Image processing system and computer-readable recording medium

Patent metadata

Field	Value
Publication number	US-10096092-B2
Application number	US-201615372402-A
Country	US
Kind code	B2
Filing date	Dec 8, 2016
Priority date	Jun 12, 2014
Publication date	Oct 9, 2018
Grant date	Oct 9, 2018

Abstract

A technique to remove fog from an image more appropriately has been called for. An image processing system is provided, including: a haze depth estimating unit that derives a haze depth estimate value of one frame among a plurality of frames included in a moving image; a parameter adjusting unit that adjusts a parameter to be used in a haze removal process of the one frame based on a haze depth estimate value of the one frame, and a relationship between the one frame and a past frame of the one frame; and a haze removing unit that executes a haze removal process on the one frame based on the parameter adjusted by the parameter adjusting unit.

First claim

What is claimed is:

1. An image processing system comprising:
a haze depth estimating unit that derives a haze depth estimate value of one frame among a plurality of frames included in a moving image;
a parameter adjusting unit that adjusts a parameter to be used in a haze removal process of the one frame based on a haze depth estimate value of the one frame, and a relationship between the one frame and a past frame of the one frame; and
a haze removing unit that executes a haze removal process on the one frame based on the parameter adjusted by the parameter adjusting unit, wherein
using a haze depth estimate value of the one frame as a haze depth target value of the one frame, the parameter adjusting unit adjusts a parameter to be used in a haze removal process of the one frame such that the parameter to be used in the haze removal process of the one frame becomes closer to, in a stepwise manner, the haze depth target value, from a parameter adjusted in a haze removal process of the past frame.

2. The image processing system according to claim 1 , further comprising a scene change judging unit that judges whether or not the one frame is a frame in which a scene change occurs, wherein
when the scene change judging unit judges that in a relationship between the one frame and the past frame, the one frame is a frame in which a scene change occurs, the parameter adjusting unit increases step-widths at which the parameter is made close to, stepwise, the haze depth target value.

3. An image processing system comprising:
a haze depth estimating unit that derives a haze depth estimate value of one frame among a plurality of frames included in a moving image;
a parameter adjusting unit that adjusts a parameter to be used in a haze removal process of the one frame based on a haze depth estimate value of the one frame, and a relationship between the one frame and a past frame of the one frame;
a haze removing unit that executes a haze removal process on the one frame based on the parameter adjusted by the parameter adjusting unit;
a haze reliability estimating unit that estimates a reliability of the haze depth estimate value;
a target value acquiring unit that acquires a haze depth target value of the past frame;
a target value determining unit that determines, as a haze depth target value of the one frame, either the haze depth target value of the past frame acquired by the target value acquiring unit or a haze depth estimate value of the one frame derived by the haze depth estimating unit; and
a difference absolute value deriving unit that derives a difference absolute value between a haze depth target value of the one frame determined by the target value determining unit and a parameter used in a haze removal process of a past frame of the one frame, wherein
the parameter adjusting unit adjust a parameter to be used in a haze removal process of the one frame with an adjustment amount corresponding to: the reliability; the difference absolute value; and whether or not the one frame is a frame in which a scene change occurs, such that a parameter used in a haze removal process of the past frame becomes close to, stepwise, a haze depth target value of the one frame determined by the target value determining unit.

4. The image processing system according to claim 3 , wherein
when the one frame is judged as a frame in which a scene change occurs, the parameter adjusting unit adjusts the parameter with a first adjustment amount,
when the one frame is judged as not a frame in which a scene change occurs, a reliability of the estimate value is higher than a first threshold, and the difference absolute value is higher than a second threshold, the parameter adjusting unit adjusts the parameter with a second adjustment amount smaller than the first adjustment amount, and
when the one frame is judged as not a frame in which a scene change occurs, and a reliability of the estimate value is lower than the first threshold or the difference absolute value is lower than the second threshold, the parameter adjusting unit adjusts the parameter with a third adjustment amount smaller than the second adjustment amount.

5. The image processing system according to claim 1 , further comprising a haze reliability estimating unit that estimates a reliability of the haze depth estimate value, wherein
when the haze reliability estimating unit judges that in the one frame, the haze depth estimate value is not reliable, the parameter adjusting unit adjusts a parameter to be used in a haze removal process of the one frame such that it becomes close to, stepwise, a target value set at a time of the past frame.

6. An image processing system comprising:
a haze depth estimating unit that derives a haze depth estimate value of one frame among a plurality of frames included in a moving image;
a parameter adjusting unit that adjusts a parameter to be used in a haze removal process of the one frame based on a haze depth estimate value of the one frame, and a relationship between the one frame and a past frame of the one frame;
a haze removing unit that executes a haze removal process on the one frame based on the parameter adjusted by the parameter adjusting unit;
a haze reliability estimating unit that estimates a reliability of the haze depth estimate value;
a target value acquiring unit that acquires a haze depth target value of the past frame; and
a target value determining unit that, based on the reliability estimated by the haze reliability estimating unit, determines which one, the haze depth target value of the past frame acquired by the target value acquiring unit or a haze depth estimate value of the one frame derived by the haze depth estimating unit, is to be used for adjusting a parameter to be used in a haze removal process of the one frame.

7. The image processing system according to claim 6 , further comprising a difference absolute value deriving unit that derives a difference absolute value between a haze depth target value of the past frame acquired by the target value acquiring unit and the haze depth estimate value of the one frame derived by the haze depth estimating unit, wherein
when the one frame is a frame in which a scene change occurs or when the one frame is not a frame in which a scene change occurs, a reliability of the estimate value is higher than a first threshold, and the difference absolute value is higher than a second threshold, the target value determining unit determines to use a haze depth estimate value of the one frame for adjusting a parameter to be used in a haze removal process of the one frame, and
when the one frame is not a frame in which a scene change occurs, and a reliability of the estimate value is lower than the first threshold or the difference absolute value is lower than the second threshold, the target value determining unit determines to use a haze depth target value of the past frame for adjusting a parameter to be used in a haze removal process of the one frame.

8. A non-transitory computer-readable recording medium having recorded thereon a program for allowing a computer to function as:
a haze depth estimating unit that derives a haze depth estimate value of one frame among a plurality of frames included in a moving image;
a parameter adjusting unit that adjusts a parameter to be used in a haze removal process of the one frame based on a haze depth estimate value of the one frame, and a relationship between the one frame and a past frame of the one frame; and
a haze removing unit that executes a haze removal process on the one frame based on the parameter adjusted by the parameter adjusting unit, wherein
using a haze depth estimate value of the one frame as a haze depth target value of the one frame, the paramet

Assignees

• Eizo Corp

Inventors

• Nakamae Takashi
• Higashi Masafumi
• Aoki Reo

Classifications

• G06T5/20

  using local operators · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/136

  involving thresholding · CPC title

• H04N1/407 Primary

  Control or modification of tonal gradation or of extreme levels, e.g. background level · CPC title

• G06T2207/20021

  Dividing image into blocks, subimages or windows · CPC title