In this paper, we present a hyper-spectral imaging system and practical calibration procedure using a low-cost calibration reference made of polytetrafluoroethylene. The imaging system includes a hyperspectral camera and an active source of illumination with a variable spectral distribution of intensity. The calibration reference is used to measure the relative reflectance of any material surface independent of the spectral distribution of light and camera sensitivity. Winter road conditions are taken as a test application, and several spectral images of snow, icy asphalt, dry asphalt, and wet asphalt were made at different exposure times using different illumination spectra. Graphs showing measured relative reflectance for different road conditions support the conclusion that measurements are independent of illumination. Principal component analysis of the acquired spectral data for road conditions shows well separated data clusters, demonstrating the system’s suitability for material classification.

By measuring the spectral reflection from the four different road conditions dry, wet, icy, and snowy asphalt, a method of classification for the different surfaces—using two and three wavelengths—is developed. The method is tested against measurements to ascertain the probability of wrong classification between the surfaces. From the angular spectral response, the fact that asphalt and snow are diffuse reflectors and water and ice are reflective are confirmed.

This study measures the spectral reflectance from snow with known liquid water content (LWC) in a climate chamber using two optical sensors, a near-infrared (NIR) spectrometer and a Road eye sensor. The spectrometer measures the backscattered radiation in the wavelength range of 920–1,650 nm. The Road eye sensor was developed to monitor and classify winter roads based on reflected intensity measurements at wavelengths of 980, 1,310, and 1,550 nm. Results of the study suggest that the spectral reflectance from snow is inversely proportional to the LWC in snow. Based on the effect of LWC on the spectral reflectance, three optimum wavelength bands are selected in which snow with different LWCs is clearly distinguishable. A widely used remote sensing index known as the normalized difference water index (NDWI) is used to develop a method to estimate the surface LWC for a given snow pack. The derived NDWI values with respect to the known LWC in snow show that the NDWI is sensitive to the LWC in snow and that the NDWI and LWC are directly proportional. Based on this information, the NDWI is used to estimate the surface LWC in snow from measurements on a ski track using the Road eye sensor. The findings suggest that the presented method can be applied to estimate the surface LWC in order to classify snow conditions potentially for ski track and piste applications.

Three different configurations utilizing polarized short-wave infrared light to classify winter road conditions have been investigated. In the first configuration, polarized broadband light was detected in the specular and backward directions, and the quotient between the detected intensities was used as the classification parameter. Best results were obtained for the $SS$-configuration. This sensor was shown to be able to distinguish between the smooth road conditions of water and ice from the diffuse road conditions of snow and dry asphalt with a probability of wrong classification as low as 7%. The second sensor configuration was a pure backward architecture utilizing polarized light with two distinct wavelengths. This configuration was shown to be effective for the important problem of distinguishing water from ice with a probability of wrong classification of only 1.5%. The third configuration was a combination of the two previous ones. This combined sensor utilizing bispectral illumination and bidirectional detection resulted in a probability of wrong classification as low as 2% among all four surfaces.

One of the main challenges in developing efficient and effective winter road maintenance is to design an accurate prediction model for the road surface friction coefficient. A reliable and accurate prediction model of road surface friction coefficient can help decision support systems to significantly increase traffic safety, while saving time and cost. High dynamicity in weather and road surface conditions can lead to the presence of uncertainties in historical data extracted by sensors. To overcome this issue, this study uses an adaptive neuro-fuzzy inference system that can appropriately address uncertainty using fuzzy logic neural networks. To investigate the ability of the proposed model to predict the road surface friction coefficient, real data were measured at equal time intervals using optical sensors and road-mounted sensors. Then, the most critical features were selected based on the Pearson correlation coefficient, and the dataset was split into two independent training and test datasets. Next, the input variables were fuzzified by generating a fuzzy inference system using the fuzzy c-means clustering method. After training the model, a testing set was used to validate the trained model. The model was evaluated by means of graphical and numerical metrics. The results show that the constructed adaptive neuro-fuzzy model has an excellent ability to learn and accurately predict the road surface friction coefficient.