Point cloud and picture fusion annotation method and system

Abstract

The invention relates to a point cloud and picture fusion annotation method and system, and the method comprises the steps: obtaining the offset and rotation amount of a laser radar from the external parameters of the laser radar, obtaining the offset and rotation amount of a camera from the external parameters of the camera, and obtaining a K matrix from the internal parameters of the camera; obtaining a point cloud annotation box set S from the point cloud annotation data, for a three-dimensional coordinate set PSi of eight vertexes of any annotation box Bi in the S, calculating eight pixel coordinates corresponding to eight three-dimensional coordinates in the picture M in the PSi by using the laser radar offset and rotation amount, the camera offset and rotation amount and the matrix K to form a set LSi; finally, according to requirements, drawing a annotation box on the picture M in combination with the LSi, and endowing the annotation box with a corresponding attribute value. According to the annotation method provided by the invention, the point cloud and the picture can be annotated at the same time, the annotation time cost and the manpower and material resource cost are saved, and the annotation efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a method and system for point cloud and image fusion labeling used in model construction training and optimization in the process of automatic driving research. Background technique [0002] In the process of autonomous driving research, a large amount of data such as pictures, point clouds and their corresponding labeled true values ​​are needed to construct, train and optimize the model. The traditional labeling method is to separate the point cloud from the image and label them separately. This annotation method performs an independent annotation on the same object corresponding to the point cloud and the picture, and the annotation efficiency is low. And there is no guarantee that the point cloud will exactly match the labeling attributes of the corresponding object in the picture. In addition, traditional image annotation methods often use rectangular or polygona...

AI Technical Summary

Problems solved by technology

This annotation method performs an independent annotation on the same object corresponding to the point cloud and the picture, and the annotation efficiency is low.

And there is no guarantee that the point cloud exactly matches the annotation attributes of the same object corresponding to the image

In addition, traditional image annotation methods often use rectangular or polygonal annotation frames to annotate the target object, which cannot obtain and display the real 3D data of the target object, which has created certain obstacles to the construction, training, and optimization of some models in autonomous driving research.

Images