CN103702111B - A kind of method detecting camera video color cast - Google Patents
A kind of method detecting camera video color cast Download PDFInfo
- Publication number
- CN103702111B CN103702111B CN201310722639.6A CN201310722639A CN103702111B CN 103702111 B CN103702111 B CN 103702111B CN 201310722639 A CN201310722639 A CN 201310722639A CN 103702111 B CN103702111 B CN 103702111B
- Authority
- CN
- China
- Prior art keywords
- video
- frame
- color
- colour cast
- image
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Analysis (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a kind of method detecting camera video color cast, comprise the steps: to receive multi-frame video; Call frame of video color processing method frame by frame and colour cast judgement is done to each frame in video; Comprehensive multi-frame video gray value judges video gradation; Comprehensive multi-frame video colour cast value judges video colour cast.The present invention, by detecting the colour cast fault in video image, sets up the Testing index of a set of value, can alleviate the burden of eye recognition, reduces the error that subjective judgement produces.
Description
Technical field
The present invention relates to a kind of method detecting camera video color cast, belong to technical field of video image processing.
Background technology
Along with the development of economy, security device has spread all over each corner of people's life gradually, video monitoring system scale is increasing, monitored picture quantity also gets more and more, only by human eye, video pictures is investigated one by one, efficiency is very low, and therefore intelligentized video failure diagnosis importance highlights day by day.
Usually, due to the impact of the factors such as environment light source, the reflection characteristic of object itself and the photosensitive coefficient of collecting device, image capture device gathers between the color of image and true picture color and there are differences, i.e. colour cast phenomenon.Mainly there are following two aspects in its reason, on the one hand, digital imaging apparatus is when imaging, the energy stored in its sensitive component not only depends on the surface color of subject, also by be subject at that time extraneous light conditions, sensitive component the impact of the factors such as physical characteristic.Therefore, there is error to a certain degree between the color of the digital picture captured by imaging device and the realistic colour of subject surface, i.e. colour cast.If can detect whether digital picture exists colour cast exactly, then can provide effective reference for the subsequent treatment of digital picture.On the other hand.In order to save bandwidth, when transmitting, monitoring video data, more prevalent use Video Coding Compression Technology carries out Internet Transmission.But, carry out in transmitting procedure at video data, not only the factor such as ageing equipment fault and transmission line can make video image produce video colour cast, and at video data in encoder compresses process, the chromatic noise also can introduced, these chromatic noises also can cause the colour cast of video data.
In prior art, the image color shift detection method of employing mainly comprises gray world method, white area domain method, neural network and priori method.But these methods all have certain limitation, the colour cast of image correctly reliably cannot be detected.
The existence of colour cast phenomenon brings difficulty to the accuracy of image procossing, and therefore carrying out that color cast detection and colour cast correct to image is a very crucial link.The previous work that color cast detection corrects as colour cast, comprises and detects in image whether there is colour cast and colour cast degree, have extremely important using value in practice.Color cast detection relies on artificial investigation not only to waste time and energy, and easily occurs failing to report, and the subjective criterion of people is difficult to unify also to cause alarming result to be lack of consistency in addition.Therefore, need the operational system with color cast detection function in the present and following all kinds of video surveillance applications, this function will become the necessary functions assembly in video monitoring system.
A kind of detection method of image color cast is provided in the Chinese invention patent application that publication No. is CN102169585A.The method comprises: image to be detected is converted to hsv color spatial image; Channel S image is extracted from described hsv color spatial image; Calculate the comentropy of described channel S image; When the comentropy of described channel S image is greater than predetermined threshold value, determine that described image to be detected exists colour cast.This technical scheme can not be subject to the limitation of scene or priori, has general adaptability, improves accuracy rate and the reliability of color cast detection simultaneously.
Summary of the invention
For the deficiency existing for prior art, technical problem to be solved by this invention is to provide a kind of method detecting camera video color cast.The method can alleviate the burden of eye recognition, reduces the error that subjective judgement produces.
For realizing above-mentioned goal of the invention, the present invention adopts following technical scheme:
Detect a method for camera video color cast, comprise the steps:
Receive multi-frame video;
Call frame of video color processing method frame by frame and do colour cast judgement to each frame in video, wherein said frame of video color processing method comprises the steps: reception one frame video; Video data is changed into RGB color image; RGB color image is converted to HSV chromaticity diagram; Calculate color saturation value; If color saturation value is less than saturation threshold value, then judge that this two field picture is as gray level image; If color saturation value is not less than saturation threshold value, then the chroma histogram of computed image; Pick out the maximum colourity of number of pixels interval, and calculate the ratio that the interval pixel of colourity accounts for image; If the ratio that the interval pixel of colourity accounts for image is greater than the interval pixel threshold of colourity, then judge that present image is as colour cast image; If the ratio that the interval pixel of colourity accounts for image is not more than the interval pixel threshold of colourity, then judge that present image is as not colour cast image;
Comprehensive multi-frame video gray value judges video gradation;
Comprehensive multi-frame video colour cast value judges video colour cast.
Wherein more preferably, described color saturation value is the mean value of color saturation.
Wherein more preferably, comprehensive multi-frame video gray value judges that the step of video gradation comprises further:
If the ratio that the gray scale frame number in described multi-frame video accounts for whole video frame images sequence is greater than gray scale frame number threshold value, then judge that described multi-frame video is as gray scale; If the ratio that the gray scale frame number in described multi-frame video accounts for whole video frame images sequence is not more than gray scale frame number threshold value, then judge whether described multi-frame video is colour cast further.
Wherein more preferably, comprehensive multi-frame video colour cast value judges that the step of video colour cast comprises further:
If the ratio that the colour cast frame number in described multi-frame video accounts for whole video frame images sequence is greater than colour cast frame number threshold value, then judge that described multi-frame video is as colour cast.
The method of detection camera video color cast provided by the present invention, by detecting the colour cast fault in video image, setting up the Testing index of a set of value, can alleviate the burden of eye recognition, reduces the error that subjective judgement produces.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of detection camera video color cast method provided by the present invention;
Fig. 2 is in the present invention, the schematic flow sheet of frame of video color processing method.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail.
As shown in Figure 1, the invention provides a kind of method detecting camera video color cast, comprise the steps: to receive multi-frame video; Call frame of video color processing method frame by frame and colour cast judgement is done to each frame in video; Comprehensive multi-frame video gray value judges video gradation; Comprehensive multi-frame video colour cast value judges video colour cast.Detailed description is launched to the present invention below.
As shown in Figure 1, after computer receives multi-frame video, each frame of video of this multi-frame video is called frame of video color processing method respectively, colour cast identifying processing is done to the frame of video of multi-frame video.As shown in Figure 2, explanation is launched to frame of video color processing method below.
1) a frame video is received;
2) this one-frame video data received is changed into RGB color video two field picture;
3) the RGB color video two field picture after conversion is converted to HSV color video two field picture;
4) the color saturation value of HSV color video two field picture is calculated by HSV algorithm; Here color saturation value is the mean value of the color saturation of all pixels;
5) compare with the saturation threshold value preset according to the color saturation value of HSV color video two field picture, determine whether HSV color video two field picture is gray level image.If color saturation value is less than saturation threshold value, then judge that this video frame images is as gray level image; If color saturation value is not less than saturation threshold value, then calculate the chroma histogram of video frame images;
6) add up Colour, from HSV color video two field picture, pick out the maximum colourity of number of pixels interval, and calculate the ratio that the interval pixel of colourity accounts for the total pixel of video frame images;
7) compare according to HSV color video two field picture and the interval pixel threshold of the colourity that presets, determine HSV color video two field picture whether colour cast.If the ratio that the interval pixel of colourity accounts for the total pixel of video frame images is greater than the interval pixel threshold of colourity, then judge that current video two field picture is as colour cast image; If the ratio that the interval pixel of colourity accounts for the total pixel of video frame images is not more than the interval pixel threshold of colourity, then judge that current video two field picture is as not colour cast image.
As shown in Figure 1, the testing result of video frame images color exception in statistics multi-frame video a period of time, if it is determined that the ratio that the video frame images number for gray scale accounts for whole video frame images sequence is greater than the gray scale frame number threshold value preset, so just confirm that current multi-frame video is greyscale video.If it is determined that the ratio that the video frame images number for colour cast accounts for whole video frame images sequence is greater than the colour cast frame number threshold value preset, so just confirm that current multi-frame video exists colour cast.
Wherein, the colourity of current multi-frame video colour cast is the mean value of interior video frame images colour cast numerical value during this period of time, and the colour cast saturation of current multi-frame video is the mean value of interior video frame images saturation during this period of time.
In sum, the present invention, by automatically detecting video image quality, alleviates the burden of artificial judgment.The present invention further provides a kind of colour cast quality index of quantification, avoid the difference that human eye subjective judgement causes; Comprehensive use saturation and Colour algorithm, decrease metrical error.
Above the method for detection camera video color cast provided by the present invention is described in detail.For one of ordinary skill in the art, to any apparent change that it does under the prerequisite not deviating from connotation of the present invention, all by formation to infringement of patent right of the present invention, corresponding legal liabilities will be born.
Claims (4)
1. detect a method for camera video color cast, it is characterized in that comprising the steps:
Receive multi-frame video;
Call frame of video color processing method frame by frame and do colour cast judgement to each frame in video, wherein said frame of video color processing method comprises the steps: reception one frame video; Video data is changed into RGB color image; RGB color image is converted to HSV chromaticity diagram; Calculate color saturation value; If color saturation value is less than saturation threshold value, then judge that this two field picture is as gray level image; If color saturation value is not less than saturation threshold value, then the chroma histogram of computed image; Pick out the maximum colourity of number of pixels interval, and calculate the ratio that the interval pixel of colourity accounts for image; If the ratio that the interval pixel of colourity accounts for image is greater than the interval pixel threshold of colourity, then judge that present image is as colour cast image; If the ratio that the interval pixel of colourity accounts for image is not more than the interval pixel threshold of colourity, then judge that present image is as not colour cast image;
Comprehensive multi-frame video gray value judges video gradation;
Comprehensive multi-frame video colour cast value judges video colour cast.
2. the method detecting camera video color cast as claimed in claim 1, is characterized in that:
Described color saturation value is the mean value of color saturation.
3. the method detecting camera video color cast as claimed in claim 1, is characterized in that described comprehensive multi-frame video gray value judges that the step of video gradation comprises further:
If the ratio that the gray scale frame number in described multi-frame video accounts for whole video frame images sequence is greater than gray scale frame number threshold value, then judge that described multi-frame video is as gray scale; If the ratio that the gray scale frame number in described multi-frame video accounts for whole video frame images sequence is not more than gray scale frame number threshold value, then judge whether described multi-frame video is colour cast further.
4. the method for the detection camera video color cast as described in claim 1 or 3, is characterized in that described comprehensive multi-frame video colour cast value judges that the step of video colour cast comprises further:
If the ratio that the colour cast frame number in described multi-frame video accounts for whole video frame images sequence is greater than colour cast frame number threshold value, then judge that described multi-frame video is as colour cast.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310722639.6A CN103702111B (en) | 2013-12-24 | 2013-12-24 | A kind of method detecting camera video color cast |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310722639.6A CN103702111B (en) | 2013-12-24 | 2013-12-24 | A kind of method detecting camera video color cast |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103702111A CN103702111A (en) | 2014-04-02 |
| CN103702111B true CN103702111B (en) | 2016-01-27 |
Family
ID=50363497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310722639.6A Expired - Fee Related CN103702111B (en) | 2013-12-24 | 2013-12-24 | A kind of method detecting camera video color cast |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103702111B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107071398A (en) * | 2015-12-10 | 2017-08-18 | 青岛海信网络科技股份有限公司 | A kind of video quality diagnosing method and system |
| CN106998464B (en) * | 2016-01-26 | 2019-02-26 | 北京佳讯飞鸿电气股份有限公司 | Detect the method and device of thorn-like noise in video image |
| CN105761285A (en) * | 2016-02-25 | 2016-07-13 | 浙江合腾信息科技有限公司 | Abnormality detection method for bluish captured image |
| CN105791817B (en) * | 2016-04-29 | 2018-10-16 | 北京牡丹视源电子有限责任公司 | A kind of method and system of test and appraisal video image color rendition degree |
| CN107272637B (en) * | 2017-06-06 | 2019-08-30 | 武汉瑞科兴业科技有限公司 | A kind of video monitoring system fault self-checking self- recoverage control system and method |
| CN111225202B (en) * | 2018-11-27 | 2022-02-11 | 杭州海康威视数字技术股份有限公司 | Picture fault diagnosis method, device and system |
| CN111402189B (en) * | 2018-12-28 | 2023-10-31 | 山东华软金盾软件股份有限公司 | Video image color cast detection device and method |
| CN110516725B (en) * | 2019-08-16 | 2023-08-01 | 三峡大学 | Machine vision-based wood board stripe spacing and color detection method |
| CN110662024A (en) * | 2019-10-31 | 2020-01-07 | 上海中铁通信信号测试有限公司 | Video quality diagnosis method and device based on multiple frames and electronic equipment |
| CN115249272A (en) * | 2021-04-27 | 2022-10-28 | 青岛海尔电冰箱有限公司 | Method and equipment for detecting image color cast and refrigerator |
| CN115278217A (en) * | 2022-07-21 | 2022-11-01 | 深圳市震有软件科技有限公司 | Image picture detection method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006345187A (en) * | 2005-06-08 | 2006-12-21 | Canon Inc | Color processing method and device thereof |
| CN102169585A (en) * | 2011-03-31 | 2011-08-31 | 汉王科技股份有限公司 | Method and device for detecting image color cast |
| CN102395043A (en) * | 2011-11-11 | 2012-03-28 | 北京声迅电子股份有限公司 | Video quality diagnosing method |
| CN103065334A (en) * | 2013-01-31 | 2013-04-24 | 金陵科技学院 | Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space |
| CN103402117A (en) * | 2013-08-06 | 2013-11-20 | 夏东 | Method for detecting color cast of video image based on Lab chrominance space |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7489420B2 (en) * | 2005-12-28 | 2009-02-10 | Kwe International, Inc. | Color editing (including brightness editing) using color coordinate systems including systems with a coordinate defined by a square root of a quadratic polynomial in tristimulus values and, possibly, by a sign of a function of one or more of tristimulus values |
-
2013
- 2013-12-24 CN CN201310722639.6A patent/CN103702111B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006345187A (en) * | 2005-06-08 | 2006-12-21 | Canon Inc | Color processing method and device thereof |
| CN102169585A (en) * | 2011-03-31 | 2011-08-31 | 汉王科技股份有限公司 | Method and device for detecting image color cast |
| CN102395043A (en) * | 2011-11-11 | 2012-03-28 | 北京声迅电子股份有限公司 | Video quality diagnosing method |
| CN103065334A (en) * | 2013-01-31 | 2013-04-24 | 金陵科技学院 | Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space |
| CN103402117A (en) * | 2013-08-06 | 2013-11-20 | 夏东 | Method for detecting color cast of video image based on Lab chrominance space |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103702111A (en) | 2014-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103702111B (en) | A kind of method detecting camera video color cast | |
| WO2021036636A1 (en) | Vibration detection method and apparatus for lifting device, server and storage medium | |
| CN105611188B (en) | Camera occlusion detection method and device based on automatic exposure | |
| CN105100632B (en) | The method of adjustment and device of imaging device automatic exposure, imaging device | |
| JP4718253B2 (en) | Image abnormality detection device for surveillance camera | |
| Martini et al. | Image quality assessment based on edge preservation | |
| CN109167997B (en) | Video quality diagnosis system and method | |
| CN105791709A (en) | Automatic exposure processing method and apparatus with back-light compensation | |
| JP2014053855A (en) | Image processing device and method, and program | |
| US10121453B2 (en) | Bit rate controller and a method for limiting output bit rate | |
| CN105227843A (en) | The filming control method of terminal, the imaging control device of terminal and terminal | |
| CN102169585A (en) | Method and device for detecting image color cast | |
| CN110493574B (en) | Security monitoring visualization system based on streaming media and AI technology | |
| CN107146252A (en) | A kind of big data image processing apparatus | |
| CN104954627B (en) | A kind of information processing method and electronic equipment | |
| US20140327796A1 (en) | Method for estimating camera response function | |
| CN114092437B (en) | Transformer leakage oil detection method | |
| KR101809031B1 (en) | Composition fire detection processing apparatus and video processing method | |
| CN104378629A (en) | Camera fault detection method | |
| JP2008252402A (en) | Imaging system, imaging method, and imaging program | |
| CN110798680B (en) | Single-frame no-reference self-adaptive video snowflake noise detection method | |
| CN101483721A (en) | Video processing method and video capturing apparatus applying the method | |
| CN111145219B (en) | Efficient video moving target detection method based on Codebook principle | |
| JP3933453B2 (en) | Image processing apparatus and moving body monitoring apparatus | |
| CN106898020B (en) | Monitoring image contrast abnormity identification method and system based on video processing |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160127 Termination date: 20201224 |