IP Library Granted Patent US 10,853,685
Granted Patent B2
US 10,853,685 · App. 15/641,801 · Granted Dec 1, 2020

Method and apparatus for detecting fog from image

Inventors: Young Hyun Lee (Changwon-si, KR); Yil Kwon Chang (Changwon-si, KR)
Assignee: HANWHA TECHWIN CO., LTD.
G06K9/4642G06K9/00771G06K9/4652
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 10,853,685
App. No.
15/641,801
Granted
Dec 1, 2020
Kind
B2
Abstract

Provided is a method for detecting fog from an image, the method including: generating a histogram based on a luminance signal of the image; calculating a histogram width from the histogram; calculating a color contrast value based on color signals of the image; and detecting a fog level of the image based on the histogram width and the color contrast value.

Claims (35)

1. A method of detecting fog from an image, the method comprising:

determining a color domain of the image;

converting the determined color domain of the image to obtain a luminance signal of the image and RGB values of pixels of the image;

generating a histogram based on the luminance signal of the image;

calculating a histogram width from the histogram;

calculating a color contrast value based on the RGB values of pixels of the image; and

detecting a fog level of the image based on the histogram width and the color contrast value.

2. The method of claim 1 , wherein the detecting of the fog level comprises detecting the fog level by using an exponential function of a linear combination of the histogram width and the color contrast value.

3. The method of claim 2 , wherein the calculating of the histogram width comprises:

detecting, from the histogram, a first luminance value and a second luminance value respectively corresponding to a first reference value and a second reference value each indicating a ratio of a number of accumulated pixels to a total number of pixels; and

determining a difference between the first luminance value and the second luminance value as the histogram width.

4. The method of claim 2 , wherein the calculating of the color contrast value comprises:

detecting a minimum value and a maximum value from among color values of each pixel;

calculating an average minimum value and an average maximum value respectively from minimum values and maximum values of all pixels; and

determining a difference between the average maximum value and the average minimum value as the color contrast value.

5. The method of claim 1 , wherein the fog level is inversely proportional to a weighted sum of the histogram width and the color contrast value.

6. The method of claim 5 , further comprising adjusting sensitivity of the fog level by adjusting a first weight of the histogram width and a second weight of the color contrast value.

7. The method of claim 1 , further comprising generating a notification when the fog level satisfies a notification condition.

8. The method of claim 7 , wherein the generating of the notification comprises generating the notification when the fog level maintains equal to or higher than a threshold level for a threshold time period or longer.

9. The method of claim 1 , further comprising setting a defogging strength corresponding to the fog level and removing fog from the image according to the defogging strength.

10. The method of claim 9 , wherein the setting of the defogging strength comprises setting, at a predetermined time interval, the defogging strength corresponding to a fog level having a highest frequency from among fog levels detected during the predetermined time interval.

11. An apparatus for detecting fog from an image, the apparatus comprising at least one processor to implement:

a detector configured to determine a color domain of the image, convert the determined color domain of the image to obtain a luminance signal of the image and RGB values of pixels of the image, generate a histogram based on the luminance signal of the image, calculate a histogram width from the histogram, calculate a color contrast value based on the RGB values of pixels of the image, and detect a fog level of the image based on the histogram width and the color contrast value.

12. The apparatus of claim 11 , wherein the fog level is inversely proportional to a weighted sum of the histogram width and the color contrast value.

13. The apparatus of claim 12 , wherein the detector is further configured to adjust sensitivity of the fog level by adjusting a first weight of the histogram width and a second weight of the color contrast value.

14. The apparatus of claim 11 , wherein the detector is further configured to generate a notification when the fog level satisfies a notification condition.

15. The apparatus of claim 14 , wherein the detector is further configured to generate a notification when the fog level maintains equal to or higher than a threshold level for a threshold time period or longer.

16. The apparatus of claim 11 , wherein the at least one processor further implements a removal unit configured to set a defogging strength corresponding to the fog level and remove fog from the image according to the defogging strength.

17. The apparatus of claim 16 , wherein the removal unit is further configured to set, at a predetermined time interval, the defogging strength corresponding to a fog level having a highest frequency from among fog levels detected during the predetermined time interval.

18. An apparatus for detecting fog from an image, the apparatus comprising at least one processor to implement:

a detector configured to generate a histogram based on a luminance signal of the image, calculate a histogram width from the histogram, calculate a color contrast value based on color signals of the image, and detect a fog level of the image based on the histogram width and the color contrast value,

wherein the detector is further configured to detect the fog level by using an exponential function of a linear combination of the histogram width and the color contrast value.

19. The apparatus of claim 18 , wherein the detector is further configured to detect, from the histogram, a first luminance value and a second luminance value respectively corresponding to a first reference value and a second reference value each indicating a ratio of a number of accumulated pixels to a total number of pixels and determine a difference between the first luminance value and the second luminance value as the histogram width.

20. The apparatus of claim 18 , wherein the detector is further configured to detect a minimum value and a maximum value from among color values of each pixel,

calculate an average minimum value and an average maximum value respectively from minimum values and maximum values of all pixels, and determine a difference between the average maximum value and the average minimum value as the color contrast value.

Assignments (5)
CHANGE OF NAME Recorded Aug 10, 2023
From: HANWHA TECHWIN CO., LTD.
To: HANWHA VISION CO., LTD.
Reel/Frame 064549/0075 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 26, 2019
From: HANWHA AEROSPACE CO., LTD.
To: HANWHA TECHWIN CO., LTD.
Reel/Frame 049013/0723 →
CORRECTIVE ASSIGNMENT TO CORRECT THE APPLICATION NUMBER 10/853,669. IN ADDITION PLEASE SEE EXHIBIT A PREVIOUSLY RECORDED ON REEL 046927 FRAME 0019. ASSIGNOR(S) HEREBY CONFIRMS THE CHANGE OF NAME. Recorded Jan 17, 2019
From: HANWHA TECHWIN CO., LTD.
To: HANWHA AEROSPACE CO., LTD.
Reel/Frame 048496/0596 →
CHANGE OF NAME Recorded Aug 24, 2018
From: HANWHA TECHWIN CO., LTD
To: HANWHA AEROSPACE CO., LTD.
Reel/Frame 046927/0019 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 5, 2017
From: LEE, YOUNG HYUN; CHANG, YIL KWON
To: HANWHA TECHWIN CO., LTD.
Reel/Frame 042905/0418 →
Priority Claims (1)
KR 10-2017-0043093 · Apr 3, 2017 · national
Continuity (1)
Related Publication 20180285680A1 · Oct 4, 2018