Mixed depth object detection
AssigneeZebra Technologies Corporation
InventorsVlad Gorodetsky, Giorgio Gallina, Anshul V. Joshi, Richard Jeffrey Rzeszutek, Joseph Lam
Life of this patent
Estimating the term…
Abstract
A method includes obtaining a point cloud captured by a depth sensor, and image data captured by an image sensor, the point cloud and the image data representing a support structure bearing a set of objects; obtaining an image boundary corresponding to an object from the set of objects; determining a portion of the point cloud corresponding to the image boundary; selecting, from the determined portion, a subset of points corresponding to a forward surface of the object; and generating a three-dimensional position of the object based on the forward surface.
Claims20
A method, comprising:
- obtaining (i) a point cloud captured by a depth sensor, and (ii) image data captured by an image sensor, the point cloud and the image data representing a support structure bearing a set of objects;
- obtaining an image boundary corresponding to an object from the set of objects;
- determining a portion of the point cloud corresponding to the image boundary;
- selecting, from the determined portion, a subset of points corresponding to a forward surface of the object;
- and
- generating a three-dimensional position of the object based on the forward surface.
A method, comprising:
- obtaining a plurality of the three-dimensional positions derived from images captured by an image sensor and a point cloud captured by a depth sensor;
- selecting a subset of the three-dimensional positions corresponding to an object;
- projecting the selected three-dimensional positions to a sequence of candidate depths;
- determining, at each candidate depth, a cost function associated with the projections;
- and
- generating a combined three-dimensional position at a selected one of the candidate depths having a lowest one of the cost functions determined at each candidate depth.
A method, comprising:
- obtaining (i) a point cloud, captured by a depth sensor, of a support structure and an obstruction, and (ii) a plurality of local support structure planes derived from the point cloud and corresponding to respective portions of the support structure;
- for each local support 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 support structure plane and the mask;
- and
- detecting obstructions from the subset of points.
Dependencies are inferred from the claim text.