Vehicle trajectory splicing method based on millimeter wave radar data

Abstract

The invention relates to a vehicle trajectory splicing method based on millimeter wave radar data and aims to solve the technical problems of multi-target trajectory tracking and cross-device splicing under the condition that millimeter-wave radar equipment lacks moving target feature information. The method comprises the following steps of: arranging millimeter-wave radars a traffic road at certain intervals so as to sense vehicles moving on the traffic road, and obtaining vehicle trajectory data detected by the millimeter-wave radars; representing continuous motion trajectories of the vehicles in the corresponding single radar monitoring area by using vehicle trajectories captured by the single radars; and according to a vehicle trajectory motion trend, performing overlapping judgment on the vehicle trajectories acquired by two adjacent radars, judging the matching degree of the two target vehicle trajectories, and finally splicing the trajectories between frame windows according to the matching degree to obtain a final target trajectory. With the method adopted, the problem of discontinuous cross-device multi-target trajectory tracking is solved. The method has the advantages of being independent of moving target feature information, low in cost, good in adaptability and the like.

Description

technical field [0001] The invention relates to the field of intelligent traffic perception, in particular to a vehicle trajectory splicing method based on millimeter wave radar data. Background technique [0002] In recent years, with the rapid economic and social development, as well as the advancement of roadside sensor technology and the decline in cost, vehicle trajectory perception technologies based on various roadside sensors have emerged in an endless stream. At present, the widely used vehicle trajectory recognition method at home and abroad is based on camera. The vehicle trajectory recognition method, on the one hand, the camera is not sensitive to the speed perception of the vehicle, therefore, the vehicle trajectory acquired by the cameras on different road sections cannot be effectively spliced ​​based on the vehicle motion characteristics; on the other hand, the recognition accuracy of the camera for the remote vehicle is low, Vehicles cannot be calibrated an...

AI Technical Summary

Problems solved by technology

[0002] In recent years, with the rapid economic and social development, as well as the advancement of roadside sensor technology and the decline in cost, vehicle trajectory perception technologies based on various roadside sensors have emerged in an endless stream. At present, the widely used vehicle trajectory recognition method at home and abroad is based on camera. The vehicle trajectory recognition method, on the one hand, the camera is not sensitive to the speed perception of the vehicle, therefore, the vehicle trajectory acquired by the cameras on different road sections cannot be effectively spliced ​​based on the vehicle motion characteristics; on the other hand, the recognition accuracy of the camera for the remote vehicle is low, Vehicles cannot be calibrated and recognized in real time based on appearance features. Therefore, vehicle trajectories acquired by cameras on different road sections cannot be effectively spliced ​​based on vehicle appearance information features.

Images