Road Surface Translation Under Snow-covered and Semantic Segmentation for Snow Hazard Index
This work addresses road safety for drivers and managers by providing automated snow hazard indicators, but it is incremental as it combines existing methods like pix2pix and DeepLabv3+ for a specific application.
The study tackled the problem of assessing snow hazard on roads by automatically calculating a snow hazard ratio indicator using deep learning, achieving practical robustness on 1,155 live snow images from a cold region in Japan.
In 2020, there was a record heavy snowfall owing to climate change. In reality, 2,000 vehicles were stuck on the highway for three days. Because of the freezing of the road surface, 10 vehicles had a billiard accident. Road managers are required to provide indicators to alert drivers regarding snow cover at hazardous locations. This study proposes a deep learning application with live image post-processing to automatically calculate a snow hazard ratio indicator. First, the road surface hidden under snow is translated using a generative adversarial network, pix2pix. Second, snow-covered and road surface classes are detected by semantic segmentation using DeepLabv3+ with MobileNet as a backbone. Based on these trained networks, we automatically compute the road to snow rate hazard index, indicating the amount of snow covered on the road surface. We demonstrate the applied results to 1,155 live snow images of the cold region in Japan. We mention the usefulness and the practical robustness of our study.