CPC G01S 17/89 (2013.01) [G06T 7/73 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/20084 (2013.01)] | 8 Claims |
1. A method for real-time object detection, comprising:
acquiring target point cloud data using a Light Detection and Ranging (LiDAR) device in a range of a preset angle, wherein the target point cloud data comprises one or more data points, and the preset angle is less than 360 degrees the round angle;
determining a one-dimensional LiDAR point feature of each of the data points in the target point cloud data;
updating a previous frame of LiDAR feature vector based on the one-dimensional LiDAR point feature of each of the data points in the target point cloud data to generate a current frame of LiDAR feature vector; and
determining object information in a real-time manner based on the current frame of LiDAR feature vector;
wherein the acquiring target point cloud data in the range of the preset angle comprises:
determining a time length T1 required for acquiring a round of point cloud data by the LiDAR device, and a time length T2 required for processing the round of point cloud data; determining the preset angle αas
where k denotes an adjusting coefficient, and R denotes 360 degrees; and
generating the target point cloud data based on the one or more data points collected by the LiDAR device in the range of the preset angle.
|