CN103473748A - Method for enhancing underground coal mine image - Google Patents
Method for enhancing underground coal mine image Download PDFInfo
- Publication number
- CN103473748A CN103473748A CN2013104334045A CN201310433404A CN103473748A CN 103473748 A CN103473748 A CN 103473748A CN 2013104334045 A CN2013104334045 A CN 2013104334045A CN 201310433404 A CN201310433404 A CN 201310433404A CN 103473748 A CN103473748 A CN 103473748A
- Authority
- CN
- China
- Prior art keywords
- image
- enhancing
- details area
- denoising
- threshold
- 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
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 25
- 239000003245 coal Substances 0.000 title claims abstract description 17
- 230000009466 transformation Effects 0.000 claims description 14
- 230000000873 masking effect Effects 0.000 abstract description 20
- 238000003672 processing method Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000005286 illumination Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000005728 strengthening Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 239000000654 additive Substances 0.000 description 2
- 230000000996 additive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000003623 enhancer Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a method for enhancing an underground coal mine image. According to the method, a novel processing method which combines wavelet denoising with unsharp masking enhancing is adopted to divide the image into a low-detail area, a middle-detail area and a high-detail area according to the detail degree, denoising is only carried out on the low-detail area (namely the flat area) of the image, and then different degrees of enhancing is carried out on the areas with different detail degrees of the image according to human vision characteristics, namely, enhancing is not carried out or slight enhancing is carried out on the low-detail area, moderate enhancing is carried out on the high-detail area, and major enhancing is carried out on the middle-detail area. According to the method for enhancing the underground coal mine image, the enhancing effect is good, noise enhancement is restrained, and the problems that according to an existing underground coal mine image enhancing method, the unsharp masking technique is too sensitive to noise and the overshooting phenomenon exists are solved.
Description
Technical field
The present invention relates to figure image intensifying field, be specifically related to a kind of method that coal mine hypograph strengthens.
Background technology
Coal is the main energy sources of China, but, due to the coal field geology complicated condition of China, working condition is severe, the production technique level is relatively backward, producers' quality is lower, the Frequent Accidents that causes China's coal-mine to be produced, and the mine safety problem has seriously restricted the sound development of China coal industry.The China's coal-mine down-hole is a special constrained environment, it is comprised of various tunnels crisscross, that shape is different, different in size, once have an accident, the ground staff is difficult to dynamically grasp in time personnel in the pit's distribution and operation situation, the efficiency of rescue and relief work, safety first-aid is low, searches and rescues weak effect.Therefore be necessary the video monitoring under coal mine, this is important leverage and the emergency management and rescue necessary means of mine safety production, under special subsurface environment, the even even complete black environment of uneven illumination, cause picture contrast little, image blurring unclear, and sneak into a large amount of noises in the video image acquisition transmitting procedure, and cause video image picture coarse, quality is low, the video pictures quality directly affects obtaining in time of mine disaster information, so figure image intensifying change is particularly important.
The figure image intensifying be by certain means to the more additional information of original image or transform data, some unwanted feature in interested feature or inhibition (covering) image in outstanding image, be complementary image and eye response characteristic selectively.The figure image intensifying is significant to the safety in production under mine, and people adopt the whole bag of tricks to be strengthened image for many years.Image enchancing method in the even situation of uneven illumination commonly used has: greyscale transformation method, histogram equalization method, the Enhancement Method based on the Retinex theory, gradient field image enchancing method, the image enchancing method based on wavelet transformation, the image enchancing method based on Hi-pass filter, Image Enhancing Method Based on Unsharp Masking.The enhancing that adopts said method to carry out image is applied very extensive.Yet, for the needed photo of mine safety production, because the down-hole shooting environmental is severe, the image of shooting exists characteristics:
(1) large, the high humidity of dust concentration under mine, and camera is difficult to realize automatic focus.
(2) the lower illumination fluctuation of mine is frequent, and for example under coal mine, main equipment is a lot, and grid disturbance is large, causes the illumination fluctuation.
(3) because the image gathered is to be formed by reflection of light, if the uneven illumination shone on scenery is even, will obtain the stronger part of illumination brighter on image, the part a little less than illumination is darker.
Therefore, due to special image-context, the method that adopts common image processing method formula to carry out image is difficult to meet the authenticity of image, the requirement of reliability, and information recognition is encountered difficulties, and is unfavorable for safe, the stable production under mine.
In recent years, the method for figure image intensifying is being updated.For example, the histogram equalization method trends towards being combined with human visual, keeps the original looks of image when strengthening image.Frequency domain method, Retinex method are tended to the combination with additive method, and it falls the deficiency that low noise function can make up additive method.The gradient field method focuses on the improvement on counting yield.In addition, the unsharp masking method has proposed for the image that degrades or degenerate that has the weak points such as edge fog, part or overall contrast in various degree be poor, classical linear unsharp masking technology is to make original image after linear Hi-pass filter, be multiplied by after a scale factor and original image addition, the image be enhanced.Although this method is simple, strengthen effect also relatively better, he has 2 great shortcomings:
(1) system is very responsive to noise: owing to having adopted linear Hi-pass filter, details and the noise of image are enhanced simultaneously, and it is the flat site at image, make very little noise also very obvious.
(2) overshoot phenomenon: the high details area of image is larger with respect to other regional enhancings, and the image after processing can present obvious artificial treatment vestige.
In order to overcome the shortcoming of linear unsharp masking technology, especially, to the susceptibility of noise, people have proposed various methods.S.K.Mitra has proposed the nonlinear operator based on the Teager algorithm, and this nonlinear operator can be approximately local mean value weight Hi-pass filter.According to the Weber law, human eye is more responsive to the details in picture black zone, therefore this operator energy noise decrease.G.Ramponi has proposed a cube unsharp masking technology, and the essence of this technology is to be multiplied by Laplace operator with the square filtering device operator of an edge sensitivity, only strengthens the image detail in local brightness variation zone, the less noise.Y. H.Lee has proposed the operator based on sequence statistics Laplce algorithm, and the difference of the output of this operator and local mean value and local intermediate value is proportional, and he can remove white Gaussian noise effectively.Although method above-mentioned has reduced noise with respect to linear unsharp masking technology, at flat site, noise is still apparent in view, and, strengthen preferably effect for the middle details area that makes image reaches, the high details area of image often strengthens excessive, causes the appearance of overshoot phenomenon.
Summary of the invention
The object of the present invention is to provide a kind of method that strengthens image under coal mine, for solving existing coal mine hypograph Enhancement Method, the problem of and the overshoot phenomenon very responsive to noise that the unsharp masking technology exists.For achieving the above object, the solution of the present invention is: a kind of method that coal mine hypograph strengthens, and step is as follows:
(1) method of employing local variance is judged the level of detail of image, and image is divided into to high, medium and low three details area;
(2) Threshold Denoising Method of employing based on wavelet transformation carries out denoising to the image of described low details area;
(3) adopt, based on unsharp mask method, described high, medium and low three details area are carried out to figure image intensifying in various degree, that is: low details area is not done and strengthened or strengthen very little, high details area is done to moderate enhancing, and the centering details area is done largely and is strengthened.
Further, the method in step (1), the level of detail of image judged is: at first calculate the local variance of the given window of a pixel, the level of detail of establishing a certain pixel (m, n) in window is D (m, n), two threshold value T are set
1and T
2, and T
1<T
2if, D (m, n)<T
1it is low details area; If T
1<D (m, n)<T
2it is middle details area; If D (m, n)>T
2it is high details area.
Further, the Threshold Denoising Method based on wavelet transformation in step (2) is: set a threshold value by hard-threshold or soft-threshold disposal route, the wavelet coefficient that absolute value is less than this threshold value is the noise wavelet coefficient, removes; Absolute value is greater than the wavelet coefficient that the wavelet coefficient of this threshold value is useful signal, retains; Finally the wavelet coefficient after processing is carried out to the useful signal after wavelet inverse transformation obtains denoising.
The beneficial effect that the present invention reaches: because denoising generally can make image blur, the details of loss image, and make denoising and strengthen between the two to be difficult to reach the effect of optimizing, the present invention adopts a kind of new disposal route that Wavelet Denoising Method and unsharp masking enhancing method are combined, according to level of detail, be divided into image low, in, a Senior Three zone, only in the low details area (that is flat site) of image, carry out denoising, because according to human-eye visual characteristic, human eye is more responsive to the noise of the noise ratio detail section of image flat site, and the subregion of generalized case hypograph is smooth, the noise quilt relative " removal " of this sampled images, and details area is by intact reservation.The problem of image blurring that the method has avoided denoising to bring, and the enhancing of image is met to human-eye visual characteristic, both improved the sensitivity of noise, not there will be again overshoot phenomenon, not only avoid the loss of image detail, strengthened effect better, and suppressed the enhancing of noise.
The accompanying drawing explanation
Fig. 1 is that the present invention carries out the denoising method schematic diagram of wavelet transformation to image;
Fig. 2 is the process flow diagram that unsharp masking of the present invention strengthens image.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described in detail.
The very responsive and overshoot phenomenon to noise that unsharp masking technology in strengthening for conventional images exists, the present invention disclose and a kind ofly first carries out the part denoising, then strengthens the method for processing.
1. denoising
The Morlet wavelet transform Image denoising algorithm is divided into three major types: the Threshold Denoising Method that the noise remove method based on spatial correlation proposed based on based on wavelet modulus maxima method, Xu etc. that Mallat proposes, Donoho etc. propose.The stable denoising effect of modulus maximum denoising and correlativity denoising, but their reconstructed image calculated amount are large, and speed is slow, accurate not, so the Threshold Denoising Method that is based on wavelet transformation that the present invention adopts.
In Threshold Denoising Method based on wavelet transformation, there is principle of different nature according to the wavelet coefficient of signal and noise on different scale, utilize corresponding mathematical tool structure coefficient selection mode, signals with noise is carried out to multi-scale wavelet transformation, transform from the time domain to wavelet field, then a threshold limit value λ is set, if the absolute value of wavelet coefficient is less than λ, think that this coefficient is mainly caused by noise, removes this part coefficient; If the absolute value of wavelet coefficient is greater than λ, think that this coefficient is mainly to be caused by signal, retain this part coefficient, then the wavelet coefficient after processing is carried out to the signal after wavelet inverse transformation obtains denoising.
In thresholding denoising method based on wavelet transformation, continuity and the precision chosen reconstruction signal of threshold function table have a great impact, the effect that relation Wavelet Denoising Method how, the mode that at present threshold value is chosen mainly contains two kinds of hard-threshold and soft-thresholds: the hard-threshold method is that the absolute value of signal and threshold value are compared, the signal that will be less than or equal to threshold value is made as zero, the signal that is greater than threshold value remains unchanged, still have obvious noise with the signal after the denoising of hard-threshold method, but it can retain the local message of image border and details well; The soft-threshold method is that the absolute value of signal and threshold value are compared, the signal that absolute value is less than or equal to threshold value is made as zero, be greater than the signal of threshold value for absolute value, it is made as to the poor of self and threshold value, signal will shrink to zero like this, the character of soft-threshold has determined that it has than the better continuity of hard-threshold, and its result can be relatively level and smooth.Wavelet Denoising Method in the present invention, can highly effectively come noise and useful signal difference, made up with unsharp masking and carried out the shortcoming of figure image intensifying to noise-sensitive.
2. image enhancement processing:
What the present invention adopted is that the unsharp masking method is strengthened image, can strengthen details and the marginal portion of image for traditional unsharp masking, but do not wish the same problem strengthened clearly in the zone strengthened for noise and some, the present invention adopts the unsharp masking method based on Region Segmentation.
Carry out the figure image intensifying based on the unsharp masking method and can simply be summarised as the fuzzy form of an image is deducted from original image, obtain image more clearly, way strengthens the purpose of image detail.Traditional unsharp masking method is very responsive to noise, and the details of image and noise can be enhanced simultaneously, and can produce overshoot phenomenon, and the present invention adopts a kind of improved method, i.e. the unsharp masking method based on Region Segmentation.
At first the present invention separates image some zones, minute three zones in the present embodiment: low details area, middle details area, high details area, then different enhancing COEFFICIENT K (x is chosen in different zones, y), low details area to image is not strengthened, middle details area to image is carried out very large enhancing, and the high details area of image is carried out to larger enhancing.
The concrete steps of the present embodiment image enchancing method are as follows:
A. the level of detail of image judged
The present embodiment adopts the method for local variance, the variance of all pixels in given window of local variance definition, and for example the local variance at 3 * 3 windows of a pixel is:
In formula, i, j is the pixel in window,
be the average brightness of picture element (m, n) 3 * 3 neighborhoods, D (m, n) has just represented the level of detail of picture element (m, n).
Two threshold value T are set
1and T
2, and T
1<T
2, be divided into basic, normal, high three detail areas according to the large wisp image of D (m, n), if D (m, n)<T
1it is low details area; If T
1<D (m, n)<T
2it is middle details area; If D (m, n)>T
2it is high details area.
B. in low details area, signal is carried out to denoising
There is mechanism of different nature according to the wavelet coefficient of signal and noise on different scale, as Fig. 1, signals and associated noises is carried out on each yardstick to wavelet decomposition, retain the whole wavelet coefficients under the large scale low resolution.At first set a threshold value, the wavelet coefficient that absolute value is less than this threshold value is considered to the noise wavelet coefficient, and it is made as to zero, removes; The wavelet coefficient that absolute value is greater than this threshold value is considered to the wavelet coefficient of useful signal, remains.The threshold process method that the present embodiment adopts is hard-threshold or soft-threshold:
Hard-threshold
Soft-threshold
Wherein, ω
j, kfor the wavelet coefficient under each resolution,
for the coefficient after processing, λ is threshold value.
If input picture x (m, n) obtains image M (m, n) after above-mentioned Wavelet Denoising Method is processed,
Utilize wavelet inverse transformation to carry out signal reconstruction the wavelet coefficient obtained after processing, obtain the useful signal after denoising.
C. adopt based on the unsharp masking method and carry out image enhancement processing
As Fig. 2, the computing formula of figure image intensifying intensity is as follows:
y(m，n)＝x(m，n)+γz(m，n) (1)
In formula, x (m, n) is received image signal; Z (m, n) is the output (only to low details area carry out denoising) of signal after denoising, and γ is a direct proportion factor, intensity that can the control chart image intensifying, and y (m, n) is the image after strengthening.
In the low details area of image, obtained the enhancing image after Wavelet Denoising Method, and human eye is very responsive to noise, so only do very little enhancing or do not strengthened; In the high details area of image, in order to prevent the generation of overshoot phenomenon, can carry out moderate enhancing; And, in the middle details area of image, strengthen largely.So (1) the enhancer γ in formula may be defined as the nonlinear function γ (m, n) of image detail degree, that is:
In formula, γ
1, γ
2, γ
3respectively the enhancer of the basic, normal, high details area of image, and 0<γ
1γ
2γ
3<1.Finally, obtain the image after denoising strengthens, formula (1) can be rewritten as
y(m，n)＝M(m，n)+γ(m，n)z(m，n)。
Claims (3)
1. the method that the coal mine hypograph strengthens, is characterized in that, step is as follows:
(1) method of employing local variance is judged the level of detail of image, and image is divided into to high, medium and low three details area;
(2) Threshold Denoising Method of employing based on wavelet transformation carries out denoising to the image of described low details area;
(3) adopt, based on unsharp mask method, described high, medium and low three details area are carried out to figure image intensifying in various degree, that is: low details area is not done and strengthened or strengthen very little, high details area is done to moderate enhancing, and the centering details area is done largely and is strengthened.
2. the method that coal mine hypograph according to claim 1 strengthens, it is characterized in that, the method in step (1), the level of detail of image judged is: at first calculate the local variance of the given window of a pixel, obtain the level of detail of pixel, two threshold value T are set
1and T
2, and T
1<T
2if, D (m, n)<T
1it is low details area; If T
1<D (m, n)<T
2it is middle details area; If D (m, n)>T
2it is high details area.
3. the method that coal mine hypograph according to claim 1 strengthens, it is characterized in that, Threshold Denoising Method based on wavelet transformation in step (2) is: by hard-threshold or soft-threshold disposal route, set a threshold value, the wavelet coefficient that absolute value is less than this threshold value is the noise wavelet coefficient, removes; Absolute value is greater than the wavelet coefficient that the wavelet coefficient of this threshold value is useful signal, retains; Finally the wavelet coefficient after processing is carried out to the useful signal after wavelet inverse transformation obtains denoising.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013104334045A CN103473748A (en) | 2013-09-23 | 2013-09-23 | Method for enhancing underground coal mine image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013104334045A CN103473748A (en) | 2013-09-23 | 2013-09-23 | Method for enhancing underground coal mine image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103473748A true CN103473748A (en) | 2013-12-25 |
Family
ID=49798582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013104334045A Pending CN103473748A (en) | 2013-09-23 | 2013-09-23 | Method for enhancing underground coal mine image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473748A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809713A (en) * | 2015-04-24 | 2015-07-29 | 上海理工大学 | CBCT panorama nonlinear sharpening enhancing method based on neighborhood information and Gaussian filter |
| CN107274365A (en) * | 2017-06-15 | 2017-10-20 | 中国矿业大学(北京) | A kind of mine image intensification method based on unsharp masking and NSCT algorithms |
| CN107333027A (en) * | 2016-04-28 | 2017-11-07 | 深圳市中兴微电子技术有限公司 | A kind of method and apparatus of video image enhancement |
| CN107730473A (en) * | 2017-11-03 | 2018-02-23 | 中国矿业大学 | A kind of underground coal mine image processing method based on deep neural network |
| CN107895356A (en) * | 2017-12-04 | 2018-04-10 | 山东大学 | A kind of near-infrared image Enhancement Method based on steerable pyramid |
| CN108596163A (en) * | 2018-07-10 | 2018-09-28 | 中国矿业大学(北京) | A kind of Coal-rock identification method based on CNN and VLAD |
| CN109660821A (en) * | 2018-11-27 | 2019-04-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN109729405A (en) * | 2018-11-27 | 2019-05-07 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN110288536A (en) * | 2019-05-15 | 2019-09-27 | 辽宁工程技术大学 | A kind of borehole image processing method based on improvement bilateral filtering |
| CN115631116A (en) * | 2022-12-21 | 2023-01-20 | 南昌航空大学 | Aircraft power inspection system based on binocular vision |
| CN117541997A (en) * | 2024-01-10 | 2024-02-09 | 泰安万川电器设备有限公司 | Roadway safety early warning method and system based on image features |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359399A (en) * | 2008-09-19 | 2009-02-04 | 常州工学院 | Cloud-removing method for optical image |
| US20120294548A1 (en) * | 2011-05-19 | 2012-11-22 | Foveon, Inc. | Methods for digital image sharpening with noise amplification avoidance |
-
2013
- 2013-09-23 CN CN2013104334045A patent/CN103473748A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101359399A (en) * | 2008-09-19 | 2009-02-04 | 常州工学院 | Cloud-removing method for optical image |
| US20120294548A1 (en) * | 2011-05-19 | 2012-11-22 | Foveon, Inc. | Methods for digital image sharpening with noise amplification avoidance |
Non-Patent Citations (2)
| Title |
|---|
| 李均利等: "一种基于模糊规则和小波变换的医学图像锐化增强算法", 《中国生物医学工程学报》 * |
| 李新锋: "一种基于小波变换的煤矿监控图像增强方法", 《黑龙江科技信息》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809713B (en) * | 2015-04-24 | 2017-09-12 | 上海理工大学 | The non-linear sharpening enhancement method of CBCT panorama sketch based on neighborhood information and gaussian filtering |
| CN104809713A (en) * | 2015-04-24 | 2015-07-29 | 上海理工大学 | CBCT panorama nonlinear sharpening enhancing method based on neighborhood information and Gaussian filter |
| CN107333027B (en) * | 2016-04-28 | 2019-11-15 | 深圳市中兴微电子技术有限公司 | A kind of method and apparatus of video image enhancement |
| CN107333027A (en) * | 2016-04-28 | 2017-11-07 | 深圳市中兴微电子技术有限公司 | A kind of method and apparatus of video image enhancement |
| CN107274365A (en) * | 2017-06-15 | 2017-10-20 | 中国矿业大学(北京) | A kind of mine image intensification method based on unsharp masking and NSCT algorithms |
| CN107730473A (en) * | 2017-11-03 | 2018-02-23 | 中国矿业大学 | A kind of underground coal mine image processing method based on deep neural network |
| CN107895356A (en) * | 2017-12-04 | 2018-04-10 | 山东大学 | A kind of near-infrared image Enhancement Method based on steerable pyramid |
| CN108596163A (en) * | 2018-07-10 | 2018-09-28 | 中国矿业大学(北京) | A kind of Coal-rock identification method based on CNN and VLAD |
| CN109729405A (en) * | 2018-11-27 | 2019-05-07 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN109660821A (en) * | 2018-11-27 | 2019-04-19 | Oppo广东移动通信有限公司 | Method for processing video frequency, device, electronic equipment and storage medium |
| CN110288536A (en) * | 2019-05-15 | 2019-09-27 | 辽宁工程技术大学 | A kind of borehole image processing method based on improvement bilateral filtering |
| CN115631116A (en) * | 2022-12-21 | 2023-01-20 | 南昌航空大学 | Aircraft power inspection system based on binocular vision |
| CN115631116B (en) * | 2022-12-21 | 2023-03-10 | 南昌航空大学 | Aircraft power inspection system based on binocular vision |
| CN117541997A (en) * | 2024-01-10 | 2024-02-09 | 泰安万川电器设备有限公司 | Roadway safety early warning method and system based on image features |
| CN117541997B (en) * | 2024-01-10 | 2024-03-12 | 泰安万川电器设备有限公司 | Roadway safety early warning method and system based on image features |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103473748A (en) | Method for enhancing underground coal mine image | |
| Wang et al. | Dehazing for images with large sky region | |
| CN107274365A (en) | A kind of mine image intensification method based on unsharp masking and NSCT algorithms | |
| Serikawa et al. | Underwater image dehazing using joint trilateral filter | |
| Singh et al. | Shadow detection and removal from remote sensing images using NDI and morphological operators | |
| Lu et al. | Underwater image enhancement using guided trigonometric bilateral filter and fast automatic color correction | |
| Fu et al. | Improved single image dehazing using dark channel prior | |
| Lv et al. | Real-time dehazing for image and video | |
| CN104809734A (en) | Infrared image and visible image fusion method based on guide filtering | |
| CN105321172A (en) | SAR, infrared and visible light image fusion method | |
| Luan et al. | Fast single image dehazing based on a regression model | |
| Park et al. | Single image haze removal with WLS-based edge-preserving smoothing filter | |
| CN105825472A (en) | Rapid tone mapping system and method based on multi-scale Gauss filters | |
| CN104050637A (en) | Quick image defogging method based on two times of guide filtration | |
| CN106504244A (en) | A kind of mine Edge-Detection Algorithm that is accumulated with wavelet scale based on Retinex | |
| CN106570839A (en) | Red Channel prior based underwater image sharpening method | |
| Wang et al. | Multiscale single image dehazing based on adaptive wavelet fusion | |
| Wang et al. | Haze removal algorithm based on single-images with chromatic properties | |
| Das et al. | A review: shadow detection and shadow removal from images | |
| Chung et al. | A Study of Single Image Haze Removal Using a Novel White-Patch RetinexBased Improved Dark Channel Prior Algorithm. | |
| CN115578274A (en) | Double-branch image defogging method based on edge constraint | |
| Goswami et al. | A hybrid approach for visibility enhancement in foggy image | |
| Zahra et al. | Visibility enhancement of scene images degraded by foggy weather condition: An application to video surveillance | |
| Wenjuan et al. | Retracted article: underwater image segmentation based on computer vision and research on recognition algorithm | |
| Deluxni et al. | A Scrutiny on Image Enhancement and Restoration Techniques for Underwater Optical Imaging Applications |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131225 |