CN105072455A - Video matching method and device - Google Patents
Video matching method and device Download PDFInfo
- Publication number
- CN105072455A CN105072455A CN201510491385.0A CN201510491385A CN105072455A CN 105072455 A CN105072455 A CN 105072455A CN 201510491385 A CN201510491385 A CN 201510491385A CN 105072455 A CN105072455 A CN 105072455A
- Authority
- CN
- China
- Prior art keywords
- picture frame
- cut
- video
- away view
- view picture
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000006641 stabilisation Effects 0.000 claims description 49
- 238000011105 stabilization Methods 0.000 claims description 49
- 230000002123 temporal effect Effects 0.000 claims description 8
- 230000001154 acute effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- 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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Television Signal Processing For Recording (AREA)
Abstract
The invention discloses a video matching method and device. The method comprises the following steps: acquiring a first intercepted image frame of a video to be matched within preset duration from an interception moment; acquiring the image stability of the first intercepted image frame, and acquiring a corresponding time period of the first intercepted image frame in the video to be matched if the image stability is greater than or equal to a preset threshold; acquiring a second intercepted image frame within a corresponding time period in a preset standard video; and comparing each image frame of the first intercepted image frame and the second intercepted image at the same moment one by one, and judging whether or not the video to be matched is matched with the standard video according to a comparison result. Through adoption of the video matching method and device, the video to be matched does not need to be subjected to a great amount of screen capture, and the video matching accuracy can be increased.
Description
Technical field
The present invention relates to mobile communication technology, particularly relate to a kind of video matching method and device.
Background technology
It is famous that video transmits aboundresources with it, can not only transmit many-sided demand, can also rendered atmosphere.But the phenomenons such as the cheating of video in the Internet, content of copyright bootlegging broadcasting are transcribed, the broadcasting of illicit video content happen occasionally, therefore, carrying out coupling retrieval for video becomes and prevents internet video from practising fraud, and safeguards the important means of copyright.There is corresponding specification in the input due to internet video, the normal video therefore taken by the video that comprises in internet video and video frequency searching manufacturer can exist the deviation of to two second.
In prior art, be generally that multiple sectional drawings of video to be matched are mated with the sectional drawing intercepted in normal video, verify that whether video to be matched is same video with normal video.But because video is dynamic image, scene switches frequent, even the time at several seconds zero point, also can there is video scene and switch very large situation.Therefore, matching process of the prior art is very easy to miss the picture identical with truncated picture in normal video, causes the problem that video matching accuracy rate is low.
Summary of the invention
The object of this invention is to provide a kind of video matching and device, be very easy to miss the picture identical with truncated picture in normal video in order to solve matching process of the prior art, cause the problem that video matching accuracy rate is low.
For achieving the above object, one aspect of the present invention provides video matching method, comprising:
Obtaining video to be matched intercepting the moment plays the first cut-away view picture frame in preset duration;
Obtain the image stabilization degree of described first cut-away view picture frame, judge whether described image stabilization degree is more than or equal to predetermined threshold value, if described image stabilization degree is more than or equal to predetermined threshold value, then obtain the described corresponding time period of the first cut-away view picture frame in described video to be matched;
Obtain the second cut-away view picture frame within the described corresponding time period in the normal video preset;
Described first cut-away view picture frame and described second cut-away view picture frame phase each picture frame are in the same time contrasted one by one, and judges whether described video to be matched mates with described normal video according to comparing result.
Another aspect provides a kind of video matching device, comprising: the first acquiring unit, playing the first cut-away view picture frame in preset duration for obtaining video to be matched intercepting the moment;
Second acquisition unit, for obtaining the image stabilization degree of described first cut-away view picture frame, judge whether described image stabilization degree is more than or equal to predetermined threshold value, if described image stabilization degree is more than or equal to predetermined threshold value, then obtain the described corresponding time period of the first cut-away view picture frame in described video to be matched;
3rd acquiring unit, for obtaining the second cut-away view picture frame in default normal video within the described corresponding time period;
According to comparing result, matching unit, for described first cut-away view picture frame and described second cut-away view picture frame phase each picture frame in the same time being contrasted one by one, and judges whether described video to be matched mates with described normal video.
From above technical scheme, video matching method provided by the invention and device, the cut-away view picture frame of predetermined threshold value is more than or equal to by obtaining image stabilization degree, namely video Scene to be matched is stablized, there is no the cut-away view picture frame of acute variation, thus carry out a large amount of sectional drawings without the need to treating match video, further, by being greater than the cut-away view picture frame of predetermined threshold value to image stabilization degree, namely contrast one by one with the first cut-away view picture frame phase each picture frame in the same time in the first cut-away view picture frame and normal video, if now normal video and video to be matched are same videos, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in the accuracy rate of video to be matched and normal video video matching, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
Accompanying drawing explanation
The flow chart of the video matching method that Fig. 1 provides for the embodiment of the present invention;
Fig. 2 is the flow chart of the video matching method that further embodiment of this invention provides;
Fig. 3 implements the structural representation of the video matching device provided for the present invention one;
Fig. 4 is the present invention's structural representation implementing the video matching device provided again.
Embodiment
Embodiment one
The flow chart of the video matching method that Fig. 1 provides for the embodiment of the present invention, before describing the specific embodiment of the present invention in detail, simply introduce wherein a kind of application scenarios of the present invention, some manufacturers are wanted to carry out advertisement putting in some video website, but play tricks to prevent advertisement putting website, want the advertisement adding up oneself to throw in before which video actually, will to the advertisement of first extracting each video and loading above, then utilize video matching technology to mate, thus acquisition there are how many videos to throw in oneself advertisement actually.As shown in Figure 1, this video matching method comprises:
Step 101, obtains video to be matched intercepting the moment and plays the first cut-away view picture frame in preset duration.
Wherein, video to be matched is the video obtained from the massive video of internet site, and such as, can be the advertisement video etc. before some serials, variety show, these video ads general time be all between 5 seconds-120 seconds.Wherein, intercepting the moment to refer in the first cut-away view picture frame the first two field picture by the moment intercepted, in general, when first time obtains the first cut-away view picture frame, intercept from the initial time of video to be matched time usual, preset duration can be chosen according to actual needs.Wherein, the frame period time between each frame of the first sectional drawing picture frame is equal, and certain frame period time also can not be waited.
Step 102, obtains the image stabilization degree of the first cut-away view picture frame, judges whether image stabilization degree is more than or equal to predetermined threshold value, if image stabilization degree is more than or equal to predetermined threshold value, then obtains the corresponding time period of the first cut-away view picture frame in video to be matched.
Wherein image stabilization degree represents the similarity degree between each frame of cut-away view picture frame, also can be called image similarity, concrete, explains that image stabilization degree being described with following example.
If the first cut-away view picture frame comprises five two field pictures, first moment corresponding first two field picture, second moment corresponding second two field picture, the like, 5th moment corresponding 5th two field picture, the rear image in a moment and the image of previous moment are contrasted, concrete can judge to compare the gray value of two two field pictures or the difference of color, if the difference between each frame of this five two field picture within the specific limits, then think that the first cut-away view picture frame picture when playing is comparatively stable, do not have violent change, also namely image stabilization degree is more than or equal to predetermined threshold value.Now, obtain the corresponding time period of the first cut-away view picture frame in video to be matched, specifically how searching the corresponding time period of the first cut-away view picture frame in be matched can adopt any means of the prior art, does not repeat them here.
Step 103, obtains the second cut-away view picture frame within the above-mentioned corresponding time period in the normal video preset.
Wherein, normal video is the normal video for video matching stored in a database, such as, be exactly advertisement video, is normally provided by the owner or input business with this video copy.And, generally speaking this normal video is normally without the video of any editing, such as, in the advertisement putting of the Internet, the time of advertisement video requires it is the integral multiple of 5 seconds usually, therefore may carry out certain editing to advertisement video in the process of throwing in, normal video is then the video without editing, and this is also the reason causing the time difference that to have to two second between video to be matched and normal video.
Wherein, if the first cut-away view picture frame is from the 0.3rd second of video to be matched, preset duration is 2 seconds, then obtain normal video and the second cut-away view picture frame in the first cut-away view picture frame corresponding time period accordingly, namely will obtain the cut-away view picture frame of the 0.3rd second to the 2.3rd second of normal video.
Step 104, contrasts the first cut-away view picture frame and the second cut-away view picture frame phase each picture frame in the same time one by one, and judges whether video to be matched mates with normal video according to comparing result.
Concrete, each picture frame contrasts one by one and refers to, if include five two field pictures in the first cut-away view picture frame and the second cut-away view picture frame, then the first two field picture in the first two field picture in the first cut-away view picture frame and the second cut-away view picture frame is contrasted, the second two field picture in the second two field picture in first cut-away view picture frame and the second cut-away view picture frame contrasts, the like.
Can find out, if treat match video in prior art to carry out sectional drawing every 0.2 second, between this 0.2 second, then likely there is the change of video scene thus cause missing the picture identical with truncated picture in normal video, thus the problem causing the accuracy rate of video matching too low, even and if treat match video in video matching method in the present embodiment and carried out sectional drawing every 0.2 second, as long as ensure that the first cut-away view picture frame is that scene is stablized, there is no the cut-away view picture frame of acute variation, on this basis, first cut-away view picture frame and the second cut-away view picture frame phase each picture frame are in the same time contrasted one by one, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in video to be matched and normal video, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
The video matching method that the present embodiment provides has following technique effect, the cut-away view picture frame of predetermined threshold value is more than or equal to by obtaining image stabilization degree, namely video Scene to be matched is stablized, there is no the cut-away view picture frame of acute variation, thus carry out a large amount of sectional drawings without the need to treating match video, further, by being greater than the cut-away view picture frame of predetermined threshold value to image stabilization degree, namely contrast one by one with the first cut-away view picture frame phase each picture frame in the same time in the first cut-away view picture frame and normal video, if now normal video and video to be matched are same videos, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in the accuracy rate of video to be matched and normal video video matching, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
Embodiment two
The present embodiment does further supplementary notes to above-described embodiment.Fig. 2 is the flow chart of the video matching method that further embodiment of this invention provides, and the method comprises:
Step 201, obtains video to be matched intercepting the moment and plays the first cut-away view picture frame in preset duration.
This step is consistent with step 101, does not repeat them here.
Step 202, obtains the image stabilization degree of the first cut-away view picture frame, judges whether image stabilization degree is more than or equal to predetermined threshold value, if image stabilization degree is more than or equal to predetermined threshold value, transfers step 204 to, otherwise transfer step 203 to.
Step 203, then obtain video to be matched intercepting the subsequent time in moment and play the 3rd cut-away view picture frame in preset duration, and the 3rd cut-away view picture frame is updated to the first cut-away view picture frame, return and perform step 201, transfer step 204 to.
Wherein, the time interval intercepted between moment and subsequent time is exactly the time interval between the first cut-away view picture frame between each frame.And, when acquisition the 3rd cut-away view picture frame, only need obtain a rear frame of the last frame of the first cut-away view picture frame, for example, if the first cut-away view picture frame comprises the first picture frame, second picture frame, 3rd picture frame, the intercepting moment of the first picture frame is the 18th second, the moment of the second picture frame in video to be matched is the 19th second, 3rd moment of picture frame in video to be matched was the 20th second, when the image stabilization degree of the first cut-away view picture frame obtained is less than predetermined threshold value, only need intercept a rear frame of the 3rd picture frame, namely the image of the 21st second of video to be matched is intercepted, now the second picture frame, 3rd picture frame, 4th picture frame i.e. the 3rd cut-away view picture frame, now be updated to the first picture frame with the 3rd cut-away view picture frame.Return and perform step 201, till getting image stabilization degree and being more than or equal to the first cut-away view picture frame of predetermined threshold value.
Step 204, obtains the second cut-away view picture frame within the described corresponding time period in the normal video preset.
This step is consistent with step 103, does not repeat them here.
Step 205, contrasts described first cut-away view picture frame and described second cut-away view picture frame phase each picture frame in the same time one by one, and judges whether described video to be matched mates with described normal video according to comparing result.
This step is consistent with step 104, does not repeat them here.
Wherein, judge that whether video to be matched mates with normal video according to comparing result to comprise: judge whether the quantity of the picture frame that the first cut-away view picture frame is similar to the second cut-away view picture frame is more than or equal to pre-determined threshold, if the determination result is YES, then determine that this video to be matched mates with normal video, namely this video to be matched and normal video are same videos.
For example, if include five two field pictures in the first cut-away view picture frame and the second cut-away view picture frame, if when the first cut-away view picture frame and the second cut-away view picture frame contrast, similar more than three two field pictures, namely when the quantity of similar picture frame is more than or equal to pre-determined threshold, then think that this video to be matched and normal video are same videos.The number of frames here comprised in the picture frame of video to be matched i.e. the first cut-away view picture frame can be selected according to actual, optionally, the preset duration of the first cut-away view picture frame is 1 to 2 second, the time interval between each frame of first cut-away view picture frame is 0.2 second, namely count from intercepting the moment, first cut-away view picture frame can comprise five two field pictures, due to the frame frequency of video camera when taking and the restriction of real scene, in general, through the first cut-away view picture frame that 2 can be found image stabilization degree to be more than or equal to predetermined threshold value for several seconds, therefore such benefit is that the time due to the first cut-away view picture frame is not long, the number of times of sectional drawing can be reduced, and preset duration can be prevented long, the first cut-away view picture frame that image stabilization degree is more than or equal to predetermined threshold value has multiple, cause the prolongation of video matching time.
The video matching method that the present embodiment provides obtains the cut-away view picture frame that image stabilization degree is more than or equal to predetermined threshold value, namely video Scene to be matched is stablized, there is no the cut-away view picture frame of acute variation, thus carry out a large amount of sectional drawings without the need to treating match video, further, by being greater than the cut-away view picture frame of predetermined threshold value to image stabilization degree, namely contrast one by one with the first cut-away view picture frame phase each picture frame in the same time in the first cut-away view picture frame and normal video, if now normal video and video to be matched are same videos, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in video to be matched and normal video, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
Embodiment three
The present embodiment is the supplementary notes to above-described embodiment.After determining that video to be matched mates with described normal video, also comprise: the second cut-away view picture frame, the temporal information of the second cut-away view picture frame in normal video are stored to database.Such object is, when second time carries out video matching, this the second cut-away view picture frame and its temporal information in normal video can be directly obtained from database, the i.e. corresponding time period of the second cut-away view picture frame in normal video, directly contrast one by one with each picture frame of the second cut-away view picture frame each picture frame with the 4th cut-away view picture frame of new video to be matched within the above-mentioned corresponding time period.For example, such as get the second cut-away view picture frame in the above-described embodiments in normal video from the 2.1st second, 4.1st second terminates, if when now again having new video to be matched to need to mate, only need the 4th cut-away view picture frame of the 2.1st second to the 4.1st second intercepting new video to be matched, compare with this second cut-away view picture frame, concrete control methods is consistent with above-described embodiment, does not repeat them here.Thus when mass data is mated, data processing amount can be reduced, improve matching efficiency.
The video matching method that the present embodiment provides not only can improve the accuracy rate of video matching, by the second cut-away view picture frame, the temporal information of the second cut-away view picture frame in normal video are stored to database thus can improve video matching efficiency when massive video is mated.
Embodiment four
Fig. 3 implements the structural representation of the video matching device provided, for performing the video matching method of embodiment one for the present invention one.As shown in Figure 3, this video matching device comprises the first acquiring unit 301, second acquisition unit 302, the 3rd acquiring unit 303 and matching unit 304.
Wherein, the first acquiring unit 301 plays the first cut-away view picture frame in preset duration for obtaining video to be matched intercepting the moment.
Wherein, video to be matched is the video obtained from the massive video of internet site, such as, can be the advertisement video etc. before some serials, variety show.Wherein, intercepting the moment to refer in the first cut-away view picture frame the first two field picture by the moment intercepted, in general, first acquiring unit 301 is when first time obtains the first cut-away view picture frame, intercept from the initial time of video to be matched time usual, preset duration can be chosen according to actual needs.Wherein, the frame period time between each frame of the first sectional drawing picture frame is equal.
Second acquisition unit 302 is connected with the first acquiring unit 301, for obtaining the image stabilization degree of the first cut-away view picture frame, judge whether image stabilization degree is more than or equal to predetermined threshold value, if image stabilization degree is more than or equal to predetermined threshold value, then obtain the corresponding time period of the first cut-away view picture frame in video to be matched.
Specifically can participate in the explanation in the embodiment one of video matching method for the explanation of image stabilization degree, not repeat them here.
3rd acquiring unit 303 is for obtaining the second cut-away view picture frame in default normal video within the corresponding time period.The corresponding time period can be sent to the 3rd acquiring unit 303 by the first acquiring unit 301, also can be obtained from the first acquiring unit 301 by second acquisition unit 302 and be forwarded to the 3rd acquiring unit 303.
Matching unit 304 is connected with second acquisition unit 302 and the 3rd acquiring unit 303 respectively, for the first cut-away view picture frame and the second cut-away view picture frame phase each picture frame in the same time being contrasted one by one, and judge whether video to be matched mates with normal video according to comparing result.
Concrete, each picture frame contrasts one by one and refers to, if include five two field pictures in the first cut-away view picture frame and the second cut-away view picture frame, the first two field picture in the first two field picture in first cut-away view picture frame and the second cut-away view picture frame contrasts by matching unit 304, the second two field picture in the second two field picture in first cut-away view picture frame and the second cut-away view picture frame contrasts, the like.
Can find out, if treat match video in prior art to carry out sectional drawing every 1 second, then the interval of sectional drawing is excessive, easily cause the problem that the accuracy rate of video matching is too low, even and if treat match video in video matching method in the present embodiment and carried out sectional drawing every 1 second, as long as ensure that the first cut-away view picture frame is that scene is stablized, there is no the cut-away view picture frame of acute variation, on this basis, matching unit 304 contrasts one by one to the first cut-away view picture frame and the second cut-away view picture frame phase each picture frame in the same time, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in video to be matched and normal video, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
The video matching device that the present embodiment provides is more than or equal to the cut-away view picture frame of predetermined threshold value by obtaining image stabilization degree, namely video Scene to be matched is stablized, there is no the cut-away view picture frame of acute variation, thus carry out a large amount of sectional drawings without the need to treating match video, further, matching unit 304 is by being greater than the cut-away view picture frame of predetermined threshold value to image stabilization degree, namely contrast one by one with the first cut-away view picture frame phase each picture frame in the same time in the first cut-away view picture frame and normal video, if now normal video and video to be matched are same videos, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in the accuracy rate of video to be matched and normal video video matching, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
Embodiment five
The present embodiment is the further explanation explanation to above-described embodiment.The video matching device of the present embodiment comprises the first acquiring unit 301, second acquisition unit 302, the 3rd acquiring unit 303 and matching unit 304.
With above-described embodiment unlike, second acquisition unit 302 in the present embodiment is also for when image stabilization degree is less than predetermined threshold value, obtaining video to be matched intercepting the subsequent time in moment plays the 3rd cut-away view picture frame in preset duration, and the 3rd cut-away view picture frame is updated to the first cut-away view picture frame.Now again obtain the image stabilization degree of the first cut-away view picture frame, until get the first cut-away view picture frame that image stabilization degree is more than or equal to predetermined threshold value.
Matching unit 304 is specifically for judging whether the quantity of the picture frame that the first cut-away view picture frame is similar to the second cut-away view picture frame is more than or equal to pre-determined threshold, if the determination result is YES, then determines that video to be matched mates with normal video.
For example, if include five two field pictures in the first cut-away view picture frame and the second cut-away view picture frame, if when the first cut-away view picture frame and the second cut-away view picture frame contrast, similar more than three two field pictures, namely when the quantity of similar picture frame is more than or equal to pre-determined threshold, then think that this video to be matched and normal video are same videos.The number of frames here comprised in the picture frame of video to be matched i.e. the first cut-away view picture frame can be selected according to actual, optionally, the preset duration of the first cut-away view picture frame is 1 to 2 second, the time interval between each frame of first cut-away view picture frame is 0.2 second, namely count from intercepting the moment, first cut-away view picture frame can comprise five two field pictures, due to the frame frequency of video camera when taking and the restriction of real scene, in general, through the first cut-away view picture frame that 2 can be found image stabilization degree to be more than or equal to predetermined threshold value for several seconds, therefore such benefit is that the time due to the first cut-away view picture frame is not long, the number of times of sectional drawing can be reduced, and preset duration can be prevented long, the first cut-away view picture frame that image stabilization degree is more than or equal to predetermined threshold value has multiple, the video matching device causing prolongation the present embodiment of video matching time to provide is greater than the cut-away view picture frame of predetermined threshold value by obtaining image stabilization degree, namely video Scene to be matched is stablized, there is no the cut-away view picture frame of acute variation, thus carry out a large amount of sectional drawings without the need to treating match video, further, matching unit 304 is by being more than or equal to the cut-away view picture frame of predetermined threshold value to image stabilization degree, namely contrast one by one with the first cut-away view picture frame phase each picture frame in the same time in the first cut-away view picture frame and normal video, if now normal video and video to be matched are same videos, because the scene of the first cut-away view picture frame is stablized, even if there is the deviation of to two second in the accuracy rate of video to be matched and normal video video matching, also still have wherein a few frames can the match is successful, thus the accuracy rate of video matching can be improved.
Embodiment six
Fig. 4 is the present invention's structural representation implementing the video matching device provided again, and this device comprises: the first acquiring unit 501, second acquisition unit 502, the 3rd acquiring unit 503, matching unit 504 and memory cell 505.Wherein, memory cell 505 is connected with the 3rd acquiring unit 503, for the second cut-away view picture frame, the temporal information of the second cut-away view picture frame in normal video are stored to database.Concrete, when second time carries out video matching, first acquiring unit 501 can directly obtain this second cut-away view picture frame and its temporal information in normal video from database, the i.e. corresponding time period of the second cut-away view picture frame in normal video, matching unit 504 directly contrasts one by one with each picture frame of the second cut-away view picture frame each picture frame with the 4th cut-away view picture frame of new video to be matched within the above-mentioned corresponding time period.For example, such as get the second cut-away view picture frame in the above-described embodiments in normal video from the 2.1st second, 2.6th second terminates, if when now again having new video to need to mate, first acquiring unit 501 needs the 4th cut-away view picture frame of the 2.1st second to the 2.6th second intercepting new video, and matching unit 504 is compared with the 4th cut-away view picture frame and this second cut-away view picture frame.Thus when mass data is mated, data processing amount can be reduced, improve matching efficiency.
The effect of the first acquiring unit 501, second acquisition unit 502, the 3rd acquiring unit 503 is distinguished identical with above-described embodiment first acquiring unit 301, second acquisition unit 302 with the 3rd acquiring unit 303, can refer to above-described embodiment.
The video matching device that the present embodiment provides not only can improve the accuracy rate of video matching, by the second cut-away view picture frame, the temporal information of the second cut-away view picture frame in normal video are stored to database thus can improve video matching efficiency when massive video is mated.
Last it is noted that above embodiment is only in order to illustrate technical scheme of the present invention, be not intended to limit; Although with reference to previous embodiment to invention has been detailed description, the ordinary skill passenger of this area is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (9)
1. a video matching method, is characterized in that, comprising:
Obtaining video to be matched intercepting the moment plays the first cut-away view picture frame in preset duration;
Obtain the image stabilization degree of described first cut-away view picture frame, judge whether described image stabilization degree is more than or equal to predetermined threshold value, if described image stabilization degree is more than or equal to predetermined threshold value, then obtain the described corresponding time period of the first cut-away view picture frame in described video to be matched;
Obtain the second cut-away view picture frame within the described corresponding time period in the normal video preset;
Described first cut-away view picture frame and described second cut-away view picture frame phase each picture frame are in the same time contrasted one by one, and judges whether described video to be matched mates with described normal video according to comparing result.
2. video matching method according to claim 1, is characterized in that, after the image stabilization degree of the described first cut-away view picture frame of described acquisition, also comprises:
If described image stabilization degree is less than predetermined threshold value, then obtain video to be matched and play the 3rd cut-away view picture frame in preset duration at the subsequent time in described intercepting moment, and described 3rd cut-away view picture frame is updated to described first cut-away view picture frame, return the step performing the image stabilization degree obtaining described first cut-away view picture frame.
3. video matching method according to claim 1, is characterized in that, described preset duration is between 1 to 2 second, and the time interval between each frame of described first cut-away view picture frame is 0.2 second.
4. video matching method according to claim 1, is characterized in that, judges that whether described video to be matched mates with described normal video comprise according to comparing result:
Judge whether the quantity of the picture frame that described first cut-away view picture frame is similar to described second cut-away view picture frame is more than or equal to pre-determined threshold;
If the determination result is YES, then determine that described video to be matched mates with described normal video.
5. video matching method according to claim 1, is characterized in that, after determining that described video to be matched mates with described normal video, also comprises:
Described second cut-away view picture frame, the temporal information of the second cut-away view picture frame in described normal video are stored to database.
6. a video matching device, is characterized in that, comprising:
First acquiring unit, plays the first cut-away view picture frame in preset duration for obtaining video to be matched intercepting the moment;
Second acquisition unit, for obtaining the image stabilization degree of described first cut-away view picture frame, judge whether described image stabilization degree is more than or equal to predetermined threshold value, if described image stabilization degree is more than or equal to predetermined threshold value, then obtain the described corresponding time period of the first cut-away view picture frame in described video to be matched;
3rd acquiring unit, for obtaining the second cut-away view picture frame in default normal video within the described corresponding time period;
According to comparing result, matching unit, for described first cut-away view picture frame and described second cut-away view picture frame phase each picture frame in the same time being contrasted one by one, and judges whether described video to be matched mates with described normal video.
7. video matching device according to claim 6, it is characterized in that, described second acquisition unit is also for when described image stabilization degree is less than predetermined threshold value, obtain video to be matched and play the 3rd cut-away view picture frame in preset duration at the subsequent time in described intercepting moment, and described 3rd cut-away view picture frame is updated to described first cut-away view picture frame, return the step performing the image stabilization degree obtaining described first cut-away view picture frame.
8. video matching device according to claim 6, is characterized in that, described matching unit is specifically for judging whether the quantity of the picture frame that described first cut-away view picture frame is similar to described second cut-away view picture frame is more than or equal to pre-determined threshold; If the determination result is YES, then determine that described video to be matched mates with described normal video.
9. video matching device according to claim 6, is characterized in that, also comprises:
Memory cell, for being stored to database by described second cut-away view picture frame, the temporal information of the second cut-away view picture frame in described normal video.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510491385.0A CN105072455A (en) | 2015-08-11 | 2015-08-11 | Video matching method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510491385.0A CN105072455A (en) | 2015-08-11 | 2015-08-11 | Video matching method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105072455A true CN105072455A (en) | 2015-11-18 |
Family
ID=54501715
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510491385.0A Pending CN105072455A (en) | 2015-08-11 | 2015-08-11 | Video matching method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105072455A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105657547A (en) * | 2015-12-31 | 2016-06-08 | 北京奇艺世纪科技有限公司 | Detection method and device for similar video and pirated video |
CN105681898A (en) * | 2015-12-31 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Similar video and pirated video detection method and device |
CN105681899A (en) * | 2015-12-31 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Method and device for detecting similar video and pirated video |
CN107944754A (en) * | 2017-12-13 | 2018-04-20 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment of rehabilitation performance rating |
CN108737812A (en) * | 2017-04-19 | 2018-11-02 | 中国移动通信有限公司研究院 | A kind of test method and device of video quality |
CN108875619A (en) * | 2018-06-08 | 2018-11-23 | Oppo广东移动通信有限公司 | Method for processing video frequency and device, electronic equipment, computer readable storage medium |
CN110020588A (en) * | 2019-01-28 | 2019-07-16 | 深圳市睿智物联科技有限公司 | A kind of building screen lamps and lanterns monitoring method and system based on video identification |
CN111597863A (en) * | 2019-02-21 | 2020-08-28 | 顺丰科技有限公司 | Loading and unloading rate determining method, system, equipment and storage medium |
CN112437344A (en) * | 2020-10-30 | 2021-03-02 | 福建星网视易信息系统有限公司 | Video matching method and terminal |
CN112907657A (en) * | 2021-03-05 | 2021-06-04 | 科益展智能装备有限公司 | Robot repositioning method, device, equipment and storage medium |
CN113347082A (en) * | 2021-08-06 | 2021-09-03 | 深圳康易世佳科技有限公司 | Method and device for intelligently displaying shared messages containing short videos |
CN116017077A (en) * | 2022-12-12 | 2023-04-25 | 北京奇艺世纪科技有限公司 | Direct playing method and device, electronic equipment and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1574019A (en) * | 2003-06-23 | 2005-02-02 | 精工爱普生株式会社 | Method and apparatus for video copy detection |
US20060182368A1 (en) * | 2005-01-21 | 2006-08-17 | Changick Kim | Efficient and robust algorithm for video sequence matching |
CN101374234A (en) * | 2008-09-25 | 2009-02-25 | 清华大学 | Method and apparatus for monitoring video copy base on content |
CN101394522A (en) * | 2007-09-19 | 2009-03-25 | 中国科学院计算技术研究所 | Detection method and system for video copy |
CN101833650A (en) * | 2009-03-13 | 2010-09-15 | 清华大学 | Video copy detection method based on contents |
CN101872415A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Video copying detection method being suitable for IPTV |
US20120143915A1 (en) * | 2009-10-01 | 2012-06-07 | Crim (Centre De Rechrche Informatique De Montreal) | Content-based video copy detection |
CN102523482A (en) * | 2011-12-07 | 2012-06-27 | 中山大学 | Advertisement monitoring technology based on video content and regression method |
CN102760169A (en) * | 2012-06-13 | 2012-10-31 | 天脉聚源(北京)传媒科技有限公司 | Method for detecting advertising slots in television direct transmission streams |
CN103390040A (en) * | 2013-07-17 | 2013-11-13 | 南京邮电大学 | Video copy detection method |
CN103686345A (en) * | 2013-12-18 | 2014-03-26 | 北京航天测控技术有限公司 | Video content comparing method based on digital signal processor |
CN104185017A (en) * | 2013-05-23 | 2014-12-03 | 中国科学院深圳先进技术研究院 | Video matching method and system |
-
2015
- 2015-08-11 CN CN201510491385.0A patent/CN105072455A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1574019A (en) * | 2003-06-23 | 2005-02-02 | 精工爱普生株式会社 | Method and apparatus for video copy detection |
US20060182368A1 (en) * | 2005-01-21 | 2006-08-17 | Changick Kim | Efficient and robust algorithm for video sequence matching |
CN101394522A (en) * | 2007-09-19 | 2009-03-25 | 中国科学院计算技术研究所 | Detection method and system for video copy |
CN101374234A (en) * | 2008-09-25 | 2009-02-25 | 清华大学 | Method and apparatus for monitoring video copy base on content |
CN101833650A (en) * | 2009-03-13 | 2010-09-15 | 清华大学 | Video copy detection method based on contents |
US20120143915A1 (en) * | 2009-10-01 | 2012-06-07 | Crim (Centre De Rechrche Informatique De Montreal) | Content-based video copy detection |
CN101872415A (en) * | 2010-05-06 | 2010-10-27 | 复旦大学 | Video copying detection method being suitable for IPTV |
CN102523482A (en) * | 2011-12-07 | 2012-06-27 | 中山大学 | Advertisement monitoring technology based on video content and regression method |
CN102760169A (en) * | 2012-06-13 | 2012-10-31 | 天脉聚源(北京)传媒科技有限公司 | Method for detecting advertising slots in television direct transmission streams |
CN104185017A (en) * | 2013-05-23 | 2014-12-03 | 中国科学院深圳先进技术研究院 | Video matching method and system |
CN103390040A (en) * | 2013-07-17 | 2013-11-13 | 南京邮电大学 | Video copy detection method |
CN103686345A (en) * | 2013-12-18 | 2014-03-26 | 北京航天测控技术有限公司 | Video content comparing method based on digital signal processor |
Non-Patent Citations (1)
Title |
---|
张三义等: "基于ORB和灰度序特征的视频拷贝检测", 《计算机应用研究》 * |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105657547B (en) * | 2015-12-31 | 2019-05-10 | 北京奇艺世纪科技有限公司 | A kind of detection method and device of similar video and pirate video |
CN105681899A (en) * | 2015-12-31 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Method and device for detecting similar video and pirated video |
CN105657547A (en) * | 2015-12-31 | 2016-06-08 | 北京奇艺世纪科技有限公司 | Detection method and device for similar video and pirated video |
CN105681899B (en) * | 2015-12-31 | 2019-05-10 | 北京奇艺世纪科技有限公司 | A kind of detection method and device of similar video and pirate video |
CN105681898B (en) * | 2015-12-31 | 2018-10-30 | 北京奇艺世纪科技有限公司 | A kind of detection method and device of similar video and pirate video |
CN105681898A (en) * | 2015-12-31 | 2016-06-15 | 北京奇艺世纪科技有限公司 | Similar video and pirated video detection method and device |
CN108737812A (en) * | 2017-04-19 | 2018-11-02 | 中国移动通信有限公司研究院 | A kind of test method and device of video quality |
CN107944754A (en) * | 2017-12-13 | 2018-04-20 | 泰康保险集团股份有限公司 | Method, apparatus, storage medium and the electronic equipment of rehabilitation performance rating |
CN108875619A (en) * | 2018-06-08 | 2018-11-23 | Oppo广东移动通信有限公司 | Method for processing video frequency and device, electronic equipment, computer readable storage medium |
CN110020588A (en) * | 2019-01-28 | 2019-07-16 | 深圳市睿智物联科技有限公司 | A kind of building screen lamps and lanterns monitoring method and system based on video identification |
CN111597863A (en) * | 2019-02-21 | 2020-08-28 | 顺丰科技有限公司 | Loading and unloading rate determining method, system, equipment and storage medium |
CN111597863B (en) * | 2019-02-21 | 2023-11-28 | 顺丰科技有限公司 | Loading and unloading rate determining method, system, equipment and storage medium |
CN112437344A (en) * | 2020-10-30 | 2021-03-02 | 福建星网视易信息系统有限公司 | Video matching method and terminal |
CN112437344B (en) * | 2020-10-30 | 2023-02-28 | 福建星网视易信息系统有限公司 | Video matching method and terminal |
CN112907657A (en) * | 2021-03-05 | 2021-06-04 | 科益展智能装备有限公司 | Robot repositioning method, device, equipment and storage medium |
CN113347082A (en) * | 2021-08-06 | 2021-09-03 | 深圳康易世佳科技有限公司 | Method and device for intelligently displaying shared messages containing short videos |
CN116017077A (en) * | 2022-12-12 | 2023-04-25 | 北京奇艺世纪科技有限公司 | Direct playing method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105072455A (en) | Video matching method and device | |
CN110971929B (en) | Cloud game video processing method, electronic equipment and storage medium | |
US10368123B2 (en) | Information pushing method, terminal and server | |
US20180255360A1 (en) | Simulation Method and Apparatus for Watching Together in Live Broadcast | |
CN111447505B (en) | Video clipping method, network device, and computer-readable storage medium | |
US10264329B2 (en) | Descriptive metadata extraction and linkage with editorial content | |
CN110870975B (en) | Method, device and equipment for processing live game and computer readable storage medium | |
WO2016037441A1 (en) | Video advertisement filtering method, device and equipment | |
JP6300792B2 (en) | Enhancing captured data | |
US20180007399A1 (en) | Method and apparatus for detecting video playability | |
CN104519124A (en) | Allocation method and device of virtual resources | |
KR102233175B1 (en) | Method for determining signature actor and for identifying image based on probability of appearance of signature actor and apparatus for the same | |
US20150156227A1 (en) | Synchronize Tape Delay and Social Networking Experience | |
CN111479143B (en) | Television advertisement pushing method based on user portrait and electronic equipment | |
US20190082235A1 (en) | Descriptive metadata extraction and linkage with editorial content | |
US20170169062A1 (en) | Method and electronic device for recommending video | |
CN111182359A (en) | Video preview method, video frame extraction method, video processing device and storage medium | |
WO2018111379A1 (en) | Methods, systems, and media for detecting stereoscopic videos by generating fingerprints for multiple portions of a video frame | |
CN106570060B (en) | Random extraction method and device for data in information flow | |
US20190037251A1 (en) | Playback apparatus, method of controlling playback apparatus, playback method and server apparatus | |
US9223782B2 (en) | System for performing instructions that are dependent upon received media-based messages and associated methods and components | |
CN106937127B (en) | Display method and system for intelligent search preparation | |
US9678991B2 (en) | Apparatus and method for processing image | |
JP6150019B2 (en) | Usage control system, personal information management system, and terminal device | |
US20170139933A1 (en) | Electronic Device, And Computer-Readable Storage Medium For Quickly Searching Video Segments |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 100041 Beijing, Shijingshan District Xing Xing street, building 30, room 3, building 9, room 9014 Applicant after: Jing Shuo Technology (Beijing) Limited by Share Ltd Address before: 100010 Beijing city Dongcheng District bamboo rod alley No. 1 9 1007 Applicant before: JINGSHUO CENTURY TECHNOLOGY (BEIJING) CO., LTD. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151118 |