Dalarna University's logo and link to the university's website

Road traffic signs provide regulatory, warning, guidance, and other important information to road users to prevent hazards and road accidents. Therefore, the traffic signs must be detectable, legible, and visible both in day and nighttime to fulfill their purpose. The nighttime visibility is critical to safe driving on the roads at night. The state of the art gives clear evidence that the retroreflectivity improves the nighttime visibility (detectability and legibility) of the road traffic signs and that the nighttime visibility can be improved by using an adequate level of retroreflectivity. Furthermore, nighttime visibility can be affected by human, sign, vehicle, environmental, and design factors. 

The retroreflectivity and colors of the road signs deteriorate over time and thus the visibility worsens, therefore, maintaining the road signs is one of the important issues to improve the safety on the roads.  Thus, it is important to judge whether the retroreflectivity and colors of the road sign are within the accepted levels for visibility and the status of the signs are accepted or not and need to be replaced. 

This thesis aims to use machine learning algorithms to predict the status of road signs in Sweden. To achieve this aim, three classifiers were invoked: Artificial Neural Network (ANN), Support Vector Machines (SVM), and Random Forest (RF). The data which was collected in Sweden by The Road and Transport Research Institute (VTI) was used to build the prediction models. High accuracy was achieved using the three algorithms (ANN, SVM, and RF) of 0.84.3, 0.93, and 0.98, respectively. Scaling the data was found to improve the accuracy of the prediction for all three models and better accuracy is achieved when the data was scaled using standardization compared with normalization. Additionally using principal component analysis (PCA) has a different impact on the accuracy of the prediction for each algorithm.

Another aim was to build prediction models to predict the retroreflectivity performance of the in-use road signs without the need to use instruments to measure the retroreflectivity or color. Experiments using linear and logarithmic regression models were conducted in this thesis to predict the retroreflectivity performance. Two datasets were used, VTI data and another data which was collected in Denmark by voluntary Nordic research cooperation (NMF group). The age of the road traffic sign, the chromaticity coordinate X for colors, and the class of retroreflectivity were found significant to the retroreflectivity in both datasets. 

The logarithmic regression models were able to predict the retroreflectivity with higher accuracy than linear models. Two suggested logarithmic regression models provided high accuracy for predicting the retroreflectivity (R2 of 0.50 on VTI data and 0.95 on NMF data) by using color, age, class, GPS position, and direction as predictors. Nearly the same accuracy (R2 of 0.57 on VTI data and 0.95 on NMF data) was achieved by using all parameters in the data as predictors (including chromaticity coordinates X, Y for colors). As a conclusion, omitting chromaticity coordinates X, Y for colors from the logarithmic regression models does not affect the accuracy of the prediction. 

Proper maintenance of road traffic signs is vital for safety, as their low visibility can cause accidents and fatalities. Many countries, including Sweden, lack a systematic approach for replacing signs due to the risky, costly, and complex methods needed to measure their color and retroreflectivity.

This thesis introduces a predictive maintenance method for road traffic signs to ensure their visibility day and night. The proposed data-driven models predict sign degradation, helping maintain optimal visibility, decreasing accidents, and enhancing safety, and environmental sustainability by reducing material consumption and waste reduction.

This thesis suggests using machine learning methods to predict the values of retroreflectivity (coefficient of retroreflection) and color (daylight chromaticity), and to estimate the status (rejected/accepted) and longevity according to color and retroreflectivity. Datasets collected in Sweden, Denmark, and Croatia were used in this research.

Regression and classification models, employing Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Networks (ANN) utilized to predict the degradation of road traffic signs. ANN showed the highest performance, 94% R2 for retroreflectivity predictions and up to 94% accuracy for color and retroreflectivity status. SVM and RF also achieved acceptable accuracies.

Statistical methods, including linear and logarithmic regression, were also applied to examine the impact of age on the retroreflectivity values and status, chromaticity, and color status of road traffic signs. Findings revealed age as a significant factor, with a generally linear relationship between chromaticity values and age, except for yellow signs which displayed non-linear patterns between 8 and 22 years. Logarithmic regression models achieved R2 values of 50% and 95%, which are more accurate than those from previous studies. These models reveal an annual decrease in retroreflectivity of 4-5% and a negative correlation with the sign's direction, indicating that signs facing south and west degrade faster due to more solar exposure.

Logistic regression and Kaplan-Meier survival analyses were used to assess road traffic signs' longevity. The longevity based on retroreflectivity and color durability varies depending on color, retroreflective sheeting classes, direction, and location.

In Sweden, the median lifespan of road traffic signs estimated based on retroreflectivity lasts up to 25 years for red, 20 for yellow, 20 for white, and 35 for blue sheeting. In Croatia, the lifespan is shorter, 12 years for red, 16 for yellow, and 17 for white, 20 for blue.

Considering color degradation, the median lifespan of yellow road traffic signs is 45 years, 35 years for white, and blue signs, while red signs have a shorter lifespan. However, the red signs deteriorate in color before retroreflectivity with a median lifespan of 16 years, whereas other signs maintain their color longer. This emphasizes the effect of factors like pigment choice and environmental conditions on the durability of road traffic signs.