Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Surface Status Classification, Utilizing Image Sensor Technology and Computer Models
Mid Sweden University, Faculty of Science, Technology and Media, Department of Electronics Design.
2015 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

There is a great need to develop systems that can continuously provide correct information about road surface status depending on the prevailing weather conditions. This will minimize accidents and optimize transportation. In this thesis different methods for the determination of the road surface status have been studied and analyzed, and suggestions of new technology are proposed. Information about the road surface status is obtained traditionally from various sensors mounted directly in the road surface. This information must then be analyzed to create automated warning systems for road users and road maintenance personnel. The purpose of this thesis is to investigate how existing technologies can be used to obtain a more accurate description of the current road conditions. Another purpose is also to investigate how existing technologies can be used to obtain a more accurate description of the current road conditions. Furthermore, the aim is to develop non-contact technologies able to determine and classify road conditions over a larger area, since there is no system available today that can identify differences in road surface status in the wheel tracks and between the wheel tracks.

Literature studies have been carried out to find the latest state of the art research and technology, and the research work is mainly based on empirical studies. A large part of the research has involved planning and setting up laboratory experiments to test and verify hypotheses that have emerged from the literature studies. Initially a few traditional road-mounted sensors were analyzed regarding their ability to determine the road conditions and the impact on their measured values when the sensors were exposed to contamination agents such as glycol and oil. Furthermore, non-contact methods for determining the status of the road surface have been studied. Images from cameras working in the visible range, together data from the Swedish Transportation Administration road weather stations, have been used to develop computerized road status classification models that can distinguish between a dry, wet, icy and snowy surface. Field observations have also been performed to get the ground truth for developing these models. In order to improve the ability to accurately distinguish between different surface statuses, measurement systems involving sensors working in the Near-Infrared (NIR) range have been utilized. In this thesis a new imaging method for determining road conditions with NIR camera technology is developed and described. This method was tested in a field study performed during the winter 2013-2014 with successful results.

The results show that some traditional sensors could be used even with future user-friendly de-icing chemicals. The findings from using visual camera systems and meteorological parameters to determine the road status showed that they provide previously unknown information about road conditions. It was discovered that certain road conditions such as black ice is not always detectable using this technology. Therefore, research was performed that utilized the NIR region where it proved to be possible to detect and distinguish different road conditions, such as black ice. NIR camera technology was introduced in the research since the aim of the thesis was to find a method that provides information on the status of the road over a larger area. The results show that if several images taken in different spectral bands are analyzed with the support of advanced computer models, it is possible to distinguish between a dry, wet, icy and snowy surface. This resulted in the development of a NIR camera system that can distinguish between different surface statuses. Finally, two of these prototype systems for road condition classification were evaluated. These systems were installed at E14 on both sides of the border between Sweden and Norway. The results of these field tests show that this new road status classification, based on NIR imaging spectral analysis, provides new information about the status of the road surface, compared to what can be obtained from existing measurement systems, particularly for detecting differences in and between the wheel tracks.

Place, publisher, year, edition, pages
Sundsvall: Mid Sweden University , 2015. , 104 p.
Series
Mid Sweden University doctoral thesis, ISSN 1652-893X ; 219
Keyword [en]
road condition, NIR, infrared, remote sensing, signal processing, classifiers
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:miun:diva-24828Local ID: STCISBN: 978-91-88025-13-5 (print)OAI: oai:DiVA.org:miun-24828DiVA: diva2:805161
Public defence
2015-05-05, Q221, Akademigatan 1, Östersund, 10:15 (English)
Opponent
Supervisors
Available from: 2015-04-15 Created: 2015-04-14 Last updated: 2016-12-23Bibliographically approved
List of papers
1. Road status sensors: A comparison of active and passive sensors
Open this publication in new window or tab >>Road status sensors: A comparison of active and passive sensors
2009 (English)In: TS116: Weather monitoring, 2009Conference paper, Published paper (Refereed)
Abstract [en]

Knowledge of the road status and specifically knowledge of the freezing point of the road surface fluid is crucial in order to perform effective and environmentally safe road maintenance. Road status sensors installed in the road can be passive conductivity sensors or active freezing point sensors. In this paper the output from a passive and an active sensor has been studied when the sensors has been contaminated with common chemicals that can be present on the road surface such as oil, alcohol and glycol. The results indicated that only intelligent active sensors reliably can detect freezing points on the road surface.

Keyword
Road status, road status sensors, freezing point
National Category
Control Engineering
Identifiers
urn:nbn:se:miun:diva-10379 (URN)2-s2.0-84954470884 (Scopus ID)
Conference
ITS World Congress 2009
Available from: 2009-12-02 Created: 2009-11-23 Last updated: 2017-09-14Bibliographically approved
2. Road Condition Discrimination: using Weather Data and Camera Images
Open this publication in new window or tab >>Road Condition Discrimination: using Weather Data and Camera Images
2011 (English)In: 2011 14TH INTERNATIONAL IEEE CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), IEEE conference proceedings, 2011, 1616-1621 p.Conference paper, Published paper (Refereed)
Abstract [en]

An intelligent way of determining the road condition is needed to perform an effective road maintenance that results in high accessibility of the road network and high traffic safety. The hypothesis is that data from existing meteorological sensors and camera images from Road Weather information Systems (RWiS) could be used to improve the road condition classification. Previous research has found that an image analysis alone can estimate the road condition. This paper aims to evaluate if an extensive dataset retrieved from a RWiS site is sufficient to give a more accurate road condition classification than one obtained with an image analysis alone. The study reveals that RWiS data gives additional information for discrimination of the road conditions compared to image analysis only.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2011
Series
IEEE International Conference on Intelligent Transportation Systems-ITSC
Keyword
RWIS, Road Condition, Camera images
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-14974 (URN)10.1109/ITSC.2011.6082921 (DOI)000298654700265 ()2-s2.0-83755174165 (Scopus ID)STC (Local ID)978-1-4577-2198-4 (ISBN)STC (Archive number)STC (OAI)
Conference
Conference: 14th International IEEE Conference on Intelligent Transportation Systems (ITSC) Location: Campus George Washington Univ (GWU), Washington, DC Date: OCT 05-07, 2011
Available from: 2011-11-30 Created: 2011-11-29 Last updated: 2016-10-19Bibliographically approved
3. Infrared Thermometry in winter road maintenance
Open this publication in new window or tab >>Infrared Thermometry in winter road maintenance
2012 (English)In: Journal of Atmospheric and Oceanic Technology, ISSN 0739-0572, E-ISSN 1520-0426, Vol. 29, no 6, 846-856 p.Article in journal (Refereed) Published
Abstract [en]

There is significant interest among road authorities in measuring pavement conditions to perform appropriate winter road maintenance. The most common monitoring methods are based on pavement-mounted sensors. This study's hypothesis is that the temperature distribution in a pavement can be measured by means of a nonintrusive method to retrieve the topmost pavement temperature values. By utilizing the latest infrared (IR) technology, it is possible to retrieve additional information concerning both road temperatures and road conditions. The authors discovered that surface temperature readings from IR sensors are more reliable than data retrieved from traditional surface-mounted sensors during wet, snowy, or icyroad conditions. It was also possible to detect changes in the road condition by examining how the temperatures in wheel tracks and in between the wheel tracks differ from a reference dry road condition. The conclusion was that nonintrusive measurement of the road temperature is able to provide an increase in relation to the knowledge about both the road temperature and the road condition. Another conclusion was that the surface temperature should not be considered as being equal to the ground temperatures retrieved from traditional surface-mounted sensors except under conditions of dry, stable roadways. © 2012 American Meteorological Society.

Keyword
Infrared detectors, Measurement techniques, Road accidents, Traffic information systems
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-14976 (URN)10.1175/JTECH-D-11-00071.1 (DOI)000305272100007 ()2-s2.0-84864765461 (Scopus ID)STC (Local ID)STC (Archive number)STC (OAI)
Available from: 2011-11-30 Created: 2011-11-29 Last updated: 2017-12-08Bibliographically approved
4. Classification of Road Conditions: From Camera Images and Weather Data
Open this publication in new window or tab >>Classification of Road Conditions: From Camera Images and Weather Data
2011 (English)In: 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE FOR MEASUREMENT SYSTEMS AND APPLICATIONS (CIMSA), IEEE conference proceedings, 2011, 91-96 p.Conference paper, Published paper (Refereed)
Abstract [en]

It is important to correctly determine road condition as it contains essential information for improving traffic safety. Knowledge about the road condition is used by maintenance personnel as a trigger for snow removal and deicing tasks. The presence of severe road conditions is also communicated as warnings and speed reduction recommendations to road users. Previous research shows that road images and data from Road Weather information Systems (RWiS) give enough information to identify road conditions, such as dry, wet, snowy, icy and tracks. The hypothesis of the new model was that it should be possible to develop a model that could classify road conditions from existing RWiS road weather data and road images. This paper proposes a model that gives a correct classification of the road conditions dry, wet, snowy and icy at an accuracy rate of 91% to 100%.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2011
Keyword
Road accidents, Traffic information systems, classification algorithms
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-14977 (URN)10.1109/CIMSA.2011.6059917 (DOI)000298805900017 ()2-s2.0-82955165719 (Scopus ID)STC (Local ID)978-1-61284-924-9 (ISBN)STC (Archive number)STC (OAI)
Conference
IEEE International Conference on Computational Intelligence for Measurement Systems and Applications (CIMSA)/IEEE International Conference on Virtual Environments, Human-Computer Interfaces and Measurement Systems (VECIMS) Location: Univ Ottawa, Ottawa, CANADA Date: SEP 19-21, 2011
Available from: 2011-11-30 Created: 2011-11-29 Last updated: 2016-10-19Bibliographically approved
5. Remote sensor for winter road surface status detection
Open this publication in new window or tab >>Remote sensor for winter road surface status detection
2011 (English)In: Proceedings of IEEE Sensors / [ed] IEEE, IEEE conference proceedings, 2011, 1285-1288 p.Conference paper, Published paper (Refereed)
Abstract [en]

This paper suggests a cost effective remote sensor for increasing traffic safety by detecting road surface conditions. One limitation of existing systems is the ability to reliably detect the presence of ice and snow on the road surface. By utilizing infrared detectors sensitive in the water absorption spectral range, it is possible to remotely detect the presence of water on a surface. Using the near infrared spectra to detect water is well known, but further research is desired on methods to distinguish water in the form of water, ice and snow. Remote sensors are easy to install and they have low service costs compared to road mounted sensors. Existing remote sensors are currently expensive, but by utilizing cost effective infrared detectors a sensor has been made that can be deployed at any road weather information system. Laboratory results showed that the sensor gave reliable output that distinguishes between the surface conditions dry, wet, snowy and icy.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2011
Keyword
Remote sensors, infrared, surface status
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-15404 (URN)10.1109/ICSENS.2011.6127089 (DOI)000299901200311 ()2-s2.0-84856894952 (Scopus ID)STC (Local ID)978-1-4244-9290-9 (ISBN)STC (Archive number)STC (OAI)
Conference
10th IEEE SENSORS Conference 2011, SENSORS 2011;Limerick;28 October 2011through31 October 2011;Category numberCFP11SEN-CDR;Code88419
Available from: 2012-01-20 Created: 2011-12-19 Last updated: 2016-10-19Bibliographically approved
6. Road surface status classification using spectral analysis of NIR camera images
Open this publication in new window or tab >>Road surface status classification using spectral analysis of NIR camera images
2015 (English)In: IEEE Sensors Journal, ISSN 1530-437X, E-ISSN 1558-1748, Vol. 15, no 3, 1641-1656 p.Article in journal (Refereed) Published
Abstract [en]

There is a need for an automated road status classification system considering the vast number of weather-related accidents that occur every winter. Previous research has shown that it is possible to detect hazardous road conditions, including, for example, icy pavements, using single point infrared illumination and infrared detectors. In this paper, we extend this research into camera surveillance of a road section allowing for classification of area segments of weather-related road surface conditions such as wet, snow covered, or icy. Infrared images have been obtained using an infrared camera equipped with a set of optical wavelength filters. The images have primarily been used to develop multivariate data models and also for the classification of road conditions in each pixel. This system is a vast improvement on existing single spot road status classification systems. The resulting imaging system can reliably distinguish between dry, wet, icy, or snow covered sections on road surfaces.

Keyword
Remote sensing, Infrared imaging, Spectral analysis, Image classification
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-24249 (URN)10.1109/JSEN.2014.2364854 (DOI)000348858300008 ()2-s2.0-84921047416 (Scopus ID)STC (Local ID)STC (Archive number)STC (OAI)
Available from: 2015-01-29 Created: 2015-01-29 Last updated: 2017-12-05Bibliographically approved
7. Road Condition Imaging: Model Development
Open this publication in new window or tab >>Road Condition Imaging: Model Development
2015 (English)Conference paper, Published paper (Refereed)
Abstract [en]

It is important to classify road conditions to plan winter road maintenance, carry out proper actions and issue warnings to road users. Existing sensor systems only cover parts of the road surface and manual observations can vary depending on those who classify the observations. One challenge is to classify road conditions with automatic monitoring systems. This paper presents a model based on data from winter 2013-2014, retrieved from two installations in Sweden and Norway. To address that challenge an innovative and cost effective road condition imaging system, capable of classifying individual pixels of an image as dry, wet, icy or snowy, is evaluated. The system uses a near infra-red image detector and optical wavelength filters. By combining data from images taken from different wavelength filters it is possible to determine the road status by using multiclass classifiers. One classifier for each road condition was developed, which implies that a pixel can be classified to two or more road conditions at the same time. This multiclass problem is solved by developing a Bayesian Network that uses road weather information system data for the calculation of the probabilities for different road conditions.

Keyword
Road condition, Near Infra Red, classification, remote sensing, Bayesian Networks
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-24250 (URN)STC (Local ID)STC (Archive number)STC (OAI)
Conference
Transportation Research Board 2015 Annual Meeting
Note

Paper number: 15-0885

Presented at the conference in Washington.

Available from: 2015-01-29 Created: 2015-01-29 Last updated: 2016-12-23Bibliographically approved
8. Road Condition Imaging - Case Study
Open this publication in new window or tab >>Road Condition Imaging - Case Study
(English)Manuscript (preprint) (Other academic)
Abstract [en]

It is often a problem to get descriptive road status information from the automatic road weather information systems. These monitoring stations are normally equipped with meteorological sensors and road temperature sensors. Even though some monitoring stations have road status sensors and cameras, it is difficult to assess the current road condition. The problem is that the road status sensors cover only a small part of the road’s width and length and camera images are time consuming and difficult to manually evaluate. In this paper, a new automatic road status camera that gives an image of the road status and that covers a whole lane is evaluated. This means that differences the road surface within and outside of wheel tracks can be examined. Hazardous situations with wet wheel tracks and ice in-between the tracks can be detected and road users can be warned until appropriate maintenance have been performed. This new infra-red road status camera was evaluated on data retrieved during winter 2013-2014, and it was found that road conditions differ considerably during the winter, and that differences in and between the wheel tracks occur. A correlation of friction data retrieved by vehicle mounted slip wheels with this new road condition imaging system was completed. The findings indicate that slip friction measurements correlate well with the classified road conditions from the infra-red imaging system.

Keyword
Road condition, imaging, case study
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:miun:diva-24827 (URN)
Available from: 2015-04-14 Created: 2015-04-14 Last updated: 2015-04-15Bibliographically approved

Open Access in DiVA

SurfStat(2756 kB)318 downloads
File information
File name FULLTEXT01.pdfFile size 2756 kBChecksum SHA-512
436beaba9cf1083ceeb8eaa9bdbc5be2dc89b21432e68672b5f9d73fe6b7d51a837a12cdc2b10878d2257eeb9254726e1641dfc8cf1cde66f178bcd30a8e1388
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Jonsson, Patrik
By organisation
Department of Electronics Design
Other Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 318 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 3051 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf