CN110248182A - A kind of scene segment lens detection method - Google Patents
A kind of scene segment lens detection method Download PDFInfo
- Publication number
- CN110248182A CN110248182A CN201910468634.2A CN201910468634A CN110248182A CN 110248182 A CN110248182 A CN 110248182A CN 201910468634 A CN201910468634 A CN 201910468634A CN 110248182 A CN110248182 A CN 110248182A
- Authority
- CN
- China
- Prior art keywords
- frame
- histogram
- related coefficient
- detection method
- lens detection
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/02—Diagnosis, testing or measuring for television systems or their details for colour television signals
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Television Signal Processing For Recording (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a kind of scene segment lens detection methods, including video frame partitioning pretreatment, calculating blocked histogram, acquisition blocked histogram related coefficient, successive frame to judge four steps.The present invention determines whether two frame pictures are a camera lens, editorial staff is facilitated to carry out scene shot segmentation to material by judging that image histogram related coefficient is whether in threshold range between every two frame.
Description
Technical field
The invention belongs to field of video processing more particularly to a kind of scene segment lens detection methods.
Background technique
In video editing process, when editorial staff finds camera lens picture in material, need to take a significant amount of time to big
It measures camera lens picture and carries out artificial cutting, in order to mitigate the workload of editorial staff, a material is pressed camera lens scene automatically and is carried out
Segmentation, then just needing a kind of scene segment lens detection method.
Summary of the invention
It is an object of the present invention in view of the above-mentioned problems, propose a kind of scene segment lens detection method.
A kind of scene segment lens detection method, which comprises the steps of:
S1: video frame partitioning pretreatment；
S2: blocked histogram is calculated；
S3: blocked histogram related coefficient is obtained；
S4: successive frame judgement.
The video frame partitioning pretreatment includes video material decoding and frame picture piecemeal.
The frame picture piecemeal is that each frame image of decoding video is divided into M*N block.
Further, a kind of scene segment lens detection method, the calculating blocked histogram includes following sub-step:
S21: the YUV color space and hsv color space of each block of image are obtained；
S22: the histogram of each piece of image Y-component and H-S component is calculated.
Further, a kind of scene segment lens detection method, the acquisition blocked histogram related coefficient include:
S31: the histogram related coefficient of corresponding blocks Y-component in two field pictures is calculated, the correlation matrix of Y-component is obtained；
S32: the histogram related coefficient of corresponding blocks H-S component in two field pictures is calculated, the related coefficient square of H-S component is obtained
Battle array；
Further include the steps that calculating correlation matrix average value after the acquisition blocked histogram related coefficient, wherein Y points
Amount correlation matrix average value is denoted as corr1, and the correlation matrix average value of H-S component is denoted as corr2
Further, a kind of scene segment lens detection method, the successive frame judgement includes following sub-step:
S41: the histogram related coefficient corr of two field pictures corresponding blocks is calculated；
S42: judge whether two frames are successive frame according to related coefficient.
The histogram related coefficient corr for calculating two field pictures corresponding blocks includes following sub-step:
S411: preset first threshold value T1；
S412: judging the size relation of corr1 Yu first threshold T1, if corr1 is less than T1, corr is taken in corr1 and corr2
The larger value；Otherwise corr=corr1 is taken.
Further, a kind of scene segment lens detection method, it is described to judge whether two frames are continuous according to related coefficient
Frame includes, and calculates the histogram coefficient for corresponding to piecemeal between all two frames, result is normalized and inverted, if adjacent two
For value between frame within the scope of preset second threshold T2, two frames are successive frame；Otherwise, two frames are not successive frame.
Beneficial effects of the present invention: the present invention is by judging that whether image histogram related coefficient is in threshold value between every two frame
In range, determine whether two frame pictures are a camera lens, editorial staff is facilitated to carry out scene shot segmentation to material.
Detailed description of the invention
Fig. 1 is scene segment lens detection method flow diagram.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, this hair of Detailed description of the invention is now compareed
Bright specific embodiment.
In the present embodiment, scene segment shot detection processes are as follows:
Step 1: material decoding
Step 2: decoded each frame frame is divided into M*N block, and calculates separately the histogram of every piece of Y-component.
Step 3: corresponding blocks histogram related coefficient is calculated, correlation matrix is obtained, by being averaged for correlation matrix
Value is used as frame difference measurement standard, is denoted as corr1；
Step 4: setting first threshold T1 judges whether corr1 < T1 meets, if satisfied, then calculating the histogram of every piece of H-S component
Figure related coefficient, is denoted as corr2, takes corr=max(corr1, corr2)；If not satisfied, then taking corr=corr1；
Step 5: the blocked histogram related coefficient in video between all two frames is successively calculated, result is normalized simultaneously
It is inverted；
Step 6: successively taking the value between two frames to judge whether within the scope of second threshold T2, if, be expressed as between two frames be
One successive frame, as a camera lens, on the contrary it is next camera lens.
The present invention determines that two frames are drawn by judging that image histogram related coefficient is whether in threshold range between every two frame
Whether face is a camera lens, and editorial staff is facilitated to carry out scene shot segmentation to material.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (7)
1. a kind of scene segment lens detection method, which comprises the steps of:
S1: video frame partitioning pretreatment；
S2: blocked histogram is calculated；
S3: blocked histogram related coefficient is obtained；
S4: successive frame judgement.
2. a kind of scene segment lens detection method according to claim 1, which is characterized in that the video frame piecemeal is pre-
Processing includes video material decoding and frame picture piecemeal.
3. a kind of scene segment lens detection method according to claim 2, which is characterized in that the frame picture piecemeal is
Each frame image of decoding video is divided into M*N block.
4. a kind of scene segment lens detection method according to claim 1, which is characterized in that the calculating piecemeal histogram
Figure includes following sub-step:
S21: the YUV color space and hsv color space of each block of image are obtained；
S22: the histogram of each piece of image Y-component and H-S component is calculated.
5. a kind of scene segment lens detection method according to claim 1, which is characterized in that the acquisition piecemeal histogram
Figure related coefficient includes:
S31: the histogram related coefficient of corresponding blocks Y-component in two field pictures is calculated, the correlation matrix of Y-component is obtained；
S32: the histogram related coefficient of corresponding blocks H-S component in two field pictures is calculated, the related coefficient square of H-S component is obtained
Battle array；
A kind of scene segment lens detection method according to claim 5, which is characterized in that the acquisition blocked histogram
Further include the steps that calculating correlation matrix average value after related coefficient, wherein Y-component correlation matrix average value note
Correlation matrix average value for corr1, H-S component is denoted as corr2
A kind of scene segment lens detection method according to claim 1, which is characterized in that successive frame judgement includes
Following sub-step:
S41: the histogram related coefficient corr of two field pictures corresponding blocks is calculated；
S42: judge whether two frames are successive frame according to related coefficient.
6. a kind of scene segment lens detection method according to claim 6,7, which is characterized in that two frame figures of the calculating
As the histogram related coefficient corr of corresponding blocks includes following sub-step:
S411: preset first threshold value T1；
S412: judging the size relation of corr1 Yu first threshold T1, if corr1 is less than T1, corr is taken in corr1 and corr2
The larger value；Otherwise corr=corr1 is taken.
7. a kind of scene segment lens detection method according to claim 7, which is characterized in that described according to related coefficient
Judge whether two frames are that successive frame includes, calculate the histogram coefficient for corresponding to piecemeal between all two frames, normalizing is carried out to result
Change and inverted, if the value between adjacent two frame, within the scope of preset second threshold T2, two frames are successive frame；Otherwise, two frame
It is not successive frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910468634.2A CN110248182B (en) | 2019-05-31 | 2019-05-31 | Scene segment shot detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910468634.2A CN110248182B (en) | 2019-05-31 | 2019-05-31 | Scene segment shot detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110248182A true CN110248182A (en) | 2019-09-17 |
| CN110248182B CN110248182B (en) | 2021-01-15 |
Family
ID=67885611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910468634.2A Active CN110248182B (en) | 2019-05-31 | 2019-05-31 | Scene segment shot detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110248182B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2158324A (en) * | 1984-04-27 | 1985-11-06 | Licentia Gmbh | Detecting scene changes in visual information |
| CN101340576A (en) * | 2007-07-06 | 2009-01-07 | 北京大学软件与微电子学院 | Scene converting image enhancing process method and system by conversion and motion compensation |
| CN101917643A (en) * | 2010-07-09 | 2010-12-15 | 清华大学 | Method and device for detecting lens in real time in fully automatic two-dimensional (2D) to three-dimensional (3D) technology |
| CN102800095A (en) * | 2012-07-17 | 2012-11-28 | 南京特雷多信息科技有限公司 | Lens boundary detection method |
| CN102833492A (en) * | 2012-08-01 | 2012-12-19 | 天津大学 | Color similarity-based video scene segmenting method |
| WO2013053385A1 (en) * | 2011-10-11 | 2013-04-18 | Telefonaktiebolaget L M Ericsson (Publ) | Scene change detection for perceptual quality evaluation in video sequences |
| CN103237233A (en) * | 2013-03-28 | 2013-08-07 | 深圳Tcl新技术有限公司 | Rapid detection method and system for television commercials |
| CN103426176A (en) * | 2013-08-27 | 2013-12-04 | 重庆邮电大学 | Video shot detection method based on histogram improvement and clustering algorithm |
| CN103780801A (en) * | 2012-10-25 | 2014-05-07 | 特克特朗尼克公司 | Heuristic method for scene cut detection in digital baseband video |
| CN104410867A (en) * | 2014-11-17 | 2015-03-11 | 北京京东尚科信息技术有限公司 | Improved video shot detection method |
| CN104539942A (en) * | 2014-12-26 | 2015-04-22 | 赞奇科技发展有限公司 | Video shot switching detection method and device based on frame difference cluster |
| CN106792005A (en) * | 2017-01-17 | 2017-05-31 | 南通同洲电子有限责任公司 | A kind of content detection algorithm combined based on audio frequency and video |
-
2019
- 2019-05-31 CN CN201910468634.2A patent/CN110248182B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2158324A (en) * | 1984-04-27 | 1985-11-06 | Licentia Gmbh | Detecting scene changes in visual information |
| CN101340576A (en) * | 2007-07-06 | 2009-01-07 | 北京大学软件与微电子学院 | Scene converting image enhancing process method and system by conversion and motion compensation |
| CN101917643A (en) * | 2010-07-09 | 2010-12-15 | 清华大学 | Method and device for detecting lens in real time in fully automatic two-dimensional (2D) to three-dimensional (3D) technology |
| WO2013053385A1 (en) * | 2011-10-11 | 2013-04-18 | Telefonaktiebolaget L M Ericsson (Publ) | Scene change detection for perceptual quality evaluation in video sequences |
| CN102800095A (en) * | 2012-07-17 | 2012-11-28 | 南京特雷多信息科技有限公司 | Lens boundary detection method |
| CN102833492A (en) * | 2012-08-01 | 2012-12-19 | 天津大学 | Color similarity-based video scene segmenting method |
| CN103780801A (en) * | 2012-10-25 | 2014-05-07 | 特克特朗尼克公司 | Heuristic method for scene cut detection in digital baseband video |
| CN103237233A (en) * | 2013-03-28 | 2013-08-07 | 深圳Tcl新技术有限公司 | Rapid detection method and system for television commercials |
| CN103426176A (en) * | 2013-08-27 | 2013-12-04 | 重庆邮电大学 | Video shot detection method based on histogram improvement and clustering algorithm |
| CN104410867A (en) * | 2014-11-17 | 2015-03-11 | 北京京东尚科信息技术有限公司 | Improved video shot detection method |
| CN104539942A (en) * | 2014-12-26 | 2015-04-22 | 赞奇科技发展有限公司 | Video shot switching detection method and device based on frame difference cluster |
| CN106792005A (en) * | 2017-01-17 | 2017-05-31 | 南通同洲电子有限责任公司 | A kind of content detection algorithm combined based on audio frequency and video |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110248182B (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101651786B (en) | Method for restoring brightness change of video sequence and video processing equipment | |
| CN109685045B (en) | Moving target video tracking method and system | |
| EP3340075B1 (en) | Video abstract using signed foreground extraction and fusion | |
| CN104700430A (en) | Method for detecting movement of airborne displays | |
| Vosters et al. | Background subtraction under sudden illumination changes | |
| CN105959510B (en) | A kind of video rapid defogging method | |
| CN109598706A (en) | A kind of camera lens occlusion detection method and system | |
| CN107346547A (en) | Real-time foreground extracting method and device based on monocular platform | |
| CN109658437A (en) | A kind of method and device of quick detection moving object | |
| TW201032180A (en) | Method and device for keeping image background by multiple gauss models | |
| CN112927262A (en) | Camera lens shielding detection method and system based on video | |
| CN111931754B (en) | Method and system for identifying target object in sample and readable storage medium | |
| CN110769262A (en) | Video image compression method and system | |
| CN111325773A (en) | Method, device and equipment for detecting moving target and readable storage medium | |
| Hu et al. | A low illumination video enhancement algorithm based on the atmospheric physical model | |
| CN111274851A (en) | Living body detection method and device | |
| JP2978039B2 (en) | Video cut screen detection method | |
| CN110248182A (en) | A kind of scene segment lens detection method | |
| CN113066077B (en) | Flame detection method and device | |
| CN106951831B (en) | Pedestrian detection tracking method based on depth camera | |
| Ince et al. | Fast video fire detection using luminous smoke and textured flame features | |
| CN114841941A (en) | Moving target detection algorithm based on depth and color image fusion | |
| CN115239551A (en) | Video enhancement method and device | |
| CN115294163A (en) | Face image quality evaluation method based on adaptive threshold segmentation algorithm | |
| Kang et al. | Specular highlight region restoration using image clustering and inpainting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |