CN103955901A - Enhancing method of weak-illumination video image - Google Patents
Enhancing method of weak-illumination video image Download PDFInfo
- Publication number
- CN103955901A CN103955901A CN201410192476.XA CN201410192476A CN103955901A CN 103955901 A CN103955901 A CN 103955901A CN 201410192476 A CN201410192476 A CN 201410192476A CN 103955901 A CN103955901 A CN 103955901A
- Authority
- CN
- China
- Prior art keywords
- image
- weak
- algorithm
- target image
- steps
- 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
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to an enhancing method of a weak-illumination video image. The method includes the following steps that first, the weak-illumination image is acquired in a weak illumination environment; second, the image is enhanced through a single-scale Retinex algorithm; third, the enhanced image is processed through a color migration algorithm, and the image with outstanding local details and abundant colors is obtained. Compared with the prior art, the method has the advantages that the image enhancement effect is obvious, the image is clear, and the colors are abundant.
Description
Technical field
The present invention relates to a kind of Enhancement Method of video image, especially relate to the Enhancement Method of a kind of low light level according to video image.
Background technology
Figure image intensifying is an important directions during image is processed, Retinex algorithm is a kind of a kind of nonlinear transformation that can improve brightness of image, contrast, sharpness, it can provide dynamic range compression, colour constancy, the large advantage of color rendering three of image simultaneously, be successfully applied to the processing of various still images, but due to image, to process related data volume huger, image processing speed becomes one of bottleneck of its development of restriction, studies real-time Retinex image processing techniques significant.
Project is taking Urban Underground construction of transformer substation as point of penetration, according to the concrete actual conditions of power construction process, as undesirable in During Initial Stage Construction illumination, and the video image effect obtaining is undesirable.Based on this, the video image enhancement algorithm of Study of The Underground construction of transformer substation scene, adopts single scale Retinex algorithm to realize the real time enhancing of the scene video image of working-yard in conjunction with color transfer algorithm.
Summary of the invention
Object of the present invention is exactly to provide the Enhancement Method of a kind of low light level according to video image in order to overcome the defect that above-mentioned prior art exists.
Object of the present invention can be achieved through the following technical solutions:
The low light level according to an Enhancement Method for video image, is characterized in that, comprises the following steps:
1), under weak photoenvironment, obtain weak light image;
2), adopt single scale Retinex algorithm to carry out figure image intensifying to image;
3), in conjunction with color transfer algorithm, the image after strengthening is processed, obtain the outstanding and coloury image of local detail.
Described step 2) in single scale Retinex algorithm comprise the following steps:
21), select Gaussian function scale parameter;
22), draw luminance picture by Gaussian function and weak light image;
23), in log-domain, ask enhancing model;
24), by the linear transformation image that is enhanced.
Described step 3) in color transfer algorithm comprise the following steps:
31), rgb color space is converted to lab space;
32), average and the standard deviation of computing reference image and three passages of target image;
33), weaken the overall color information of target image;
34), the detailed information of reference picture is delivered in target image;
35), the Global Information of reference picture is delivered in target image;
36), target image color transfer completes, and is transformed into rgb color space by lab space.
Compared with prior art, it is obvious that the present invention has the image effect of enhancing, clear picture, coloury advantage.
Brief description of the drawings
Fig. 1 is method flow diagram of the present invention;
Fig. 2 is the method flow diagram of step 2;
Fig. 3 is the method flow diagram of step 3.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.The present embodiment is implemented as prerequisite taking technical solution of the present invention, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
Embodiment:
As shown in Figure 1, a kind of low light level, according to the Enhancement Method of video image, comprises the following steps:
1), under weak photoenvironment, obtain weak light image;
2), adopt single scale Retinex algorithm to carry out figure image intensifying to image;
3), in conjunction with color transfer algorithm, the image after strengthening is processed, obtain the outstanding and coloury image of local detail.
As shown in Figure 2, described step 2) in single scale Retinex algorithm comprise the following steps:
21), select Gaussian function scale parameter;
22), draw luminance picture by Gaussian function and weak light image;
23), in log-domain, ask enhancing model;
24), by the linear transformation image that is enhanced.
As shown in Figure 3, described step 3) in color transfer algorithm comprise the following steps:
31), rgb color space is converted to lab space;
32), average and the standard deviation of computing reference image and three passages of target image;
33), weaken the overall color information of target image;
34), the detailed information of reference picture is delivered in target image;
35), the Global Information of reference picture is delivered in target image;
36), target image color transfer completes, and is transformed into rgb color space by lab space.
For the image of underground substation construction scene low light level photograph, in great many of experiments, find the optimal scale parameter of SSR by subjective assessment and objective image evaluation herein, now image entropy maximum, figure image intensifying effect is best.By the contrast of former figure and single scale Retinex figure image intensifying and RGB histogram of component, describe single scale Retinex algorithm in detail and can strengthen weak light image, improve image visual effect.
For weak light image, the information of image is by almost illegible.So the first step can not be used color transfer.In literary composition, the first step is passed through the outstanding easily identification of image local details after single scale Retinex (SSR) algorithm strengthens, but strengthen image through single scale Retinex, dark areas information is more outstanding, color is more single, for head it off, the image enchancing method of single scale Retinex and color transfer combination is proposed, image local details is given prominence to and rich color, color transfer has Reinhard algorithm and Welsh algorithm etc., adopts Reinhard algorithm to obtain good effect in literary composition.
Claims (3)
1. the low light level, according to an Enhancement Method for video image, is characterized in that, comprises the following steps:
1), under weak photoenvironment, obtain weak light image;
2), adopt single scale Retinex algorithm to carry out figure image intensifying to image;
3), in conjunction with color transfer algorithm, the image after strengthening is processed, obtain the outstanding and coloury image of local detail.
2. a kind of low light level according to claim 1, according to the Enhancement Method of video image, is characterized in that described step 2) in single scale Retinex algorithm comprise the following steps:
21), select Gaussian function scale parameter;
22), draw luminance picture by Gaussian function and weak light image;
23), in log-domain, ask enhancing model;
24), by the linear transformation image that is enhanced.
3. a kind of low light level according to claim 1, according to the Enhancement Method of video image, is characterized in that described step 3) in color transfer algorithm comprise the following steps:
31), rgb color space is converted to lab space;
32), average and the standard deviation of computing reference image and three passages of target image;
33), weaken the overall color information of target image;
34), the detailed information of reference picture is delivered in target image;
35), the Global Information of reference picture is delivered in target image;
36), target image color transfer completes, and is transformed into rgb color space by lab space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410192476.XA CN103955901A (en) | 2014-05-08 | 2014-05-08 | Enhancing method of weak-illumination video image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410192476.XA CN103955901A (en) | 2014-05-08 | 2014-05-08 | Enhancing method of weak-illumination video image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103955901A true CN103955901A (en) | 2014-07-30 |
Family
ID=51333170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410192476.XA Pending CN103955901A (en) | 2014-05-08 | 2014-05-08 | Enhancing method of weak-illumination video image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103955901A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872331A (en) * | 2019-01-30 | 2019-06-11 | 天津大学 | A kind of remote sensing image data automatic recognition classification method based on deep learning |
| CN109886885A (en) * | 2019-01-23 | 2019-06-14 | 齐鲁工业大学 | A kind of image enchancing method and system based on Lab color space and Retinex |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100266214A1 (en) * | 2009-04-15 | 2010-10-21 | United States of America as represented by the Administrator of the National Aeronautics and | Smart Image Enhancement Process |
| CN103606134A (en) * | 2013-11-26 | 2014-02-26 | 国网上海市电力公司 | Enhancing method of low-light video images |
-
2014
- 2014-05-08 CN CN201410192476.XA patent/CN103955901A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100266214A1 (en) * | 2009-04-15 | 2010-10-21 | United States of America as represented by the Administrator of the National Aeronautics and | Smart Image Enhancement Process |
| CN103606134A (en) * | 2013-11-26 | 2014-02-26 | 国网上海市电力公司 | Enhancing method of low-light video images |
Non-Patent Citations (2)
| Title |
|---|
| HYUNCHAN AHN等: "Adaptive local tone mapping based on retinex for high dynamic range images", 《CONSUMER ELECTRONICS (ICCE), 2013 IEEE INTERNATIONAL CONFERENCE ON》 * |
| 华顺刚等: "高动态范围图像及其色彩迁移", 《计算机工程与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886885A (en) * | 2019-01-23 | 2019-06-14 | 齐鲁工业大学 | A kind of image enchancing method and system based on Lab color space and Retinex |
| CN109872331A (en) * | 2019-01-30 | 2019-06-11 | 天津大学 | A kind of remote sensing image data automatic recognition classification method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10937167B2 (en) | Automated generation of pre-labeled training data | |
| CN102063706B (en) | Rapid defogging method | |
| US10592754B2 (en) | Shadow removing method for color image and application | |
| Peng et al. | Image haze removal using airlight white correction, local light filter, and aerial perspective prior | |
| CN103440674B (en) | A kind of rapid generation of digital picture wax crayon specially good effect | |
| CN102779330A (en) | Image reinforcement method, image reinforcement device and display device | |
| CN105424709A (en) | Fruit surface defect detection method based on image marking | |
| CN103593830A (en) | Low-light video image reinforcing method | |
| CN107256539B (en) | Image sharpening method based on local contrast | |
| CN103606134A (en) | Enhancing method of low-light video images | |
| CN104504722A (en) | Method for correcting image colors through gray points | |
| EP2500865A3 (en) | Image segmentation apparatus, method and program | |
| CN108711160B (en) | Target segmentation method based on HSI (high speed input/output) enhanced model | |
| CN104021527A (en) | Rain and snow removal method in image | |
| CN104504666B (en) | A kind of tone mapping method based on laplacian pyramid | |
| Wei et al. | An image fusion dehazing algorithm based on dark channel prior and retinex | |
| CN111027564A (en) | Low-illumination imaging license plate recognition method and device based on deep learning integration | |
| Othman et al. | Enhanced single image dehazing technique based on hsv color space | |
| CN103955901A (en) | Enhancing method of weak-illumination video image | |
| Hu et al. | A low illumination video enhancement algorithm based on the atmospheric physical model | |
| CN110827241B (en) | Low-brightness enhanced picture full-reference method based on color distortion and contrast enhancement | |
| He et al. | Effective haze removal under mixed domain and retract neighborhood | |
| CN107563340A (en) | The machine identification method of contained cloud in a kind of image | |
| CN104700111A (en) | Method and system for vehicle color identification based on Retinex image enhancement algorithm | |
| Li et al. | Contrast enhancement algorithm for outdoor infrared images based on local gradient-grayscale statistical feature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140730 |