CN110248182B - Scene segment shot detection method - Google Patents
Scene segment shot detection method Download PDFInfo
- Publication number
- CN110248182B CN110248182B CN201910468634.2A CN201910468634A CN110248182B CN 110248182 B CN110248182 B CN 110248182B CN 201910468634 A CN201910468634 A CN 201910468634A CN 110248182 B CN110248182 B CN 110248182B
- Authority
- CN
- China
- Prior art keywords
- images
- correlation coefficient
- frames
- histogram
- corr
- 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
Images
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 scene segment shot detection method which comprises four steps of video frame blocking pretreatment, block histogram calculation, block histogram correlation coefficient acquisition and continuous frame judgment. The invention determines whether the two frames of pictures are a shot or not by judging whether the image histogram correlation coefficient between every two frames is within the threshold range, thereby facilitating the editor to carry out scene shot segmentation on the material.
Description
Technical Field
The invention belongs to the field of video processing, and particularly relates to a scene segment shot detection method.
Background
In the process of video editing, when an editor searches for shot pictures in a material, a large amount of time is needed to manually segment a large number of shot pictures, and in order to reduce the workload of the editor, a material is automatically segmented according to shot scenes, so that a scene segment shot detection method is needed.
Disclosure of Invention
The present invention is directed to a method for detecting a scene segment shot.
A scene segment shot detection method is characterized by comprising the following steps:
s1: video frame block pretreatment;
s2: calculating a block histogram;
s3: obtaining a relevant coefficient of a block histogram;
s4: and judging continuous frames.
The video frame blocking pre-processing comprises video material decoding and frame picture blocking.
The frame picture block is a block dividing each frame picture of the decoded video into M × N blocks.
Further, the method for detecting the shot of the scene segment, wherein the step of calculating the block histogram, comprises the following sub-steps:
s21: acquiring a YUV color space and an HSV color space of each image;
s22: a histogram of the Y component and the H-S component of each block of the image is calculated.
Further, the method for detecting a scene segment shot, where the obtaining of the correlation coefficient of the block histogram includes:
s31: calculating the histogram correlation coefficient of the Y component of the corresponding block in the two frames of images to obtain a correlation coefficient matrix of the Y component;
s32: calculating the histogram correlation coefficient of the H-S component of the corresponding block in the two frames of images to obtain a correlation coefficient matrix of the H-S component;
the method further comprises the step of calculating the average value of the correlation coefficient matrix after obtaining the correlation coefficient of the block histogram, wherein the average value of the correlation coefficient matrix of the Y component is marked as corr1, and the average value of the correlation coefficient matrix of the H-S component is marked as corr2
Further, the method for detecting scene segment shots includes the following sub-steps:
s41: calculating the histogram correlation coefficient corr of the blocks corresponding to the two frames of images;
s42: and judging whether the two frames are continuous frames or not according to the correlation coefficient.
The calculation of the histogram correlation coefficient corr of the corresponding blocks of the two frames of images comprises the following sub-steps:
s411: presetting a first threshold value T1;
s412: judging the size relationship between corr1 and a first threshold value T1, and if corr1 is smaller than T1, taking the larger value of corr1 and corr2 from the corr; otherwise take corr = corr 1.
Further, the scene segment shot detection method comprises the steps of judging whether two frames are continuous frames according to the correlation coefficient, calculating histogram coefficients of corresponding blocks between all the two frames, normalizing the result and taking the reciprocal, wherein if the value between two adjacent frames is within a preset second threshold value T2, the two frames are continuous frames; otherwise, the two frames are not consecutive frames.
The invention has the beneficial effects that: the invention determines whether the two frames of pictures are a shot or not by judging whether the image histogram correlation coefficient between every two frames is within the threshold range, thereby facilitating the editor to carry out scene shot segmentation on the material.
Drawings
Fig. 1 is a flowchart illustrating a scene segment shot detection method.
Detailed Description
In order to more clearly understand the technical features, objects, and effects of the present invention, embodiments of the present invention will now be described with reference to the accompanying drawings.
In this embodiment, the scene segment shot detection process is as follows:
the method comprises the following steps: decoding of material
Step two: dividing each decoded frame into M x N blocks, and respectively calculating a histogram of Y components of each block.
Step three: calculating the correlation coefficient of the corresponding block histogram to obtain a correlation coefficient matrix, and taking the average value of the correlation coefficient matrix as the interframe difference measurement standard and marking as corr 1;
step four: setting a first threshold value T1, judging whether corr1< T1 is satisfied, if so, calculating a histogram correlation coefficient of each H-S component, marking the histogram correlation coefficient as corr2, and taking corr = max (corr 1, corr 2); if not, taking corr = corr 1;
step five: calculating the related coefficients of the block histograms between all two frames in the video in sequence, normalizing the result and taking the reciprocal;
step six: and sequentially taking values between two frames to judge whether the values are within the range of a second threshold value T2, if so, indicating that two frames are a continuous frame, namely a shot, and otherwise, indicating that the shot is the next shot.
The invention determines whether the two frames of pictures are a shot or not by judging whether the image histogram correlation coefficient between every two frames is within the threshold range, thereby facilitating the editor to carry out scene shot segmentation on the material.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (3)
1. A scene segment shot detection method is characterized by comprising the following steps:
s1: performing blocking pretreatment on each video frame in the scene segment;
s2: for each video frame, calculating a block histogram;
the calculating the block histogram includes the sub-steps of:
s21: acquiring image data of each image in a YUV color space and an HSV color space respectively;
s22: calculating a histogram of a Y component and a histogram of an H-S component of each block of image, wherein the H-S component is a result of weighted summation of the H component and the S component of the pixels of the block of image by preset weight;
s3: acquiring the average value of the correlation coefficients of two adjacent frames of images in the scene segment;
the obtaining of the average value of the correlation coefficients of two adjacent frames of images in the scene segment specifically includes:
s31: calculating the correlation coefficient of the histogram of the Y component of the corresponding block in the two adjacent frames of images so as to obtain a correlation coefficient matrix of the Y component corresponding to the two adjacent frames of images;
s32: calculating the correlation coefficient of the histogram of the H-S component of the corresponding block in the two adjacent frames of images so as to obtain a correlation coefficient matrix of the H-S component corresponding to the two adjacent frames of images;
s33: calculating the average value of the correlation coefficients of the Y components of the two adjacent frames of images based on the elements in the correlation coefficient matrix of the Y components, and calculating the average value of the correlation coefficients of the H-S components of the two adjacent frames of images according to the elements in the correlation coefficient matrix of the H-S components, wherein the average value of the correlation coefficients of the Y components is marked as corr1, and the average value of the correlation coefficients of the H-S components is marked as corr 2;
s4: judging continuous frames;
the continuous frame judgment comprises the following sub-steps:
s41: calculating the correlation coefficient corr of the histograms of the two adjacent frames of images;
s42: judging whether two adjacent frames of images are continuous frames or not according to the histogram correlation coefficient corr;
the judging whether the two adjacent frames of images are continuous frames according to the histogram correlation coefficient corr comprises the following steps: normalizing the histogram correlation coefficient corr, performing reciprocal processing on the result of the normalization processing, and if the value of the histogram correlation coefficient corr after the normalization processing and the reciprocal processing is less than or equal to a preset second threshold value T2, judging that the two frames of images are continuous frames; otherwise, judging that the two frames of images are not continuous frames;
the calculation of the histogram correlation coefficient corr of the two adjacent frames of images comprises the following sub-steps:
s411: presetting a first threshold value T1;
s412: judging the size relationship between corr1 and a first threshold value T1, and if corr1 is smaller than T1, taking the larger value of corr1 and corr2 from the corr; otherwise corr = corr 1.
2. The method as claimed in claim 1, wherein the pre-processing of the blocks of each video frame in the scene segment comprises decoding video material of the scene segment and performing frame picture blocking on each decoded video frame.
3. The method of claim 2, wherein the frame picture blocking is performed by dividing each video frame into M x N blocks.
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 CN110248182A (en) | 2019-09-17 |
| CN110248182B true 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) |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3415685A1 (en) * | 1984-04-27 | 1985-11-07 | Licentia Patent-Verwaltungs-Gmbh, 6000 Frankfurt | METHOD FOR DETECTING SCENE CHANGES IN FILMS AND VIDEO RECORDINGS AND FOR MONITORING OBJECTS BY VIDEO CAMERAS |
| 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 |
| CN101917643B (en) * | 2010-07-09 | 2012-05-30 | 清华大学 | Method and device for detecting lens in real time in fully automatic two-dimensional (2D) to three-dimensional (3D) technology |
| MY168103A (en) * | 2011-10-11 | 2018-10-11 | Ericsson Telefon Ab L M | Scene change detection for perceptual quality evaluation in video sequences |
| CN102800095B (en) * | 2012-07-17 | 2014-10-01 | 南京来坞信息科技有限公司 | Lens boundary detection method |
| CN102833492B (en) * | 2012-08-01 | 2016-12-21 | 天津大学 | A kind of video scene dividing method based on color similarity |
| 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 |
| CN103237233B (en) * | 2013-03-28 | 2017-01-25 | 深圳Tcl新技术有限公司 | Rapid detection method and system for television commercials |
| CN103426176B (en) * | 2013-08-27 | 2017-03-01 | 重庆邮电大学 | Based on the shot detection method improving rectangular histogram 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 |
| CN104539942B (en) * | 2014-12-26 | 2017-07-18 | 江苏赞奇科技股份有限公司 | Video lens switching detection method and its device based on frame difference cluster |
| CN106792005B (en) * | 2017-01-17 | 2020-08-28 | 南通同洲电子有限责任公司 | Content detection method based on audio and video combination |
-
2019
- 2019-05-31 CN CN201910468634.2A patent/CN110248182B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110248182A (en) | 2019-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4720705B2 (en) | Program, detection method, and detection apparatus | |
| US8582915B2 (en) | Image enhancement for challenging lighting conditions | |
| EP2457214B1 (en) | A method for detecting and adapting video processing for far-view scenes in sports video | |
| Karaman et al. | Comparison of static background segmentation methods | |
| US8699818B2 (en) | Method, system, and program for determining image quality based on pixel changes between image frames | |
| EP1456960A2 (en) | Apparatus and method for detection of scene changes in motion video | |
| CN108010044B (en) | Video boundary detection method | |
| CN111985314B (en) | Smoke detection method based on ViBe and improved LBP | |
| US20110085026A1 (en) | Detection method and detection system of moving object | |
| CN109543487B (en) | Automatic induction triggering method and system based on bar code edge segmentation | |
| US20090180670A1 (en) | Blocker image identification apparatus and method | |
| KR101296318B1 (en) | Apparatus and method for object tracking by adaptive block partitioning | |
| CN110769262A (en) | Video image compression method and system | |
| CN110248182B (en) | Scene segment shot detection method | |
| US8582882B2 (en) | Unit for and method of segmentation using average homogeneity | |
| Zhang et al. | Spatial-temporal nonparametric background subtraction in dynamic scenes | |
| US10686969B2 (en) | Detecting shot changes in a video | |
| CN115866295A (en) | Video key frame secondary extraction method and system for terminal row of convertor station | |
| JP2859345B2 (en) | Scene change detection method | |
| CN115239551A (en) | Video enhancement method and device | |
| Ekin et al. | Spatial detection of TV channel logos as outliers from the content | |
| CN111402189B (en) | Video image color cast detection device and method | |
| CN108737814B (en) | Video shot detection method based on dynamic mode decomposition | |
| KR20100118811A (en) | Shot change detection method, shot change detection reliability calculation method, and software for management of surveillance camera system | |
| Hsu et al. | Efficient moving object extraction in compressed low-bit-rate video |
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 |