Obstacle state identification method in automatic driving environment
The embodiment of the invention provides an obstacle state recognition method in an automatic driving environment, and the method comprises the steps: obtaining continuous multi-frame data of an obstacle in the automatic driving environment in a preset time window, and numbering each frame of the mu...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
04.11.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The embodiment of the invention provides an obstacle state recognition method in an automatic driving environment, and the method comprises the steps: obtaining continuous multi-frame data of an obstacle in the automatic driving environment in a preset time window, and numbering each frame of the multi-frame data; three-dimensional point cloud data of the obstacle is extracted based on the multi-frame data, and each frame data comprises multiple pieces of three-dimensional point cloud data; performing three-dimensional rasterization processing on the three-dimensional point cloud data point by point, and constructing voxel units of the three-dimensional point cloud data; counting the number of the voxel units occupied by the point clouds in the historical frames in the preset time window; determining a motion state of the voxel unit based on the number; and determining the motion state of the obstacle based on the motion state of the voxel unit. According to the invention, the flexibility and comprehensivenes |
---|---|
Bibliography: | Application Number: CN202210926055 |