| Title |
A Smart City Application for Sharing Up-to-date Road Surface Conditions Detected from Crowdsourced Data |
| ID_Doc |
37117 |
| Authors |
Aihara, K; Bin, P; Imura, H; Takasu, A; Tanaka, Y |
| Title |
A Smart City Application for Sharing Up-to-date Road Surface Conditions Detected from Crowdsourced Data |
| Year |
2017 |
| Published |
|
| Abstract |
This paper introduces a smart city application to share road conditions. The application is based on a mobile sensing framework to collect sensor data reflecting personal-scale, or microscopic, roadside phenomena using crowdsourcing. To collect data, a driving recorder smartphone application that records not only sensor data but also videos from the driver's view is used. To extract specific roadside phenomena, collected data are integrated and analyzed at the service platform. One example is estimating road surface conditions. The paper shows our method to estimate road surface type (RST) and road surface shape (RSS). Features are defined in Sequential Forward Floating Search (SFFS) algorithm from collected data. By using random forest as classifier, average recall was about 91% in the 50 km/h - 80km/h range. The result may support to build a service that provides detected road conditions from up-to-date crowdsourced mobile sensing application. |
| PDF |
|
