CN104378628B - A kind of method of detection image flicker striped - Google Patents
A kind of method of detection image flicker striped Download PDFInfo
- Publication number
- CN104378628B CN104378628B CN201410705325.XA CN201410705325A CN104378628B CN 104378628 B CN104378628 B CN 104378628B CN 201410705325 A CN201410705325 A CN 201410705325A CN 104378628 B CN104378628 B CN 104378628B
- Authority
- CN
- China
- Prior art keywords
- flicker
- striped
- field pictures
- detected
- video sequence
- 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
Landscapes
- Picture Signal Circuits (AREA)
- Studio Devices (AREA)
Abstract
An embodiment of the present invention provides a kind of method of detection image flicker striped, can achieve the purpose that to flicker striped from time for exposure and single-frame images output time limitation detection video sequence by analysis spectrum information.The method of detection image flicker striped includes：Obtain the row mean vector of two field pictures in the video sequence to be detected；Wherein, each element in the row mean vector is the average of the pixel value of one-row pixels in current frame image；Obtain the ratio vector of the row mean vector of the two field pictures；Ratio vector is subjected to Fourier transformation and obtains spectrum information, removes the spectrum information of DC component in the spectrum information；Flicker striped in the video sequence to be detected is detected according to the spectrum information.
Description
Technical field
The present invention relates to video processing technique, more particularly to a kind of method of detection image flicker striped.
Technical background
The light source used in daily life is mostly AC power, and the brightness of headlamp is with the period of waves of alternating source
And change.When headlamp uses 50Hz power supplys, brightness period of change is 1/100 second；When headlamp uses 60Hz power supplys,
Brightness period of change is 1/120 second.And for the lens sensors (sensor) using row exposure (Rolling shutter)
For, the image do not gone together is collected in exposure at different moments, therefore will usually be arranged to the time for exposure 1/100 second or
The integral multiple of 1/120 second, to eliminate the luminous energy difference do not gone together and accumulated within the time for exposure, to eliminate flicker striped
(Flicker).But when not being the integral multiple of 1/100 or 1/120 second between upon exposure, it may result in what every row pixel received
Luminous energy has differences, and the Flicker stripeds between bright dark phase can be thus produced in single image.If the output per two field picture
Time nor during the integral multiple of 1/100 second or 1/120 second, will result in starting of the adjacent two field pictures with the pixel of a line
Phase difference between time for exposure, so as to observe the Flicker stripeds rolled in continuous sequence of video images.And
The presence of Flicker stripeds can seriously affect the quality and visual effect of video image, and the particularly target to monitoring field is supervised
Depending on and identification bring very big puzzlement.
Therefore it is badly in need of a kind of method of detection image flicker striped, early-stage preparations is carried out for the follow-up Flicker stripeds that eliminate.
The content of the invention
In view of this, the embodiment of the present invention provides a kind of method of detection image flicker striped, to reach detection video sequence
The purpose of striped is flickered in row.
In order to achieve the above object, a kind of method of detection image flicker striped provided in an embodiment of the present invention includes：
Obtain the row mean vector of two field pictures in the video sequence to be detected；Wherein, in the row mean vector
Each element is the average of the pixel value of one-row pixels in current frame image；
Obtain the ratio vector of the row mean vector of the two field pictures；
Ratio vector is subjected to Fourier transformation and obtains spectrum information, removes DC component in the spectrum information
Spectrum information；
Flicker striped in the video sequence to be detected is detected according to the spectrum information.
A kind of method of detection image flicker striped provided in an embodiment of the present invention, based on Fourier transformation, will treat
The flicker striped function information for detecting different two field pictures in video sequence is converted for spectrum information by Fourier transformation；And energy
The flicker striped being accurately judged to according to the frequency spectrum characteristic of spectrum information in video sequence to be detected, when detection process is from exposure
Between and the limitation of single-frame images output time, filled up the technological gap for the flicker striped that the exposure of current detection row produces.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the method for detection image flicker striped that one embodiment of the invention provides.
Fig. 2 is a kind of space periodic for flicker striped for working as known video sequence to be detected that one embodiment of the invention provides
With the flow chart of the method for detection image flicker striped during frame per second.
Fig. 3 is a kind of space periodic for flicker striped for working as unknown video sequence to be detected that one embodiment of the invention provides
With the flow chart of the method for detection image flicker striped during frame per second.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, the present invention is made below in conjunction with the accompanying drawings further
Detailed description.
Fig. 1 is a kind of flow chart of the method for detection image flicker striped provided in an embodiment of the present invention.As shown in Figure 1,
This method comprises the following steps：
Step 101：Obtain the row mean vector of two field pictures in the video sequence to be detected；Wherein, the row average
Each element in vector is the average of the pixel value of one-row pixels in current frame image.
In an embodiment of the present invention, pixel value is set as flicker striped functional value and the product of background function value.Wherein,
Flicker striped function can be with flicker the space periodic of striped (being represented hereinafter with Flicker), flicker striped initial phase and
The function for being biased to parameter of striped is flickered, which can be the trigonometric function for including SIN function or cosine function.
In an embodiment of the present invention, flicker striped function F is represented by：
Wherein ω is the space periodic of Flicker stripeds, and d is the inclined of Flicker stripeds
Put,The initial phase of Flicker stripeds respectively in two field pictures.
Since the image with Flicker stripeds can be broken down into two parts of Flicker stripeds and background image,
Pixel value in one two field picture is represented by：
Wherein B is background function, is m * n matrix, and m and n are respectively to work as
The line number and columns of prior image frame pixel.
Since the frame output time (inverse of frame per second) of video image is not that (brightness under alternating current 50Hz became in 1/100 second
Change the cycle) or 1/120 second (the brightness period of change under alternating current 60Hz) integral multiple, cause the Flicker of the two field pictures
The phase of striped is different.The pixel value of the two field pictures in step 101 is represented by this time：
Wherein, dI is the biasing of two field pictures Flicker stripeds,WithRespectively two field pictures Flicker stripeds
Initial phase, B1And B2The background function value of pixel respectively in two field pictures.
Then the row mean vector for trying to achieve two field pictures is respectively mean (I1) and mean (I2)。
In an embodiment of the present invention, which is adjacent two field pictures；Or the flicker bar when adjacent two field pictures
When the phase difference of line curve is smaller, which can also be spaced a frame or multiple image.In an alternative embodiment of the invention, when
When known to the flicker stripe rolling speed of the video sequence to be detected, can also according to it is described flicker striped rolling speed,
If when calculating the two field pictures and there is flicker striped, the flicker striped curves of the two field pictures reaches phase during certain phase difference
Every frame number；And the two field pictures for being separated by frame number with this are subsequently calculated.
, can be with it will be understood by those skilled in the art that in order to further improve the accuracy of subsequent detection Flicker stripeds
Be calculate two field pictures flicker striped curve reach maximum phase difference when minimum be separated by frame number；And frame is separated by with the minimum
Several two field pictures are subsequently calculated.
Step 102：Obtain the ratio vector of the row mean vector of the two field pictures.
Ratio vector div detailed processes are obtained to be represented by：
Since the background image of two field pictures respective pixel is static image, i.e. B1=B2=B, tries to achieve ratio vector
During background function value can be removed, therefore the ratio vector is only related with the Flicker striped functional values of two images.
In an embodiment of the present invention, occur the situation of div=" 0/0 " in order to prevent, doing two frame line mean vector phases
Except before, first adding a correction value (offset) for every corresponding two elements in the row mean vector of two field pictures.When this
Offset relative to the element value in row mean vector it is sufficiently small when, not only avoided the situation of appearance " 0/0 ", but also will not reduced value
Produce large effect.
Detailed process represents：
Wherein, offset=max (max (mean (I1)), max (mean (I2)))/8, max represents maximizing.Repair
On the occasion of the row mean vector mean (I that offset is two field pictures1) and mean (I2) all elements in maximum 1/8.
In an embodiment of the present invention, can be to the row of two field pictures in order to reduce the calculation amount of follow-up Fourier transformation
Element in mean vector is sampled, and obtain the two field pictures it is sampled after row mean vector ratio vector.This
Field technology personnel are appreciated that the number of sampled point can be smaller when the Flicker cycles depending on the size by the Flicker cycles
When it is necessary to suitably increase the number of sampled point, the present invention does not limit the number of sampled point.
Step 103：Ratio vector is subjected to Fourier transformation and obtains spectrum information, is removed straight in the spectrum information
The spectrum information of flow component.
Since the ratio vector obtained by step 102 has certain periodicity, its cycle is by Flicker bars in two field pictures
The cycle of line determines that its phase is determined that its fluctuating range is by two field pictures by the phase difference of Flicker stripeds in two field pictures
Phase difference and biasing d are determined.Therefore Fourier transformation can be carried out using ratio vector, and frequency is done for the curve of conversion gained
Spectrum analysis, the Flicker in video sequence to be detected is detected according to frequency spectrum characteristic.
After ratio vector is carried out Fourier transformation, the frequency spectrum letter of the maximum of spectrum information necessarily DC component
Breath, and the spectrum information of the DC component can not reflect the cyclically-varying of Flicker fringe values, therefore the direct current is divided
The spectrum information of amount removes.Otherwise the spectrum position of later use spectrum information maximum and number can go out during threshold decision
Existing error.
Step 104：Flicker striped in the video sequence to be detected is detected according to the spectrum information.
In an embodiment of the present invention, in order to further improve the accuracy rate of detection, no longer for single ratio vector
Fourier transformation (FFT) frequency spectrum performs an analysis, but obtains the FFT spectrum letter for the multiple ratios vector being calculated by multiple image
The average of breath, then threshold decision is made to the spectrum mean.At this time, step 104 may include：First, by the frequency in a default frame number
Spectrum information averages to obtain mean spectrum information；Secondly, the flicker in mean spectrum infomation detection video sequence to be detected is utilized
Striped.
In an embodiment of the present invention, can be when time for detecting appearance flicker striped in the video sequence to be detected
When number reaches a predetermined threshold value, then export testing result.
It will be understood by those skilled in the art that since the space periodic and frame per second of the flicker striped of video sequence to be detected can
Can be known, it is also possible to unknown.Therefore in both cases, the detection image flicker that the embodiment of the present invention is provided
The detailed process of striping methods will be different.
When the space periodic and frame per second of the flicker striped of known video sequence to be detected, step 104 specifically may include two
A step：First, there is peak in the spectrum information for predicting the ratio vector according to the space periodic of the flicker striped
Prediction spectrum position.Secondly, judge spectrum information occur peak spectrum position whether with prediction spectrum position it is consistent, and
Whether the absolute value of peak and the ratio of all spectrum information average values are more than or equal to a predetermined threshold value；It is if returning the result
It is then to illustrate occur flicker striped in video sequence to be detected.
Fig. 2 is a kind of space periodic for flicker striped for working as known video sequence to be detected that one embodiment of the invention provides
With the flow chart of the method for detection image flicker striped during frame per second.As shown in Fig. 2, the idiographic flow of this method is：
Input parameter num, fd and T first, wherein num are accumulative frame number when seeking multiple ratio vector FFT spectrum averages,
Fd is represented as exporting one-time detection every fd frames as a result, T is the minimum alarm value of the frame number of the Flicker occurred in fd frames
(S21)；Three counters count1, count2 and count3 are initialized to 0 (S22)；Then chosen from video sequence
Two field pictures (S23), and try to achieve the row mean vector (S24) of the two field pictures；Seek the ratio of the row mean vector of the two field pictures
Value vector, and FFT transform is carried out to ratio vector, the result of FFT transform is added up (S25)；Counter count3 is added 1
(S26), then judge whether count3 has reached num (S27)；S23 is returned if not up to and reads two field pictures progress again
Calculate, to continue the result of cumulative FFT transform；If reached, average, will count to the result of the FFT transform after adding up
Number device count2 adds 1, and count3 is reset (S28), and starts the follow-up threshold value of the average progress to the FFT transform result and sentence
It is disconnected；First determine whether the ratio of maximum spectrum and all spectrum means in addition to DC component is more than a predetermined threshold value, and most
High spectrum appears in expected position (S29)；If S29 judging results are Y, illustrate flicker striped occurred, at this time will meter
Number device count1 adds 1 (S210), then judges whether count2 reaches fd (S211)；If S29 judging results are N, also to connect
And judge whether count2 reaches fd (S211)；If S211 judging results are N, illustrate also to be not reaching to output testing result
Threshold value, returns to S23 and reads two field pictures again and calculated at this time；If S211 judging results are Y, then whether count1 is judged
T (S212) is reached；If the judging result of S212 is N, illustrate not occurring T flicker striped in fd frames, this makees nothing
Flicker prompts (S213)；If the judging result of S212 is Y, illustrate to have reached the alarm for occurring T flicker striped in fd frames
Threshold value, this alarm (S214)；Counter count1 and count2 are finally reset into (S215), and returns to S23 and reads two frames again
Image is calculated.
When the space periodic and frame per second of the flicker striped of the unknown video sequence to be detected, step 104 can specifically wrap
Include：Judge that the spectrum information peak is located at the frame number of a fixed frequency spectrum position and whether is more than N/2 in a default frame number N,
And whether the absolute value of the peak and the ratio of all spectrum information average values are more than or equal to a predetermined threshold value；Or, one
Judge whether respectively N/2 peak at least occur on two neighboring spectrum position in default frame number N.If any of the above one
Kind judging result is yes, then illustrates flicker striped occur in the video sequence to be detected.
Fig. 3 is a kind of space periodic for flicker striped for working as unknown video sequence to be detected that one embodiment of the invention provides
With the flow chart of the method for detection image flicker striped during frame per second.As shown in figure 3, the idiographic flow of this method is：
Input parameter fd and T first, wherein fd are represented as (namely foregoing default every fd frames output one-time detection result
Frame number N), T is the minimum alarm value (S31) of the frame number of the flicker striped occurred in fd frames；Counter count is initialized as 0
(S32)；Then two field pictures (S33) are chosen from video sequence, and try to achieve the row mean vector (S34) of the two field pictures；Ask
The ratio vector of row average, and reduced value vector does FFT transform, after DC component frequency spectrum is removed, stores the FFT transform frequency spectrum
(S35)；Counter count is added into 1 (S36), then judges whether count has reached fd (S37)；Returned if not up to
S33 reads the calculating that two field pictures carry out next round FFT transform frequency spectrum again；If reached, illustrate to have reached output detection
As a result threshold value, at this time resets counter count, and flicker striated state value Flicker is initialized as 0 (S38)；Then
In this fd frame exports testing result, the position of maximum spectrum appearance is counted, records other positions in addition to first spectrum position
Put the number (S39) for maximum spectrum occur；Whether the number for then judging spectrum information peak occur in a fixed position is big
In equal to T (S310)；If S310's returns the result as Y, the flat of the peak that occurs in the fixed position is and then calculated
Average and the ratio r atio (S311) of all spectrum means；Then judge whether ratio is more than or equal to a predetermined threshold value
(S312)；If S312's returns the result as Y, Flicker is assigned a value of 1 (S313), S316 is then entered if N to Flicker
Value whether be 1 to be judged；If S310's returns the result as N, judge whether respectively to go out on two neighboring spectrum position
Fd/2 maximum (S314) is showed；If S314's returns the result as Y, Flicker is assigned a value of 1 (S313), if N then into
Whether enter S316 is 1 to judge to the value of Flicker；If the judging result of S316 is Y, prove flicker striped occurred,
This alarm (S318)；If the judging result of S316 is N, the prompting (S317) for not occurring flickering striped is done.
A kind of method of detection image flicker striped provided in an embodiment of the present invention, based on Fourier transformation, will treat
The flicker striped function information for detecting different two field pictures in video sequence is converted for spectrum information by Fourier transformation.And energy
The flicker striped being accurately judged to according to the frequency spectrum characteristic of spectrum information in video sequence to be detected, when detection process is from exposure
Between and the limitation of single-frame images output time, filled up the technological gap for the flicker striped that the exposure of current detection row produces.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
Within god and principle, any modification for being made, equivalent substitution etc., should all be included in the protection scope of the present invention.
Claims (7)
- A kind of 1. method of detection image flicker striped, it is characterised in that including：Obtain the row mean vector of two field pictures in video sequence to be detected；Wherein, each element in the row mean vector For the average of the pixel value of one-row pixels in current frame image, the pixel value is flicker striped functional value and background function value Product, the flicker striped function are to flicker the inclined of the space periodic of striped, the initial phase for flickering striped and flicker striped The function of parameter is set to, the minimum when two field pictures reach maximum phase difference for the flicker striped function is separated by frame number；Add a correction value for each element in the row mean vector of the two field pictures, wherein the correction value is described two The 1/8 of maximum in all elements of the row mean vector of two field picture；Obtain the ratio vector of the row mean vector of the two field pictures；Ratio vector is subjected to Fourier transformation and obtains spectrum information, removes the frequency spectrum of DC component in the spectrum information Information；Flicker striped in the video sequence to be detected is detected according to the spectrum information, wherein, by a default frame number The spectrum information averages to obtain mean spectrum information, utilizes video sequence to be detected described in the mean spectrum infomation detection In flicker striped.
- 2. according to the method described in claim 1, it is characterized in that, the function is trigonometric function.
- 3. according to the method described in claim 1, it is characterized in that, the two field pictures are adjacent two field pictures；Or,One two field picture of two field pictures interval；Or,When known to the flicker stripe rolling speed of the video sequence to be detected, the row mean vector of the two field pictures is obtained Ratio vector include：According to the rolling speed of the flicker striped, if calculate the two field pictures in the presence of flicker striped, the two field pictures It is separated by frame number when flicker striped curve reaches certain phase difference；It is separated by the ratio vector of the row mean vector of the two field pictures of frame number described in acquisition.
- 4. according to the method described in claim 1, it is characterized in that, obtain the ratio of the row mean vector of the two field pictures to Amount includes：Element in the row mean vector of the two field pictures is sampled, and obtain the two field pictures it is sampled after row The ratio vector of mean vector.
- 5. according to the method described in claim 1, it is characterized in that, when the flicker striped of the known video sequence to be detected When space periodic and frame per second, detecting the flicker striped in the video sequence to be detected according to the spectrum information includes：The pre- frequency measurement of peak is occurred according to the spectrum information that the space periodic of the flicker striped predicts the ratio vector Spectral position；Judge the spectrum information occur peak spectrum position it is whether consistent with the prediction spectrum position, and the highest Whether the absolute value of value and the ratio of all spectrum information average values are more than or equal to a predetermined threshold value；If it is to be to return the result, Then illustrate flicker striped occur in the video sequence to be detected.
- 6. according to the method described in claim 1, it is characterized in that, when the flicker striped of the unknown video sequence to be detected When space periodic and frame per second, detecting the flicker striped in the video sequence to be detected according to the spectrum information includes：Judge that the spectrum information peak is located at the frame number of a fixed frequency spectrum position and whether is more than N/2 in a default frame number N, And whether the absolute value of the peak and the ratio of all spectrum information average values are more than or equal to a predetermined threshold value；Or,Judge whether respectively N/2 peak at least occur on two neighboring spectrum position in a default frame number N；If it is judged that being yes, then illustrate flicker striped occur in the video sequence to be detected.
- 7. according to the method described in claim 1, it is characterized in that, further comprise：When detecting that the number for occurring flicker striped in the video sequence to be detected reaches a predetermined threshold value, output detection knot Fruit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410705325.XA CN104378628B (en) | 2014-11-28 | 2014-11-28 | A kind of method of detection image flicker striped |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410705325.XA CN104378628B (en) | 2014-11-28 | 2014-11-28 | A kind of method of detection image flicker striped |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104378628A CN104378628A (en) | 2015-02-25 |
| CN104378628B true CN104378628B (en) | 2018-04-24 |
Family
ID=52557241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410705325.XA Active CN104378628B (en) | 2014-11-28 | 2014-11-28 | A kind of method of detection image flicker striped |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104378628B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106572345B (en) * | 2015-10-13 | 2018-09-25 | 富士通株式会社 | Flash detecting device and method |
| CN106303158B (en) * | 2016-09-30 | 2019-05-21 | 杭州电子科技大学 | A kind of striped method for detecting abnormality in video image |
| CN110896470A (en) * | 2018-09-13 | 2020-03-20 | 广州弘度信息科技有限公司 | Video fringe detection method |
| CN110211523B (en) * | 2019-07-26 | 2019-11-05 | 武汉精立电子技术有限公司 | A kind of method, apparatus and system of telemeasurement Flicker value of liquid crystal module |
| CN114630054A (en) * | 2020-12-14 | 2022-06-14 | 瑞昱半导体股份有限公司 | Image acquisition device with image flicker detection mechanism and image flicker detection method thereof |
| CN112714308B (en) * | 2020-12-22 | 2022-05-06 | 武汉微创光电股份有限公司 | Method and device for detecting video rolling stripes |
| CN113301220B (en) * | 2021-04-27 | 2024-01-05 | 上海欧菲智能车联科技有限公司 | Synchronization method of vehicle-mounted camera and car lamp and FPGA chip |
| CN113688820A (en) * | 2021-08-25 | 2021-11-23 | 维沃移动通信有限公司 | Stroboscopic stripe information identification method and device and electronic equipment |
| CN114354138A (en) * | 2021-12-30 | 2022-04-15 | 杭州电子科技大学 | Screen stroboscopic detection system and method based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000007363A1 (en) * | 1998-07-28 | 2000-02-10 | Intel Corporation | Method and apparatus for reducing flicker effects from discharge lamps during pipelined digital video capture |
| CN101414357A (en) * | 2008-11-12 | 2009-04-22 | 北京中星微电子有限公司 | Method and apparatus for detecting film flicker |
| CN101567977A (en) * | 2009-06-09 | 2009-10-28 | 北京中星微电子有限公司 | Flicker detection method and device thereof |
| CN102572504A (en) * | 2011-03-29 | 2012-07-11 | 广州市浩云安防科技股份有限公司 | Method for detecting scrolling based on fast Fourier transformation |
| CN103093179A (en) * | 2011-10-28 | 2013-05-08 | 浙江大华技术股份有限公司 | Video strip quantitative calculation method |
-
2014
- 2014-11-28 CN CN201410705325.XA patent/CN104378628B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000007363A1 (en) * | 1998-07-28 | 2000-02-10 | Intel Corporation | Method and apparatus for reducing flicker effects from discharge lamps during pipelined digital video capture |
| CN101414357A (en) * | 2008-11-12 | 2009-04-22 | 北京中星微电子有限公司 | Method and apparatus for detecting film flicker |
| CN101567977A (en) * | 2009-06-09 | 2009-10-28 | 北京中星微电子有限公司 | Flicker detection method and device thereof |
| CN102572504A (en) * | 2011-03-29 | 2012-07-11 | 广州市浩云安防科技股份有限公司 | Method for detecting scrolling based on fast Fourier transformation |
| CN103093179A (en) * | 2011-10-28 | 2013-05-08 | 浙江大华技术股份有限公司 | Video strip quantitative calculation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104378628A (en) | 2015-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104378628B (en) | A kind of method of detection image flicker striped | |
| EP2695373B1 (en) | Spatially-varying flicker detection | |
| US9098748B2 (en) | Object detection apparatus, object detection method, monitoring camera system and storage medium | |
| KR20140045854A (en) | Method and apparatus for monitoring video for estimating gradient of single object | |
| JP2004260574A (en) | Flicker detecting method and detector | |
| JP6468439B2 (en) | Gas detection image processing apparatus, gas detection image processing method, and gas detection image processing program | |
| CA2780595A1 (en) | Method and multi-scale attention system for spatiotemporal change determination and object detection | |
| KR101674391B1 (en) | Apparatus for measuring contamination on lens | |
| CN102760230B (en) | Flame detection method based on multi-dimensional time domain characteristics | |
| KR101693959B1 (en) | Fire detection System and Method using Features of Spatio-temporal Video Blocks | |
| CN104574381A (en) | Full reference image quality evaluation method based on LBP (local binary pattern) | |
| CN107079098B (en) | Image playing method and device based on PTZ camera | |
| JP2019503751A5 (en) | ||
| US20150139554A1 (en) | Consecutive thin edge detection system and method for enhancing a color filter array image | |
| EP2827580B1 (en) | Flicker detection method and flicker detection apparatus | |
| CN117635649A (en) | Landslide monitoring method and system | |
| KR101640527B1 (en) | Method and Apparatus for Monitoring Video for Estimating Size of Single Object | |
| JP5286342B2 (en) | Smoke detection frequency component identification method and smoke detection device | |
| CN106063251B (en) | Image processing apparatus and image processing method | |
| JP2020170303A (en) | Image processing device, image processing method and program | |
| CN101414357A (en) | Method and apparatus for detecting film flicker | |
| JP2010515381A5 (en) | ||
| RU2465649C1 (en) | Method of detecting appearance of objects on images | |
| CN114529729B (en) | Strobe detection and elimination method, device, camera and storage medium | |
| JP5656964B2 (en) | Scene change determination apparatus or 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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190311 Address after: 519031 Room 105-15070, No. 6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Patentee after: Guangdong Vimicro Corp Address before: 519000 room 105, 6 Baohua Road, Hengqin New District, Zhuhai, Guangdong -478 Patentee before: GUANGDONG ZHONGXING ELECTRONICS CO., LTD. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210129 Address after: No. 602, 6th floor, shining building, 35 Xueyuan Road, Haidian District, Beijing 100083 Patentee after: BEIJING ZHONGXINGTIANSHI TECHNOLOGY Co.,Ltd. Address before: 519031 Room 105-15070, No. 6 Baohua Road, Hengqin New District, Zhuhai City, Guangdong Province Patentee before: GUANGDONG VIMICRO ELECTRONICS Co.,Ltd. |