IP Library Granted Patent US 12,380,545
Granted Patent B2
US 12,380,545 · App. 17/963,410 · Granted Aug 5, 2025

Systems and methods for quantifying light flares in images

Inventor: Koji L. Gardiner (San Francisco, CA)
Assignee: Volkswagen Group of America Investments, LLC
G06T7/0002G06T3/60G06T7/70G06T11/60G06T2207/20076G06T2207/20224
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 12,380,545
App. No.
17/963,410
Granted
Aug 5, 2025
Kind
B2
Abstract

Systems, methods, and computer-readable media are disclosed for identifying light flares in images. An example method may involve receiving an image from an imaging device, the image including data indicative of a flare artifact originating from a region of the image. The example method may also involve determining, based on the image data, a first array of pixels extending radially outwards from the region and a second array of pixels extending radially outwards from the region. The example method may also involve creating, based on the image data, a flare array, the flare array including the first array of pixels and the second array of pixels. The example method may also involve determining, based on the flare array, a peak flare artifact value indicative of a size of the flare artifact; and determining, based on the peak flare artifact value, a flare artifact score for the imaging device.

Claims (76)

1. A system, comprising:

a processor configured to:

receive image data indicative of a flare artifact extending from a region of an image;

generate a flare array including a first row of pixels and a second row of pixels based on the image data;

generate a peak flare artifact value indicative of a size of the flare artifact based on the flare array and a first mean value of the first row of pixels and a second mean value of the second row of pixels; and

generate a flare artifact score based on the peak flare artifact value.

2. The system of claim 1 further comprising a camera, and wherein the processor is further configured to:

receive the image data from the camera;

generate the flare artifact score for the camera; and

generate a prompt, or control a cleaning mechanism, to clean the camera based on the flare artifact score.

3. The system of claim 1 , wherein the processor is further configured to:

identify a first array of pixels extending from the region and a second array of pixels extending from the region based on the image data;

generate the first row of pixels of the flare array based on the first array of pixels; and

generate the second row of pixels of the flare array based on the second array of pixels.

4. The system of claim 3 , wherein the processor is further configured to:

assign a first value to artifact values above a predetermined threshold;

assign a second value to artifact values below the predetermined threshold;

generate a binary map based on the artifact values; and

localize the region within the image based on the binary map.

5. The system of claim 4 , wherein the processor is further configured to filter data associated with the flare artifact based on the localization of the region.

6. The system of claim 4 , wherein the processor is further configured to generate a centroid of the region based on the binary map.

7. The system of claim 6 , wherein the processor is further configured to add at least one pixel to the binary map to align the centroid of the region with a center of the image.

8. The system of claim 7 , wherein generating the flare array further comprises:

generating the first row of pixels from the image data;

rotating the image about the center of the image; and

generating the second row of pixels from the image data.

9. The system of claim 1 , wherein the image comprises a first image, and wherein the processor is further configured to:

receive second image data indicative of the flare artifact extending from the region of a second image, the second image being at a different orientation than the first image;

generate a second flare artifact score based on the second image; and

calculate an overall flare artifact score based on the flare artifact score and the second flare artifact score.

10. A method comprising:

receiving first image data indicative of a flare artifact extending from a region of a first image;

receiving second image data indicative of the flare artifact extending from the region of a second image, the second image being at a different orientation than the first image;

generating a flare array including a first row of pixels and a second row of pixels based on the first image data;

generating a peak flare artifact value indicative of a size of the flare artifact based on the flare array and a first mean value of the first row of pixels and a second mean value of the second row of pixels; and

generating a first flare artifact score based on the peak flare artifact value;

generating a second flare artifact score based on the second image; and

calculating an overall flare artifact score based on the first flare artifact score and the second flare artifact score.

11. The method of claim 10 , further comprising:

generating the overall flare artifact score for a camera; and

generating a prompt, or controlling a cleaning mechanism, to clean the camera based on the overall flare artifact score.

12. The method of claim 11 , further comprising:

identifying a first array of pixels extending from the region and a second array of pixels extending from the region based on the first image data;

generating the first row of pixels of the flare array based on the first array of pixels; and

generating the second row of pixels of the flare array based on the second array of pixels.

13. The method of claim 12 , further comprising:

assigning a first value to artifact values above a predetermined threshold;

assigning a second value to artifact values below the predetermined threshold;

generating a binary map based on the artifact values;

generating a centroid of the region based on the binary map; and

adding at least one pixel to the binary map to align the centroid of the region with a center of the first image.

14. The method of claim 10 , wherein generating the flare array further comprises:

generating the first row of pixels from the first image data;

rotating the first image about the center of the first image; and

generating the second row of pixels from the second image data.

15. A non-transitory computer readable medium including computer-executable instructions stored thereon, which when executed by one or more processors, cause the one or more processors to perform operations of:

generating a flare array including a first row of pixels and a second row of pixels based on image data indicative of a flare artifact extending from a region of an image;

generating a peak flare artifact value indicative of a size of the flare artifact based on the flare array and a first mean value of the first row of pixels and a second mean value of the second row of pixels; and

generating a flare artifact score based on the peak flare artifact value.

16. The non-transitory computer readable medium of claim 15 , wherein the computer-executable instructions are further configured to cause the one or more processors to perform operations of:

generating a prompt, or controlling a cleaning mechanism, to clean a camera based on the flare artifact score.

17. The non-transitory computer readable medium of claim 15 , wherein the computer-executable instructions are further configured to cause the one or more processors to perform operations of:

identifying a first array of pixels extending from the region and a second array of pixels extending from the region based on the image data;

generating the first row of pixels of the flare array based on the first array of pixels; and

generating the second row of pixels of the flare array based on the second array of pixels.

18. The non-transitory computer readable medium of claim 15 , wherein the computer-executable instructions are further configured to cause the one or more processors to perform operations of:

assigning a first value to artifact values above a predetermined threshold;

assigning a second value to artifact values below the predetermined threshold;

generating a binary map based on the artifact values; and

generating a centroid of the region based on the binary map.

19. The non-transitory computer readable medium of claim 18 , wherein the computer-executable instructions are further configured to cause the one or more processors to perform operations of:

adding at least one pixel to the binary map to align the centroid of the region with a center of the image.

20. The non-transitory computer readable medium of claim 15 , wherein the computer-executable instructions are further configured to cause the one or more processors to perform operations of:

generating the first row of pixels from the image data;

rotating the image about the center of the image; and

generating the second row of pixels from the image data.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 9, 2024
From: ARGO AI, LLC
To: VOLKSWAGEN GROUP OF AMERICA INVESTMENTS, LLC
Reel/Frame 069177/0099 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 11, 2022
From: GARDINER, KOJI L.
To: ARGO AI, LLC
Reel/Frame 061379/0578 →
Continuity (2)
Continuation 17017654 · Sep 10, 2020
Related Publication 20230030689A1 · Feb 2, 2023
References Cited (19)
US 7006210B2 · Overbeck et al. · 2006 [cited by applicant]
US 9230310B2 · Black et al. · 2016 [cited by applicant]
US 9979909B2 · Kuang et al. · 2018 [cited by applicant]
US 10298863B2 · Silverstein et al. · 2019 [cited by applicant]
US 10382712B1 · Forutanpour et al. · 2019 [cited by applicant]
US 11508052B2 · Gardiner · 2022 [cited by examiner]
US 20090273843A1 · Raskar et al. · 2009 [cited by applicant]
US 20110242352A1 · Hikosaka · 2011 [cited by applicant]
US 20130063788A1 · Iwayama et al. · 2013 [cited by applicant]
US 20130329132A1 · Tico et al. · 2013 [cited by applicant]
US 20170070689A1 · Silverstein et al. · 2017 [cited by applicant]
US 20170243373A1 · Bevensee et al. · 2017 [cited by applicant]
US 20180255254A1 · Kuang et al. · 2018 [cited by applicant]
US 20190260978A1 · Guerin et al. · 2019 [cited by applicant]
US 20190356873A1 · Douady-Pleven et al. · 2019 [cited by applicant]
US 20210035146A1 · Odom et al. · 2021 [cited by applicant]
International Search Report & Written Opinion of PCT/US2021/049840 mailed Dec. 28, 2021, 10 pages. [cited by applicant]
F. Chabert, “Automated Lens Flare Removal”, Stanford University, 2015, pp. 1-4, Stanford University, United States. [cited by applicant]
Vitoria et al., “Automatic Flare Spot Artifacts Detection and Removal in Photographs”, Journal of Mathematical Imaging and Vision, May 2019, pp. 1-20, vol. 61, Spain. [cited by applicant]