CN103729828B - video rain removing method - Google Patents
video rain removing method Download PDFInfo
- Publication number
- CN103729828B CN103729828B CN201310683538.2A CN201310683538A CN103729828B CN 103729828 B CN103729828 B CN 103729828B CN 201310683538 A CN201310683538 A CN 201310683538A CN 103729828 B CN103729828 B CN 103729828B
- Authority
- CN
- China
- Prior art keywords
- video
- removing method
- value
- illumination variation
- rain removing
- 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 present invention proposes a kind of video rain removing method, that takes into account illumination variation factor, first determine whether whether ambient lighting changes, realize there be rainy the going of illumination variation situation according to illumination variation by changing Kalman gain Kg on this basis, and the extent by the brightness measurements of present frame with the brightness actual value of former frame, judge under illumination, whether pixel is covered by raindrop, and then remove raindrop.Described video rain removing method goes to consider ambient lighting changing factor in the rain at video, it is possible to is effectively taking place video when environment exists illumination variation and removes rain.
Description
Technical field
The present invention relates to technical field of computer vision, particularly relate to a kind of video raindrop minimizing technology containing illumination variation factor.
Background technology
Video image imaging is had a great impact by rain, can cause the covering of the fuzzy of video image imaging and information, and the definition that its direct result is video image declines, and the digitized processing of video image can be influenced by this to be affected and hydraulic performance decline.The video image polluted by raindrop is carried out repair process and is conducive to the further process of video image.And the target detection of video image, tracking, identification or cutting techniques are all used widely in multiple fields such as modern military, traffic and security monitorings.
Video went rain technology to propose to have been achieved for till now significant progress from 2003, and the various methods based on different mathematics physics model are successively proposed by scholars, and the effect that raindrop are removed also is enhanced gradually.In existing rain removing method, having incorporated the temporal information of video based on the algorithm of video successive frame, effect when it removes video raindrop is generally also better than the rain removing method based on single-frame images, particularly more significantly on the retention to background object edge.As based on the pixel intensity degree of bias (skew), gray tone, K mean cluster, Kalman filter, fuzzy connectedness rain removing method be all relatively new, effective.A kind of method carrying out raindrop removal based on multi-frame video image is introduced below for Kalman filter.
Kalman filter is a kind of optimization autoregression data processing algorithm.Discrete control procedures system is represented for following formula:
X (k)=AX (k-1)+BU (k)+W (k) (1)
System measurement:
Z (k)=HX (k)+V (k) (2)
Wherein, system mode during X (k), X (k-1) express time k and k-1 respectively, U (k) represents that system controling parameter, W (k) and V (k) represent the noise of process and measurement respectively, and they meet Gauss distribution.A, B are systematic parameter, and H is for measuring systematic parameter, and for multifactor system, they are all matrixes.
For meeting the system of the both the above linear random differential equation, it is possible to carry out optimal estimation by Kalman filter.The core of Kalman filter is following 5 equatioies:
X (k | k-1)=AX (k-1 | k-1)+BU (k) (3)
P (k | k-1)=AP (k-1 | k-1) A'+Q(4)
X (k | k)=X (k | k-1)+Kg (k) (Z (k)-HX (k | k-1)) (5)
Kg (k)=P (k | k-1) H'/(HP (k | k-1) H'+R) (6)
P (k | k)=(I-Kg (k) H) P (k | k-1) (7)
Wherein, the variance of the corresponding X of P (k | k) (k | k), Q is the variance of systematic procedure, and Kg (k) is called Kalman gain (KalmanGain).Kalman filter is in simple terms, it is simply that estimate actual value by system prediction value and measured value.
When Kalman filter is used for removing raindrop, if initial value X (0)=100, A=1, H (0)=1, P (0)=1.Owing to raindrop can regard the noise that variance is very big as, therefore the initial variance of V (k) is set to 50, the initial variance of W (k) is set to 5 simultaneously.Side's extent determines the speed reaching estimated value and the removal effect quality to noise, and little the meaning of variance reaches predictive value more slowly, but removal effect is better.
In prior art, based on the rain removing method of video continuous multiple frames monochrome information all without the factor considering that ambient lighting changes, if therefore there is illumination variation in practice, will largely have influence on rain effect.For Kalman filter, if a certain moment k intensity of illumination increases, so will be less much than real actual value according to above-mentioned formula (5) pixel intensity calculated " actual value ".
Summary of the invention
For the problems referred to above, it is an object of the invention to provide a kind of video rain removing method containing illumination variation factor, to increase the robustness of existing video rain removing method.
A kind of video rain removing method, it is characterised in that comprise the steps:
S11, calculate the difference of the brightness actual value of the brightness measurements of present frame and former frame, as the first element and build the first matrix;
S12, other the first element sums calculated within the scope of surrounding's predeterminable area of each described first element average, as the second element and build the second matrix;
, if the absolute value of described second element is more than the threshold values of described illumination variation, then there is illumination variation, perform S14, otherwise perform S16 in the absolute value of the second element described in S13, comparison and the threshold values of illumination variation;
S14, the element calculated between described first element and described second element are poor, and compare with pre-set threshold value, if described element difference is more than described pre-set threshold value, then judge that the pixel that described first element is corresponding is covered by raindrop, and perform S16, otherwise perform S15;
S15, utilizing Kalman filter to calculate the intrinsic brilliance value of described present frame, and Kalman gain changes Kg=Kg+a* | y |+b into, wherein a, b are for being used for the described second normalized parameter of element;
S16, utilize Kalman filter calculate described present frame intrinsic brilliance value;
S17, execution next frame are until terminating.
In the present invention one better embodiment, before step S11, also include: S10, reading video, it is thus achieved that the brightness actual value of described former frame.
In the present invention one better embodiment, before step S11, also include: the initial value of Kalman filter is set.
In the present invention one better embodiment, described predeterminable area ranges for the square area of 21x21.
Compared to prior art, video rain removing method provided by the invention goes to consider ambient lighting changing factor in the rain at video, it is possible to is effectively taking place video when environment exists illumination variation and removes rain.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention, and can be practiced according to the content of description, and in order to above and other objects of the present invention, feature and advantage can be become apparent, below especially exemplified by embodiment, and coordinate accompanying drawing, describe in detail as follows.
Accompanying drawing explanation
The flow chart of the video rain removing method that Fig. 1 provides for a preferred embodiment of the present invention.
Detailed description of the invention
Below in conjunction with drawings and the specific embodiments, the present invention is further detailed explanation.
Referring to Fig. 1, one embodiment of the invention provides a kind of video rain removing method, and it comprises the steps:
S11, calculate the difference of the brightness actual value of the brightness measurements of present frame and former frame, as the first element and build the first matrix.
Specifically, obtaining the brightness measurements of present frame and the difference of the calculated brightness actual value of former frame, before and after namely, the luminance difference of two frames, is stored in the first matrix x as the first element.It is understood that described first matrix x includes multiple first element.
In the present embodiment, before step S11, also include: S10, reading video, and obtain the brightness actual value of described former frame.
Thereafter also include step (not shown): the initial value of Kalman filter is set.Namely set initial value X (0)=100, A=1, H (0)=1, P (0)=1, the concrete content being referred to background of invention, repeat no more herein.
S12, other the first element sums calculated within the scope of surrounding's predeterminable area of each described first element average, as the second element and build the second matrix.
In the present embodiment, described predeterminable area ranges for the square area of 21x21.Specifically, calculate in described first matrix x the average of other the first element sums in 21x21 square area around each first element, be stored in the second matrix y as the second element.Certainly, described predeterminable area scope is not limited in the present embodiment, it is also possible to set as required, as long as square area meets: on the one hand, square area be large enough to get rid of that its brightness increases is caused by a large amount of raindrop;On the other hand, it is to avoid the erroneous judgement that the regional area illumination variation that the too big point light sources of square area causes causes other region to there is also illumination variation.
It is understood that described second matrix y also includes multiple second element.
, if the absolute value of described second element is more than the threshold values of described illumination variation, then there is illumination variation, perform S14, otherwise perform S16 in the absolute value of the second element described in S13, comparison and the threshold values of illumination variation.
In the present embodiment, for each second element in described second matrix y, it may be judged whether there is | y | > c, wherein c represents the threshold value that there is illumination variation, thinks there is illumination variation when | y | is very big, performs step S14, otherwise performs step S16.
S14, the element calculated between described first element and described second element are poor, and compare with pre-set threshold value, if described element difference is more than described pre-set threshold value, then judge that the pixel that described first element is corresponding is covered by raindrop, and perform S16, otherwise perform S15.
In the present embodiment, it may be judged whether have (x-y) > T, wherein, T is a threshold value that can be manually set.Thus, it is possible to judge whether x is covered by raindrop, if set up, then illustrate that x is very big, now may determine that x is covered by raindrop, perform step S16, otherwise perform step S15.
S15, utilizing Kalman filter to calculate the intrinsic brilliance value of described present frame, and Kalman gain changes Kg=Kg+a* | y |+b into, wherein a, b are for being used for the described second normalized parameter of element.
In the present embodiment, the brightness actual value (herein repeating no more) of present frame is calculated according to formula (3)~(7) in background of invention, and Kg is changed into Kg=Kg+a* | y |+b, wherein a, b are used to normalized for y parameter.
It is understood that as | y |>c time, represent illumination variation, no matter be that illumination strengthens (y>0) or illumination weakens (y<0), the weight Kg of measured value Z (k) will be increased to adapt to illumination variation.
S16, utilize Kalman filter calculate described present frame intrinsic brilliance value.
In the present embodiment, calculating the brightness actual value (herein repeating no more) of present frame according to formula (3)~(7) in background of invention, next frame is not ready.
S17, execution next frame are until terminating.
It is understandable that, described video rain removing method provided by the invention considers illumination variation factor, first determine whether whether ambient lighting changes, realize there be rainy the going of illumination variation situation according to illumination variation by changing Kalman gain Kg on this basis, and the extent by the brightness measurements of present frame with the brightness actual value of former frame, judge under illumination, whether pixel is covered by raindrop, and then remove raindrop.
Compared to prior art, described video rain removing method provided by the invention goes to consider ambient lighting changing factor in the rain at video, it is possible to is effectively taking place video when environment exists illumination variation and removes rain.
The above, it is only embodiments of the invention, not the present invention is done any pro forma restriction, although the present invention is disclosed above with embodiment, but it is not limited to the present invention, any those skilled in the art, without departing within the scope of technical solution of the present invention, when the technology contents of available the disclosure above makes a little change or is modified to the Equivalent embodiments of equivalent variations, in every case it is without departing from technical solution of the present invention content, according to any simple modification that above example is made by the technical spirit of the present invention, equivalent variations and modification, all still fall within the scope of technical solution of the present invention.
Claims (4)
1. a video rain removing method, it is characterised in that comprise the steps:
S11, calculate the difference of the brightness actual value of the brightness measurements of present frame and former frame, as the first element and build the first matrix;
S12, other the first element sums calculated within the scope of surrounding's predeterminable area of each described first element average, as the second element and build the second matrix y;
, if the absolute value of described second element is more than the threshold values of described illumination variation, then there is illumination variation, perform S14, otherwise perform S16 in the absolute value of the second element described in S13, comparison and the threshold values of illumination variation;
S14, the element calculated between described first element and described second element are poor, and compare with pre-set threshold value, if described element difference is more than described pre-set threshold value, then judge that the pixel that described first element is corresponding is covered by raindrop, and perform S16, otherwise perform S15;
S15, utilizing Kalman filter to calculate the intrinsic brilliance value of described present frame, and Kalman gain changes Kg=Kg+a* | y |+b into, wherein a, b are for being used for the described second normalized parameter of element;
S16, utilize Kalman filter calculate described present frame intrinsic brilliance value;
S17, execution next frame are until terminating.
2. video rain removing method as claimed in claim 1, it is characterised in that before step S11, also include: S10, reading video, it is thus achieved that the brightness actual value of described former frame.
3. video rain removing method as claimed in claim 1, it is characterised in that before step S11, also include: the initial value of Kalman filter is set.
4. video rain removing method as claimed in claim 1, it is characterised in that described predeterminable area ranges for the square area of 21x21.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310683538.2A CN103729828B (en) | 2013-12-12 | 2013-12-12 | video rain removing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310683538.2A CN103729828B (en) | 2013-12-12 | 2013-12-12 | video rain removing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103729828A CN103729828A (en) | 2014-04-16 |
CN103729828B true CN103729828B (en) | 2016-06-29 |
Family
ID=50453889
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310683538.2A Active CN103729828B (en) | 2013-12-12 | 2013-12-12 | video rain removing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103729828B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104299214B (en) * | 2014-09-30 | 2017-12-29 | 中国科学院深圳先进技术研究院 | The detection of raindrop and minimizing technology and system in light rain scene video data |
CN104318537B (en) * | 2014-09-30 | 2017-07-28 | 中国科学院深圳先进技术研究院 | The detection of raindrop and minimizing technology and system in heavy rain scene video data |
CN104978720A (en) * | 2015-07-01 | 2015-10-14 | 深圳先进技术研究院 | Video image raindrop removal method and apparatus |
CN105184761A (en) * | 2015-08-28 | 2015-12-23 | 中国科学院深圳先进技术研究院 | Image rain removing method based on wavelet analysis and system |
CN106067163A (en) * | 2016-05-24 | 2016-11-02 | 中国科学院深圳先进技术研究院 | A kind of image rain removing method based on wavelet analysis and system |
CN106023112A (en) * | 2016-05-24 | 2016-10-12 | 中国科学院深圳先进技术研究院 | Image rain removing method and system based on wavelet analysis |
CN109360155B (en) * | 2018-08-17 | 2020-10-13 | 上海交通大学 | Single-frame image rain removing method based on multi-scale feature fusion |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103337061A (en) * | 2013-07-18 | 2013-10-02 | 厦门大学 | Rain and snow removing method for image based on multiple guided filtering |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2641230B1 (en) * | 2010-11-15 | 2017-09-06 | Indian Institute Of Technology, Kharagpur | Method and apparatus for detection and removal of rain from videos using temporal and spatiotemporal properties |
TWI480810B (en) * | 2012-03-08 | 2015-04-11 | Ind Tech Res Inst | Method and apparatus for rain removal based on a single image |
-
2013
- 2013-12-12 CN CN201310683538.2A patent/CN103729828B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103337061A (en) * | 2013-07-18 | 2013-10-02 | 厦门大学 | Rain and snow removing method for image based on multiple guided filtering |
Also Published As
Publication number | Publication date |
---|---|
CN103729828A (en) | 2014-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103729828B (en) | video rain removing method | |
CN107301623B (en) | Traffic image defogging method and system based on dark channel and image segmentation | |
US8873835B2 (en) | Methods and apparatus for correcting disparity maps using statistical analysis on local neighborhoods | |
JP4616046B2 (en) | VEHICLE IMAGE PROCESSING SYSTEM, VEHICLE IMAGE PROCESSING METHOD, VEHICLE IMAGE PROCESSING PROGRAM, AND VEHICLE | |
EP2568438A2 (en) | Image defogging method and system | |
CN112036254B (en) | Moving vehicle foreground detection method based on video image | |
US11108970B2 (en) | Flicker mitigation via image signal processing | |
KR20150146045A (en) | Apparatus and method for image defogging | |
CN103258332A (en) | Moving object detection method resisting illumination variation | |
CN103578083A (en) | Single image defogging method based on joint mean shift | |
CN104952256A (en) | Video information based method for detecting vehicles at intersection | |
CN102930515A (en) | Automatic geometric distortion correction method of digital image | |
CN109255799B (en) | Target tracking method and system based on spatial adaptive correlation filter | |
CN108898561B (en) | Defogging method, server and system for foggy image containing sky area | |
CN105631825B (en) | Based on the image defogging method for rolling guiding | |
CN104484865A (en) | Method for removing raindrops in video image | |
CN104268845A (en) | Self-adaptive double local reinforcement method of extreme-value temperature difference short wave infrared image | |
CN105405112A (en) | Multispectral satellite image distance deviation index defogging method | |
CN105740796B (en) | Lane line image binaryzation method after a kind of perspective transform based on grey level histogram | |
CN109658441B (en) | Foreground detection method and device based on depth information | |
CN104657972A (en) | Ambiguity judging method and system of image block | |
CN106611406A (en) | Image correction method and image correction device | |
KR101535630B1 (en) | Apparatus for enhancing the brightness of night image using brightness conversion model | |
CN110580706A (en) | Method and device for extracting video background model | |
CN115660990A (en) | Endoscope image mirror reflection detection and restoration method based on brightness classification |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |