Mixed depth object detection

Patent metadata

Field	Value
Publication number	US-12579686-B2
Application number	US-202418661521-A
Country	US
Kind code	B2
Filing date	May 10, 2024
Priority date	Jul 17, 2020
Publication date	Mar 17, 2026
Grant date	Mar 17, 2026

Abstract

A method includes obtaining (i) a point cloud, captured by a depth sensor, of a structure and an obstruction, and (ii) a plurality of local structure planes derived from the point cloud and corresponding to respective portions of the structure, for each local structure plane: selecting a membership set of points from the point cloud, generating a mask based on the membership set of points, selecting a subset of points from the point cloud based on the local structure plane and the mask, and detecting obstructions from the subset of points.

First claim

The invention claimed is:

1 . A method, comprising:
obtaining (i) a point cloud, captured by a depth sensor, of a structure and an obstruction, and (ii) a plurality of local structure planes derived from the point cloud and corresponding to respective edges of the structure; for each local structure plane:
selecting a membership set of points from the point cloud, each of the points from the membership set being within a threshold of a depth corresponding to the local structure plane;
generating a mask based on the membership set of points;
establishing a selection depth by decrementing the depth corresponding to the local structure plane by a coarse interval;
generating a selection plane parallel to the local structure plane at the selection depth;
selecting a subset of points from the point cloud between the local structure plane and the selection plane, wherein points exterior to a selection region of the mask are discarded; and
detecting obstructions from the subset of points.

2 . The method of claim 1 , wherein generating the mask comprises:
projecting the membership set of points to the depth of the local structure plane.

3 . The method of claim 2 , wherein selecting the subset of points includes:
identifying points having a depth smaller than the selection depth; and selecting, from the identified points, the subset of points having locations within a selection region of the mask.

4 . The method of claim 2 , wherein generating the mask comprises performing a morphological operation including a dilation and/or erosion to fill gaps between the projected membership set of points.

5 . The method of claim 1 , wherein selecting the membership set of points further includes selecting points located within a boundary defined by the local structure plane.

6 . The method of claim 1 , further comprising projecting points from the point cloud on to the selection plane.

7 . The method of claim 6 , wherein detecting obstructions from the subset of points comprises detecting a contiguous region of points on the selection plane.

8 . The method of claim 7 , wherein detecting obstructions from the subset of points comprises comparing the detecting contiguous region of points to a minimum size threshold.

9 . The method of claim 1 , wherein selecting a subset of points from the point cloud between the local structure plane and the selection plane comprises shifting the selection plane towards the local structure plane by a smaller interval than the coarse interval.

Assignees

• Zebra Tech Corp

Inventors

• Gorodetsky Vlad
• Gallina Giorgio
• Joshi Anshul V
• Rzeszutek Richard Jeffrey
• Lam Joseph

Classifications

• G06T7/13

  Edge detection · CPC title

• G01S17/894 Primary

  Three-dimensional [3D] imaging with simultaneous measurement of time-of-flight at a two-dimensional [2D] array of receiver pixels, e.g. time-of-flight cameras or flash lidar · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G01S17/931

  of land vehicles · CPC title