CN109040784A - Commercial detection method and device - Google Patents
Commercial detection method and device Download PDFInfo
- Publication number
- CN109040784A CN109040784A CN201811076425.5A CN201811076425A CN109040784A CN 109040784 A CN109040784 A CN 109040784A CN 201811076425 A CN201811076425 A CN 201811076425A CN 109040784 A CN109040784 A CN 109040784A
- Authority
- CN
- China
- Prior art keywords
- video frame
- detected
- hash value
- perceptual hash
- advertising copy
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 33
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000005236 sound signal Effects 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
-
- 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
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention relates to purposes of commercial detection technical field, a kind of commercial detection method and device are provided.Wherein, commercial detection method comprises determining that video frame to be detected；Calculate the perceptual hash value of the video frame to be detected；Judge the perceptual hash value of the video frame to be detected, if match with the perceptual hash value of the video frame of the advertising copy in advertising copy library；If matching, the advertising copy where video frame that perceptual hash value matches is determined as the corresponding advertisement of the video frame to be detected.This method matches to detect whether video frame belongs to advertisement by perceptual hash value, and detection efficiency is high, affected by noise small, can effectively meet the needs of related services such as monitoring of the advertisement.
Description
Technical field
The present invention relates to purposes of commercial detection technical fields, in particular to a kind of commercial detection method and device.
Background technique
With gradually deeply developing for digital technology, public media video and audio resource is more and more abundant, the broadcast electricity of various regions
Television stations, content supplier also sharply increase, how from the video/audio of TV programme, using the means of modernization, quickly
Advertisement video content is effectively detected out, has become the important topic of monitoring of the advertisement industry.
However, commercial detection method in the prior art is perhaps excessively complicated or more sensitive to noise, can not expire
Demand of the sufficient monitoring of the advertisement business in terms of high efficiency, real-time.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of commercial detection method and device, to solve the above technical problems.
To achieve the above object, the invention provides the following technical scheme:
In a first aspect, the embodiment of the present invention provides a kind of commercial detection method, comprising:
Determine video frame to be detected；
Calculate the perceptual hash value of video frame to be detected；
Judge the perceptual hash value of video frame to be detected, if the sense with the video frame of the advertising copy in advertising copy library
Know that cryptographic Hash matches；
If matching, the advertising copy where video frame that perceptual hash value matches is determined as video frame pair to be detected
The advertisement answered.
The above method matches to detect whether video frame belongs to advertisement by perceptual hash value, and detection efficiency is high, by noise
It influences small, can effectively meet the needs of related services such as monitoring of the advertisement.This method can be used for detecting television program video
In advertisement, can be used for detecting the advertisement in other videos, the detection of other content can also be generalized to, be not limited to advertisement
Detection.
With reference to first aspect, in the first possible implementation of the first aspect, perceptual hash value is divided into multiple areas
Section, judges the perceptual hash value of video frame to be detected, if the perception with the video frame of the advertising copy in advertising copy library is breathed out
Uncommon value matches, comprising:
Judge any zone in the perceptual hash value of video frame to be detected, if with the advertising copy in advertising copy library
Video frame perceptual hash value in the section of same position match；
If matching, it is determined that the perceptual hash value of video frame to be detected, the view with the advertising copy in advertising copy library
The perceptual hash value of frequency frame matches, if not matching that, it is determined that the perceptual hash value of video frame to be detected, with advertising copy library
In the perceptual hash value of video frame of advertising copy do not match that.
Perceptual hash value is divided into multiple sections and matched respectively by above-mentioned implementation, and perceptual hash value can be improved
Matched efficiency.
The possible implementation of with reference to first aspect the first, in second of possible implementation of first aspect
In, judge any zone in the perceptual hash value of video frame to be detected, if the view with the advertising copy in advertising copy library
The section of same position matches in the perceptual hash value of frequency frame, comprising:
Judge any zone in the perceptual hash value of video frame to be detected, the view with the advertising copy in advertising copy library
Whether the Hamming distance in the perceptual hash value of frequency frame between the section of same position is less than preset threshold；
If being less than preset threshold, it is determined that any zone in the perceptual hash value of video frame to be detected, with advertising copy
The section of same position matches in the perceptual hash value of the video frame of advertising copy in library；
If being not less than preset threshold, it is determined that any zone in the perceptual hash value of video frame to be detected, with advertisement sample
The section of same position does not match that in the perceptual hash value of the video frame of advertising copy in this library.
With reference to first aspect, in a third possible implementation of the first aspect, determine video frame to be detected it
Afterwards, before the perceptual hash value for calculating video frame to be detected, method further include:
Video frame to be detected is pre-processed, the region in video frame to be detected comprising interference information is cropped.
Cutting processing is carried out to video frame to be detected, while the video frame of the advertising copy in advertising copy library is also carried out
Cutting processing, then Hash values match is carried out, due to eliminating interference information, matching result is more acurrate.
The third possible implementation with reference to first aspect, in the 4th kind of possible implementation of first aspect
In, interference information includes at least one of black surround, subtitle, TV logo information.
With reference to first aspect, in the fifth possible implementation of the first aspect, the sense of video frame to be detected is calculated
Know cryptographic Hash, comprising:
Video frame to be detected is subjected to diminution processing；
Grayscale image is converted by the video frame to be detected after diminution；
Discrete cosine transform (Discrete Cosine Transform, DCT) is carried out to grayscale image, obtains DCT matrix；
Calculate the mean value of the DCT value of all pixels in DCT matrix；
Judge whether the DCT value of each pixel in DCT matrix is less than mean value, if being less than mean value, determines perceptual hash value
In position corresponding with the pixel be 0, if more than mean value, determine in perceptual hash value that position corresponding with the pixel is 1.
Perceptual hash algorithm is calculated based on the low frequency mean value of image, and calculation method is simple, the scaling of image, brightness,
Influence of the change of contrast or color to calculated perceptual hash value is all little, therefore is used for purposes of commercial detection, can
Obtain preferable effect.
With reference to first aspect or first aspect the first to any one possible implementation in the 5th kind,
In 6th kind of possible implementation of one side, video frame to be detected is determined, comprising:
Obtain video data packet to be detected；
The key frame in video data packet to be detected is extracted, decoded key frame is determined as video frame to be detected.
Key frame (also referred to as intra prediction frame, I frame), forward predicted frame (P frame) and double are generally comprised in video data packet
To prediction frame (B frame), wherein key frame decrement is smaller, and the information content for including is more, and decoding is relatively easy, and adjacent view
Similarity between frequency frame is very high, therefore can greatly improve detection efficiency, while base for key frame as video frame to be detected
This does not influence the accuracy of testing result.
The 6th kind of possible implementation with reference to first aspect, in the 7th kind of possible implementation of first aspect
In, obtain video data packet to be detected, comprising:
Extract transmitting stream (Transport Stream, TS) data packet in the source data of TV programme；
TS data packet is parsed according to pre-arranged code standard, obtains the TV program information in TS data packet；
The program identification for needing to carry out the TV programme of purposes of commercial detection is determined based on TV program information；
Video data packet to be detected is obtained from TS data packet based on program identification.
The 7th kind of possible implementation with reference to first aspect, in the 8th kind of possible implementation of first aspect
In, extract the transmitting stream TS data packet in the source data of TV programme, comprising:
Determine the data type of source data；
If data type is real-time IP data stream, it is based on IP agreement, by the TS data in the IP data payload obtained in real time
It is determined as TS data packet；
If data type is video and audio file, it is based on file sharing protocol, by the video and audio TS in the shared disk of reading
File is determined as TS data packet.
At least there are two types of presentation modes for source data, and one is streamings, and one is file-types, two kinds in above-mentioned implementation
Mode can be handled.
Second aspect, the embodiment of the present invention provide a kind of purposes of commercial detection device, comprising:
Video frame determining module to be detected, for determining video frame to be detected；
Perceptual hash value computing module, for calculating the perceptual hash value of video frame to be detected；
Matching judgment module, for judging the perceptual hash value of video frame to be detected, if with it is wide in advertising copy library
The perceptual hash value for accusing the video frame of sample matches；
Matching result determining module, if the advertisement sample for matching, where the video frame that perceptual hash value is matched
Originally it is determined as the corresponding advertisement of video frame to be detected.
The third aspect, the embodiment of the present invention provide a kind of computer storage medium, meter are stored in computer storage medium
Calculation machine program instruction when computer program instructions are read and run by the processor of computer, executes first aspect or first party
The step of method that the possible embodiment of any one of face provides.
Fourth aspect, the embodiment of the present invention provide a kind of electronic equipment, including processor and computer storage medium, meter
It is stored with computer program instructions in calculation machine storage medium, when computer program instructions are read out by the processor and run, executes the
The step of method that the possible embodiment of any one of one side or first aspect provides.
To enable above-mentioned purpose of the invention, technical scheme and beneficial effects to be clearer and more comprehensible, special embodiment below, and
Cooperate appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of structural block diagram that can be applied to the electronic equipment in the embodiment of the present invention；
Fig. 2 shows the flow charts for the commercial detection method that first embodiment of the invention provides；
Fig. 3 shows the flow chart of the step S11 of the commercial detection method of first embodiment of the invention offer；
Fig. 4 shows the flow chart of the commercial detection method of second embodiment of the invention offer；
Fig. 5 shows the functional block diagram of the purposes of commercial detection device of third embodiment of the invention offer.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile of the invention
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
Fig. 1 shows the structural schematic diagram of electronic equipment 100 provided in an embodiment of the present invention.Referring to Fig.1, electronic equipment
100 include memory 102, storage control 104, one or more (one is only shown in figure) processors 106, Peripheral Interface
108, radio-frequency module 110, audio-frequency module 112, display module 114 etc..These components pass through one or more communication bus/signal
Line 116 mutually communicates.
Memory 102 can be used for storing software program and module, as in the embodiment of the present invention commercial detection method and
Corresponding program instruction/the module of device, the software program and module that processor 106 is stored in memory 102 by operation,
Thereby executing various function application and data processing, such as commercial detection method provided in an embodiment of the present invention and device.
Memory 102 may be, but not limited to, random access memory (Random Access Memory, RAM), only
It reads memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM)
Deng.Processor 106 and other possible components can carry out the access of memory 102 under the control of storage control 104.
Processor 106 can be a kind of IC chip, the processing capacity with signal.It specifically can be general procedure
Device, including central processing unit (Central Processing Unit, CPU), micro-control unit (Micro Controller
Unit, MCU), network processing unit (Network Processor, NP) or other conventional processors；It can also be dedicated processes
Device, including digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application
Specific Integrated Circuits, ASIC), field programmable gate array (Field Programmable Gate
Array, FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.It can be with
Realize or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.
Various input/output devices are couple processor 106 and memory 102 by Peripheral Interface 108.In some implementations
In example, Peripheral Interface 108, processor 106 and storage control 104 can be realized in one single chip.In some other reality
In example, they can be realized by independent chip respectively.
Radio-frequency module 110 is used to receive and transmit electromagnetic wave, realizes the mutual conversion of electromagnetic wave and electric signal, thus with
Communication network or other equipment are communicated.
Audio-frequency module 112 provides a user audio interface, may include one or more microphones, one or more raises
Sound device and voicefrequency circuit.
Display module 114 provides a display interface between electronic equipment 100 and user.Specifically, display module 114
Video output is shown to user, and the content of these videos output may include text, figure, video and any combination thereof.
It is appreciated that structure shown in FIG. 1 is only to illustrate, electronic equipment 100 may also include it is more than shown in Fig. 1 or
Less component, or with the configuration different from shown in Fig. 1.Each component shown in Fig. 1 can using hardware, software or its
Combination is realized.In the embodiment of the present invention, electronic equipment 100 can be server, personal computer, Intelligent mobile equipment, intelligence
It can the equipment with calculation processing power such as wearable device and intelligent vehicle-carried equipment.
First embodiment
Fig. 2 shows the flow charts for the commercial detection method that first embodiment of the invention provides.Referring to Fig.1, this method packet
It includes:
S10: the processor of electronic equipment determines video frame to be detected.
Video frame to be detected can be any one frame in video to be detected, typically, in the video after compressed encoding
There are three kinds of video frames, are key frame (I frame), forward predicted frame (P frame) and bi-directional predicted frames (B frame) respectively.It is wherein crucial
Frame decrement is smaller, and the information content for including is more, and in view of the similarity between adjacent video frame is very high, therefore the
It, can be using key frame as video frame to be detected in a kind of embodiment of one embodiment.Due to key frame quantity relatively
It is few, and because using only intra prediction in coding, decoding is relatively easy to, therefore using key frame as video to be detected
Frame can significantly improve purposes of commercial detection efficiency, while have substantially no effect on the accuracy of testing result.
Certainly in other embodiments, by one of above-mentioned three kinds of video frames or a variety of conducts video frame to be detected
It is possible.
S11: the processor of electronic equipment calculates the perceptual hash value of video frame to be detected.
The perceptual hash value for calculating video frame to be detected, can use, but be not limited to using following calculation method:
Fig. 3 shows the flow chart of the step S11 of the commercial detection method of first embodiment of the invention offer.Reference Fig. 3,
Step S11 may include:
S110: video frame to be detected is carried out diminution processing by the processor of electronic equipment.
Diminution handles the high frequency detail data that can remove image, retains the key messages such as light and shade, the structure of image, simultaneously
Reduce the operand of subsequent DCT operation.Meanwhile the perceptual hash value characteristic insensitive to zoom operations is determined and is carried out at diminution
Reason is feasible.For example, original video frame to be detected can be reduced into the image of 8x8 resolution ratio, it is reduced into other certainly
Resolution ratio is also possible.
S111: the video frame to be detected after diminution is converted grayscale image by the processor of electronic equipment.
For example, formula Gray=R*0.299+G* can be used for the case where video frame to be detected is RGB image
0.587+B*0.114 is converted, wherein Gray indicates the gray value of pixel after conversion, and R, G, B respectively indicate conversion preceding pixel
Red channel, green channel, blue channel value.
S112: the processor of electronic equipment carries out DCT to grayscale image, obtains DCT matrix.
For example, for the image of 8x8 resolution ratio two-dimensional dct can be carried out by following equation, and then obtain the DCT of 8x8
Matrix, the pixel value of each pixel is known as the DCT value of the pixel in DCT matrix.
S113: the processor of electronic equipment calculates the mean value of the DCT value of all pixels in DCT matrix.
S114: the processor of electronic equipment judges whether the DCT value of each pixel in DCT matrix is less than mean value, if small
In mean value, determine in perceptual hash value that position corresponding with the pixel is 0, if more than mean value, determine in perceptual hash value with the picture
The corresponding position of element is 1.
For example, for the DCT matrix of 8x8, perceptual hash value totally 64, in each of these corresponding DCT matrix
One pixel, and calculated and obtained by the method in step S114.
By step S111 to step S114 it is found that perceptual hash value is calculated based on the low frequency mean value of image, embody
The main feature of image, calculation method is simple, and the scaling of image, the change of brightness, contrast or color is to calculating
The influence of perceptual hash value out is all little, therefore can effectively characterize the main feature of video frame to be detected.
It can also include to be checked before step S11 after step S10 in a kind of embodiment of first embodiment
It surveys video frame and carries out pretreated step, pretreatment here is primarily referred to as cropping in video frame to be detected comprising interference information
Region.
Wherein, interference information may include at least one of black surround, subtitle, TV logo information.Interference information may
Have an adverse effect to follow-up l detecting step.For example, some advertisement when some TV station plays, can fold on its picture
It is powered on the logo of television stations, causes advertisement picture and original advertising copy inconsistent.In another example playing high definition on Standard Definition Television
When TV programme, due to the difference of resolution ratio, there can be black surround in video, but may and this be not present in original advertising copy
A little black surrounds.
In pre-treatment step, these interference informations are got rid of by cutting method, subsequent progress cryptographic Hash can be made
The result matched is more accurate.It should be understood that it is able to confirm that in video frame to be detected that there is no interference informations if realized, it can also
Not pre-processed to video frame to be detected.
It is exemplified below, it is assumed that video frame to be detected is the video frame in Standard Definition Television program video, original resolution
Rate is 720x576.Can be cut to 520x376 (resolution ratio for referring to remaining area after cutting), avoid subtitle, logo it is dry
It disturbs.If there are black surrounds for the left and right of video frame to be detected, it can be further cut to 390x376；If video to be detected
There is black surround up and down, can be further cut to 520x282；If existing up and down for video frame to be detected is black
Side can be further cut to 390x282.It is appreciated that above-mentioned method of cutting out and specific value are merely illustrative, it is specific to cut out
The process of cutting can determine according to actual needs.
It may be noted that once video to be detected is pre-processed, then the advertising copy in advertising copy library will also carry out
Same pretreatment, to ensure the validity of calculated perceptual hash value in step S12.
S12: the processor of electronic equipment judges the perceptual hash value of video frame to be detected, if in advertising copy library
The perceptual hash value of the video frame of advertising copy matches.
S13: the processor of electronic equipment by the advertising copy where video frame that perceptual hash value matches be determined as to
Detect the corresponding advertisement of video frame.
Step S12 and step S13 is contacted more closely, combines two steps be illustrated below.
Advertising copy library is usually the set for the advertising copy that may be detected, can be to every before step S12 execution
Each video frame in a advertising copy also uses the method in similar step S11 to calculate its perceptual hash value.For example, for
The case where video frame to be detected is key frame, each advertising copy can also extract key frame and to calculate each key frame corresponding
Perceptual hash value forms perceptual hash value sequence.
In step s 12, each perception in the perceptual hash value of video frame to be detected and above-mentioned sequence of hash values is breathed out
Uncommon value successively compares, if matching with one of those, thens follow the steps S13, and the matched perceptual hash value is corresponding
Video frame where advertising copy be determined as the corresponding advertisement of video frame to be detected, that is, detect an advertisement, no longer need to after
Remaining perceptual hash value in continuous comparison sequence of hash values.If the not no perceptual hash with video frame to be detected in sequence of hash values
It is worth matched perceptual hash value, then shows that video frame to be detected is not the video frame in advertisement, that is, advertisement is not detected.
Judge whether two perceptual hash values match, the Hamming distance between two perceptual hash values can be calculated, if
It less than some preset threshold, then matches, otherwise mismatches.Certainly, the matching of two perceptual hash values can also pass through its other party
Formula is defined.
In a kind of embodiment of first embodiment, perceptual hash value can also be divided into multiple sections, for example, right
In 64 perceptual hash values, 4 sections, each section 16 can be divided into.For the perceptual hash of video frame to be detected
Value, and adopted based on each perceptual hash value in the calculated perceptual hash value sequence of advertising copy in advertising copy library
Section partition is carried out in the same way.
In this embodiment, by each sense in the perceptual hash value of video frame to be detected and above-mentioned sequence of hash values
When knowing that cryptographic Hash compares, first section of two perceptual hash values can be first compared by the way of by section comparison,
Such as first 16, without continuing to compare if matching, if mismatching second section for continuing to compare two perceptual hash values,
Until all section comparisons finish.The section of any one group of corresponding position matches, and can think two perceptual hash values
Match, while not having to be further continued for comparing remaining section.
Judge whether two perceptual hash values match in the section of same position, the Hamming between two sections can be calculated
Distance is matched, is otherwise mismatched if being less than some preset threshold.Certainly, the matching of two sections can also pass through its other party
Formula is defined.According to long-term practice as a result, for perceptual hash value be 64, each section be 16 the case where, preset threshold
Value can take 5, take other values also possible certainly.
In this embodiment, it perceptual hash value is divided into multiple sections carries out matched side respectively due to using
Formula so as to improve the matched efficiency of perceptual hash value, and then improves the speed of purposes of commercial detection.
In conclusion the commercial detection method that first embodiment of the invention provides matches to detect view by perceptual hash value
Whether frequency frame belongs to advertisement, and detection efficiency is high, and robustness is good, can effectively meet the need of the related services such as monitoring of the advertisement
It asks.This method can be used for detecting the advertisement in television program video, can be used for detecting the advertisement in other videos, may be used also
To be generalized to the detection of other content, it is not limited to purposes of commercial detection.
Second embodiment
Fig. 4 shows the flow chart of the commercial detection method of second embodiment of the invention offer.It is wide in second embodiment
It accuses detection method and is considered as the commercial detection method of first embodiment offer in terms of the advertisement in detection television program video
Concrete application.Referring to Fig. 4, this method comprises:
Step S20: the processor of electronic equipment extracts the TS data packet in the source data of TV programme.
At least there are two types of data types for the source data of TV programme: one is real-time IP data stream (TS Over IP), separately
One is video and audio files.The data type that can determine source data first, is then based on different data types and takes difference
Operation.
If data type is real-time IP data stream, it is based on IP agreement, by the TS number in the IP data payload obtained in real time
According to being determined as TS data packet；If data type is video and audio file, it is based on file sharing protocol, it will be in the shared disk of reading
Video and audio TS file is determined as TS data packet.
Step S21: the processor of electronic equipment parses TS data packet according to pre-arranged code standard, obtains TS data
TV program information in packet.
Here pre-arranged code standard may be, but not limited to, country of People's Republic of China (PRC) mark " information technology motion diagram
The universal coding of picture and its audio signal " (each revision including the standard).TS data are parsed based on the coding standard
Packet demultiplexes TV programme therein, obtains the TV program information for including in TS data packet.
Step S22: the processor of electronic equipment determines the TV Festival for needing to carry out purposes of commercial detection based on TV program information
Purpose program identification.
It include the program identification (Program ID, PID) of each TV programme in TV program information, for distinguishing difference
TV programme.If it is desired to carry out purposes of commercial detection to some TV programme, it is first determined the corresponding program mark of the TV programme
Know.
Step S23: the processor of electronic equipment is based on program identification and obtains video data packet to be detected from TS data packet.
All views corresponding with the program identification of TV programme to be detected in video data packet to be detected, that is, TS data packet
Frequency evidence.
Step S24: the processor of electronic equipment extracts the key frame in video data packet to be detected, by decoded key
Frame is determined as video frame to be detected.
Typically, include multiple key frames in video data packet to be detected, constitute a keyframe sequence, it can should
Each key frame in keyframe sequence is used as video frame to be detected, in some embodiments, also can choose therein
Some key frames are as video frame to be detected.
Step S25: the processor of electronic equipment carries out advertisement by the matching of perceptual hash value to each video frame to be detected
Detection.
Commercial detection method in first embodiment can be used to each video frame progress purposes of commercial detection to be detected,
Elaboration is not repeated herein.After step S25 has been executed, the existing advertisement in video data packet to be detected has been marked,
The number that can be played on this basis to advertisement, the frequency etc. that different advertisements occur is counted, to realize monitoring of the advertisement
Business demand.
The commercial detection method has real-time good, the accurate advantage of testing result.
3rd embodiment
Fig. 5 shows the functional block diagram of the purposes of commercial detection device 200 of third embodiment of the invention offer.Referring to Fig. 5, originally
The purposes of commercial detection device 200 that invention 3rd embodiment provides, including video frame determining module 210 to be detected, perceptual hash value meter
Calculate module 220, matching judgment module 230 and matching result determining module 240.
Wherein, video frame determining module 210 to be detected is for determining video frame to be detected；
Perceptual hash value computing module 220 is used to calculate the perceptual hash value of video frame to be detected；
Matching judgment module 230 is used to judge the perceptual hash value of video frame to be detected, if in advertising copy library
The perceptual hash value of the video frame of advertising copy matches；
If matching result determining module 240 is for matching, the advertisement where the video frame that perceptual hash value is matched
Sample is determined as the corresponding advertisement of video frame to be detected.
The technical effect of the purposes of commercial detection device 200 that third embodiment of the invention provides, realization principle and generation is preceding
It states in embodiment and has illustrated, to briefly describe, Installation practice part does not refer to place, can refer in preceding method embodiment
Corresponding contents.
Fourth embodiment
Fourth embodiment of the invention provides a kind of computer storage medium, and computer journey is stored in computer storage medium
Sequence instruction when computer program instructions are read and run by the processor of computer, is executed and is provided in first embodiment of the invention
Method the step of.The computer storage medium can be implemented as, but be not limited to memory 102 shown in fig. 1.
5th embodiment
Fifth embodiment of the invention provides a kind of electronic equipment, including processor and computer storage medium, computer
It is stored with computer program instructions in storage medium and executes the present invention when computer program instructions are read out by the processor and run
The step of method provided in first embodiment.The electronic equipment can be implemented as, but be not limited to electronic equipment shown in fig. 1
100。
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through it
Its mode is realized.The apparatus embodiments described above are merely exemplary, for example, the flow chart and block diagram in attached drawing are aobvious
The device of multiple embodiments according to the present invention, architectural framework in the cards, the function of method and computer program product are shown
It can and operate.In this regard, each box in flowchart or block diagram can represent one of a module, section or code
Point, a part of the module, section or code includes one or more for implementing the specified logical function executable
Instruction.It should also be noted that function marked in the box can also be attached to be different from some implementations as replacement
The sequence marked in figure occurs.For example, two continuous boxes can actually be basically executed in parallel, they sometimes may be used
To execute in the opposite order, this depends on the function involved.It is also noted that each of block diagram and or flow chart
The combination of box in box and block diagram and or flow chart can be based on the defined function of execution or the dedicated of movement
The system of hardware is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in computer-readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing
Having the part for the part or the technical solution that technology contributes can be embodied in the form of software products, the computer
Software product is stored in a storage medium, including some instructions are used so that computer equipment executes each embodiment institute of the present invention
State all or part of the steps of method.Computer equipment above-mentioned includes: personal computer, server, mobile device, intelligently wears
The various equipment with execution program code ability such as equipment, the network equipment, virtual unit are worn, storage medium above-mentioned includes: U
Disk, mobile hard disk, read-only memory, random access memory, magnetic disk, tape or CD etc. are various to can store program code
Medium.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Claims (10)
1. a kind of commercial detection method characterized by comprising
Determine video frame to be detected；
Calculate the perceptual hash value of the video frame to be detected；
Judge the perceptual hash value of the video frame to be detected, if the sense with the video frame of the advertising copy in advertising copy library
Know that cryptographic Hash matches；
If matching, the advertising copy where video frame that perceptual hash value matches is determined as the video frame pair to be detected
The advertisement answered.
2. commercial detection method according to claim 1, which is characterized in that the perceptual hash value is divided into multiple sections,
The perceptual hash value of the judgement video frame to be detected, if the sense with the video frame of the advertising copy in advertising copy library
Know that cryptographic Hash matches, comprising:
Judge any zone in the perceptual hash value of the video frame to be detected, if with the advertising copy in advertising copy library
Video frame perceptual hash value in the section of same position match；
If matching, it is determined that the perceptual hash value of the video frame to be detected, the view with the advertising copy in advertising copy library
The perceptual hash value of frequency frame matches, if not matching that, it is determined that the perceptual hash value of the video frame to be detected, with advertisement sample
The perceptual hash value of the video frame of advertising copy in this library does not match that.
3. commercial detection method according to claim 2, which is characterized in that the sense of the judgement video frame to be detected
Know any zone in cryptographic Hash, if with same position in the perceptual hash value of the video frame of the advertising copy in advertising copy library
The section set matches, comprising:
Judge any zone in the perceptual hash value of the video frame to be detected, the view with the advertising copy in advertising copy library
Whether the Hamming distance in the perceptual hash value of frequency frame between the section of same position is less than preset threshold；
If being less than the preset threshold, it is determined that any zone in the perceptual hash value of the video frame to be detected, with advertisement
The section of same position matches in the perceptual hash value of the video frame of advertising copy in sample database；
If being not less than the preset threshold, it is determined that any zone in the perceptual hash value of the video frame to be detected, and it is wide
The section for accusing same position in the perceptual hash value of the video frame of the advertising copy in sample database does not match that.
4. the commercial detection method described in any one of according to claim 1, which is characterized in that in determination video to be detected
After frame, before the perceptual hash value for calculating the video frame to be detected, the method also includes:
The video frame to be detected is pre-processed, the region in the video frame to be detected comprising interference information is cropped.
5. commercial detection method according to claim 4, which is characterized in that the interference information includes black surround, subtitle, electricity
At least one of television stations mark information.
6. commercial detection method according to claim 1, which is characterized in that the sense for calculating the video frame to be detected
Know cryptographic Hash, comprising:
The video frame to be detected is subjected to diminution processing；
Grayscale image is converted by the video frame to be detected after diminution；
Discrete cosine transform is carried out to the grayscale image, obtains DCT matrix；
Calculate the mean value of the DCT value of all pixels in the DCT matrix；
Judge whether the DCT value of each pixel in the DCT matrix is less than the mean value, if being less than the mean value, determines institute
Stating in perceptual hash value position corresponding with the pixel is 0, if more than the mean value, determine in the perceptual hash value with the pixel
Corresponding position is 1.
7. commercial detection method according to claim 1 to 6, which is characterized in that the determination view to be detected
Frequency frame, comprising:
Obtain video data packet to be detected；
The key frame in the video data packet to be detected is extracted, decoded key frame is determined as the video to be detected
Frame.
8. commercial detection method according to claim 7, which is characterized in that described to obtain video data packet to be detected, packet
It includes:
Extract the transmitting stream TS data packet in the source data of TV programme；
The TS data packet is parsed according to pre-arranged code standard, obtains the TV program information in the TS data packet；
The program identification for needing to carry out the TV programme of purposes of commercial detection is determined based on the TV program information；
The video data packet to be detected is obtained from the TS data packet based on the program identification.
9. commercial detection method according to claim 8, which is characterized in that in the source data for extracting TV programme
Transmitting stream TS data packet, comprising:
Determine the data type of the source data；
If the data type is real-time IP data stream, it is based on IP agreement, by the TS data in the IP data payload obtained in real time
It is determined as the TS data packet；
If the data type is video and audio file, it is based on file sharing protocol, by the video and audio TS in the shared disk of reading
File is determined as the TS data packet.
10. a kind of purposes of commercial detection device characterized by comprising
Video frame determining module to be detected, for determining video frame to be detected；
Perceptual hash value computing module, for calculating the perceptual hash value of the video frame to be detected；
Matching judgment module, for judging the perceptual hash value of the video frame to be detected, if with it is wide in advertising copy library
The perceptual hash value for accusing the video frame of sample matches；
Matching result determining module, if the advertising copy where the video frame that perceptual hash value matches is true for matching
It is set to the corresponding advertisement of the video frame to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811076425.5A CN109040784A (en) | 2018-09-14 | 2018-09-14 | Commercial detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811076425.5A CN109040784A (en) | 2018-09-14 | 2018-09-14 | Commercial detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109040784A true CN109040784A (en) | 2018-12-18 |
Family
ID=64622391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811076425.5A Pending CN109040784A (en) | 2018-09-14 | 2018-09-14 | Commercial detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040784A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110830836A (en) * | 2019-11-18 | 2020-02-21 | 电子科技大学 | Video advertisement broadcasting monitoring method |
| CN110969202A (en) * | 2019-11-28 | 2020-04-07 | 上海观安信息技术股份有限公司 | Portrait collection environment verification method and system based on color component and perceptual hash algorithm |
| CN111898587A (en) * | 2020-08-14 | 2020-11-06 | 广州盈可视电子科技有限公司 | Video coding processing method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101162470A (en) * | 2007-11-16 | 2008-04-16 | 北京交通大学 | Video frequency advertisement recognition method based on layered matching |
| CN102905189A (en) * | 2011-07-25 | 2013-01-30 | 北京国微集成技术有限公司 | Multi-program transport stream separating method and multi-program transport stream separating device |
| US8494234B1 (en) * | 2007-03-07 | 2013-07-23 | MotionDSP, Inc. | Video hashing system and method |
| CN103984776A (en) * | 2014-06-05 | 2014-08-13 | 北京奇虎科技有限公司 | Repeated image identification method and image search duplicate removal method and device |
| CN105718861A (en) * | 2016-01-15 | 2016-06-29 | 北京市博汇科技股份有限公司 | Method and device for identifying video streaming data category |
| CN107657629A (en) * | 2017-10-27 | 2018-02-02 | 广东工业大学 | The tracking and tracking system of a kind of target |
-
2018
- 2018-09-14 CN CN201811076425.5A patent/CN109040784A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8494234B1 (en) * | 2007-03-07 | 2013-07-23 | MotionDSP, Inc. | Video hashing system and method |
| CN101162470A (en) * | 2007-11-16 | 2008-04-16 | 北京交通大学 | Video frequency advertisement recognition method based on layered matching |
| CN102905189A (en) * | 2011-07-25 | 2013-01-30 | 北京国微集成技术有限公司 | Multi-program transport stream separating method and multi-program transport stream separating device |
| CN103984776A (en) * | 2014-06-05 | 2014-08-13 | 北京奇虎科技有限公司 | Repeated image identification method and image search duplicate removal method and device |
| CN105718861A (en) * | 2016-01-15 | 2016-06-29 | 北京市博汇科技股份有限公司 | Method and device for identifying video streaming data category |
| CN107657629A (en) * | 2017-10-27 | 2018-02-02 | 广东工业大学 | The tracking and tracking system of a kind of target |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110830836A (en) * | 2019-11-18 | 2020-02-21 | 电子科技大学 | Video advertisement broadcasting monitoring method |
| CN110830836B (en) * | 2019-11-18 | 2020-10-27 | 电子科技大学 | Video advertisement broadcasting monitoring method |
| CN110969202A (en) * | 2019-11-28 | 2020-04-07 | 上海观安信息技术股份有限公司 | Portrait collection environment verification method and system based on color component and perceptual hash algorithm |
| CN110969202B (en) * | 2019-11-28 | 2023-12-19 | 上海观安信息技术股份有限公司 | Portrait acquisition environment verification method and system based on color component and perceptual hash algorithm |
| CN111898587A (en) * | 2020-08-14 | 2020-11-06 | 广州盈可视电子科技有限公司 | Video coding processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Du et al. | Server-driven video streaming for deep learning inference | |
| Zhang et al. | Efficient video frame insertion and deletion detection based on inconsistency of correlations between local binary pattern coded frames | |
| CN101374234B (en) | Method and apparatus for monitoring video copy base on content | |
| US8494234B1 (en) | Video hashing system and method | |
| Shi et al. | A fast and robust key frame extraction method for video copyright protection | |
| US20110142348A1 (en) | Signature Derivation for Images | |
| CN109040784A (en) | Commercial detection method and device | |
| CN103873852A (en) | Multi-mode parallel video quality fault detection method and device | |
| CN108933935A (en) | Detection method, device, storage medium and the computer equipment of video communication system | |
| US20090290752A1 (en) | Method for producing video signatures and identifying video clips | |
| Yu et al. | Exposing frame deletion by detecting abrupt changes in video streams | |
| CN101389029B (en) | Method and apparatus for video image encoding and retrieval | |
| CN102890778A (en) | Content-based video detection method and device | |
| CN105975939A (en) | Video detection method and device | |
| CN105718861A (en) | Method and device for identifying video streaming data category | |
| WO2017032245A1 (en) | Method and device for generating video file index information | |
| US20190188221A1 (en) | Using cross-matching between users and matching against reference data to facilitate content identification | |
| CN106375771B (en) | Image Feature Matching method and apparatus | |
| CN113382284B (en) | Pirate video classification method and device | |
| CN104853244A (en) | Method and apparatus for managing audio visual, audio or visual content | |
| US20130101014A1 (en) | Layered Screen Video Encoding | |
| CN111914649A (en) | Face recognition method and device, electronic equipment and storage medium | |
| Bozkurt et al. | Detection and localization of frame duplication using binary image template | |
| CN101339662B (en) | Method and device for creating video frequency feature data | |
| CN103716635A (en) | Method and device for improving intelligent analysis performance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |