Space segmentation method for 3D point clouds

• US 9,076,219 B2
• Filed: 08/31/2012
• Issued: 07/07/2015
• Est. Priority Date: 10/07/2011
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Chu, Chang Woo, Park, Il Kyu, Lee, Ji Hyung, Koo, Bonki, Cha, Youngmi
• Primary Examiner(s): Liu, Li
• Application Number:
  US13/601,851
• Publication Number:
  US 20130089259A1
• Time in Patent Office: 1,040 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/38 Outdoor scenes

Abstract

A space segmentation method for 3D point clouds is disclosed. A space segmentation method for 3D point clouds includes equally segmenting a space of the 3D point clouds into a plurality of grid cells; establishing a base plane corresponding to a ground part of the space of the 3D point clouds; accumulating points of all grid cells located perpendicular to the base plane in a grid cell of the base plane; and segmenting the grid cell in which the points are accumulated into an object part and a ground part according to the number of accumulated points.

Claims

1. A space segmentation method for 3D point clouds, the method comprising:

equally segmenting a space of the 3D point clouds into a plurality of grid cells;

establishing a base plane corresponding to a bottom part of the space of the 3D point clouds;

accumulating points of all grid cells of each column into a grid cell located on the base plane of each column, the column being extended perpendicularly from the grid cell located on the base plane

filtering a total number of the accumulated points;

determining a corresponding grid cell located on the base plane to be an object-estimation grid cell used for object estimation when a value of definition of each grid cell of the base plane is equal to or higher than a threshold value; and

determining the grid cell located on the base plane of each column as an object part or a ground part based on the filtered total number of accumulated points.

2. The method according to claim 1, wherein equally segmenting a space of the 3D point clouds into a plurality of grid cells includes:

equally segmenting a space of the 3D point clouds into a plurality of grid cells based on a number of points included in the 3D point clouds.

3. The method according to claim 1, wherein determining the grid cell located on the base plane of each column as an object part or a ground part based on the filtered total number of accumulated points includes:

arranging the object-estimation grid cells in descending numerical order of the accumulated points, searching for a neighboring grid cell adjacent to the object-estimation grid cells according to the arranged order, and establishing a group using the searched result;

extending the group to a three-dimensional (3D) range, and establishing an object-estimation bounding box estimated to be the object part;

from among the object-estimation grid cells and the neighboring grid cell contained in the object-estimation bounding box, determining the smallest bounding box including the points to be an object-group bounding box indicating the object part; and

determining a ground cell indicating the ground part using base-plane base grid cells not contained in the object-group bounding box.

4. The method according to claim 3, wherein the neighboring grid cell is a grid cell located adjacent to the object-estimation grid cell in up, down, left, right, and diagonal directions.

5. The method according to claim 3, wherein the establishing the group by searching for the neighboring grid cell adjacent to the object-estimation grid cells includes:

incorporating the object-estimation grid cells and the neighboring grid cell in the same group.

6. The method according to claim 5, wherein the establishing the group by searching for the neighboring grid cell adjacent to the object-estimation grid cells includes:

if the object-estimation grid cells are previously contained in the group, incorporating the corresponding object-estimation grid cells in the same group.

7. The method according to claim 3, wherein the determining the ground cell indicating the ground part includes:

from among the base grid cells not contained in the object-group bounding box, determining the lowest-height grid cell including the points to be the ground cell.