CN102368330A - Processing method for camera image and apparatus thereof - Google Patents
Processing method for camera image and apparatus thereof Download PDFInfo
- Publication number
- CN102368330A CN102368330A CN2011103268070A CN201110326807A CN102368330A CN 102368330 A CN102368330 A CN 102368330A CN 2011103268070 A CN2011103268070 A CN 2011103268070A CN 201110326807 A CN201110326807 A CN 201110326807A CN 102368330 A CN102368330 A CN 102368330A
- Authority
- CN
- China
- Prior art keywords
- image
- atmospheric environment
- value
- imaging
- actual photographed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a processing method for a camera image and an apparatus thereof. On the basis of an image that is actually shot by a camera, an imaging value of an atmospheric environment is obtained by an analysis as well as a certain imaging proportion coefficient is calculated, so that an influence caused by the atmospheric environment in the image that is actually shot can be removed; that is, an darkening aspect is removed; therefore, an image that is similar to a real scene image can be presented and the color expressive force is strong. According to the method and the apparatus in the invention, images that are shot on the cloudy weather conditions like dusty, smoky and misty weathers and the like can be presented with gorgeous colors.
Description
Technical field
The present invention relates to a kind of image processing method and device, particularly a kind of camera review disposal route and device.
Background technology
Because the influence of the dust in the atmosphere, cigarette, mist; Under the most actual outdoor scene; Light all is divergent shape before getting into camera lens, this just causes the image serious degradation taken, resolution and contrast reduction; Make entire image or video pictures seem bright-coloured inadequately, expressive force is not strong.
The solution of problem has two kinds of approach hereto at present: image restoration and figure image intensifying.Image recovery method is set up the physical model of image degradation through the analysis to the image degradation reason, inverting degenerative process, the image before obtaining degenerating.Image enchancing method is not generally considered the image degradation reason, just to present image, utilizes method degree of comparing enhancings such as histogram stretching.
Computer vision and field of Computer Graphics, following physical model are widely used in the imaging of outdoor scene: I (x)=J (x) t (x)+A (1-t (x))
Wherein, I is the image that actual photographed arrives, and J is the true picture of scene, and A representes the atmospheric environment image, and t representes scene true picture shared scale-up factor in final actual imaging.
The purpose of image restoration, the image I that arrives through actual photographed exactly recovers the true picture J of scene.
Summary of the invention
The objective of the invention is to, a kind of image processing method and device are provided.It can be directed against the picture of the high-definition camera shooting of outdoor scene, strengthens its color representation power, makes the image of under muddy weather conditions such as dust, cigarette, mist, taking also can present gorgeous color.
Technical scheme of the present invention: a kind of camera review disposal route, be characterized in, may further comprise the steps:
1. from actual photographed image (I), filter out the atmospheric environment imaging (A) under this scene;
2. ask for scene true picture (J) shared scale-up factor (t) in actual photographed image (final actual imaging);
3. according to formula I (x)=J (x) t (x)+A (1-t (x)), from actual photographed image (I), restore scene true picture (J).
In the above-mentioned camera review disposal route; Said step 1.; The method of screening atmospheric environment imaging (A) is: from the RGB data source of actual photographed image (I), filter out the pixel that saturation degree is lower than threshold value; And therefrom select higher preceding 10% pixel of gray-scale value, calculate its corresponding RGB average, with this value as atmospheric environment imaging (A).Atmospheric environment imaging (A) is with (A
r, A
g, A
b) expression, A
rExpression R channel environment imaging value, A
gExpression G channel environment imaging value, A
bExpression B channel environment imaging value.
In the aforesaid camera review disposal route; Said step 2.; The method of asking for scale-up factor (t) is: the value based on the smallest passage in R, G, three passages of B in the scene true picture (J) is zero, and according to formula I (x)=J (x) t (x)+A (1-t (x)), draws t (x)=1-k * min (I (x))/A; Wherein min (I (x)) is the value of the smallest passage of actual photographed image (I) in R, G, three passages of B, and k is the equilibrium constant greater than 0 Xiao Yu 1.
In the aforesaid camera review disposal route, the threshold value of said saturation degree is 0.3.
In the aforesaid camera review disposal route, the value of the said equilibrium constant (k) is 0.7.
A kind of camera review treating apparatus is characterized in, comprising:
The RGB data source memory is used to store the RGB data source of actual photographed image;
The atmospheric environment image-forming module links to each other with the RGB data source memory, is used to obtain the atmospheric environment imaging;
The imaging coefficient module links to each other with the atmospheric environment image-forming module with the RGB data source memory, is used for obtaining the imaging coefficient;
The image restoration module links to each other with the atmospheric environment image-forming module with imaging coefficient module, RGB data source memory, and being used for actual photographed image is restored is the scene true picture.
Compared with prior art; The present invention is the basis with the video camera actual photographed image, analyzes and draws atmospheric environment imaging value, and draw certain imaging scale-up factor; Thereby the influence that can the atmospheric environment in the actual photographed image be caused is removed; Promptly removed haze, can make to demonstrate the image close with the scene true picture at last, its color representation power is stronger.Therefore use method and apparatus of the present invention can make the image of under muddy weather conditions such as dust, cigarette, mist, taking also can present gorgeous color.
Description of drawings
Fig. 1 is a structural representation of the present invention;
Fig. 2 is a step of the present invention process flow diagram 1.;
Fig. 3 is a step of the present invention process flow diagram 2.;
Fig. 4 is a step of the present invention process flow diagram 3.;
Fig. 5 is the effect contrast figure of the embodiment of the invention.
Embodiment
Below in conjunction with accompanying drawing and embodiment the present invention is further described, but not as the foundation to the present invention's restriction.
Embodiment.A kind of camera review disposal route may further comprise the steps:
1. from actual photographed image I, filter out the atmospheric environment imaging A under this scene;
2. ask for scene true picture J shared scale-up factor t in actual photographed image (final actual imaging);
3. according to formula I (x)=J (x) t (x)+A (1-t (x)), from actual photographed image I, restore scene true picture J.
Said step 1.; The method of screening atmospheric environment imaging A is: from the RGB data source of actual photographed image I, filter out the pixel that saturation degree is lower than threshold value; And therefrom select higher preceding 10% pixel of gray-scale value, calculate its corresponding RGB average, with this value as atmospheric environment imaging A.A is with (A in the atmospheric environment imaging
r, A
g, A
b) expression, A
rExpression R passage atmospheric environment imaging value, A
gExpression G passage atmospheric environment imaging value, A
bExpression B passage atmospheric environment imaging value.
Said step 2.; The method of asking for scale-up factor t is: the value based on the smallest passage in R, G, three passages of B among the scene true picture J is zero; And according to formula I (x)=J (x) t (x)+A (1-t (x)); Draw t (x)=1-k * min (I (x))/A, wherein min (I (x)) is the value of the smallest passage of actual photographed image I in R, G, three passages of B, and k is the equilibrium constant greater than 0 Xiao Yu 1.
Realize a kind of camera review treating apparatus of said method, comprising:
RGB data source memory 11 is used to store the RGB data source of actual photographed image;
Atmospheric environment image-forming module 12 links to each other with RGB data source memory 11, is used to obtain the atmospheric environment imaging;
Imaging coefficient module 13 links to each other with atmospheric environment image-forming module 12 with RGB data source memory 11, is used for obtaining the imaging coefficient;
Image restoration module 14 links to each other with atmospheric environment image-forming module 12 with imaging coefficient module 13, RGB data source memory 11, and being used for actual photographed image is restored is the scene true picture.
The step detailed step 1. in 12 completion of atmospheric environment image-forming module of the preferred embodiment of the present invention is as shown in Figure 2:
(S21) read original rgb image data.
(S22) utilize the RGB data, ask for the intensity value of each pixel, it is as follows that saturation degree is asked for formula:
G
max＝max(R、B、G) (2)
Wherein, C
MinThe minimum value of expression current pixel R, G, B, C
MaxThe maximal value of expression current pixel R, G, B, S representes the intensity value of current pixel.
(S23) intensity value and empirical value compare (this preferred embodiment is made as 0.3 with this threshold value), if saturation degree, thinks that this pixel is a valid pixel less than empirical value, keep this pixel, get into the statistics flow process.If intensity value, is ignored this pixel greater than empirical value, continue to read next pixel.
(S24) valid pixel of statistics after the S23 screening counted out, the value of asking for grey level histogram and adding up the corresponding R of wherein maximum 10% pixel, G, three passages of B respectively, and formula is following:
R
a＝R
a+R
G
a＝G
a+G
B
a＝B
a+B (3)
V
num＝V
num+1
Wherein, R
aExpression R passage aggregate-value, G
aExpression G passage aggregate-value, B
aExpression B passage aggregate-value, V
NumRemarked pixel is counted out.
(S25) utilize following formula to ask for environment imaging A
r, A
g, A
bValue:
A
g＝G
a/V
num (4)
Wherein, A
rExpression R passage atmospheric environment imaging value, A
gExpression G passage atmospheric environment imaging value, A
bExpression B passage atmospheric environment imaging value.
As shown in Figure 3, preferred embodiment of the present invention completing steps detailed step 2. on imaging coefficient module 13 is following:
(S31) read original rgb image data.
(S32) ask for the minimum value of each pixel R, G, B.
(S33) ask for the imaging coefficient t (x) of each pixel.Can know that by formula (1) the imaging coefficient of pixel is relevant with the true pixel values of scene and atmospheric environment value.The arrangement formula
I(x)＝J(x)t(x)+A(1-t(x)) (1)
Can get formula (5) as follows:
1-t(x)＝I(x)/A-J(x)×t(x)/A (5)
Formula (5) is got the minimum value in R, G, the B component among I (x) and the J (x) respectively, releases formula (6):
1-t(x)＝min(I(x))/A-min(J(x))/A (6)
Wherein, min (I (x)) expression actual photographed to image I in the locational pixel R of x, G, the three-channel minimum value of B, the locational pixel R of x, G, the three-channel minimum value of B among the true picture J of min (J (x)) expression scene.
The value of supposing the smallest passage in R in the scene true picture, G, three passages of B goes to zero; Be that min (J (x)) goes to zero; Consider the influence of min (J (x)) being forced to be changed to 0 pair of equality, we increase a constant parameter k (0＜k＜1) and come balance, so formula (6) changes into:
t(x)＝1-k×min(I(x))/A (7)
In the preferred embodiments of the present invention, we are made as 0.7 with k.
As shown in Figure 4, preferred embodiment of the present invention completing steps detailed step 3. on image restoration module 14 is following:
(S41) read original rgb image data.
(S42) read each pixel imaging coefficient data t (x).
(S43) restore the real scene image.Can release by formula (1):
J(x)＝(I(x)-A)/t(x)+A (8)
For avoiding the too small J of causing of t (x) value (x) to overflow, increase restriction to t (x) in the formula (8), be rewritten as:
J(x)＝(I(x)-A)/max(t(x)，0.1)+A (9)
Utilize formula (9), can restore the real scene image.
Method and apparatus of the present invention can make the image of under muddy weather conditions such as dust, cigarette, mist, taking also can present gorgeous color.As shown in Figure 5, Image to left is for being treated image, and the right side is the image after the inventive method is handled.
Claims (6)
1. a camera review disposal route is characterized in that, may further comprise the steps:
1. from actual photographed image (I), filter out the atmospheric environment imaging (A) under this scene;
2. ask for scene true picture (J) shared scale-up factor (t) in actual photographed image;
3. according to formula I (x)=J (x) t (x)+A (1-t (x)), from actual photographed image (I), restore scene true picture (J).
2. camera review disposal route according to claim 1; It is characterized in that; Said step 1., the method for screening atmospheric environment imaging (A) is: from the RGB data source of actual photographed image (I), filter out the pixel that saturation degree is lower than threshold value, and therefrom screen higher preceding 10% pixel of gray-scale value; Obtain its corresponding RGB average, with this value as atmospheric environment imaging (A).
3. camera review disposal route according to claim 1; It is characterized in that, said step 2., the method for asking for scale-up factor (t) is: the value based on the smallest passage in R, G, three passages of B in the scene true picture (J) is zero; And according to formula I (x)=J (x) t (x)+A (1-t (x)); Draw t (x)=1-k * min (I (x))/A, wherein min (I (x)) is the value of the smallest passage of actual photographed image (I) in R, G, three passages of B, and k is less than 1 the equilibrium constant greater than 0.
4. camera review disposal route according to claim 2 is characterized in that: the threshold value of said saturation degree is 0.3.
5. camera review disposal route according to claim 3 is characterized in that: the value of the said equilibrium constant (k) is 0.7.
6. a camera review treating apparatus is characterized in that, comprising:
RGB data source memory (11) is used to store the RGB data source of actual photographed image;
Atmospheric environment image-forming module (12) links to each other with RGB data source memory (11), is used to obtain the atmospheric environment imaging;
Imaging coefficient module (13) links to each other with atmospheric environment image-forming module (12) with RGB data source memory (11), is used for obtaining the imaging coefficient;
Image restoration module (14) links to each other with atmospheric environment image-forming module (12) with imaging coefficient module (13), RGB data source memory (11), and being used for actual photographed image is restored is the scene true picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103268070A CN102368330A (en) | 2011-10-25 | 2011-10-25 | Processing method for camera image and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103268070A CN102368330A (en) | 2011-10-25 | 2011-10-25 | Processing method for camera image and apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102368330A true CN102368330A (en) | 2012-03-07 |
Family
ID=45760891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011103268070A Pending CN102368330A (en) | 2011-10-25 | 2011-10-25 | Processing method for camera image and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102368330A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750674A (en) * | 2012-04-26 | 2012-10-24 | 长春理工大学 | Video image defogging method based on self-adapting allowance |
| CN104050637A (en) * | 2014-06-05 | 2014-09-17 | 华侨大学 | Quick image defogging method based on two times of guide filtration |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101588481A (en) * | 2009-06-15 | 2009-11-25 | 浙江金汇科技股份有限公司 | CCD fog-penetration imaging system and control method thereof |
| CN101950416A (en) * | 2010-09-15 | 2011-01-19 | 北京理工大学 | Bidirectional filtration-based real-time image de-hazing and enhancing method |
-
2011
- 2011-10-25 CN CN2011103268070A patent/CN102368330A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101588481A (en) * | 2009-06-15 | 2009-11-25 | 浙江金汇科技股份有限公司 | CCD fog-penetration imaging system and control method thereof |
| CN101950416A (en) * | 2010-09-15 | 2011-01-19 | 北京理工大学 | Bidirectional filtration-based real-time image de-hazing and enhancing method |
Non-Patent Citations (1)
| Title |
|---|
| 占吉清: "雾天图像复原算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102750674A (en) * | 2012-04-26 | 2012-10-24 | 长春理工大学 | Video image defogging method based on self-adapting allowance |
| CN102750674B (en) * | 2012-04-26 | 2014-06-18 | 长春理工大学 | Video image defogging method based on self-adapting allowance |
| CN104050637A (en) * | 2014-06-05 | 2014-09-17 | 华侨大学 | Quick image defogging method based on two times of guide filtration |
| CN104050637B (en) * | 2014-06-05 | 2017-02-22 | 华侨大学 | Quick image defogging method based on two times of guide filtration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106780356B (en) | Image defogging method based on convolutional neural network and prior information | |
| US9672601B2 (en) | System, method and computer-accessible medium for restoring an image taken through a window | |
| CN107292830B (en) | Low-illumination image enhancement and evaluation method | |
| RU2017100022A (en) | IMAGE PROCESSING SYSTEM AND MACHINE READABLE RECORDING MEDIA | |
| CN104700430A (en) | Method for detecting movement of airborne displays | |
| CN104639920A (en) | Wide dynamic fusion method based on single-frame double-pulse exposure mode | |
| CN104299192A (en) | Single image defogging method based on atmosphere light scattering physical model | |
| CN104881845B (en) | Method and apparatus for handling image | |
| CN104766307A (en) | Picture processing method and device | |
| US9258485B2 (en) | Image sensor cropping images in response to cropping coordinate feedback | |
| CN104331867B (en) | The method, device and mobile terminal of image defogging | |
| CN105989583B (en) | A kind of image defogging method | |
| CN102368330A (en) | Processing method for camera image and apparatus thereof | |
| JP4340303B2 (en) | Image processing apparatus and image processing program | |
| CN102572374A (en) | Demisting image collection device | |
| CN104869287A (en) | Video shooting noise reduction method based on mobile apparatus GPU and angular velocity sensor | |
| EP3799415A3 (en) | Method and device for processing videos, and medium | |
| KR101477505B1 (en) | Forming Method of High Dynamic Range Image | |
| CN117274107A (en) | End-to-end color and detail enhancement method, device and equipment under low-illumination scene | |
| CN106327439A (en) | Rapid fog and haze image sharpening method | |
| CN201898578U (en) | Demisting image acquisition device | |
| Yoo et al. | 7‐5: Synthetic Dataset for Improving UDC Video Restoration Network Performance | |
| CN115205731A (en) | Video noise reduction device and method and terminal | |
| KR20130044793A (en) | Video processing apparatus and method for removing rain from video | |
| CN102724386A (en) | Real-time video intelligent system and processing method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120307 |