CPC G06V 10/44 (2022.01) [G01S 7/4802 (2013.01); G06F 18/2413 (2023.01)] | 14 Claims |
1. A system for extracting an outline of a static object, the system comprising:
a light detection and ranging (LiDAR) sensor configured to obtain a plurality of points and
a processor coupled to the LiDAR, and configured to:
derive a regression line being a point selection criterion, based on linearity of segments interconnecting the points obtained from the LiDAR sensor;
calculate a separation distance where each point is vertically away from the regression line, when the separation distance is greater than or equal to a reference distance, classify the points as removal points,
when the separation distance is less than the reference distance, classify the points as valid points;
generate and extract the outline of the static object by connecting the classified valid points except for the classified removal points, and wherein the processor coupled to the LiDAR is further configured to:
determine that a plurality of consecutive segments, of the segments, linearity, when at least two consecutive angles, each of which is defined by a segment and another segment adjacent to the segment, are greater than a reference angle; and
select points forming the determined plurality of consecutive segments as a regression line candidate;
calculate an angle defined by one segment and another segment adjacent to the segment among the determined plurality of consecutive segments;
select an i-1th point, which is a start point of a segment including an ith point, as the start point of the regression line candidate, when an angle between segments at both sides with respect to the ith point is greater than the reference angle,
select a jth point as the end point of the regression line candidate, when an angle between segments at both sides with respect to the jth point is less than or equal to the reference angle and when there is the start point before the jth point, and
select the selected start point and the selected end point of the segments to form a line as the regression line candidate which is the derived regression line.
|