CN104506968A - Method and device for determining video abstract figure - Google Patents
Method and device for determining video abstract figure Download PDFInfo
- Publication number
- CN104506968A CN104506968A CN201410852729.1A CN201410852729A CN104506968A CN 104506968 A CN104506968 A CN 104506968A CN 201410852729 A CN201410852729 A CN 201410852729A CN 104506968 A CN104506968 A CN 104506968A
- Authority
- CN
- China
- Prior art keywords
- image
- video
- video image
- value
- gradation
- 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
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/854—Content authoring
- H04N21/8549—Creating video summaries, e.g. movie trailer
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method and a device for determining a video abstract figure. The method comprises the following steps: capturing N-frame video image in a target video according to a preset video image sampling and capturing rule; judging whether any captured video image simultaneously meets the preset conditions or not, wherein the preset conditions include image grey value matching and corresponding judging condition of the video image, image gradient matching and corresponding judging condition of the video image, and image mean square error matching and corresponding judging condition of the video image; taking the video image which simultaneously meets the preset conditions an alternative video abstract figure; determining the video image with the biggest image gradient as the abstract figure of the target video from the determined alternative abstract figure. Compared with the prior art, the whole video is not needed to be scanned, and the system expense is small.
Description
Technical field
The present invention relates to internet arena, particularly a kind of video frequency abstract figure defining method and device.
Background technology
Video frequency abstract figure (sectional drawing) is the representative of video content.User is when access to netwoks video content, and video frequency abstract figure shows the most intuitively usually used as video content, is also the first impression of user to video content.Good video frequency abstract figure, just as outstanding book cover, can allow user have correct understanding to video content, attracts user to watch video further.
In the prior art, a kind of video frequency abstract figure defining method is: analyze whole video content, automatically determines the summary figure of this video according to analysis result.First this method will carry out graphical analysis according to video content, common are scene analysis, cluster, motion detection, object detection, Face datection etc., and analyzing after terminating, can be video frequency abstract figure according to the frame video image in analysis result determination video.But this method needs to travel through whole video usually, and overhead is large.
Summary of the invention
For solving the problem, the embodiment of the invention discloses a kind of video frequency abstract figure defining method and device.Technical scheme is as follows:
A kind of video frequency abstract figure defining method, can comprise the following steps:
Video image sampling according to presetting intercepts rule, intercepts the N frame video image in target video;
Judge whether arbitrary video image of intercepting meets pre-conditioned simultaneously, describedly pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it;
Described pre-conditioned video image will be met as the alternative summary figure of video simultaneously;
From determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video.
In the preferred embodiment of the present invention, the video image sampling that described basis is preset intercepts rule, intercepts the N frame video image in target video, comprising:
According to the time point selection rule preset, choose the N number of time point in target video, the N frame video image corresponding to N number of time point selected by intercepting.
In the preferred embodiment of the present invention, the time point selection rule that described basis is preset, choose the N number of time point in target video, comprising:
According to video image frame number N that is predetermined, that need intercepting, and target video duration, choose N number of time point uniformly.
In the preferred embodiment of the present invention, the time point selection rule that described basis is preset, choose the N number of time point in target video, comprising:
According to the scene number in target video, determine the video image frame number N needing to intercept, and choose N number of time point, wherein, each time point is selected from a scene.
In the preferred embodiment of the present invention, described from determined alternative summary figure, determine that the maximum frame video image of image gradient is as the summary figure of described target video, comprising:
When determined alternative summary figure quantity is not less than M, from determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video;
When determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercept alternate video image, and judge whether alternate video image is alternative summary figure, until the quantity of alternative summary figure reaches M;
Wherein, described M is default value, and M≤N.
In the preferred embodiment of the present invention, judge whether the arbitrary video image intercepted meets pre-conditioned method simultaneously, comprising:
From these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation, select arbitrary characteristics of image not yet participating in judging, calculate this characteristics of image and judge whether result of calculation meets the decision condition corresponding with this characteristics of image; If so, then repeat this step until there is not the characteristics of image having neither part nor lot in judgement, determine that intercepted video image meets the condition preset simultaneously; If not, then terminate to judge, when determining that intercepted video image is different, meet default condition.
In the preferred embodiment of the present invention,
The computational methods of gradation of image Distribution value comprise: according to preset, the brightness value of pixel is interval, the pixel count adding up each brightness value interval in the gradation of image Distribution value of the video image intercepted accounts for the ratio of total pixel number;
The computational methods of image gradient comprise: according to formula
G(x,y)＝dx(x,y)+dy(x,y)；
Calculate the image gradient of arbitrary pixel (x, y) of the video image intercepted;
Wherein, dx (x, y)=Y (x+1, y)-Y (x, y); Dy (x, y)=Y (x, y+1)-Y (x, y);
X, y are the coordinate figure of arbitrary pixel in image, the image gradient that G (x, y) is this pixel, and Y is the image intensity value of this pixel;
The computational methods of image mean-squared deviation comprise: according to formula
Calculate the image mean-squared deviation of the video image intercepted, wherein,
yn is the brightness value of arbitrary pixel, and N is pixel count.
In the preferred embodiment of the present invention,
Gradation of image Distribution value meets the decision condition corresponding with it and comprises: in gradation of image Distribution value, the ratio that the pixel count being less than the first brightness value or being greater than the second brightness value accounts for total pixel number is all less than first threshold, wherein, the first brightness value is less than the second brightness value;
Image gradient meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, arithmetic mean corresponding to image gradient is greater than the 3rd threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, the arithmetic mean corresponding to image gradient is greater than the 4th threshold value; Wherein, the 3rd threshold value is less than the 4th threshold value;
Image mean-squared deviation meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, image mean-squared deviation is greater than the 5th threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, image mean-squared deviation is greater than the 6th threshold value, and wherein, the 5th threshold value is less than the 6th threshold value.
A kind of video frequency abstract figure determining device, can comprise:
Video image determining unit, for intercepting rule according to the video image sampling preset, intercepts the N frame video image in target video;
Video image judging unit, pre-conditioned for judging whether intercepted arbitrary video image meets simultaneously, describedly pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it;
Alternative summary figure determining unit, for will meet described pre-conditioned video image as the alternative summary figure of video simultaneously;
Summary figure determining unit, for from determined alternative summary figure, determines the summary figure of the maximum frame video image of image gradient as described target video.
In the preferred embodiment of the present invention, described video image determining unit, comprising: time point chooses subelement, and video image intercepts subelement; Wherein,
Described time point chooses subelement, for according to the time point selection rule preset, chooses the N number of time point in target video;
Described video image intercepts subelement, for intercepting the N frame video image corresponding to selected N number of time point.
In the preferred embodiment of the present invention, described time point chooses subelement, specifically for:
According to video image frame number N that is predetermined, that need intercepting, and target video duration, choose N number of time point uniformly.
In the preferred embodiment of the present invention, described time point chooses subelement, specifically for:
According to the scene number in target video, determine the video image frame number N needing to intercept, and choose N number of time point, wherein, each time point is selected from a scene.
In the preferred embodiment of the present invention, summary figure determining unit, specifically for:
When determined alternative summary figure quantity is not less than M, from determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video;
When determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercept alternate video image, and judge whether alternate video image is alternative summary figure, until the quantity of alternative summary figure reaches M;
Wherein, described M is default value, and M≤N.
In the preferred embodiment of the present invention, described video image judging unit is for judging whether intercepted arbitrary video image meets pre-conditioned method, comprising simultaneously:
Determine 3 kinds of characteristics of image gradation of image Distribution value, image gradient and image mean-squared deviations needing to participate in judging;
From these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation, select arbitrary characteristics of image not yet participating in judging, calculate this characteristics of image and judge whether result of calculation meets the decision condition corresponding with this characteristics of image; If so, then repeat this step until there is not the characteristics of image having neither part nor lot in judgement, determine that intercepted video image meets the condition preset simultaneously; If not, then terminate to judge, when determining that intercepted video image is different, meet default condition.
In the preferred embodiment of the present invention,
Described video image judging unit, utilizes following methods computed image grey value profile:
According to preset, the brightness value of pixel is interval, the pixel count adding up each brightness value interval in the gradation of image Distribution value of the video image intercepted accounts for the ratio of total pixel number;
Described video image judging unit, utilizes following methods computed image gradient: according to formula
G(x,y)＝dx(x,y)+dy(x,y)；
Calculate the image gradient of arbitrary pixel (x, y) of the video image intercepted;
Wherein, dx (x, y)=Y (x+1, y)-Y (x, y); Dy (x, y)=Y (x, y+1)-Y (x, y);
X, y are the coordinate figure of arbitrary pixel in image, the image gradient that G (x, y) is this pixel, and Y is the image intensity value of this pixel;
Described video image judging unit, utilizes following methods computed image mean square deviation: according to formula
Calculate the image mean-squared deviation of the video image intercepted, wherein,
yn is the brightness value of arbitrary pixel, and N is pixel count.
In the preferred embodiment of the present invention,
Gradation of image Distribution value meets the decision condition corresponding with it and comprises: in gradation of image Distribution value, the ratio that the pixel count being less than the first brightness value or being greater than the second brightness value accounts for total pixel number is all less than first threshold, wherein, the first brightness value is less than the second brightness value;
Image gradient meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, arithmetic mean corresponding to image gradient is greater than the 3rd threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, the arithmetic mean corresponding to image gradient is greater than the 4th threshold value; Wherein, the 3rd threshold value is less than the 4th threshold value;
Image mean-squared deviation meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, image mean-squared deviation is greater than the 5th threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, image mean-squared deviation is greater than the 6th threshold value, and wherein, the 5th threshold value is less than the 6th threshold value.
Technical scheme of the present invention first intercepts rule according to the video image sampling preset, and intercepts the N frame video image in target video; After intercepting this N frame video image, then from intercepted N frame video image, determine alternative summary figure, from alternative summary figure, finally determine the summary figure of the maximum frame video image of image gradient as described target video.Compared with prior art, do not need to travel through whole video, overhead is little.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the flow chart of a kind of video frequency abstract figure defining method provided by the invention;
Whether arbitrary video image that Fig. 2 intercepts for a kind of judgement provided by the invention meets pre-conditioned method flow diagram simultaneously;
Fig. 3 be one provided by the invention from determined alternative summary figure, determine the flow chart of a frame video image as the summary figure of described target video;
Fig. 4 is the structural representation of a kind of video frequency abstract figure determining device provided by the invention.
Embodiment
First, be described a kind of video frequency abstract figure defining method provided by the invention, the method can comprise the following steps:
Video image sampling according to presetting intercepts rule, intercepts the N frame video image in target video;
Judge whether arbitrary video image of intercepting meets pre-conditioned simultaneously, describedly pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it;
Described pre-conditioned video image will be met as the alternative summary figure of video simultaneously;
From determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video.
Technical scheme of the present invention first intercepts rule according to the video image sampling preset, and intercepts the N frame video image in target video; After intercepting this N frame video image, then from intercepted N frame video image, determine alternative summary figure, from alternative summary figure, finally determine the summary figure of the maximum frame video image of image gradient as described target video.Compared with prior art, do not need to travel through whole video, overhead is little.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
As shown in Figure 1, a kind of video frequency abstract figure defining method, the method can comprise:
S101, the video image sampling according to presetting intercepts rule, intercepts the N frame video image in target video.
Target video mentioned here is exactly the video of summary figure to be determined.Determine the summary figure of this target video, first will intercept the N frame video image in target video.Wherein, N >=1; Be understandable that, along with N is increasing, determine the workload also corresponding increase of summary figure, but the selectable scope of summary figure also become large, is more conducive to selecting high-quality summary figure.The size of N can be selected according to actual conditions by those skilled in the art, and the present invention does not do concrete restriction at this.
It can be arbitrary that said default video image sampling intercepts rule, such as, can be that random sampling intercepts N frame video image in target video.But this sampling intercept method at random may occur, such as be truncated to the situation of two identical video images, also may there is the situation being truncated to multiple close video images, and once when having a frame to be not suitable as summary figure in multiple images, due to adjacent very near, the content of multiple images may be very alike, and like this, other video image also may all be not suitable as summary figure.
In order to avoid the appearance of the problems referred to above, in actual applications, according to the time point selection rule preset, the N number of time point in target video can be chosen, the N frame video image corresponding to N number of time point selected by intercepting.
Can ensure that intercepted N frame video image is different video image like this.
Said default time point selection rule can be determined by those skilled in the art, but is understandable that, selected time point is overstepping the bounds of propriety loose better, so more can embody the feature of target video full content.
According to the time point selection rule preset, choose the N number of time point in target video, be preferably: according to video image frame number N that is predetermined, that need intercepting, and target video duration, choose N number of time point uniformly;
Or
According to the scene number in target video, determine the video image frame number N needing to intercept, and choose N number of time point, wherein, each time point is selected from a scene.
When adopting the first preferred implementation, N frame video image can be intercepted out more uniformly in all video images of target video, the dispersiveness of each video image can be ensured.
When adopting the second preferred implementation, first to determine the scene number S in target video, and then determine according to scene number S the video image frame number N needing intercepting, N≤S, then in N number of scene, each scene selects a frame video image, can ensure the dispersiveness of each video image equally, can embody the feature of target video full content.The method intercepting a frame video image in each scene can be random selecting in this scenario, and can adopt other method to choose, the present invention does not do concrete restriction at this yet.
It should be noted that, said default time point selection rule includes but not limited to above-mentioned two kinds, the Else Rule that those skilled in the art determine, as long as can ensure that determined video image is dispersion, and also can be rational.
S102, judges whether the arbitrary video image intercepted meets pre-conditioned simultaneously.
In this step, pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it.
When selecting characteristics of image, should ensure that characteristics of image can meet the requirement determining video frequency abstract figure, consider the complexity of characteristics of image algorithm again, namely under the prerequisite that can meet the requirement determining video frequency abstract figure, the complexity of characteristics of image algorithm is more low better.
According to above-mentioned analysis, embodiments provide three kinds of characteristics of image, be respectively gradation of image Distribution value, image gradient, image mean-squared deviation.
Accordingly,
The computational methods of gradation of image distribution comprise: according to preset, the brightness value of pixel is interval, the pixel count adding up each brightness value interval in the gradation of image Distribution value of the video image intercepted accounts for the ratio of total pixel number;
Such as brightness value 0 ~ 255 can be divided into following interval: 0 ~ 40,40 ~ 60,60 ~ 80,80 ~ 100,100 ~ 120,120 ~ 140,140 ~ 160,160 ~ 180,180 ~ 200,200 ~ 255,40 ~ 70,70 ~ 90,90 ~ 110,110 ~ 130,130 ~ 150,150 ~ 170,170 ~ 190,190 ~ 210,210 ~ 255; Then the pixel count adding up each brightness value interval in the video image intercepted respectively accounts for the ratio of total pixel number;
The computational methods of described image gradient comprise: according to formula
G(x,y)＝dx(x,y)+dy(x,y)；
Calculate the image gradient of arbitrary pixel (x, y) of the video image intercepted;
Wherein, dx (x, y)=Y (x+1, y)-Y (x, y); Dy (x, y)=Y (x, y+1)-Y (x, y);
X, y are the coordinate figure of arbitrary pixel in image, the image gradient that G (x, y) is this pixel, and Y is the image intensity value of this pixel;
The computational methods of described image mean-squared deviation comprise: according to formula
Calculate the image mean-squared deviation of the video image intercepted, wherein,
yn is the brightness value of arbitrary pixel, and N is pixel count.
When practical application, the decision condition that the image mean-squared deviation of the decision condition that the decision condition that the gradation of image Distribution value of video image is corresponding, the image gradient of video image are corresponding and video image is corresponding all can be determined after expounding adequately by those skilled in the art, and the present invention does not do concrete restriction at this.Such as,
Gradation of image Distribution value meets the decision condition corresponding with it and comprises: in gradation of image Distribution value, the ratio that the pixel count being less than the first brightness value or being greater than the second brightness value accounts for total pixel number is all less than first threshold, wherein, the first brightness value is less than the second brightness value; Here the first brightness value mentioned, the second brightness value and first threshold can be determined voluntarily by those skilled in the art, such as, first brightness value can select 40, second brightness value can select 200, first threshold can select 20%, and now, above-mentioned decision condition can be: in gradation of image Distribution value, brightness value is less than 40 or the pixel count that is greater than 200 ratio that accounts for total pixel number when being all less than 20%, and gradation of image Distribution value meets the decision condition corresponding with it.
Image gradient meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, arithmetic mean corresponding to image gradient is greater than the 3rd threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, the arithmetic mean corresponding to image gradient is greater than the 4th threshold value; Wherein, the 3rd threshold value is less than the 4th threshold value; Said Second Threshold, the 3rd threshold value, the 4th threshold value can be determined voluntarily by those skilled in the art, and such as, Second Threshold can be the 70%, three threshold value be the 2, four threshold value is 3; Now, above-mentioned decision condition can be: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than 70%, arithmetic mean corresponding to image gradient is greater than 2, the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than 70%, the arithmetic mean corresponding to image gradient is greater than 3;
Image mean-squared deviation meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, image mean-squared deviation is greater than the 5th threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, image mean-squared deviation is greater than the 6th threshold value, and wherein, the 5th threshold value is less than the 6th threshold value; Said 5th threshold value, the 6th threshold value can be determined voluntarily by those skilled in the art, and such as, the 5th threshold value can be the 800, six threshold value can be 1000; Now, above-mentioned decision condition can be: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than 70%, image mean-squared deviation is greater than 800, the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than 70%, the arithmetic mean corresponding to image gradient is greater than 1000.
In embody rule process, judge whether arbitrary video image of intercepting meets pre-conditioned simultaneously, can be intercept a frame video image at every turn, then judges whether this frame video image meets simultaneously above-mentioned pre-conditioned.And then other video image intercepted in N frame video image, till N frame video image has all intercepted.
Also can be once N frame video image has all been intercepted, then it be above-mentioned pre-conditioned to judge whether the N frame video image that intercepts meets simultaneously.
Certainly, also can be once intercept the part in N frame video image, wait judged the video image of intercepting whether meet simultaneously above-mentioned pre-conditioned after, then intercept the other parts in N frame video image.
And judge whether the arbitrary video image intercepted meets pre-conditioned method simultaneously and also can have multiple, concrete method is determined voluntarily by those skilled in the art, and the present invention does not do concrete restriction at this, such as, following method can be adopted to judge:
From these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation, select arbitrary characteristics of image not yet participating in judging, calculate this characteristics of image and judge whether result of calculation meets the decision condition corresponding with this characteristics of image; If so, then repeat this step until there is not the characteristics of image having neither part nor lot in judgement, determine that intercepted video image meets default condition; If not, then terminate to judge, determine that intercepted video image does not meet the condition preset.
In actual applications, the concrete implementation step of the method can as shown in Figure 2, comprise:
S201, selects arbitrary characteristics of image not yet participating in judging from these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation.
S202, calculates this characteristics of image.
S203, judges whether result of calculation meets the decision condition corresponding with this characteristics of image.
S204, when judged result does not meet the decision condition corresponding with this characteristics of image, meets default condition when determining that intercepted video image is different.
S205, when judged result meets the decision condition corresponding with this characteristics of image, judges whether also to exist the characteristics of image not yet participating in judging further; When there is the characteristics of image not yet participating in judging, repeat S201.
S206, when there is not the characteristics of image not yet participating in judging, determines that intercepted video image meets the condition preset simultaneously.
Certainly, whether the arbitrary video image intercepted except above-mentioned judgement meets except pre-conditioned method simultaneously, can also be specified the judgement order of these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation by those skilled in the art,
Such as, first can judge whether gradation of image Distribution value meets the decision condition corresponding with it, when meeting, judge whether image gradient meets the decision condition corresponding with it further, when meeting, judging whether image mean-squared deviation meets the decision condition corresponding with it again, when meeting, determining that intercepted video image meets the condition preset simultaneously.
Or, first can judge whether gradation of image Distribution value meets the decision condition corresponding with it, when meeting, judge whether image mean-squared deviation meets the decision condition corresponding with it further, when meeting, judging whether image gradient meets the decision condition corresponding with it again, when meeting, determining that intercepted video image meets the condition preset simultaneously.
S103, will meet described pre-conditioned video image as the alternative summary figure of video simultaneously.
S104, from determined alternative summary figure, determines the summary figure of the maximum frame video image of image gradient as described target video.
After executing S103, in N frame video image, determine the alternative summary figure of some frames, and then from wherein determining the summary figure of the maximum video image of a two field picture gradient as described target video.Summary figure selected is like this that alternative summary picture in picture is maximum as gradient, illustrates that the content of this video image is the abundantest, most suitable as the summary figure of target video.
Be understandable that in extreme situations, a frame video image may do not had to meet in initial N frame video image described pre-conditioned simultaneously.That is, do not have a frame video image can scheme as alternative summary, cause the summary figure that finally cannot determine target video.For the solution of this kind of situation, the video image of selecting the arithmetic mean corresponding to image gradient maximum from N frame video image can be adopted as the method for the summary figure of target video, or adopt other summary figure defining method to determine summary figure.But predictably, when adopting first method, determined summary plot quality is lower, and when adopting second method, overhead may increase accordingly.
In order to also can determine the summary figure of high-quality target video when above-mentioned extreme case occurs, in the preferred embodiment of the present invention, after determining alternative summary figure, first judge whether the quantity of alternative summary figure is less than default quantity M,
When determined alternative summary figure quantity is not less than M, from determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video;
When determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercept alternate video image, and judge whether alternate video image is alternative summary figure, until the quantity of alternative summary figure reaches M; Wherein M≤N.
It should be noted that, judge whether the arbitrary video image whether alternate video image can adopt above-mentioned judgement to intercept for the method for alternative summary figure meets pre-conditioned method simultaneously.
The mentioned video image preset intercepts regular those skilled in the art and can determine voluntarily, as long as ensure that the video image intercepted was not intercepted, such as, can intercept the next frame in N frame video image in target video.Specifically, first can intercept the next frame of the first frame in target video in N frame video image, then intercept the next frame of the second frame in target video in N frame video image, until do not need to intercept.
When practical application, intercept rule according to the video image preset and intercept alternate video image, it can be intercepting one frame alternate video image, now, described from determined alternative summary figure, determine that the maximum frame video image of image gradient can as shown in Figure 3, comprise as the concrete implementation step of the summary figure of described target video:
S301, judges whether the quantity of alternative summary figure is less than M.
S302, when determined alternative summary figure quantity is not less than M, determines the summary figure of the maximum frame video image of image gradient as described target video from determined alternative summary figure.
S303, when determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercepts a frame alternate video image.
S304, judges whether alternate video image is alternative summary figure; If so, then perform S305, the quantity of alternative summary figure is added 1; If not, then S303 is repeated.
After executing S305, repeat S301.
The method also can when determined alternative summary figure quantity be not less than M, direct intercepting is from all alternate video images reaching M frame alternative summary figure and also lack, such as, when M is 6, if S103 has determined the alternative summary figure of 3 frame, 3 frame alternate video images now directly can be intercepted.
By said method, the alternative summary figure of M frame can be determined completely, there will not be the problem can not determining alternative summary figure under above-mentioned extreme case.
Corresponding to embodiment of the method above, present invention also offers a kind of video frequency abstract figure determining device, as shown in Figure 4, comprising:
Video image determining unit 101, for intercepting rule according to the video image sampling preset, intercepts the N frame video image in target video;
Video image judging unit 102, pre-conditioned for judging whether intercepted arbitrary video image meets simultaneously, describedly pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it;
Alternative summary figure determining unit 103, for will meet described pre-conditioned video image as the alternative summary figure of video simultaneously;
Summary figure determining unit 104, for from determined alternative summary figure, determines the summary figure of the maximum frame video image of image gradient as described target video.
Technical scheme of the present invention first intercepts rule according to the video image sampling preset, and intercepts the N frame video image in target video; After intercepting this N frame video image, then from intercepted N frame video image, determine alternative summary figure, from alternative summary figure, finally determine the summary figure of the maximum frame video image of image gradient as described target video.Compared with prior art, do not need to travel through whole video, overhead is little.
In actual applications, video image determining unit 101 can intercept the N frame video image in target video at random, but this random defining method may occur, such as be truncated to the situation of two identical video images, also may there is the situation being truncated to multiple close video images, and once when having a frame to be not suitable as summary figure in these multiple images, due to adjacent very near, the content of these multiple images may be very alike, like this, other video image also may all be not suitable as summary figure.
In order to avoid the appearance of the problems referred to above, in the preferred embodiment of the present invention, time point chooses subelement, and video image intercepts subelement; Wherein,
Described time point chooses subelement, for according to the time point selection rule preset, chooses the N number of time point in target video;
Described video image intercepts subelement, for intercepting the N frame video image corresponding to selected N number of time point.
Can ensure that intercepted N frame video image is different video image like this.
Preferably, described time point chooses subelement, specifically for:
According to video image frame number N that is predetermined, that need intercepting, and target video duration, choose N number of time point uniformly.
Or
Described time point chooses subelement, specifically for:
According to the scene number in target video, determine the video image frame number N needing to intercept, and choose N number of time point, wherein, each time point is selected from a scene.
When the time click get subelement adopt above-mentioned two kinds of preferred technical schemes time, the dispersiveness of intercepted video image can be ensured, make intercepted video image can embody the feature of target video full content.
In the preferred embodiment of the present invention, summary figure determining unit 104, specifically for:
When determined alternative summary figure quantity is not less than M, from determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video;
When determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercept alternate video image, and judge whether alternate video image is alternative summary figure, until the quantity of alternative summary figure reaches M;
Wherein, described M is default value, and M≤N.
In the preferred embodiment of the present invention, described video image judging unit 102 is for judging whether intercepted arbitrary video image meets pre-conditioned method, comprising simultaneously:
From these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation, select arbitrary characteristics of image not yet participating in judging, calculate this characteristics of image and judge whether result of calculation meets the decision condition corresponding with this characteristics of image; If so, then repeat this step until there is not the characteristics of image having neither part nor lot in judgement, determine that intercepted video image meets the condition preset simultaneously; If not, then terminate to judge, when determining that intercepted video image is different, meet default condition.
In the preferred embodiment of the present invention,
Described video image judging unit 102, utilizes following methods computed image grey value profile:
According to preset, the brightness value of pixel is interval, the pixel count adding up each brightness value interval in the gradation of image Distribution value of the video image intercepted accounts for the ratio of total pixel number;
Such as brightness value 0 ~ 255 can be divided into following interval: 0 ~ 40,40 ~ 60,60 ~ 80,80 ~ 100,100 ~ 120,120 ~ 140,140 ~ 160,160 ~ 180,180 ~ 200,200 ~ 255,40 ~ 70,70 ~ 90,90 ~ 110,110 ~ 130,130 ~ 150,150 ~ 170,170 ~ 190,190 ~ 210,210 ~ 255; Then the pixel count adding up each brightness value interval in the video image intercepted respectively accounts for the ratio of total pixel number;
Described video image judging unit 102, utilizes following methods computed image gradient: according to formula
G(x,y)＝dx(x,y)+dy(x,y)；
Calculate the image gradient of arbitrary pixel (x, y) of the video image intercepted;
Wherein, dx (x, y)=Y (x+1, y)-Y (x, y); Dy (x, y)=Y (x, y+1)-Y (x, y);
X, y are the coordinate figure of arbitrary pixel in image, the image gradient that G (x, y) is this pixel, and Y is the image intensity value of this pixel;
Described video image judging unit 102, utilizes following methods computed image mean square deviation: according to formula
Calculate the image mean-squared deviation of the video image intercepted, wherein,
yn is the brightness value of arbitrary pixel, and N is pixel count.
When practical application, the decision condition that the image mean-squared deviation of the decision condition that the decision condition that the gradation of image Distribution value of video image is corresponding, the image gradient of video image are corresponding and video image is corresponding all can be determined according to actual conditions by those skilled in the art, and the present invention does not do concrete restriction at this.Such as,
In the preferred embodiment of the present invention,
Gradation of image Distribution value meets the decision condition corresponding with it and comprises: in gradation of image Distribution value, the ratio that the pixel count being less than the first brightness value or being greater than the second brightness value accounts for total pixel number is all less than first threshold, wherein, the first brightness value is less than the second brightness value; Here the first brightness value mentioned, the second brightness value and first threshold can be determined voluntarily by those skilled in the art, such as, first brightness value can select 40, second brightness value can select 200, first threshold can select 20%, and now, above-mentioned decision condition can be: in gradation of image Distribution value, brightness value is less than 40 or the pixel count that is greater than 200 ratio that accounts for total pixel number when being all less than 20%, and gradation of image Distribution value meets the decision condition corresponding with it.
Image gradient meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, arithmetic mean corresponding to image gradient is greater than the 3rd threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, the arithmetic mean corresponding to image gradient is greater than the 4th threshold value; Wherein, the 3rd threshold value is less than the 4th threshold value; Said Second Threshold, the 3rd threshold value, the 4th threshold value can be determined voluntarily by those skilled in the art, and such as, Second Threshold can be the 70%, three threshold value be the 2, four threshold value is 3; Now, above-mentioned decision condition can be: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than 70%, arithmetic mean corresponding to image gradient is greater than 2, the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than 70%, the arithmetic mean corresponding to image gradient is greater than 3;
Image mean-squared deviation meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, image mean-squared deviation is greater than the 5th threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, image mean-squared deviation is greater than the 6th threshold value, and wherein, the 5th threshold value is less than the 6th threshold value; Said 5th threshold value, the 6th threshold value can be determined voluntarily by those skilled in the art, and such as, the 5th threshold value can be the 800, six threshold value can be 1000; Now, above-mentioned decision condition can be: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than 70%, image mean-squared deviation is greater than 800, the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than 70%, the arithmetic mean corresponding to image gradient is greater than 1000.
It should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.
Each embodiment in this specification all adopts relevant mode to describe, between each embodiment identical similar part mutually see, what each embodiment stressed is the difference with other embodiments.Especially, for device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
One of ordinary skill in the art will appreciate that all or part of step realized in said method execution mode is that the hardware that can carry out instruction relevant by program has come, described program can be stored in computer read/write memory medium, here the alleged storage medium obtained, as: ROM/RAM, magnetic disc, CD etc.
The foregoing is only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.All any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., be all included in protection scope of the present invention.
Claims (16)
1. a video frequency abstract figure defining method, is characterized in that, comprises the following steps:
Video image sampling according to presetting intercepts rule, intercepts the N frame video image in target video;
Judge whether arbitrary video image of intercepting meets pre-conditioned simultaneously, describedly pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it;
Described pre-conditioned video image will be met as the alternative summary figure of video simultaneously;
From determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video.
2. the method for claim 1, is characterized in that, the video image sampling that described basis is preset intercepts rule, intercepts the N frame video image in target video, comprising:
According to the time point selection rule preset, choose the N number of time point in target video, the N frame video image corresponding to N number of time point selected by intercepting.
3. method as claimed in claim 2, is characterized in that, the time point selection rule that described basis is preset is chosen the N number of time point in target video, being comprised:
According to video image frame number N that is predetermined, that need intercepting, and target video duration, choose N number of time point uniformly.
4. method as claimed in claim 2, is characterized in that, the time point selection rule that described basis is preset is chosen the N number of time point in target video, being comprised:
According to the scene number in target video, determine the video image frame number N needing to intercept, and choose N number of time point, wherein, each time point is selected from a scene.
5. the method for claim 1, is characterized in that, described from determined alternative summary figure, determines that the maximum frame video image of image gradient is as the summary figure of described target video, comprising:
When determined alternative summary figure quantity is not less than M, from determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video;
When determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercept alternate video image, and judge whether alternate video image is alternative summary figure, until the quantity of alternative summary figure reaches M;
Wherein, described M is default value, and M≤N.
6. the method for claim 1, is characterized in that, judges whether the arbitrary video image intercepted meets pre-conditioned method simultaneously, comprising:
From these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation, select arbitrary characteristics of image not yet participating in judging, calculate this characteristics of image and judge whether result of calculation meets the decision condition corresponding with this characteristics of image; If so, then repeat this step until there is not the characteristics of image having neither part nor lot in judgement, determine that intercepted video image meets the condition preset simultaneously; If not, then terminate to judge, when determining that intercepted video image is different, meet default condition.
7. method as claimed in claim 6, is characterized in that,
The computational methods of gradation of image Distribution value comprise: according to preset, the brightness value of pixel is interval, the pixel count adding up each brightness value interval in the gradation of image Distribution value of the video image intercepted accounts for the ratio of total pixel number;
The computational methods of image gradient comprise: according to formula
G(x,y)＝dx(x,y)+dy(x,y)；
Calculate the image gradient of arbitrary pixel (x, y) of the video image intercepted;
Wherein, dx (x, y)=Y (x+1, y)-Y (x, y); Dy (x, y)=Y (x, y+1)-Y (x, y);
X, y are the coordinate figure of arbitrary pixel in image, the image gradient that G (x, y) is this pixel, and Y is the image intensity value of this pixel;
The computational methods of image mean-squared deviation comprise: according to formula
Calculate the image mean-squared deviation of the video image intercepted, wherein,
yn is the brightness value of arbitrary pixel, and N is pixel count.
8. the method for claim 1, is characterized in that,
Gradation of image Distribution value meets the decision condition corresponding with it and comprises: in gradation of image Distribution value, the ratio that the pixel count being less than the first brightness value or being greater than the second brightness value accounts for total pixel number is all less than first threshold, wherein, the first brightness value is less than the second brightness value;
Image gradient meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, arithmetic mean corresponding to image gradient is greater than the 3rd threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, the arithmetic mean corresponding to image gradient is greater than the 4th threshold value; Wherein, the 3rd threshold value is less than the 4th threshold value;
Image mean-squared deviation meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, image mean-squared deviation is greater than the 5th threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, image mean-squared deviation is greater than the 6th threshold value, and wherein, the 5th threshold value is less than the 6th threshold value.
9. a video frequency abstract figure determining device, is characterized in that, comprising:
Video image determining unit, for intercepting rule according to the video image sampling preset, intercepts the N frame video image in target video;
Video image judging unit, pre-conditioned for judging whether intercepted arbitrary video image meets simultaneously, describedly pre-conditionedly to comprise: the image mean-squared deviation that the gradation of image Distribution value of video image meets the decision condition corresponding with it, the image gradient of video image meets the decision condition corresponding with it and video image meets the decision condition corresponding with it;
Alternative summary figure determining unit, for will meet described pre-conditioned video image as the alternative summary figure of video simultaneously;
Summary figure determining unit, for from determined alternative summary figure, determines the summary figure of the maximum frame video image of image gradient as described target video.
10. device as claimed in claim 9, it is characterized in that, described video image determining unit, comprising: time point chooses subelement, and video image intercepts subelement; Wherein,
Described time point chooses subelement, for according to the time point selection rule preset, chooses the N number of time point in target video;
Described video image intercepts subelement, for intercepting the N frame video image corresponding to selected N number of time point.
11. devices as claimed in claim 10, it is characterized in that, described time point chooses subelement, specifically for:
According to video image frame number N that is predetermined, that need intercepting, and target video duration, choose N number of time point uniformly.
12. devices as claimed in claim 10, it is characterized in that, described time point chooses subelement, specifically for:
According to the scene number in target video, determine the video image frame number N needing to intercept, and choose N number of time point, wherein, each time point is selected from a scene.
13. devices as claimed in claim 9, is characterized in that, summary figure determining unit, specifically for:
When determined alternative summary figure quantity is not less than M, from determined alternative summary figure, determine the summary figure of the maximum frame video image of image gradient as described target video;
When determined alternative summary figure quantity is less than M, intercepts rule according to the video image preset and intercept alternate video image, and judge whether alternate video image is alternative summary figure, until the quantity of alternative summary figure reaches M;
Wherein, described M is default value, and M≤N.
14. devices as claimed in claim 9, is characterized in that, described video image judging unit is for judging whether intercepted arbitrary video image meets pre-conditioned method, comprising simultaneously:
Determine 3 kinds of characteristics of image gradation of image Distribution value, image gradient and image mean-squared deviations needing to participate in judging;
From these 3 kinds of characteristics of image of gradation of image Distribution value, image gradient and image mean-squared deviation, select arbitrary characteristics of image not yet participating in judging, calculate this characteristics of image and judge whether result of calculation meets the decision condition corresponding with this characteristics of image; If so, then repeat this step until there is not the characteristics of image having neither part nor lot in judgement, determine that intercepted video image meets the condition preset simultaneously; If not, then terminate to judge, when determining that intercepted video image is different, meet default condition.
15. devices as claimed in claim 9, is characterized in that,
Described video image judging unit, utilizes following methods computed image grey value profile:
According to preset, the brightness value of pixel is interval, the pixel count adding up each brightness value interval in the gradation of image Distribution value of the video image intercepted accounts for the ratio of total pixel number;
Described video image judging unit, utilizes following methods computed image gradient: according to formula
G(x,y)＝dx(x,y)+dy(x,y)；
Calculate the image gradient of arbitrary pixel (x, y) of the video image intercepted;
Wherein, dx (x, y)=Y (x+1, y)-Y (x, y); Dy (x, y)=Y (x, y+1)-Y (x, y);
X, y are the coordinate figure of arbitrary pixel in image, the image gradient that G (x, y) is this pixel, and Y is the image intensity value of this pixel;
Described video image judging unit, utilizes following methods computed image mean square deviation: according to formula
Calculate the image mean-squared deviation of the video image intercepted, wherein,
yn is the brightness value of arbitrary pixel, and N is pixel count.
16. devices as claimed in claim 9, is characterized in that,
Gradation of image Distribution value meets the decision condition corresponding with it and comprises: in gradation of image Distribution value, the ratio that the pixel count being less than the first brightness value or being greater than the second brightness value accounts for total pixel number is all less than first threshold, wherein, the first brightness value is less than the second brightness value;
Image gradient meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, arithmetic mean corresponding to image gradient is greater than the 3rd threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, the arithmetic mean corresponding to image gradient is greater than the 4th threshold value; Wherein, the 3rd threshold value is less than the 4th threshold value;
Image mean-squared deviation meets the decision condition corresponding with it and comprises: the ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is all not more than Second Threshold, image mean-squared deviation is greater than the 5th threshold value, or
The ratio that the pixel count of brightness section that any one is preset in gradation of image Distribution value accounts for total pixel number is greater than Second Threshold, image mean-squared deviation is greater than the 6th threshold value, and wherein, the 5th threshold value is less than the 6th threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410852729.1A CN104506968B (en) | 2014-12-31 | 2014-12-31 | A kind of video frequency abstract figure determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410852729.1A CN104506968B (en) | 2014-12-31 | 2014-12-31 | A kind of video frequency abstract figure determines method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104506968A true CN104506968A (en) | 2015-04-08 |
| CN104506968B CN104506968B (en) | 2018-08-07 |
Family
ID=52948672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410852729.1A Active CN104506968B (en) | 2014-12-31 | 2014-12-31 | A kind of video frequency abstract figure determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104506968B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516735A (en) * | 2015-12-11 | 2016-04-20 | 小米科技有限责任公司 | Representation frame acquisition method and representation frame acquisition apparatus |
| CN105847816A (en) * | 2016-04-01 | 2016-08-10 | 广州华多网络科技有限公司 | Video file thumbnail creation method and electronic device |
| CN106101868A (en) * | 2016-07-18 | 2016-11-09 | 乐视控股（北京）有限公司 | Reduced graph generating method and generating means |
| CN106331786A (en) * | 2016-08-22 | 2017-01-11 | 暴风集团股份有限公司 | Method and system for displaying playlist in image-text mode |
| CN106604126A (en) * | 2016-12-20 | 2017-04-26 | 天脉聚源(北京)传媒科技有限公司 | Intelligent video screenshot capture method and device |
| WO2020052084A1 (en) * | 2018-09-13 | 2020-03-19 | 北京字节跳动网络技术有限公司 | Video cover selection method, device and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040035128A (en) * | 2002-10-18 | 2004-04-29 | 엘지전자 주식회사 | Apparatus for generating thumbnail image of digital video |
| US20080046406A1 (en) * | 2006-08-15 | 2008-02-21 | Microsoft Corporation | Audio and video thumbnails |
| CN101483763A (en) * | 2008-12-16 | 2009-07-15 | 南京大学 | Digital video processing method oriented to social security monitoring and apparatus thereof |
| CN101853286A (en) * | 2010-05-20 | 2010-10-06 | 上海全土豆网络科技有限公司 | Intelligent selection method of video thumbnails |
| CN102523536A (en) * | 2011-12-15 | 2012-06-27 | 清华大学 | Video semantic visualization method |
-
2014
- 2014-12-31 CN CN201410852729.1A patent/CN104506968B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040035128A (en) * | 2002-10-18 | 2004-04-29 | 엘지전자 주식회사 | Apparatus for generating thumbnail image of digital video |
| US20080046406A1 (en) * | 2006-08-15 | 2008-02-21 | Microsoft Corporation | Audio and video thumbnails |
| CN101483763A (en) * | 2008-12-16 | 2009-07-15 | 南京大学 | Digital video processing method oriented to social security monitoring and apparatus thereof |
| CN101853286A (en) * | 2010-05-20 | 2010-10-06 | 上海全土豆网络科技有限公司 | Intelligent selection method of video thumbnails |
| CN102523536A (en) * | 2011-12-15 | 2012-06-27 | 清华大学 | Video semantic visualization method |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516735A (en) * | 2015-12-11 | 2016-04-20 | 小米科技有限责任公司 | Representation frame acquisition method and representation frame acquisition apparatus |
| CN105516735B (en) * | 2015-12-11 | 2019-03-22 | 小米科技有限责任公司 | Represent frame acquisition methods and device |
| CN105847816A (en) * | 2016-04-01 | 2016-08-10 | 广州华多网络科技有限公司 | Video file thumbnail creation method and electronic device |
| CN105847816B (en) * | 2016-04-01 | 2019-07-12 | 广州华多网络科技有限公司 | The creation method and electronic device of video file thumbnail |
| CN106101868A (en) * | 2016-07-18 | 2016-11-09 | 乐视控股（北京）有限公司 | Reduced graph generating method and generating means |
| CN106331786A (en) * | 2016-08-22 | 2017-01-11 | 暴风集团股份有限公司 | Method and system for displaying playlist in image-text mode |
| CN106604126A (en) * | 2016-12-20 | 2017-04-26 | 天脉聚源(北京)传媒科技有限公司 | Intelligent video screenshot capture method and device |
| WO2020052084A1 (en) * | 2018-09-13 | 2020-03-19 | 北京字节跳动网络技术有限公司 | Video cover selection method, device and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104506968B (en) | 2018-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104506968A (en) | Method and device for determining video abstract figure | |
| US9674425B2 (en) | Image acquisition method and apparatus | |
| CN103916603B (en) | Backlighting detecting and equipment | |
| US20150363913A1 (en) | Adaptive filter demosaicizing for super resolution | |
| US20150154763A1 (en) | Control system and method for controlling background colors for mobile terminal | |
| CN104349045B (en) | A kind of image-pickup method and electronic equipment | |
| JP2016510140A (en) | Method and apparatus for determining the afterimage level of a display | |
| CN104301624A (en) | Image shooting brightness control method and device | |
| CN109686342B (en) | Image processing method and device | |
| CN110084155B (en) | Method, device and equipment for counting dense people and storage medium | |
| CN104243992B (en) | Image processing apparatus and image processing method | |
| US8970591B2 (en) | Memory efficient progressive refinement in ray tracing | |
| CN103702059A (en) | Frame rate conversion control method and device | |
| CN103076954B (en) | The method of adjustment display effect and device | |
| CN103530431A (en) | Data processing method and device for webpage clicking amount statistics | |
| CN105446692A (en) | Seam compensation method and device of spliced screen | |
| CN103559278A (en) | Data processing method and device for webpage page click quantity statistics | |
| WO2022271269A1 (en) | Hierarchical grid interpolation systems and methods | |
| KR20120015980A (en) | Method, system and computer program product for object color correction | |
| CN109274950A (en) | Image processing method, device and electronic equipment | |
| CN104978731A (en) | Information processing method and electronic equipment | |
| CN110751703A (en) | Winding picture generation method, device, equipment and storage medium | |
| Tian et al. | A fractional-order Laplacian operator for image edge detection | |
| CN109740337A (en) | A kind of method and device for realizing the identification of sliding block identifying code | |
| CN105487853A (en) | Method and system for creating application shortcut in screen-locking interface |
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 |