Method and apparatus of estimating road condition, and method and apparatus of establishing road condition estimation model

A method of establishing a road condition estimation model, comprising:

• acquiring training data, including a sequence of user tracks for a sample road for a first preset duration before a second moment, a sequence of road images for the sample road for the first preset duration before the second moment and a road condition label for the sample road for a second preset duration after the second moment;
• extracting a track-related feature of the sample road from the sequence of the user tracks, and extracting an image-related feature of the sample road from the sequence of the road images;
• and
• training a classification model, by using the track-related feature of the sample road and the image-related feature of the sample road as an input of the classification model, and using the road condition label for the sample road as a target output of the classification model, so as to obtain the road condition estimation model,
• wherein the track-related feature includes a speed feature;
• the image-related feature includes at least one of a road empty-degree feature, a traffic flow feature and a building feature;
• and
• the extracting an image-related feature of the sample road from the sequence of the road images comprises:
• recognizing a building area from each road image in the sequence of the road images, by using a pre-trained image semantic segmentation model;
• and
• calculating a similarity mean and/or a similarity variance of building areas of adjacent road images in the sequence of the road images, as the building feature of the sample road.

An electronic device, comprising:

• at least one processor;
• and
• a memory communicatively connected to the at least one processor,
• wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to implement operations of estimating a road condition, comprising:
• acquiring, for a first preset duration before a first moment, a sequence of user tracks for a road and a sequence of road images for the road;
• extracting a track-related feature of the road from the sequence of the user tracks, and extracting an image-related feature of the road from the sequence of the road images;
• and
• inputting the track-related feature of the road and the image-related feature of the road into a pre-trained road condition estimation model, so as to determine, for a second preset duration after the first moment, a road condition information of the road by using an estimated result of the road condition estimation model.