Traffic condition prediction system and traffic condition prediction method

A traffic condition prediction system, comprising:

• a storage, being configured to store a first scene feature of a first traffic scene, a first prediction model for predicting traffic condition of the first traffic scene, at least one actual vehicle trajectory related to a second traffic scene, and a surveillance image of the second traffic scene;
• and
• a processor electrically connected to the storage, being configured to:
• determine a center of circle in the surveillance image;
• determine a first circle based on the center of circle and a first radius;
• extract a plurality of first feature points on the surveillance image along the circumference of the first circle according to a first preset sampling frequency;
• generate a second scene feature of the second traffic scene at least according to the plurality of first feature points;
• determine whether the first scene feature is similar to the second scene feature;
• when determining that the first scene feature is similar to the second scene feature, predict at least one vehicle trajectory related to the second traffic scene through the first prediction model, and determine whether the at least one actual vehicle trajectory is similar to the at least one predicted vehicle trajectory;
• and
• when determining that the at least one actual vehicle trajectory is similar to the at least one predicted vehicle trajectory, predict the traffic condition of the second traffic scene through the first prediction model;
• wherein the first scene feature and the second scene feature are generated in a same way.

A traffic condition prediction method for a traffic condition prediction system, the traffic condition prediction system storing a first scene feature of a first traffic scene, a first prediction model for predicting traffic condition of the first traffic scene, and a surveillance image of a second traffic scene, the traffic condition prediction method comprising:

• determining a center of circle in the surveillance image;
• determining a first circle based on the center of circle and a first radius;
• extracting a plurality of first feature points on the surveillance image along the circumference of the first circle according to a first preset sampling frequency;
• generating a second scene feature of the second traffic scene at least according to the plurality of first feature points;
• determining whether the first scene feature is similar to the second scene feature;
• and
• when determining that the first scene feature is similar to the second scene feature, predicting traffic condition of the second traffic scene through the first prediction model;
• wherein the first scene feature and the second scene feature are generated in a same way.