CN103714520B - Digital video image strengthening system and its method are realized based on FPGA - Google Patents
Digital video image strengthening system and its method are realized based on FPGA Download PDFInfo
- Publication number
- CN103714520B CN103714520B CN201310732749.0A CN201310732749A CN103714520B CN 103714520 B CN103714520 B CN 103714520B CN 201310732749 A CN201310732749 A CN 201310732749A CN 103714520 B CN103714520 B CN 103714520B
- Authority
- CN
- China
- Prior art keywords
- image
- frame image
- mist elimination
- previous frame
- dark primary
- 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.)
- Active
Links
Abstract
The invention discloses one kind realizes digital video image strengthening system and method based on FPGA, wherein, it is described that the enhanced method of digital video image is realized based on FPGA, mainly include to current frame image mist elimination process step and the anti-reflection process step to current frame image, the above-mentioned mist elimination process step to video image is realized by dark primary priori mist elimination algorithm, can realize preferably removing fog effect, and the above-mentioned anti-reflection process step to current frame image is then realized by image histogram equalization algorithm, can realize that the ash of low-light (level) covers image and changes into clearly image effect.The present invention makes that image is apparent, penetrating and color is full by using above-mentioned image mist elimination step and the anti-reflection step of image, being capable of brightness, contrast and the color saturation of image.
Description
Technical field
The present invention relates to Digital Video Processing technical field, more particularly to based on FPGA, one kind realizes that digital video image increases
Strong system and its method.
Background technology
Image enhancement technique is widely used already in other field:As the later stage that photography is used for photo is processed,
The specialty later stage such as Photoshop, lightroom processes software the function of powerful image enhaucament;Many videos in recent years
Player is also integrated with image enhancement functions, such as the sharpening of KMplayer, YUV diffusions, Auto Laves control etc., MPC
Left eye strengthens.Which realizes that effect can be used for reference by field of video monitoring.Field of video monitoring also begins to notice figure in recent years
The value of image intensifying technology application, the image being directly obtained from imageing sensor are not often met because of of low quality subsequently
The requirement for processing and applying, needs through the process step such as various processing and conversion to improve quality, beneficial to the place of subsequent step
Reason and application, and meet the vision or application demand of the mankind.
Also there are some image enchancing methods in prior art, the such as applying date is:Application No. disclosed in April 15 in 2010:
201010153257.2 Chinese patent disclose a kind of image enchancing method and system, methods described includes:By previous frame figure
As gray space being transformed to by rgb space, obtain the corresponding gray level image of previous frame image, calculate the gray scale of the gray level image
Meansigma methodss, and the average gray is compared with default threshold value, obtain gray scale comparative result;To the previous frame figure
As carrying out contrast stretching, contrast stretching parameter is determined according to the gray scale comparative result;By the image after contrast stretching
Image co-registration is carried out with the previous frame image, enhanced image is obtained.Contrast is processed using above-mentioned image enchancing method
The poor image of degree, can provide the user contrast it is apparent, comprising the more images of detailed information.Above-mentioned figure strengthens
Image of the method after by contrast stretching carries out image co-registration with the previous frame image, to reach the mesh for strengthening image
's.However, when affected by environment larger of above-mentioned image enchancing method, such as greasy weather cause image ash to cover, using said method figure
Image intensifying method can not make image return to the presentation of preferable brightness, contrast and color, be allowed to be more suitable for eye-observation.Again
When such as dusk ambient light illumination is relatively low, gray-level is reduced, and the subjective feeling ash that image gives people is covered, and lifts image using said method
Contrast and color saturation it is limited, the effect of image is unsatisfactory.In view of this, it is necessary to above-mentioned image enhaucament side
Method is further improved.
The content of the invention
The present invention proposes one kind and realizes digital video image strengthening system and its method based on FPGA, and what is mainly solved is
In prior art, image enchancing method is protected from environmental big, and image ash illiteracy, stereovision and the color saturation for easily causing is not
The problem of foot.
To solve above-mentioned technical problem, one aspect of the present invention is:One kind is provided number is realized based on FPGA
The method of word video image enhancement, including to current frame image mist elimination process step and the anti-reflection process step to current frame image
Suddenly;
" the mist elimination process step to video image " is realized by dark primary priori mist elimination algorithm, is specifically included
Following steps:
S11. pretreatment is carried out to previous frame image, the corresponding gray level image of previous frame image is obtained, is alignd with original image
After export;
S12, grey image R GB passage minima is taken as respective pixel dark primary value, dark primary figure is asked for this, and it is right
Dark primary figure carries out intensity profile statistics, takes maximum gray scale of the pixel number more than 200 as air light value;
S13, transmitance figure is asked for according to dark primary figure and air light value, and rate figure is will transmit through as current frame image mist elimination
The reference value of process;
S14, the transmitance figure and air light value asked for according to previous frame image carry out mist elimination process to current frame image;
The current frame image that S15, output mist elimination are processed;
" the anti-reflection process step to video image " is realized by image histogram equalization algorithm, concrete to wrap
Include following steps:
The pixel number of S21, the statistically each gray level of a two field picture, obtains the rectangular histogram of previous frame image;
S22, setting pixel number threshold value, part of the pixel number in all gray levels more than the threshold value is added up,
Then accumulation result is divided equally into all gray levels;
S23, the pixel to each gray level in amended rectangular histogram add up;
Current frame image after S24, input mist elimination, and histogram-equalized image is drawn according to parabolic equation;
The current frame image of S25, output equalization processing.
In a specific scheme, the step S11 pretreatment previous frame image specifically includes step:
S111, the rgb video data for extracting previous frame image, and by rgb video data conversion into yuv space data;
S112, the gradation data Y extracted in yuv space data, and gradation data Y is converted into obtaining after rgb space data
To the gray level image of previous frame image.
Wherein, in step S13, the computing formula of the transmitance of previous frame image is as follows:
t=1-wdmax/A
Wherein, t is transmitance, and w is Dynamic gene, dmax be according to dark primary figure meansigma methodss carry out sky areas with it is normal
Dark primary value after region division optimization, A is the gray level of atmosphere light composition.
Wherein, in step S14, dark primary priori mist elimination formula is as follows:
J=(I-A)/t+A
Wherein, J is the image after mist elimination, and I is that input has mist image, and A is the gray level of atmosphere light composition, t is to pass through
Rate.
Wherein, the parabolic formula in step S23 is:
Wherein, y is the gray level after mapping, and a is maximum gray scale coefficient, and b is input picture gray level corresponding upper
The accumulation result of two field picture pixel, s are that total valid pixel of image is counted out, and n is parabolical coefficient.
Wherein, also include after the dark primary figure that previous frame image is drawn in step S12, ask for the gray scale of dark primary figure
The step of meansigma methodss of level.
To solve above-mentioned technical problem, another technical solution used in the present invention is:There is provided a kind of based on FPGA realizations
Digital video image strengthening system, including to current frame image mist elimination processing meanss and the anti-reflection process dress to current frame image
Put;
The mist elimination processing meanss include,
Pretreatment module, for carrying out pretreatment to previous frame image, obtains the gray-scale maps corresponding with previous frame image
Picture, is exported after being alignd with original image;
Dark primary figure asks for module, for taking grey image R GB passage minima as respective pixel dark primary value, with this
Dark primary figure is asked for, and intensity profile statistics is carried out to dark primary figure, taken maximum gray scale of the pixel number more than 200 and make
For air light value;
Transmitance computing module, for asking for transmitance figure according to dark primary figure and air light value, and will transmit through rate figure work
For the reference value of current frame image mist elimination process;
Mist elimination processing module, the transmitance figure and air light value for being asked for according to previous frame image are entered to current frame image
The process of row mist elimination;
First output module, for exporting the current frame image of mist elimination process;
The histogram equalization module includes,
Statistics with histogram module, for the pixel number of the statistically each gray level of a two field picture, obtains previous frame image
Rectangular histogram;
Histogram modification module, for according to setting pixel number threshold value, will be pixel number in all gray levels big
Add up in the part of the threshold value, then divide equally accumulation result into all gray levels;
Rectangular histogram accumulator module, for adding up to the pixel of each gray level in amended rectangular histogram;
Parabola conversion module, for the current frame image being input into after mist elimination, and draws rectangular histogram according to parabolic equation
Equalization image;
Second output module, for exporting the current frame image of equalization processing.
In a specific scheme, the pretreatment module also includes,
RGB-YUV units, for extracting the rgb video data of previous frame image, and by rgb video data conversion into YUV
Spatial data;
YUV-RGB units, for extracting the gradation data Y in yuv space data, and it is empty that gradation data Y is converted into RGB
Between the gray level image of previous frame image is obtained after data.
In a specific scheme, the dark primary figure is asked for module and is also asked for including the gray level meansigma methodss of dark primary figure
Unit, for calculating the meansigma methodss of dark primary figure gray level.
The method have the benefit that:It is different from image enchancing method of the prior art protected from environmental big,
The image ash for easily causing is covered, the problem that stereovision and color saturation are not enough, the invention provides a kind of realized based on FPGA
The enhanced method of digital video image, which mainly includes two parts, and one is that, to current frame image mist elimination process step, this pair regards
The mist elimination process step of frequency image is realized by dark primary priori mist elimination algorithm, can realize preferably removing fog effect;Two be and
Anti-reflection process step to current frame image, the anti-reflection process step of this pair of current frame image are then equalized by image histogram
Algorithm realization, can realize that the ash of low-light (level) covers image and changes into clearly image effect.The present invention is by using above-mentioned figure
As mist elimination step and the anti-reflection step of image, it is possible to increase the brightness of image, contrast and color saturation, make image more clear
Clear, penetrating and color is full.
Present invention also offers one kind realizes digital video image strengthening system based on FPGA, the above-mentioned side of the system application
Method, it is possible to increase the brightness of image, contrast and color saturation, makes that image is apparent, penetrating and color is full.
Description of the drawings
Fig. 1 is the flow chart that the present invention realizes the enhanced method of digital video image based on FPGA;
Fig. 2 is the block diagram of image mist elimination processing meanss in the present invention;
Fig. 3 is the block diagram of the anti-reflection processing meanss of image in the present invention.
Specific embodiment
By describing technology contents of the invention, structural features in detail, realizing purpose and effect, below in conjunction with embodiment
And coordinate accompanying drawing to be explained in detail.
RGB is a kind of color standard of industrial quarters, be by red (R), green (G), blue (B) three Color Channels change
And their superpositions each other, obtaining color miscellaneous, RGB is the face for representing three passages of red, green, blue
Color;
YUV is a kind of colour coding method adopted by eurovision system(Belong to PAL), it is PAL and SECAM simulations
The color space that colour television standard is adopted.In modern color television system, three pipe colour cameras or colour are generally adopted
CCD camera carries out capture, the colour picture signal for obtaining is obtained RGB after amplification correction Jing color separation, respectively then, then is passed through
Matrixer obtains grey scale signal Y and two colour difference signal R-Y(That is U), B-Y(That is V),
Fig. 1 is referred to, the present embodiment one kind realizes the enhanced method of digital video image based on FPGA, including to present frame
Image mist elimination process step and the anti-reflection process step to current frame image;
" the mist elimination process step to video image " is realized by dark primary priori mist elimination algorithm, can be very big
Impact of the fog to image is eliminated in degree, the color of image is maintained, is specifically included following steps:
S11. pretreatment is carried out to previous frame image, the corresponding gray level image of previous frame image is obtained, is alignd with original image
After export;
S12, grey image R GB passage minima is taken as respective pixel dark primary value, dark primary figure is asked for this, and it is right
Dark primary figure carries out intensity profile statistics, takes maximum gray scale of the pixel number more than 200 as air light value;
S13, transmitance figure is asked for according to dark primary figure and air light value, and rate figure is will transmit through as current frame image mist elimination
The reference value of process;
S14, the transmitance figure and air light value asked for by previous frame image carry out mist elimination process to current frame image;
The current frame image that S15, output mist elimination are processed;
" the anti-reflection process step to video image " is realized by image histogram equalization algorithm, concrete to wrap
Include step:
The pixel number of S21, the statistically each gray level of a two field picture, obtains the rectangular histogram of previous frame image;
S22, setting pixel number threshold value, part of the pixel number in all gray levels more than the threshold value is added up,
Then accumulation result is divided equally into all gray levels;
S23, the pixel to each gray level in amended rectangular histogram add up;
Current frame image after S24, input mist elimination, and histogram-equalized image is drawn according to parabolic equation;
The current frame image of S25, output equalization processing.
In a specific embodiment, the step S11 pretreatment previous frame image specifically includes step:
S111, the rgb video data for extracting previous frame image, and by rgb video data conversion into yuv space data;
S112, the gradation data Y extracted in yuv space data, and gradation data Y is converted into obtaining after rgb space data
To the gray level image of previous frame image.The gray level image of original image is obtained using the mutual conversion between RGB and YUV, then
Again asking for dark primary figure, impact of the colored noise to dark primary figure result so can be largely eliminated.
In a specific embodiment, in step S13, the computing formula of the transmitance of previous frame image is as follows:
t=1-wdmax/A
Wherein, t is transmitance, and w is Dynamic gene, dmax be according to dark primary figure meansigma methodss carry out sky areas with it is normal
Dark primary value after region division optimization, A is the gray level of atmosphere light composition.It is the average ash using dark primary figure in the present invention
The intensity arranges value of angle value and dark primary priori mist elimination automatically adjusting the value, to realize the self adaptation of effect.
In a specific embodiment, in step S14, dark primary priori mist elimination formula is as follows:
J=(I-A)/t+A
Wherein, J is the image after mist elimination, and I is that input has mist image, and A is the gray level of atmosphere light composition, t is to pass through
Rate.
In a specific embodiment, the parabolic formula in step S23 is:
Wherein, y is the gray level after mapping, and a is maximum gray scale coefficient, and b is input picture gray level corresponding upper
The accumulation result of two field picture pixel, s are that total valid pixel of image is counted out, and n is parabolical coefficient.Using above-mentioned
Parabolic type transforming function transformation function, can targetedly project dark space or clear zone details by regulation coefficient.
In addition, in such scheme by by the result of calculation of previous frame image applying on present frame, reduce
The needs of a two field picture are cached using DDR, system complexity is reduced.
The present invention is different from the image ash that image enchancing method of the prior art is protected from environmental big, easily causes
The not enough problem of illiteracy, stereovision and color saturation, the invention provides based on FPGA, one kind realizes that digital video image strengthens
Method, which mainly includes two parts, and one is that to current frame image mist elimination process step, the mist elimination of this pair of video image is processed
Step is realized by dark primary priori mist elimination algorithm, can realize preferably removing fog effect;Two are and the increasing to current frame image
Saturating process step, the anti-reflection process step of this pair of current frame image then realized by image histogram equalization algorithm, Neng Goushi
The ash of existing low-light (level) covers image and changes into clearly image effect.The present invention is by using above-mentioned image mist elimination step and figure
As anti-reflection step, it is possible to increase the brightness of image, contrast and color saturation, make that image is apparent, penetrating and color is full.
Refering to Fig. 2 and Fig. 3, the present invention also provides one kind and realizes digital video image strengthening system based on FPGA, including right
Current frame image mist elimination processing meanss and the anti-reflection processing meanss to current frame image;
The mist elimination processing meanss include,
Pretreatment module, for carrying out pretreatment to previous frame image, obtains the corresponding gray level image of previous frame image, with
Export after original image alignment;
Dark primary figure asks for module, for taking grey image R GB passage minima as respective pixel dark primary value, with this
Dark primary figure is asked for, and intensity profile statistics is carried out to dark primary figure, taken maximum gray scale of the pixel number more than 200 and make
For air light value.
Transmitance computing module, for asking for transmitance figure according to dark primary figure and air light value, and will transmit through rate figure work
For the reference value of current frame image mist elimination process;
Mist elimination processing module, the transmitance figure and air light value for being asked for according to previous frame image are entered to current frame image
The process of row mist elimination;
First output module, for exporting the current frame image of mist elimination process;
The histogram equalization module includes,
Statistics with histogram module, for the pixel number of the statistically each gray level of a two field picture, obtains previous frame image
Rectangular histogram;
Histogram modification module, for according to setting pixel number threshold value, will be pixel number in all gray levels big
Add up in the part of the threshold value, then divide equally accumulation result into all gray levels;
Rectangular histogram accumulator module, for adding up to the pixel of each gray level in amended rectangular histogram;
Parabola conversion module, for the current frame image being input into after mist elimination, and draws rectangular histogram according to parabolic equation
Equalization image;
Second output module, for exporting the current frame image of equalization processing.
In a specific scheme, the pretreatment module also includes,
RGB-YUV units, for extracting the rgb video data of previous frame image, and by rgb video data conversion into YUV
Spatial data;
YUV-RGB units, for extracting the gradation data Y in yuv space data, and it is empty that gradation data Y is converted into RGB
Between the gray level image of previous frame image is obtained after data.
Present invention also offers one kind realizes digital video image strengthening system based on FPGA, the above-mentioned side of the system application
Method, it is possible to increase the brightness of image, contrast and color saturation, makes that image is apparent, penetrating and color is full.
The invention has the beneficial effects as follows, reasonable combination dark primary priori mist elimination and histogram equalization two kinds of algorithms, and
And every kind of algorithm has carried out effective improvement all on the basis of canonical algorithm, realize that excellent image is anti-reflection and mist elimination function, and
The real-time processing to video is realized on FPGA.
Dark primary priori mist elimination improvement part:
1st, when dark primary figure is asked for, the gray scale of previous frame image is obtained first with the mutual conversion between RGB and YUV
Image, then again asking for dark primary figure, so can largely eliminate impact of the colored noise to dark primary figure result;
2nd, when atmosphere light composition is asked for, it is more than the maximum gray scale conduct of the dark primary figure of 200 with pixel number
Atmosphere light composition, and the value is just updated when upper atmosphere light composition result of calculation once differs certain numerical value with currency, this
Sample can avoid result that saltus step occurs, and increase stability;
3rd, in canonical algorithm, a Dynamic gene when calculating transmitance figure, needs to be manually set, and in the present invention
In be the intensity arranges value of average gray value and dark primary priori mist elimination using dark primary figure automatically adjusting the value, to realize
The self adaptation of effect;
4th, using the result of calculation of previous frame image applying on present frame, reduce using DDR to cache a frame figure
The needs of picture, reduce system complexity.
In place of the improvement of histogram equalization:
1st, histogram modification module is increased, the side effect of canonical algorithm is reduced, enhancing, dark space details is crossed in such as clear zone
Loss, realizes the controllable of effect;
2nd, the transforming function transformation function of canonical algorithm is changed to into parabolic type transforming function transformation function, can be targeted by regulation coefficient
The prominent dark space in ground or clear zone details;
3rd, using the result of calculation of previous frame image applying on present frame, reduce using DDR to cache a frame figure
The needs of picture, reduce system complexity.
Embodiments of the invention are the foregoing is only, the scope of the claims of the present invention is not thereby limited, it is every using this
Equivalent structure or equivalent flow conversion that bright description and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (7)
1. one kind realizes the enhanced method of digital video image based on FPGA, it is characterised in that include to current frame image mist elimination
Process step and the anti-reflection process step to current frame image;
The mist elimination process step is realized by dark primary priori mist elimination algorithm, specifically includes following steps:
S11, pretreatment is carried out to previous frame image, obtain the corresponding gray level image of previous frame image, the original with previous frame image
Export after image alignment;
S12, grey image R GB passage minima is taken as respective pixel dark primary value, dark primary figure is asked for this, and to dark former
Chromatic graph carries out intensity profile statistics, takes maximum gray scale of the pixel number more than 200 as air light value;
S13, transmitance figure is asked for according to dark primary figure and air light value, and rate figure is will transmit through as the process of current frame image mist elimination
Reference value;
S14, the transmitance figure and air light value asked for by previous frame image carry out mist elimination process to current frame image;
The current frame image that S15, output mist elimination are processed;
What the anti-reflection process step was realized by image histogram equalization algorithm, specifically include step:
The pixel number of S21, the statistically each gray level of a two field picture, obtains the rectangular histogram of previous frame image;
S22, setting pixel number threshold value, part of the pixel number in all gray levels more than the threshold value are added up, then
Accumulation result is divided equally into all gray levels;
S23, the pixel to each gray level in amended rectangular histogram add up;
Current frame image after S24, input mist elimination, and histogram-equalized image is drawn according to parabolic equation;
The current frame image of S25, output equalization processing;
The step S11 pretreatment previous frame image specifically includes step:
S111, the rgb video data for extracting previous frame image, and by rgb video data conversion into yuv space data;
S112, the gradation data Y extracted in yuv space data, and obtain after gradation data Y is converted into rgb space data
The gray level image of one two field picture.
2. it is according to claim 1 that the enhanced method of digital video image is realized based on FPGA, it is characterised in that the step
In rapid S13, the computing formula of the transmitance of previous frame image is as follows:
T=1-wdmax/ A,
Wherein, t is transmitance, and w is Dynamic gene, dmaxIt is to carry out sky areas and normal region according to dark primary figure meansigma methodss
Dark primary value after Partitioning optimization, A are the gray levels of atmosphere light composition.
3. it is according to claim 1 that the enhanced method of digital video image is realized based on FPGA, it is characterised in that the step
In rapid S14, dark primary priori mist elimination formula is as follows:
J=(I-A)/t+A
Wherein, J is the image after mist elimination, and I is that input has mist image, and A is the gray level of atmosphere light composition, and t is transmitance.
4. it is according to claim 1 that the enhanced method of digital video image is realized based on FPGA, it is characterised in that the step
Suddenly the parabolic formula in S23 is:
Wherein, y is the gray level after mapping, and a is maximum gray scale coefficient, and b is the corresponding previous frame figure of input picture gray level
As the accumulation result of pixel, s is that total valid pixel of image is counted out, and n is parabolical coefficient.
5. it is according to claim 1 that the enhanced method of digital video image is realized based on FPGA, it is characterised in that the step
Also include after the dark primary figure that previous frame image is drawn in rapid S12, the step of the meansigma methodss of the gray level for asking for dark primary figure.
6. one kind realizes digital video image strengthening system based on FPGA, it is characterised in that include at current frame image mist elimination
Reason device and the anti-reflection processing meanss to current frame image;
The mist elimination processing meanss include:
Pretreatment module, for carrying out pretreatment to previous frame image, obtains the gray level image corresponding with previous frame image, with
Export after the alignment of previous frame image original image;
Dark primary figure asks for module, for taking grey image R GB passage minima as respective pixel dark primary value, is asked for this
Dark primary figure, and intensity profile statistics is carried out to dark primary figure, maximum gray scale of the pixel number more than 200 is taken as big
Gas light value;
Transmitance computing module, for asking for transmitance figure according to dark primary figure and air light value, and will transmit through rate figure as working as
The reference value of prior image frame mist elimination process;
Mist elimination processing module, the transmitance figure and air light value for being asked for according to previous frame image are gone to current frame image
Mist process;
First output module, for exporting the current frame image of mist elimination process;
The anti-reflection processing meanss include:
Statistics with histogram module, for the pixel number of the statistically each gray level of a two field picture, obtains the straight of previous frame image
Fang Tu;
Histogram modification module, for according to setting pixel number threshold value, pixel number in all gray levels is more than should
The part of threshold value is added up, and then divides equally accumulation result into all gray levels;
Rectangular histogram accumulator module, for adding up to the pixel of each gray level in amended rectangular histogram;
Parabola conversion module, for the current frame image being input into after mist elimination, and draws histogram equalization according to parabolic equation
Change image;
Second output module, for exporting the current frame image of equalization processing;
The pretreatment module also includes:
RGB-YUV units, for extracting the rgb video data of previous frame image, and by rgb video data conversion into yuv space
Data;
Gradation data Y for extracting the gradation data Y in yuv space data, and is converted into rgb space number by YUV-RGB units
The gray level image of previous frame image is obtained according to after.
7. one kind according to claim 6 realizes digital video image strengthening system based on FPGA, it is characterised in that described
Dark primary figure is asked for module and also asks for unit including the gray level meansigma methodss of dark primary figure, for calculating dark primary figure gray level
Meansigma methodss.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310732749.0A CN103714520B (en) | 2013-12-26 | 2013-12-26 | Digital video image strengthening system and its method are realized based on FPGA |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310732749.0A CN103714520B (en) | 2013-12-26 | 2013-12-26 | Digital video image strengthening system and its method are realized based on FPGA |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103714520A CN103714520A (en) | 2014-04-09 |
CN103714520B true CN103714520B (en) | 2017-03-29 |
Family
ID=50407464
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310732749.0A Active CN103714520B (en) | 2013-12-26 | 2013-12-26 | Digital video image strengthening system and its method are realized based on FPGA |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103714520B (en) |
Families Citing this family (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104394302A (en) * | 2014-11-28 | 2015-03-04 | 深圳职业技术学院 | Real-time video defogging system based on FPGA |
CN104463816A (en) * | 2014-12-02 | 2015-03-25 | 苏州大学 | Image processing method and device |
CN104506755B (en) * | 2015-01-13 | 2017-06-30 | 武汉烽火众智数字技术有限责任公司 | HD video based on FPGA automates defogging method in real time |
CN104732496B (en) * | 2015-03-23 | 2018-11-30 | 青岛海信电器股份有限公司 | A kind of video streaming image defogging processing method and display device |
CN104732497A (en) * | 2015-03-31 | 2015-06-24 | 北京交通大学 | Image defogging method, FPGA and defogging system including FPGA |
CN104700107A (en) * | 2015-03-31 | 2015-06-10 | 徐晶 | Electric energy meter reading recognition apparatus based on image processing |
CN106355556B (en) * | 2015-07-21 | 2019-04-12 | 杭州海康威视数字技术股份有限公司 | The method and apparatus of image defogging |
CN105046666B (en) * | 2015-07-24 | 2018-05-29 | 中国科学技术大学 | A kind of method of the real-time defogging of traffic video based on dark primary priori |
CN106023118B (en) * | 2016-06-13 | 2018-12-04 | 凌云光技术集团有限责任公司 | A kind of image defogging method and its implementation method on FPGA |
CN106846234B (en) * | 2016-12-22 | 2020-09-25 | Tcl移动通信科技(宁波)有限公司 | Image video enhancement method, system and equipment based on FPGA |
CN108498061A (en) * | 2018-01-30 | 2018-09-07 | 千奥星科南京生物科技有限公司 | Miniature cystoscope probe and cystoscope system for portable medical |
CN109493300B (en) * | 2018-11-15 | 2022-05-20 | 湖南鲲鹏智汇无人机技术有限公司 | Aerial image real-time defogging method based on FPGA (field programmable Gate array) convolutional neural network and unmanned aerial vehicle |
CN109753878B (en) * | 2018-12-06 | 2020-11-20 | 北京科技大学 | Imaging identification method and system under severe weather |
CN109961412A (en) * | 2019-03-18 | 2019-07-02 | 浙江大华技术股份有限公司 | A kind of video frame images defogging method and equipment |
CN111246010B (en) * | 2019-04-24 | 2020-11-10 | 吕衍荣 | Environment monitoring method based on signal analysis |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164845A (en) * | 2011-12-16 | 2013-06-19 | 中国科学院沈阳自动化研究所 | Real-time image mist elimination device and method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100756318B1 (en) * | 2006-01-16 | 2007-09-06 | 삼성전자주식회사 | Image Processing Method and System Using Gain-Controllable Clipped Histogram Equalization |
-
2013
- 2013-12-26 CN CN201310732749.0A patent/CN103714520B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164845A (en) * | 2011-12-16 | 2013-06-19 | 中国科学院沈阳自动化研究所 | Real-time image mist elimination device and method |
Non-Patent Citations (4)
Title |
---|
Real-time defogging processing of aerial images;Xiaoqiang Ji等;《Wireless Communications Networking and Mobile Computing (WiCOM), 2010 6th International Conference on》;20100925;第1-4页 * |
基于FPGA的视频图像去雾系统的设计与实现;龚亮 等;《电视技术》;20130402;第37卷(第7期);第6-8页 * |
基于FPGA的视频直方图均衡化的改进设计;元海文等;《传感器与微系统》;20131029;第32卷(第11期);第115-117页 * |
基于抛物线调整的直方图均衡化;高彦平等;《福建电脑》;20050425(第4期);第43-44页 * |
Also Published As
Publication number | Publication date |
---|---|
CN103714520A (en) | 2014-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103714520B (en) | Digital video image strengthening system and its method are realized based on FPGA | |
CN106897981A (en) | A kind of enhancement method of low-illumination image based on guiding filtering | |
US7869649B2 (en) | Image processing device, image processing method, program, storage medium and integrated circuit | |
CN103593830B (en) | A kind of low illumination level video image enhancement | |
US10565742B1 (en) | Image processing method and apparatus | |
CN101325035B (en) | Method for processing liquid crystal image | |
CN103093429B (en) | Image enchancing method | |
CN103455979B (en) | A kind of low illumination level video image enhancement | |
CN106504212A (en) | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement | |
CN110473152B (en) | Image enhancement method based on improved Retinex algorithm | |
CN102752604B (en) | Image display method and intelligent device | |
CN102750674A (en) | Video image defogging method based on self-adapting allowance | |
CN104867121B (en) | Image Quick demisting method based on dark primary priori and Retinex theories | |
CN102568386A (en) | Method and system for dynamic backlight local control liquid crystal display | |
CN109816608B (en) | Low-illumination image self-adaptive brightness enhancement method based on noise suppression | |
CN107909562A (en) | A kind of Fast Image Fusion based on Pixel-level | |
CN104809700B (en) | A kind of low-light (level) video real time enhancing method based on bright passage | |
CN102883168A (en) | White balance processing method directed towards atypical-feature image | |
CN109801233B (en) | Method for enhancing true color remote sensing image | |
CN107895357A (en) | A kind of real-time water surface thick fog scene image Enhancement Method based on FPGA | |
CN105354801A (en) | HSV color space based image enhancement method | |
CN105898252A (en) | Television color adjustment method and device | |
CN110223262A (en) | A kind of rapid image fusion method based on Pixel-level | |
CN114187222A (en) | Low-illumination image enhancement method and system and storage medium | |
CN107358592B (en) | Iterative global adaptive image enhancement method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |