Method and system for real-time landmark extraction from a sparse three-dimensional point cloud

Patent metadata

Field	Value
Publication number	US-11860304-B2
Application number	US-202017061367-A
Country	US
Kind code	B2
Filing date	Oct 1, 2020
Priority date	Oct 1, 2020
Publication date	Jan 2, 2024
Grant date	Jan 2, 2024

Abstract

A system and method for processing a 3D point cloud to generate a segmented point cloud in real time are disclosed, the method includes: receiving a sparse 3D point cloud captured by a detection and ranging sensor mounted to a vehicle, the 3D point cloud comprising a plurality of data points, each data point in the 3D point cloud having a set of coordinates in a coordinate system of the detection and ranging sensor; generating, from the 3D point cloud, a range map comprising a plurality of elements, each of the plurality of data points of the 3D point cloud occupying a respective element of the plurality of elements; labelling the data point in each respective element of the range map as one of a pole-like data point or a vertical-plane-like data point; and generating the segmented point cloud including one or more of the labeled data points.

First claim

The invention claimed is:

1. A computer-implemented method of processing a sparse three dimensional (3D) point cloud to generate a segmented point cloud in real time, comprising:
receiving a sparse 3D point cloud captured by a multi-laser spinning light detection and ranging (LIDAR) sensor mounted to a vehicle, the sparse 3D point cloud comprising a plurality of data points, each of the plurality of data points in the sparse 3D point cloud having a set of coordinates in a coordinate system of the multi-laser spinning LIDAR sensor and being associated with a beam number from a plurality of beam numbers of the multi-laser spinning LIDAR sensor, each respective beam number from the plurality of beam numbers corresponding to a respective laser head of the multi-laser spinning LIDAR sensor;
generating, from the sparse 3D point cloud, a range map comprising a plurality of elements, each element of the range map corresponding to a value representing an Azimuth angle along an x-axis of the range map and a value representing an integer number along a y-axis of the range map, the x-axis having values ranging from −180 degrees to +180 degrees, the y-axis having integer numbers ranging from 0 to N−1, wherein N represents a total number of laser heads of the multi-laser spinning LIDAR sensor of the vehicle, and each integer number along the y-axis corresponds to a respective beam number from the plurality of beam numbers, each of the plurality of data points of the sparse 3D point cloud occupying a respective element of the plurality of elements;
for each beam number from the plurality of beam numbers, determining the Azimuth angle for each data point in the plurality of data points that is associated with the beam number;
for each data point from the plurality of data points associated with the beam number, marking a respective element of the range map as occupied by the respective data point based on the Azimuth angle and the associated beam number of the respective data point;
computing and storing a curvature value for each of the plurality of data points of the sparse 3D point cloud, wherein for any data point P i occupying a respective element of the range map and having a set of coordinate values [x i ,y i ,z i ] the curvature value of the data point P i is represented by c and computed by:

c
=

(

2
⁢
k
⁢

x
i

-

∑

j
=

i
-
k

,

j
≠
i

i
+
k

x
j

)

2

+

(

2
⁢
k
⁢

y
i

-

∑

j
=

i
-
k

,

j
≠
i

i
+
k

y
j

)

2

+

(

2
⁢
k
⁢

z
i

-

∑

j
=

i
-
k

,

j
≠
i

i
+
k

z
j

)

2

(

x
i

Assignees

• Ren Yuan
• Liu Bingbing
• Cheng Ran
• Huawei Tech Co Ltd

Inventors

• Ren Yuan
• Liu Bingbing
• Cheng Ran

Classifications

• G01S7/4802 Primary

  using analysis of echo signal for target characterisation; Target signature; Target cross-section · CPC title

• G01S17/42

  Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S17/46) · CPC title

• G01S17/931

  of land vehicles · CPC title

• G06F18/232

  Non-hierarchical techniques · CPC title

• G06F18/251

  of input or preprocessed data · CPC title