Target detection method and device, computer equipment and storage medium

Abstract

The invention provides a target detection method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining first fragmentation point cloud data currently outputted by a radar and first fragmentation point cloud data previously outputted by the radar wherein the first fragmented point cloud data is the point cloud data acquired when the radar rotates by a preset angle every time, and the preset angle is smaller than 360 degrees; extracting to-be-spliced point cloud data from first fragment point cloud data output by the radar last time, wherein the to-be-spliced point cloud data is partial point cloud data adjacent to the first fragment point cloud data currently output by the radar in the first fragment point cloud data output by the radar last time; splicing the to-be-spliced point cloud data with the currently output first fragment point cloud data to obtain second fragment point cloud data; and detecting the second fragment point cloud data to obtain a target detection result. The problem of missing detection at the segmentation position can be solved, and the detection accuracy is improved. In addition, the point cloud data are fragmented, so that the detection efficiency can be improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular, to a target detection method, device, computer equipment and storage medium. Background technique [0002] At present, the radar perception algorithm provides stable obstacle perception results for the automatic driving system, so the radar perception algorithm has become one of the indispensable core technologies of the automatic driving system. Radar perception algorithms need to process a large amount of point cloud input data and provide accurate and real-time perception results, which poses a huge challenge to the complexity and hardware performance of radar perception algorithms. In addition, radar sensing algorithms are often based on deep neural networks with huge parameters, so it is difficult for radar sensing algorithms to meet the real-time requirements of automatic driving systems. Contents of the invention [0003] Embodiments of the present disclosure a...

AI Technical Summary

Problems solved by technology

The radar perception algorithm needs to process a huge amount of point cloud input data and provide accurate and real-time perception results, which poses a huge challenge to the complexity and hardware performance of the radar perception algorithm

In addition, radar perception algorithms are often based on deep neural networks with huge parameters, so it is difficult for radar perception algorithms to meet the real-time requirements of automatic driving systems.

Images