Data set establishing method, vehicle and storage medium

Abstract

The invention relates to the technical field of automatic driving, in particular to a data set establishment method and a vehicle. The method comprises the steps: obtaining a millimeter-wave radar image and a laser radar image; performing space and time calibration on the millimeter-wave radar and the laser radar; constructing a deep neural network for speculating the laser radar image, and generating a target speculation result of the laser radar by using the deep neural network; projecting a target speculation result to the matched millimeter-wave radar image to serve as a pseudo label of the millimeter-wave radar image; generating a radar target confidence coefficient according to the millimeter wave radar local signal of the area where the pseudo label is located; and establishing a millimeter wave radar data set according to the target confidence and the pseudo label. Compared with traditional manual labeling, automatic labeling can be achieved by means of the laser radar, so thatthe labeling efficiency is improved; and target recognition with the high recall rate can be achieved based on the deep neural network of model integration, and a false positive target detection boxis filtered out, so that the labeling quality is improved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a method for establishing a data set, a vehicle and a storage medium. Background technique [0002] Millimeter-wave radar has become an integral part of the Advanced Driver Assistance Systems (ADAS) of automobiles. The radar can also work normally and has strong robustness. The work of traditional millimeter-wave radar is to use digital signal processing algorithm to extract the position and velocity information of the target, and establish a data set based on a series of radar points or point clouds. However, the generated radar point or point cloud does not have information such as the size and attitude of the target. In automatic driving, it is usually necessary to use the pose information including the position, depth, size and angle of the target to complete the work of environment perception. However, since the millimeter-wave radar datasets applied to automatic...

AI Technical Summary

Problems solved by technology

However, the generated radar point or point cloud does not have information such as the size and attitude of the target.

In automatic driving, it is usually necessary to use the pose information including the position, depth, size and angle of the target to complete the work of environment perception. However, since the millimeter-wave radar datasets applied to automatic driving are usually annotated manually, the annotation efficiency is extremely high. Low

[0003] Although other sensors, such as cameras, can also be used to mark mmWave radar, the accuracy of camera estimation for pose information is low

Images