foundation of the road. The maps below show the amplitude of waviness with a spatial wavelength of 2 m and a spatial wavelength of 10 m.

Spatial length: 2 m

Spatial length: 10 m

Further developments

The technology developed by ASAsense within the project will be made available as a service for road authorities, such as cities or local governments. The technology is broadly applicable and covers local roads that can have a wide variety of pavements (asphalt, concrete, cobblestones etc.). For more information, please visit roads.asasense.com.

In the longer run, ASAsense plans to further refine the system, by including an expert system that helps to interpret texture data and identify road defects such as potholes, alligator cracks, rutting, etc., and by including predictive models for the evolution of pavement state, allowing to deploy maintenance campaigns just in time.

Publications

More technical details about this solution can be found in the references below. Feel free to contact us for inquiries.

J. David, W. Van Hauwermeiren, L. Dekoninck, T. De Pessemier, W. Joseph, K. Filipan, B. De Coensel, D. Botteldooren, L. Martens. Rolling-noise-relevant classification of pavement based on opportunistic sound and vibration monitoring in cars. In Proceedings of the 48th International Congress and Exhibition on Noise Control Engineering (Internoise), Madrid, Spain (2019).
W. Van Hauwermeiren, J. David, L. Dekoninck, T. De Pessemier, W. Joseph, D. Botteldooren, L. Martens, K. Filipan, B. De Coensel. Assessing road pavement quality based on opportunistic in-car sound and vibration monitoring. In Proceedings of the 26th International Congress on Sound and Vibration (ICSV), Montreal, Canada (2019).
L. Dekoninck, W. Van Hauwermeiren, J. David, K. Filipan, T. De Pessemier, B. De Coensel, W. Joseph, L. Martens, D. Botteldooren. Opportunistic in-vehicle noise measurements assess road surface quality to improve noise mapping: preliminary results from the MobiSense project. In Proceedings of the 23rd International Congress on Acoustics (ICA), Aachen, Germany (2019).
B. De Coensel, K. Filipan, W. Van Hauwermeiren, J. David, L. Dekoninck, T. De Pessemier, W. Joseph, L. Martens, D. Botteldooren. Opportunistic sensing for road pavement monitoring. In Proceedings of the Transport Research Arena (TRA), Helsinki, Finland (2020).
J. David, T. De Pessemier, L. Dekoninck, B. De Coensel, W. Joseph, D. Botteldooren, L. Martens. Detection of road pavement quality using statistical clustering methods. Journal of Intelligent Information Systems (2019).

Press coverage

The MobiSense project received some press coverage, links can be found below (all in Dutch):

De Standaard: https://www.standaard.be/cnt/dmf20191125_04737246
Het Nieuwsblad: https://www.nieuwsblad.be/cnt/dmf20191126_04738960
imec portfolio: MobiSense leaflet

MobiSense

The project

Technology

Outcomes

Further developments

Publications

Press coverage

Partners

Navigation

Company

Disclaimer