Generating 3D depth map using parallax
First Claim
Patent Images
1. An assembly comprising:
- plural computerized devices;
each computerized device comprising at least one laser emitter configured to output signals useful for generating at least one three-dimensional (3D) depth map;
a first one of the computerized devices being programmed with instructions to;
generate an initial two-dimensional (2D) camera image and an initial laser-based time of flight (TOF) image of a target object;
move a camera generating the initial laser-based TOF image of the target object;
generate a secondary laser-based TOF image of the target object;
use the initial laser-based TOF image of the target object and secondary laser-based TOF image of the target object to generate a 3D depth map of the target object;
identify whether a discrepancy between the initial 2D camera image and the initial laser-based TOF image satisfies at least one criterion;
responsive to determining that a discrepancy between the initial 2D camera image and the initial laser-based TOF image satisfies the criterion, remove data points from the initial 3D depth map; and
responsive to determining that a discrepancy between the initial 2D camera image and the initial laser-based TOF image does not satisfy the criterion, not remove data points from the initial 3D depth map.
1 Assignment
0 Petitions
Accused Products
Abstract
Parallax views of objects are used to generate 3D depth maps of the objects using time of flight (TOF) information. In this way, the deleterious effects of multipath interference can be reduced to improve 3D depth map accuracy without using computationally intensive algorithms.
133 Citations
12 Claims
-
1. An assembly comprising:
-
plural computerized devices; each computerized device comprising at least one laser emitter configured to output signals useful for generating at least one three-dimensional (3D) depth map; a first one of the computerized devices being programmed with instructions to; generate an initial two-dimensional (2D) camera image and an initial laser-based time of flight (TOF) image of a target object; move a camera generating the initial laser-based TOF image of the target object; generate a secondary laser-based TOF image of the target object; use the initial laser-based TOF image of the target object and secondary laser-based TOF image of the target object to generate a 3D depth map of the target object; identify whether a discrepancy between the initial 2D camera image and the initial laser-based TOF image satisfies at least one criterion; responsive to determining that a discrepancy between the initial 2D camera image and the initial laser-based TOF image satisfies the criterion, remove data points from the initial 3D depth map; and responsive to determining that a discrepancy between the initial 2D camera image and the initial laser-based TOF image does not satisfy the criterion, not remove data points from the initial 3D depth map. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. An assembly comprising:
-
plural computerized devices; each computerized device comprising at least one laser emitter configured to output signals useful for generating at least one three-dimensional (3D) depth map; a first one of the computerized devices being programmed with instructions to; generate an initial two-dimensional (2D) camera image and an initial laser-based time of flight (TOF) image of a target object; move a camera generating the initial laser-based TOF image of the target object; generate a secondary laser-based TOF image of the target object; use the initial laser-based TOF image of the target object and secondary laser-based TOF image of the target object to generate a 3D depth map of the target object; and move the camera and/or an imaging device supporting the camera at least in part based on a direction of a surface causing multipath errors in the initial 3D depth map. - View Dependent Claims (9, 10, 11)
-
-
12. An assembly comprising:
-
plural computerized devices; each computerized device comprising at least one laser emitter configured to output signals useful for generating at least one three-dimensional (3D) depth map; a first one of the computerized devices being programmed with instructions to; generate an initial two-dimensional (2D) camera image and an initial laser-based time of flight (TOF) image of a target object; move a camera generating the initial laser-based TOF image of the target object; generate a secondary laser-based TOF image of the target object; use at least one of the initial laser-based TOF image of the target object and secondary laser-based TOF image of the target object to generate a 3D depth map of the target object; and use the initial laser-based TOF image of the target object and secondary laser-based TOF image of the target object to generate a 3D depth map of the target object by determining which of the initial and secondary TOF images exhibits less noise, and using the image exhibiting less noise to establish the 3D depth map.
-
Specification