IP Library › Granted Patent US 11,676,291
Granted Patent B1
US 11,676,291 · App. 17/232,646 · Granted Jun 13, 2023

Adaptive multimodal safety systems and methods

Inventors: Sandeep Pandya (Irvine, CA); Sundeep Ahluwalia (San Diego, CA); Changsoo Jeong (Rancho Palos, CA); Michael Korkin (Glendale, CA); Kyungsuk Lee (Rancho Palos, CA); Christopher Ro (Aliso Viejo, CA); Yong Wu (Signal Hill, CA)
Assignee: Everguard, Inc.
G06T7/33G06T5/009G06T7/521G06T7/70G06V20/20G06T2207/10028G06V2201/07
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 11,676,291
App. No.
17/232,646
Granted
Jun 13, 2023
Kind
B1
Abstract

An adaptive multimodal system is provided for managing safety in an industrial environment. The system comprises: a computer vision component for generating a computer vision output data; a real-time locating component for generating location data about an object within the industrial environment; a LIDAR component for generating 3D point cloud data of the industrial environment; and one or more processors coupled to the computer vision component, the real-time locating component and the LIDAR component and configured to: (i) obtain an identity of the object and the location data, and (ii) adjust, based at least in part on the identity and the location data, a pixel distribution for acquiring the 3D point cloud data, the process for generating the computer vision output data, or one or more parameters for acquiring an image data by the computer vision component.

Claims (31)

1. An adaptive multimodal system for managing safety in an industrial environment comprising:

(a) a computer vision component for generating a computer vision output data;

(b) a real-time locating component configured for generating location data and identity data about an object within the industrial environment, wherein the identity data is provided by a mobile tag device carried by the object;

(c) a light detection and ranging (LIDAR) component for generating 3D point cloud data of the industrial environment; and

(d) one or more processors coupled to the computer vision component, the real-time locating component and the LIDAR component and wherein the one or more processors are configured to:

adjust, based at least in part on the location data and the identity data about the object generated in (b), a density distribution of pixels for acquiring the 3D point cloud data, and

adjust, based at least in part on the location data and the identity data about the object generated in (b), at least one of a process for generating the computer vision output data, or one or more parameters for acquiring an image data by the computer vision component.

2. The adaptive multimodal system of claim 1 , wherein the process for generating the computer vision output data is adjusted by not recognizing the identity of the object using computer vision techniques.

3. The adaptive multimodal system of claim 2 , wherein the one or more processors are configured to further adjust a computational resource allocated to the computer vision component.

4. The adaptive multimodal system of claim 1 , wherein the process for generating the computer vision output data is adjusted by performing action recognition or objection recognition for the object based at least in part on the identity data to determine whether the object complies with a safety protocol.

5. The adaptive multimodal system of claim 1 , wherein the computer vision output data comprises a description of the industrial environment.

6. The adaptive multimodal system of claim 1 , wherein the one or more parameters for acquiring the image data include a spatial resolution for acquiring the image data, a zoom level, a or region of interest to zoom-in.

7. The adaptive multimodal system of claim 6 , wherein the one or more processors are configured to further generate a control command to an imaging device of the computer vision component to adjust the one or more parameters.

8. The adaptive multimodal system of claim 1 , wherein the real-time locating component comprises one or more reference point devices deployed within the industrial environment.

9. The adaptive multimodal system of claim 1 , wherein the mobile tag device further detects an orientation or motion state of the object.

10. The adaptive multimodal system of claim 1 , wherein the density distribution of pixels for acquiring the 3D point cloud data is adjusted by controlling a scanning pattern of the LIDAR component.

11. A method for managing safety in an industrial environment comprising:

(a) generating a computer vision output data using a computer vision component;

(b) generating location data and identity data about an object within the industrial environment using a real-time locating component, wherein the identity data is provided by a mobile tag device carried by the object;

(c) generating 3D point cloud data of the industrial environment using a light detection and ranging (LIDAR) component;

(d) adjusting, based at least in part on the location data and the identity data about the object generated in (b), a density distribution of pixels for acquiring the 3D point cloud data, and

(e) adjusting, based at least in part on the location data and the identity data about the object generated in (b), at least one of a process for generating the computer vision output data, or one or more parameters for acquiring an image data by the computer vision component.

12. The method of claim 11 , wherein adjusting the process for generating the computer vision output data comprises not using computer vision techniques for recognizing the identity of the object.

13. The method of claim 12 , further comprising adjusting a computational resource allocated to the computer vision component.

14. The method of claim 11 , wherein adjusting the process for generating the computer vision output data comprises performing action recognition or objection recognition for the object based at least in part on the identity data to determine whether the object complies with a safety protocol.

15. The method of claim 11 , wherein the computer vision output data comprises a description of the industrial environment.

16. The method of claim 11 , wherein the one or more parameters for acquiring the image data include a spatial resolution for acquiring the image data, a zoom level, a or region of interest to zoom-in.

17. The method of claim 16 , further comprising generating a control command to an imaging device of the computer vision component to adjust the one or more parameters.

18. The method of claim 11 , wherein the real-time locating component comprises one or more reference point devices deployed within the industrial environment.

19. The method of claim 11 , wherein the mobile tag device further detects anorientation or motion state of the object.

20. The method of claim 11 , wherein adjusting the density distribution of pixels for acquiring the 3D point cloud data comprises controlling a scanning pattern of the LIDAR component.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 7, 2022
From: KORKIN, MICHAEL
To: EVERGUARD, INC.
Reel/Frame 061012/0235 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 7, 2022
From: LEE, KYUNGSUK
To: EVERGUARD, INC.
Reel/Frame 061012/0279 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 1, 2022
From: PANDYA, SANDEEP; AHLUWALIA, SUNDEEP; JEONG, CHANGSOO; KORKIN, MICHAEL; LEE, KYUNGSUK; RO, CHRISTOPHER; WU, YONG
To: EVERGUARD, INC.
Reel/Frame 060420/0072 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 1, 2022
From: PANDYA, SANDEEP; AHLUWALIA, SUNDEEP; JEONG, CHANGSOO; RO, CHRISTOPHER; WU, YONG
To: EVERGUARD, INC.
Reel/Frame 061011/0908 →
Continuity (1)
Provisional Application 63012734 · Apr 20, 2020