IP Library Granted Patent US 10,567,732
Granted Patent B2
US 10,567,732 · App. 15/889,548 · Granted Feb 18, 2020

Method and device for stereoscopic vision

Inventors: Yosef Arie Wolf (Tel Aviv, IL); Gal Goren (Beit Oren, IL); Efraim Vitzrabin (Holon, IL); Gil Gilad (Haifa, IL)
Assignee: ROBOTEMI LTD
H04N13/15H04N5/332H04N13/254H04N2013/0081
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,567,732
App. No.
15/889,548
Granted
Feb 18, 2020
Kind
B2
Abstract

A stereoscopic vision device, a method and a robot, the stereoscopic vision device comprising: a first image capture device and a second image capture device configured to capture a light pattern formed in an environment of the device by a light source configured to emit NIR light at a multiplicity of directions, each of the first image capture device and the second image capture device comprising a filter configured to transmit at least 75 percent of the NIR light, and to transmit at most 50 percent of visible light; and a processor configured to: determine depth information of the environment from a first image captured by the first image capture device and a second image captured by the second image capture device, based on the light pattern as depicted in the first image and the second image; and determine color information of the environment the first image and the second image.

Claims (35)

1. A stereoscopic vision device, comprising:

a first near infrared (NIR) image capture device and a second NIR image capture device each configured to capture a NIR light pattern formed in an environment of the devices by a light source configured to emit near infrared (NIR) light at a multiplicity of directions, each of the first NIR image capture device and the second NIR image capture device comprising a filter configured to transmit at least 75 percent of the NIR light in a NIR wavelength of at least 850 nanometers, and to transmit at least part of and at most 50 percent of visible light; and

a processor configured to:

determine depth information of the environment from a first image captured by the first NIR image capture device and a second image captured by the second NIR image capture device, based on the NIR light pattern depicted in the first image and the second image, wherein the depth information is determined by comparing locations of points in the NIR light pattern as captured in the first image and in the second image; and

determine color information of the environment based on the transmitted visible light,

wherein the filter is configured to transmit between 10 and 40 percent of the visible light at a wavelength range of 400-650 nanometers.

2. The device of claim 1 , wherein the NIR light has a wavelength of at least 850 nanometers.

3. The device of claim 1 , wherein the visible light has a wavelength range of 400-650 nanometers.

4. The device of claim 1 , wherein the filter is configured to transmit at least 85 percent of the NIR light at a wavelength of at least 850 nanometers.

5. The device of claim 1 , further comprising the light source configured to emit near infrared (NIR) light at the multiplicity of directions.

6. The device of claim 1 , wherein the multiplicity of directions comprise selectively emitting the NIR light in the NIR light pattern.

7. The device of claim 1 , wherein the depth information is determined by (i) identifying the NIR light pattern depicted in the first image and in the second image, and (ii) registration of the NIR light pattern depicted in the first image with the NIR light pattern depicted in the second image.

8. A method for obtaining stereoscopic data of an environment, comprising:

emitting near infrared (NIR) light at a multiplicity of directions, thus forming a NIR light pattern in the environment;

obtaining a first image captured by a first NIR image capture device and a second image captured by a second NIR capture device, the first image and the second image each depicting at least a part of the NIR light pattern,

wherein each of the first NIR image capture device and the second NIR image capture device capture the first image and the second image, respectively, through a filter configured to transmit at least 75 percent of the NIR light, and to transmit at least part of and at most 50 percent of visible light;

identifying the NIR light pattern depicted in each of the first image and the second image;

registering the first image and the second image in accordance with the NIR light pattern;

determining depth information for each light point comprised in the NIR light pattern depicted in the registered first and second images, wherein the depth information is determined by comparing locations of points in the NIR light pattern as depicted in the first image and in the second image; and

determining color information of the environment based on the transmitted visible light,

wherein the filter is configured to transmit between 10 and 40 percent of the visible light at a wavelength range of 400-650 nanometers.

9. The method of claim 8 , wherein the NIR light has a wavelength of at least 850 nanometers.

10. The method of claim 8 , wherein the visible light has a wavelength range of 400-650 nanometers.

11. The method of claim 8 , wherein the filter is configured to transmit at least 85 percent of the NIR light at a wavelength of at least 850 nanometers.

12. The method of claim 8 , wherein the multiplicity of directions comprise selectively emitting the NIR light in the NIR light pattern.

13. A robot comprising:

a light source configured to emit a pattern of near infrared (NIR) light at a multiplicity of directions, thus forming a NIR light pattern in an environment of the robot;

a first NIR image capture device and a second NIR image capture device, each comprising a filter configured to transmit at least 75 percent of the NIR light, and to transmit at least part of and at most 50 percent of visible light, the first NIR image capture device and the second NIR image capture device configured to each capture at least a part of the NIR light pattern, wherein the filter is configured to transmit between 10 and 40 percent of the visible light at a wavelength range of 400-650 nanometers; and

a processor configured to:

determine depth information of the environment from a first image captured by the first NIR image capture device and a second image captured by the second NIR image capture device, based on the at least part of the NIR light pattern as depicted in each of the first image and the second image, wherein the depth information is determined by comparing locations of points in the NIR light pattern as depicted in the first image and in the second image; and

determine color information of at least one object from the first image and the second image based on the transmitted visible light;

a steering mechanism or changing a position of the robot in accordance with the at least one object; and

a motor for activating the steering mechanism.

14. The robot of claim 13 , wherein the filter is configured to transmit at least 85 percent of the NIR light at a wavelength of at least 850 nanometers.

15. The robot of claim 13 , wherein the depth information is determined by (i) identifying the NIR light pattern in each of the first image and the second image, and (ii) registration of the NIR light pattern depicted in the first image with the NIR light pattern depicted in the second image.

Assignments (2)
CHANGE OF NAME Recorded Dec 16, 2019
From: ROBO-TEAM HOME LTD
To: ROBOTEMI LTD
Reel/Frame 051302/0909 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 7, 2018
From: WOLF, YOSEF ARIE; GOREN, GAL; VITZRABIN, EFRAIM; GILAD, GIL
To: ROBO-TEAM HOME LTD.
Reel/Frame 044852/0187 →
Continuity (2)
Provisional Application 62454970 · Feb 6, 2017
Related Publication 20180227564A1 · Aug 9, 2018