Accurate detection of road surface conditions in adverse winter weather is essential for traffic safety. To promote safe driving and efficient road management, this study presents an accurate and generalizable data-driven learning model for the estimation of road surface conditions. The machine model was a support vector machine (SVM), which has been successfully applied in diverse fields, and kernel functions (linear, Gaussian, second-order polynomial) with a soft margin classification technique were also adopted. Two learner designs (one-vs-one, one-vs-all) extended their application to multi-class classification. In addition to this non-probabilistic classifier, this study calculated the posterior probability of belonging to each group by applying the sigmoid function to the classification scores obtained by the trained SVM. The results indicate that the classification errors of all the classifiers, excluding the one-vs-all linear learners, were below 3%, thereby accurately classifying road surface conditions, and that the generalization performance of all the one-vs-one learners was within an error rate of 4%. The results also showed that the posterior probabilities can analyze certain atmospheric and road surface conditions that correspond to a high probability of hazardous road surface conditions. Therefore, this study demonstrates the potential of data-driven learning models in classifying road surface conditions accurately.

Adverse weather conditions at night are very fatal to drivers, causing serious traffic accidents. Road lighting is a facility that can alleviate these dangerous situations. Nevertheless, road lighting has only rarely been studied during adverse weather. The reason is that the current road lighting performance evaluation method is presented based on normal weather. The current road lighting performance evaluation method uses a luminance meter to measure the road surface, which is not suitable due to scattering during adverse weather such as rain and fog. Therefore, this study proposes obstacle recognition distance as a measure of effectiveness to evaluate the performance of road lighting during adverse weather. There is a lack of actual research on whether obstacle recognition distance can be used as a measure of effectiveness for road lighting during adverse weather. Therefore, in this study, 30 subjects were used to measure the subjects’ obstacle recognition distance according to changes in weather conditions, road lighting grade, and road lighting color temperature. As a result, it was analyzed that there was a clear trend of change in obstacle recognition distance depending on the change in each condition. It was found that, under the same road lighting performance conditions, there was a difference of up to 72.86% by weather condition; under the same weather conditions, there was a difference of up to 22.75% by road lighting grade; and by color temperature, there was a difference of up to 21.87%. In addition, a statistical significance test was performed to support the existence of a difference, and the results were synthesized to suggest that obstacle recognition distance can be used as a performance measure of effectiveness of road lighting in adverse weather.

This study proposes an intelligent surveillance framework that integrates image preprocessing, illuminance-adaptive object detection, multi-object tracking, and pedestrian abnormal behavior recognition to address the rapid degradation of image recognition performance under low-illuminance street lighting conditions. In the preprocessing stage, image quality was enhanced by correcting color distortion and contour loss, while in the detection stage, illuminance-based loss weighting was applied to maintain high detection sensitivity even in dark environments. During the tracking process, a Kalman filter was employed to ensure inter-frame consistency of detected objects. In the abnormal behavior recognition stage, temporal motion patterns were analyzed to detect events such as falls and prolonged inactivity in real time. The experimental results indicate that the proposed method maintained an average detection accuracy of approximately 0.9 and adequate tracking performance in the 80% range under low-illuminance conditions, while also exhibiting stable recognition rates across various weather environments. Although slight performance degradation was observed under dense fog or highly crowded scenes, such limitations are expected to be mitigated through sensor fusion and enhanced processing efficiency. These findings experimentally demonstrate the technical feasibility of a real-time intelligent recognition system for nighttime street lighting environments.