CN105023243A - Video image enhancement method and device, and parking assisting system - Google Patents
Video image enhancement method and device, and parking assisting system Download PDFInfo
- Publication number
- CN105023243A CN105023243A CN201410174747.9A CN201410174747A CN105023243A CN 105023243 A CN105023243 A CN 105023243A CN 201410174747 A CN201410174747 A CN 201410174747A CN 105023243 A CN105023243 A CN 105023243A
- Authority
- CN
- China
- Prior art keywords
- component image
- gray component
- gray
- image
- pixel
- Prior art date
Links
- 238000009499 grossing Methods 0.000 claims abstract description 40
- 230000002708 enhancing Effects 0.000 claims description 58
- 238000000034 method Methods 0.000 claims description 57
- 238000001914 filtration Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 4
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 230000002194 synthesizing Effects 0.000 claims description 4
- 201000010874 syndrome Diseases 0.000 claims description 3
- 238000005286 illumination Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005728 strengthening Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 210000003710 Cerebral Cortex Anatomy 0.000 description 1
- 210000001525 Retina Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006011 modification reaction Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Abstract
Provided are a video image enhancement method and device, and a parking assisting system. The method comprises extracting a gray level component image in original images collected by a camera in real time; according to relative light and shade relations between pixel points of the gray level component image and the pixel points in the gray level component image after Gaussian smoothing, carrying out gray level correction on the pixel points of the gray level component image; and compiling the gray level component image after the gray level correction, thus to obtain an enhanced image. According to the above technical scheme, the gray level of the pixel points of the gray level component image is compared with that of the pixel points of the image after Gaussian smoothing, and gray level correction is carried out on the gray level component image, such that the image obtained after enhancement is constant in color and high in contract ratio and definition.
Description
Technical field
The present invention relates to technical field of image processing, particularly relate to a kind of video image enhancing method and device, parking assisting system.
Background technology
Along with the raising of living standards of the people, automobile enters common people house.Popularizing of automobile, while being convenient for people to trip, brings many worries and inconvenience also to the life of people.There is the generation of the major accident much bumped against about cars many under low visibility meteorological condition in recent years, cause the heavy losses of national wealth and people's lives and properties.
For solving the problem, the way that prior art is taked is: gather road ahead image by vehicle-mounted camera, adopt and through overall Retinex (abbreviation of retina " Retina " and cerebral cortex " Cortex ") method of video image processing, collected video image is processed, then output to the liquid crystal indicator of automobile cab.Driver just can in the boisterous situations such as road visibility is extremely low, according to liquid crystal indicator spread out of that the vision signal after enhancing is clear differentiates road ahead situation, thus reduce the traffic hazard probability of happening caused because of poor visibility, reduce economic loss.
Theoretical according to Retinex, the color of object is determined by the reflection potential of object long wave, medium wave and shortwave light, instead of determined by the absolute value of intensity of reflected light; The color of object does not affect by illumination is heteropic, has consistance.Retinex theory is mainly used for compensating by the serious image of illumination effect, Main is exactly the image that will two width be become different a given picture breakdown, irradiate component image and reflecting component image, this benefit by piece image resolution process is to remove prospect illumination and background illumination to the impact of image, and can in enhanced room and the space illumination variation of outdoor images.Overall situation Retinex method of video image processing is based upon in above-mentioned Retinex theoretical foundation, is corrected the gray-scale value of preimage vegetarian refreshments by the relative relationship between light and dark between pixel with other pixels in whole image.But the low and unsharp problem of cross-color, contrast may be there is in the image adopting the process of overall Retinex method of video image processing to obtain.
Summary of the invention
How what the embodiment of the present invention solved obtains the high and video image clearly of constant color, contrast if being.
For solving the problem, embodiments provide a kind of video image enhancing method, described method comprises:
Extract camera Real-time Collection to original image in gray component image;
According to pixel and the relative relationship between light and dark between pixel described in the gray component image after Gaussian smoothing of described gray component image, gray level correction is carried out to the pixel of described gray component image;
Synthesized by the described gray component image through gray level correction, be enhanced image.
Alternatively, at the described pixel according to described gray component image and the relative relationship between light and dark between pixel described in the gray component image after Gaussian smoothing, before gray level correction is carried out to the pixel of described gray component image, also comprise: the data type of the pixel of described gray component image is converted into double type from byte type.
Alternatively, the described pixel according to described gray component image and the relative relationship between light and dark between pixel described in the gray component image after Gaussian smoothing, carry out gray level correction to the pixel of described gray component image, comprising:
Described gray component image is put into log-domain process, be enhanced gray component image;
The gray-scale value of pixel in described enhancing gray component image is initialized as constant;
With Gaussian template, convolution is done to described enhancing gray component image, obtain low-pass filtering gray component image;
Described low-pass filtering gray component image is put into log-domain process, obtain the gray component image after Gaussian smoothing;
Calculate the relative relationship between light and dark between the pixel of described gray component image and the pixel of the gray component image after described Gaussian smoothing;
Gray level correction is carried out according to the pixel of described relative relationship between light and dark to described enhancing gray component image.
Alternatively, the described gray-scale value by the pixel in described enhancing gray component image is initialized as constant and comprises: the mean value gray-scale value of the pixel in described enhancing gray component image being initialized as pixel gray-scale value in described enhancing gray component image.
Alternatively, following formula is adopted to do convolution to described enhancing gray component image:
D(x,y)＝S(x,y)*F(x,y)
Wherein, D (x, y) for described low-pass filtering gray component image, S (x, y) be described original image, F (x, y) is Gaussian filter function.
Alternatively, the relative relationship between light and dark between the pixel of gray component image described in following formulae discovery and the pixel of the gray component image after described Gaussian smoothing is adopted:
relation(x,y)＝log D(x,y)–logS(x,y)
Wherein, relation (x, y) is relation function, log D (x, y) for the logarithm of described low-pass filtering gray component image, log S (x, y) be the logarithm of described original image.
Alternatively, described gray component image comprises R gray component image, G gray component image and B gray component image.
The embodiment of the present invention additionally provides a kind of video image enhancement device, comprising:
Extraction unit, be suitable for extracting camera Real-time Collection to original image in gray component image;
Correcting unit, is suitable for the pixel according to described gray component image and the relative relationship between light and dark between pixel described in the gray component image after Gaussian smoothing, carries out gray level correction to the pixel of described gray component image;
Synthesis unit, be suitable for the gray component image through described correcting unit gray level correction to synthesize, be enhanced image.
Alternatively, also comprise:
Converting unit, the data type being suitable for the gray-scale value of pixel in the described gray component image extracted by described extraction unit is converted into double type by byte type;
Alternatively, described correcting unit comprises:
Process subelement, be suitable for that described gray component image is put into log-domain and process, be enhanced gray component image;
Initialization subelement, the gray-scale value being suitable for pixel in the enhancing gray component image process of described process subelement obtained is initialized as constant;
Low-pass filtering subelement, is suitable for doing convolution with Gaussian template to the described enhancing gray component image that the process of described process subelement obtains, obtains low-pass filtering gray component image;
Gaussian smoothing subelement, the described low-pass filtering gray component image being suitable for the process of low-pass filtering subelement being obtained is put into log-domain and is processed, and obtains the gray component image after Gaussian smoothing;
Computation subunit, the relative relationship between light and dark between the pixel of the gray component image after the Gaussian smoothing that the pixel being suitable for calculating the described gray component image that the process of described process subelement obtains and the process of described Gaussian smoothing subelement obtain;
Syndrome unit, the pixel of relative relationship between light and dark to described enhancing gray component image being suitable for calculating according to described computation subunit carries out gray level correction.
Alternatively, described initialization subelement is suitable for the gray-scale value of pixel in described enhancing gray component image to be initialized as the mean value of the pixel gray-scale value in described enhancing gray component image.
Alternatively, gray component image comprises R gray component image, G gray component image and B gray component image.
The embodiment of the present invention additionally provides a kind of parking assisting system, comprises;
Rearview camera, is suitable for Real-time Collection and parks the image of rear view of vehicle in process;
Above-mentioned video image enhancement device;
Display device, for showing the enhancing image that described video image enhancement device exports.
Compared with prior art, the technical scheme of the embodiment of the present invention has following advantage:
Due to the gray-scale value of pixel in the image after pixel gray-scale value in gray component image and the Gaussian smoothing centered by it is contrasted, gray correction is carried out to described gray component image, and the impact of distant pixel on preimage vegetarian refreshments need not be considered, can the difference of reflected image vegetarian refreshments on reflecting component more exactly, make the color of image that obtains after strengthening process keep constant, and contrast and sharpness higher.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of video image enhancing method in the embodiment of the present invention;
Fig. 2 is the process flow diagram of the another kind of video image enhancing method in the embodiment of the present invention;
Fig. 3 is the structural representation of a kind of video image enhancement device in the embodiment of the present invention;
Fig. 4 is the structural representation of the correcting unit in the video image enhancement device shown in Fig. 3;
Fig. 5 is the structural representation of the parking assisting system in the embodiment of the present invention.
Embodiment
In prior art, the irradiation component of overall situation Retinex method of video image processing supposition image slices vegetarian refreshments is identical, but in fact the irradiation component of different pixels point has nuance, utilize overall Retinex method of video image processing can not calculate actual reflection differences between pixel, cause the video image color distortion obtained after treatment, and contrast is lower, unintelligible.
For solving the problem, the technical scheme that the embodiment of the present invention adopts by the image of vehicle rearview camera Real-time Collection in vehicle parking process after treatment, can obtain constant color and strengthens image clearly.
For enabling above-mentioned purpose of the present invention, feature and advantage more become apparent, and are described in detail specific embodiments of the invention below in conjunction with accompanying drawing.
Fig. 1 shows the process flow diagram of the video image enhancing method in the embodiment of the present invention.Video image enhancing method as shown in Figure 1, can comprise:
Step S11: extract camera Real-time Collection to original image in gray component image.
In an embodiment of the present invention, the original image that camera collects can be coloured image, and the gray component image of described coloured image can comprise: R gray component image, G gray component image and B gray component image.
Step S12: according to pixel and the relative relationship between light and dark between pixel in the gray component image after Gaussian smoothing of described gray component image, gray level correction is carried out to the pixel of described gray component image.
In an embodiment of the present invention, the pixel of gray component image and the relative relationship between light and dark between pixel described in the gray component image after Gaussian smoothing can be passed through, calculate reflection differences real between different pixels point, thus the gray-scale value of pixel in gray component image is corrected.
Step S13: synthesized by the described gray component image through gray level correction, be enhanced image.
In an embodiment of the present invention, by through the R gray component image of gray level correction, G gray component image and B gray component Images uniting, be enhanced after coloured image at maintenance constant color simultaneously, there is higher contrast and sharpness.
Fig. 2 shows the process flow diagram of the another kind of video image enhancing method in the embodiment of the present invention.Video image enhancing method as shown in Figure 2 comprises:
Step S21: extract camera Real-time Collection to original image in gray component image.
In concrete enforcement, can camera Real-time Collection original image be passed through, then by gray level image extraction algorithm, the R gray component image in original image, G gray component image and B gray component image can be extracted.Such as, R gray component image, G gray component image and the B gray component image in the extraction such as method of weighted mean, maximum value process original image can be adopted.
Step S22: the data type of the pixel of described gray component image is converted into double type from byte type.
In an embodiment of the present invention, the conveniently follow-up process for gray component image, can be converted into double type by the data type of pixel in R gray component image, G gray component image and B gray component image by byte type respectively.
Step S23: described gray component image is put into log-domain and processes, be enhanced gray component image.
In an embodiment of the present invention, described gray component image is put into log-domain and processes, can the product form of the complexity related in computation process be changed into simple plus-minus, be convenient to the analytical calculation of image.Meanwhile, the pixel of the gray component image represented with logarithmic form, is more suitable for simulation human eye to the perception of brightness.
Step S24: the gray-scale value of pixel in described enhancing gray component image is initialized as constant.
In concrete enforcement, the gray-scale value of pixel in described enhancing gray component image is initialized as constant, so that calculate the relative relationship between light and dark between the pixel of described gray component image and the pixel of the gray component image after described Gaussian smoothing.Such as, the gray-scale value of pixel in described enhancing gray component image can be initialized as and will state the average gray strengthening pixel in gray component image.
Step S25: with Gaussian template, convolution is done to described enhancing gray component image, obtain low-pass filtering gray component image.
In concrete enforcement, first can set the size of Gaussian template, re-use the Gaussian template set and convolution is done to described enhancing gray component image, that is to say that the Gaussian template set described in using scans each pixel in described enhancing gray component image, in the region determined with Gaussian template, the weighted mean value of pixel replaces the gray-scale value of pixel in Gaussian template.Said process is equivalent to do low-pass filtering treatment to described enhancing gray component image, thus obtains low-pass filtering gray component image.
In concrete enforcement, convolution can be done by following formula to described enhancing gray component image:
D(x,y)＝S(x,y)*F(x,y)；
Wherein, D (x, y) for described low-pass filtering gray component image, S (x, y) be described original image, F (x, y) is Gaussian filter function.
Step S26: described low-pass filtering gray component image is put into log-domain and processes, obtain the gray component image after Gaussian smoothing.
In an embodiment of the present invention, for the ease of the analytical calculation of successive image, described low-pass filtering gray component image can be put into log-domain and process.
Step S27: calculate the relative relationship between light and dark between the pixel of described gray component image and the pixel of the gray component image after described Gaussian smoothing.
In concrete enforcement, can by the relative relationship between light and dark between the pixel of gray component image described in following formulae discovery and the gray component image slices vegetarian refreshments after described Gaussian smoothing:
relation(x,y)＝log D(x,y)–logS(x,y)
Wherein, relation (x, y) is relation function, log D (x, y) for the logarithm of described low-pass filtering gray component image, log S (x, y) be the logarithm of described original image.
In an embodiment of the present invention, calculate the relative relationship between light and dark between the pixel of described gray component image and the gray component image slices vegetarian refreshments after described Gaussian smoothing, that is to say that the gray-scale value of the image slices vegetarian refreshments after by the pixel of described gray component image and the Gaussian smoothing centered by it contrasts, just can reflect reflection differences real between different pixels point more exactly.
Step S28: carry out gray level correction according to the pixel of described relative relationship between light and dark to described enhancing gray component image.
As previously mentioned, the irradiation component of overall situation Retinex method of video image processing supposition pixel is identical, but in fact the irradiation component of different pixels point has nuance, utilize overall Retinex method of video image processing really can not to calculate reflection differences between pixel.Thus, adopt overall Retinex method of video image processing can cause correcting rear pixel and occur lower, the unsharp problem of cross-color, contrast sometimes.
In an embodiment of the present invention, due to the gray-scale value of the image slices vegetarian refreshments after the pixel of described gray component image and the Gaussian smoothing centered by it is contrasted, but not the irradiation component of supposition image is identical, really can calculate the reflection differences between different pixels point, therefore, by the relative relationship between light and dark between pixel, the gray-scale value of the pixel in gray component image can be corrected.
Step S29: synthesized by the described gray component image through gray level correction, be enhanced image.
In an embodiment of the present invention, by through the R gray component image of gray level correction, G gray component image and B gray component Images uniting, be enhanced after coloured image.
Due to the image intensity value after preimage vegetarian refreshments gray-scale value and the Gaussian smoothing centered by it is contrasted, gray level correction is carried out to original image, and the impact of distant pixel on preimage vegetarian refreshments need not be considered, can the difference of reflected image vegetarian refreshments on reflecting component more exactly, make the video image color that obtains after strengthening process keep constant, and contrast and sharpness higher.
Fig. 3 shows the structural representation of a kind of video image enhancement device in the embodiment of the present invention.Video image enhancement device 3 as shown in Figure 3, can comprise the extraction unit 31, correcting unit 32 and the synthesis unit 33 that connect successively.Wherein,
Extraction unit 31, be suitable for extracting camera Real-time Collection to original image in gray component image.
Correcting unit 32, be suitable for the pixel of the described gray component image extracted according to extraction unit 31 and the relative relationship between light and dark between pixel in the gray component image after Gaussian smoothing, gray level correction is carried out to the pixel of described gray component image.
Synthesis unit 33, be suitable for the gray component image obtained after described correcting unit 32 carries out gray level correction to synthesize, be enhanced image.
In concrete enforcement, for the ease of the process of correcting unit 32 for image, described video image enhancement device 3 can also comprise converting unit 34, and described converting unit 34 is connected with correcting unit 32 with described extraction unit 31 respectively.Wherein, converting unit 34, the data type being suitable for the gray-scale value of pixel in the described gray component image extracted by described extraction unit 31 is converted into double type by byte type.
Fig. 4 shows the structural representation of the correcting unit in the embodiment of the present invention.Correcting unit as shown in Figure 4 can comprise:
Process subelement 321, be suitable for that described gray component image is put into log-domain and process, be enhanced gray component image.
Initialization subelement 322, the gray-scale value being suitable for described process subelement 321 to process pixel in the enhancing gray component image obtained is initialized as constant.In concrete enforcement, described initialization subelement 322 is suitable for 322 and the gray-scale value of pixel in described enhancing gray component image is initialized as the mean value of the pixel gray-scale value in described enhancing gray component image.
Low-pass filtering subelement 323, is suitable for processing to described process subelement 321 the described enhancing gray component image obtained with Gaussian template and does convolution, obtain low-pass filtering gray component image.
Gaussian smoothing subelement 324, is suitable for low-pass filtering subelement 323 to process the described low-pass filtering gray component image obtained and puts into log-domain and process, obtain the gray component image after Gaussian smoothing.
Computation subunit 325, is suitable for calculating pixel that described process subelement 321 processes the described gray component image obtained and described Gaussian smoothing subelement 324 and processes relative relationship between light and dark in the gray component image after the Gaussian smoothing obtained between pixel.
Syndrome unit 326, the pixel of relative relationship between light and dark to described enhancing gray component image being suitable for calculating according to described computation subunit 325 carries out gray level correction.
Fig. 5 shows the structural representation of a kind of parking assisting system in the embodiment of the present invention.Parking assisting system as shown in Figure 5, comprises rearview camera 51, above-mentioned video image enhancement device 3 and display device 53.Wherein, video image enhancement device 3 can be connected with rearview camera 51, display device 52 respectively.
Wherein, rearview camera 51, is suitable for the image of the rear view of vehicle in Real-time Collection vehicle parking process.
Video image enhancement device 3, the image being suitable for rear view of vehicle in the vehicle parking process collected by described rearview camera 51 processes, and be enhanced image;
Display device 52, for showing the enhancing image that described video image enhancement device 3 exports.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is that the hardware that can carry out instruction relevant by program has come, this program can be stored in computer-readable recording medium, and storage medium can comprise: ROM, RAM, disk or CD etc.
Done detailed introduction to the method and system of the embodiment of the present invention above, the present invention is not limited to this.Any those skilled in the art, without departing from the spirit and scope of the present invention, all can make various changes or modifications, and therefore protection scope of the present invention should be as the criterion with claim limited range.
Claims (13)
1. a video image enhancing method, is characterized in that, comprising:
Extract camera Real-time Collection to original image in gray component image;
According to pixel and the relative relationship between light and dark between pixel in the gray component image after Gaussian smoothing of described gray component image, gray level correction is carried out to the pixel of described gray component image;
Synthesized by the described gray component image through gray level correction, be enhanced image.
2. video image enhancing method according to claim 1, it is characterized in that, at the described pixel according to described gray component image and the relative relationship between light and dark between pixel in the gray component image after Gaussian smoothing, before gray level correction is carried out to the pixel of described gray component image, also comprise: the data type of the pixel of described gray component image is converted into double type from byte type.
3. video image enhancing method according to claim 2, it is characterized in that, the described pixel according to described gray component image and the relative relationship between light and dark between pixel in the gray component image after Gaussian smoothing, gray level correction is carried out to the pixel of described gray component image, comprising:
Described gray component image is put into log-domain process, be enhanced gray component image;
The gray-scale value of pixel in described enhancing gray component image is initialized as constant;
With Gaussian template, convolution is done to described enhancing gray component image, obtain low-pass filtering gray component image;
Described low-pass filtering gray component image is put into log-domain process, obtain the gray component image after Gaussian smoothing;
Calculate the relative relationship between light and dark between the pixel of described gray component image and the pixel of the gray component image after described Gaussian smoothing;
Gray level correction is carried out according to the pixel of described relative relationship between light and dark to described enhancing gray component image.
4. video image enhancing method according to claim 3, it is characterized in that, the described gray-scale value by the pixel in described enhancing gray component image is initialized as constant and comprises: the mean value gray-scale value of the pixel in described enhancing gray component image being initialized as pixel gray-scale value in described enhancing gray component image.
5. video image enhancing method according to claim 4, is characterized in that, adopts following formula to do convolution to described enhancing gray component image:
D(x,y)＝S(x,y)*F(x,y)
Wherein, D (x, y) for described low-pass filtering gray component image, S (x, y) be described original image, F (x, y) is Gaussian filter function.
6. video image enhancing method according to claim 5, is characterized in that, adopts the relative relationship between light and dark between the pixel of gray component image described in following formulae discovery and the pixel of the gray component image after described Gaussian smoothing:
relation(x,y)＝log D(x,y)–logS(x,y)
Wherein, relation (x, y) is relation function, log D (x, y) for the logarithm of described low-pass filtering gray component image, log S (x, y) be the logarithm of described original image.
7. video image enhancing method according to claim 1, is characterized in that, described gray component image comprises R gray component image, G gray component image and B gray component image.
8. a video image enhancement device, is characterized in that, comprising:
Extraction unit, is suitable for the gray component image extracting the original image that camera Real-time Collection arrives;
Correcting unit, is suitable for the pixel according to described gray component image and the relative relationship between light and dark between pixel in the gray component image after Gaussian smoothing, carries out gray level correction to the pixel of described gray component image;
Synthesis unit, be suitable for the gray component image through described correcting unit gray level correction to synthesize, be enhanced image.
9. video image enhancement device according to claim 8, is characterized in that, also comprise:
Converting unit, the data type being suitable for the gray-scale value of pixel in the described gray component image extracted by described extraction unit is converted into double type by byte type.
10. video image enhancement device according to claim 9, is characterized in that, described correcting unit comprises:
Process subelement, be suitable for that described gray component image is put into log-domain and process, be enhanced gray component image;
Initialization subelement, the gray-scale value being suitable for pixel in the enhancing gray component image process of described process subelement obtained is initialized as constant;
Low-pass filtering subelement, is suitable for doing convolution with Gaussian template to the described enhancing gray component image that the process of described process subelement obtains, obtains low-pass filtering gray component image;
Gaussian smoothing subelement, the described low-pass filtering gray component image being suitable for the process of low-pass filtering subelement being obtained is put into log-domain and is processed, and obtains the gray component image after Gaussian smoothing;
Computation subunit, the relative relationship between light and dark between the pixel of the gray component image after the Gaussian smoothing that the pixel being suitable for calculating the described gray component image that the process of described process subelement obtains and the process of described Gaussian smoothing subelement obtain;
Syndrome unit, the pixel of relative relationship between light and dark to described enhancing gray component image being suitable for calculating according to described computation subunit carries out gray level correction.
11. video image enhancement devices according to claim 10, it is characterized in that, described initialization subelement is suitable for the gray-scale value of pixel in described enhancing gray component image to be initialized as the mean value of the pixel gray-scale value in described enhancing gray component image.
12. video image enhancement devices according to claim 8, is characterized in that, described gray component image comprises R gray component image, G gray component image and B gray component image.
13. 1 kinds of parking assisting systems, is characterized in that, comprising:
Rearview camera, is suitable for Real-time Collection and parks the image of rear view of vehicle in process;
Video image enhancement device according to Claim 8 described in-12 any one;
Display device, for showing the enhancing image that described video image enhancement device exports.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410174747.9A CN105023243A (en) | 2014-04-28 | 2014-04-28 | Video image enhancement method and device, and parking assisting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410174747.9A CN105023243A (en) | 2014-04-28 | 2014-04-28 | Video image enhancement method and device, and parking assisting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105023243A true CN105023243A (en) | 2015-11-04 |
Family
ID=54413188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410174747.9A CN105023243A (en) | 2014-04-28 | 2014-04-28 | Video image enhancement method and device, and parking assisting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105023243A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107547886A (en) * | 2016-09-12 | 2018-01-05 | 郑州蓝视科技有限公司 | Video image enhancement system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080107333A1 (en) * | 2006-11-08 | 2008-05-08 | Amir Mazinani | Method and apparatus for color image correction |
| CN101303766A (en) * | 2008-07-09 | 2008-11-12 | 北京航空航天大学 | Method for rapidly reinforcing color image based on Retinex theory |
| CN102231206A (en) * | 2011-07-14 | 2011-11-02 | 浙江理工大学 | Colorized night vision image brightness enhancement method applicable to automotive assisted driving system |
| CN103295205A (en) * | 2013-06-25 | 2013-09-11 | 安科智慧城市技术（中国）有限公司 | Low-light-level image quick enhancement method and device based on Retinex |
| CN103745431A (en) * | 2013-11-16 | 2014-04-23 | 中航华东光电有限公司 | Parallel image processing method |
-
2014
- 2014-04-28 CN CN201410174747.9A patent/CN105023243A/en not_active Application Discontinuation
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080107333A1 (en) * | 2006-11-08 | 2008-05-08 | Amir Mazinani | Method and apparatus for color image correction |
| CN101303766A (en) * | 2008-07-09 | 2008-11-12 | 北京航空航天大学 | Method for rapidly reinforcing color image based on Retinex theory |
| CN102231206A (en) * | 2011-07-14 | 2011-11-02 | 浙江理工大学 | Colorized night vision image brightness enhancement method applicable to automotive assisted driving system |
| CN103295205A (en) * | 2013-06-25 | 2013-09-11 | 安科智慧城市技术（中国）有限公司 | Low-light-level image quick enhancement method and device based on Retinex |
| CN103745431A (en) * | 2013-11-16 | 2014-04-23 | 中航华东光电有限公司 | Parallel image processing method |
Non-Patent Citations (1)
| Title |
|---|
| 乔小燕等: ""一种改进的全局 Retinex 图像增强算法及其仿真研究"", 《系统仿真学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107547886A (en) * | 2016-09-12 | 2018-01-05 | 郑州蓝视科技有限公司 | Video image enhancement system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| ES2743759T3 (en) | Fusion processing system for visible light and infrared images and fusion method | |
| Guorong et al. | Multi-focus image fusion based on non-subsampled shearlet transform | |
| Huang et al. | Visibility restoration of single hazy images captured in real-world weather conditions | |
| Gibson et al. | Fast single image fog removal using the adaptive Wiener filter | |
| CN103770708B (en) | The dynamic reversing mirror self adaptation dimming estimated by scene brightness is covered | |
| US7474798B2 (en) | Method and device for image processing, in addition to a night viewing system for motor vehicles | |
| JP5362878B2 (en) | Image processing apparatus and image processing method | |
| CN104683767B (en) | Penetrating Fog image generating method and device | |
| Wang et al. | Biologically inspired image enhancement based on Retinex | |
| CN103413276B (en) | A kind of degree of depth Enhancement Method based on grain distribution feature | |
| DE102013206153A1 (en) | Method and system for robust tilt adjustment and cutting number plate images | |
| CN103996170B (en) | Image edge saw-tooth eliminating method with super resolution | |
| Li et al. | Single image dehazing using the change of detail prior | |
| CN105654437A (en) | Enhancement method for low-illumination image | |
| CN102750674B (en) | Video image defogging method based on self-adapting allowance | |
| Yao et al. | Improving long range and high magnification face recognition: Database acquisition, evaluation, and enhancement | |
| CN103218778B (en) | The disposal route of a kind of image and video and device | |
| EP3026885A1 (en) | Dirty lens detection device and dirty lens detection method | |
| Shiau et al. | Weighted haze removal method with halo prevention | |
| CN106296612B (en) | A kind of stagewise monitor video sharpening system and method for image quality evaluation and weather conditions guidance | |
| TWI509567B (en) | Method and image processing apparatus for image visibility restoration | |
| US20030068095A1 (en) | System for recovery of degraded images | |
| CN104077773A (en) | Image edge detection method, and image target identification method and device | |
| EP3087730A1 (en) | Method for inverse tone mapping of an image | |
| US7970178B2 (en) | Visibility range estimation method and system |
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: 20151104 |