Space segmentation method for 3D point clouds
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.
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.