A modified ResNet road state recognition algorithm is proposed to address the problems of low accuracy in traditional methods for road state recognition and the complex process of manually extracting road image features, which can recognize 7 types of road states. Firstly, a Dense Block dense connection module is added to the ResNet classic model algorithm to extract more shallow edge features of the road surface state. Then, a dual attention mechanism is introduced in the ResNet residual module to adaptively extract deep key features according to the importance of different channel features. Finally, by adding two fully connected layers and introducing Dropout to suppress overfitting, the recognition of road surface states is ultimately achieved. The experimental results show that the accuracy, precision, recall, and specificity of the proposed method all reach over 99.0%. It can effectively extract key feature information and has strong robustness, effectively improving the recognition accuracy of road surface states.