Varying Road Surface Condition Estimation in Ego and Adjacent Lanes

Images from a front-facing camera on a vehicle can be used to estimate the varying Road Surface Conditions (RSC) ahead to warn the driver or to initiate automatic speed reduction in slippery road conditions. Previous works have successfully used deep-learning models to identify the RSC in the ego lane. Here, we focused on developing a model for predicting the RSC in multiple lanes simultaneously, relevant if changing lanes is an option. The proposed model estimate the RSC on the ego lane as well as in the adjacent lanes only if the adjacent lanes exists in the image. Furthermore, a data set is developed using more than 12,000 images from public benchmarks and privately captured images to facilitate multi-lane RSC estimation. Each image is assigned three RSC labels: with one for the ego, left and right lanes. The classes used are dry, wet, snow and snow-tracks. Our analysis with several network architectures has revealed that the model is capable of estimating the RSC in adjacent lanes with a similar level of performance as of the ego-lane.