Recognition of road type for unmanned vehicle based on texture and color features

Apperceiving the road type timely is beneficial to the acceleration, braking and other operations of the unmanned vehicle, so as to improve the safety and reliability. Recognition of the road type plays an important role in the field of unmanned vehicles. In this paper, color correlation feature and Tamura texture feature has been extracted from the image taken by the car camera and fused together, then the BP neural network in deep learning is used for training and testing the fusion features. The result shows that the proposed method improves the recognition rate obviously.