| CPC G06V 20/58 (2022.01) [B60W 40/06 (2013.01); G06F 18/214 (2023.01); B60W 2420/403 (2013.01); B60W 2552/40 (2020.02)] | 20 Claims |
|
1. A method for detecting road conditions comprising:
obtaining images of a scene in front of a vehicle as detection images;
inputting the detection images into a trained semantic segmentation model, the trained semantic segmentation model comprising a backbone network and a head network;
inputting the detection images into the backbone network to extract features and obtain a plurality of feature maps;
inputting the plurality of the feature maps into the head network, processing the plurality of the feature maps by a first segmentation network of the head network, and outputting a first recognition result;
processing the plurality of the feature maps by a second segmentation network of the head network, and outputting a second recognition result;
determining driving operations of the vehicle according to the first recognition result and the second recognition result.
|