CN109993579B - Advertisement delivery area determination method, system, server and computer readable medium - Google Patents
Advertisement delivery area determination method, system, server and computer readable medium Download PDFInfo
- Publication number
- CN109993579B CN109993579B CN201910244476.2A CN201910244476A CN109993579B CN 109993579 B CN109993579 B CN 109993579B CN 201910244476 A CN201910244476 A CN 201910244476A CN 109993579 B CN109993579 B CN 109993579B
- Authority
- CN
- China
- Prior art keywords
- suitability
- advertisement
- video
- extraction position
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Abstract
The present disclosure provides a method for determining an advertisement delivery area in a video segment, where the video segment includes: at least one frame of video image, wherein the advertisement placement area determination method comprises the following steps: step S1, aiming at each frame of video image contained in the video clip, inputting the display data of the video image into a pre-trained advertisement putting suitability degree scoring model so that the advertisement putting suitability degree scoring model outputs the advertisement putting suitability degree of each extraction position in the video image; step S2, determining an advertisement placement area for the video segment according to the advertisement placement suitability of each extracted position in each frame of the video image included in the video segment. The present disclosure also provides a system, a server, and a computer readable medium for determining an advertisement placement area in a video clip.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method, a system, a server and a computer readable medium for determining an advertisement delivery area in a video clip.
Background
The placement of the tile advertisements in the video is generally performed in a fixed area, for example, the tile advertisements are all located in the upper left corner of the picture during the process of continuously playing a plurality of video clips.
Because the video content is dynamically changed and the advertisement can block a part of the area of the video image, although the advertisement is generally selected to be placed in the marginal area of the image, the display position of the advertisement is always fixed, so that the important visual information under some video pictures can be inevitably blocked, and the watching experience of a user can be greatly influenced.
The main reason for the above technical problem is that the advertisement placement position in the prior art does not change with the playing content of the video clip.
Disclosure of Invention
The invention aims to solve at least one technical problem in the prior art, and provides a method, a system, a server and a computer readable medium for determining an advertisement delivery area in a video clip.
In a first aspect, an embodiment of the present disclosure provides a method for determining an advertisement delivery area in a video segment, where the video segment includes: at least one frame of video image, wherein the advertisement placement area determination method comprises the following steps:
step S1, aiming at each frame of video image contained in the video clip, inputting the display data of the video image into a pre-trained advertisement putting suitability degree scoring model so that the advertisement putting suitability degree scoring model outputs the advertisement putting suitability degree of each extraction position in the video image;
step S2, determining an advertisement placement area for the video segment according to the advertisement placement suitability of each extracted position in each frame of the video image included in the video segment.
In some embodiments, the video clip comprises a frame of video image;
step S2 specifically includes:
step S201a, comparing the advertisement placement suitability of each extraction position in one frame of the video image included in the video segment with a first predetermined suitability threshold, and selecting an extraction position with an advertisement placement suitability greater than the first predetermined suitability threshold, where the coverage area of all the selected extraction positions is used as the advertisement placeable area of the video segment.
In some embodiments, the video segment includes N frames of video images, each having M extraction positions, where the jth extraction position is noted as (x)j,yj) And the suitability of advertisement placement at the jth extraction position in the ith frame of video image is recorded as
1≤i≤N，1≤j≤M；
Step S2 specifically includes:
step S201b, calculating the average suitability of advertisement delivery of each extraction position aiming at each of M extraction positions according to the suitability of advertisement delivery of each extraction position in each frame of video image contained in the video clip; wherein, the average suitability of the advertisement delivery of the jth extraction position is recorded as
Step S202b, comparing the average suitability of advertisement placement at each extraction position with a second predetermined suitability threshold, and selecting the extraction position with the average suitability of advertisement placement greater than the second predetermined suitability threshold, wherein the area covered by all the selected extraction positions is extracted as the advertisement placeable area of the video segment.
In some embodiments, after step S2, the method further includes:
and step S3, determining a local optimal extraction position in the advertisement putting area by adopting a non-maximum suppression algorithm to be used as a preferred position for advertisement putting.
In a second aspect, an embodiment of the present disclosure further provides a system for determining an advertisement delivery area in a video segment, where the video segment includes: at least one frame of video image, the advertisement placement area determination system comprising:
the suitability determination module is used for inputting display data of the video image into a pre-trained advertisement putting suitability scoring model aiming at each frame of video image contained in the video clip, so that the advertisement putting suitability scoring model outputs the advertisement putting suitability of each extraction position in the video image;
and the delivery area determining module is used for determining the advertisement delivery area aiming at the video clip according to the advertisement delivery suitability of each extracted position in each frame of the video image contained in the video clip.
In some embodiments, the video clip comprises a frame of video image;
the delivery area determination module comprises:
and the first comparison and selection unit is used for comparing the advertisement putting suitability of each extraction position in one frame of video image contained in the video clip with a first preset suitability threshold value respectively, selecting the extraction position with the advertisement putting suitability larger than the first preset suitability threshold value, and taking the area covered by all the selected extraction positions as the advertisement putting-able area of the video clip.
In some embodiments, the video clip comprises N frames of video images, each video image having M extraction positions, N and M each being an integer greater than 1;
wherein, the jth extraction position is recorded as (x)j,yj) And the suitability of advertisement placement at the jth extraction position in the ith frame of video image is recorded as
1≤i≤N，1≤j≤M，
The delivery area determination module comprises:
a calculating unit, configured to calculate, for each of M extraction positions, an average suitability of advertisement delivery for the extraction position according to the suitability of advertisement delivery for each extraction position in each frame of the video image included in the video clip; wherein, the average suitability of the advertisement delivery of the jth extraction position is recorded as
And the second comparison and selection unit is used for comparing the average suitability of advertisement putting at each extraction position with a second preset suitability threshold value respectively, selecting the extraction position with the average suitability of advertisement putting larger than the second preset suitability threshold value, and extracting the area covered by all the selected extraction positions as the advertisement putting-possible area of the video clip.
In some embodiments, further comprising:
the optimal position determining module is used for determining a local optimal extraction position in the advertisement putting area by adopting a non-maximum suppression algorithm to be used as an optimal position for advertisement putting;
in a third aspect, an embodiment of the present disclosure further provides a server, including:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method for advertising placement area determination in a video clip as described above.
In a fourth aspect, the disclosed embodiments also provide a computer readable medium, on which a computer program is stored, which when executed by a processor, implements the method for determining an advertisement placement area in a video segment as described above.
Drawings
Fig. 1 is a flowchart of a method for determining an advertisement delivery area in a video segment according to an embodiment of the present disclosure;
fig. 2 is a flowchart of another method for determining an advertisement delivery area in a video segment according to an embodiment of the present disclosure;
fig. 3 is a block diagram illustrating a structure of a system for determining an advertisement delivery area in a video segment according to an embodiment of the present disclosure;
fig. 4 is a block diagram of a placement area determination module according to the present disclosure;
fig. 5 is a block diagram of another structure of the drop zone determination module in the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, a method, a system, a server and a computer readable medium for determining an advertisement placement area in a video clip provided by the present invention are described in detail below with reference to the accompanying drawings.
Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but which may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The technical solution of the present disclosure is based on an advertisement delivery suitability scoring model, and the advertisement delivery suitability scoring model has a function of outputting advertisement delivery suitability scores of each extraction position in one frame of video image according to the input display data of the frame of video image. The training process of the advertisement putting suitability scoring model is approximately as follows:
1) machine learning sample data is determined.
First, sample images having a predetermined resolution, for example, 1080P (1920 × 1080), are randomly selected. The resolution of the sample image can be set and adjusted according to actual needs. Assume that the number of sample images selected is Q.
Then, a plurality of extraction positions are manually selected or randomly selected or selected according to a certain rule. Wherein, assuming that the number of the finally selected extraction positions is M, the jth extraction position is recorded as (x)j,yj) (ii) a Note that, the jth extraction position (x) in the present disclosurej,yj) A certain area with a certain size, for example, an area corresponding to a 128 × 128 pixel array, is represented instead of a certain pixel point, and the size of the area can be set and adjusted according to actual needs; thus, the extraction locations in this disclosure may also be referred to as "extraction regions"; in addition, the areas corresponding to different extraction positions can be partially overlapped; in addition, the extraction position in the disclosure is represented in a coordinate form, which is only one representation way of the extraction position, and does not limit the technical solution of the disclosure; in practical application, when the extraction position is represented in a coordinate form, the coordinate data of the upper left corner of the area corresponding to the extraction position may be selected for representation, or the coordinate data of the center point of the area corresponding to the extraction position may be selected for representation.
Next, an ad placement suitability score is determined for each of the extracted locations in each of the sample images. Taking the advertisement delivery suitability score of one extraction position in one sample image as an example, covering a random image block with a corresponding size (the same size as the area corresponding to the extraction position, for example, 128 × 128) at the extraction position in the sample image, and then allowing S users (audiences) to subjectively score whether the overall viewing experience of the sample image is affected after the random image block covers the extraction position or not; if the user considers that the random image block covers the extraction position and then affects the overall viewing experience of the sample image, the score is 1, and if the user considers that the random image block covers the extraction position, the score is 1The overall viewing experience of the sample image is not influenced after the position is taken, and the score is 0; and accumulating and summing the scores of the S users to obtain an accumulated score, dividing the accumulated score by S, and obtaining a quotient which is the advertisement putting suitability score of the extraction position in the sample image. The higher the advertisement putting suitability score is, the smaller the influence of the random image block on the overall viewing experience of the sample image is, and the more suitable the extraction position is for advertisement putting. Repeating the above process to obtain the advertisement putting suitability score of each extracted position in each sample image. Wherein, the advertisement putting suitability score of the jth extraction position in the kth sample image is recorded as
1≤k≤Q。
In this case, the display data of the Q sample images, the extraction positions in the Q sample images, and the advertisement placement suitability scores corresponding thereto are set as machine learning sample data. Wherein, the display data of the kth sample image is marked as Ik。
2) And (5) carrying out model training.
Firstly, extracting image blocks at each extraction position in each sample image through a given extraction algorithm. Taking the example of extracting image blocks from k sample images, display data of an area corresponding to each extraction position in the k sample image is obtained, and display data of an image block of an area corresponding to the jth extraction position in the k sample image is recorded as
Then, display data of each image block is displayed
Performing convolutional neural network learning to convert into feature vector, and extracting position (x)j,yj) Together as an input term for logistic regression. The finally trained scoring model has the function of scoring the advertisement putting suitability of any extracted position of any imageAnd (4) performing functions.
The above process of training the scoring model based on the display data, the extraction position, and the advertisement delivery suitability score of the image block extracted from the sample image can be regarded as minimizing the following objective function:
wherein the function f (I)k,xj,yj) Characterization scoring model, f (I)k,xj,yj) With two arguments (two inputs to the scoring model): display data of image block
And the extraction position (x)j,yj) (ii) a By minimizing the above objective function, it can be seen as an optimization function f (I)k,xj,yj) And (5) parameter (c).
It should be noted that the specific process of model training (process of minimizing the objective function) by using the convolutional neural network technique is a conventional technique in the art, and is not described in detail herein.
And integrally packaging the image block extraction algorithm used for carrying out image block lifting on the sample image and the trained scoring model to obtain the advertisement putting suitability scoring model required by the disclosure.
This advertisement putting suitability score model possesses including two functional module: the system comprises an image block extraction module and a scoring module; the image block extraction module is used for extracting corresponding image block display data from each extraction position in the video image by adopting a preset image block extraction algorithm; the scoring module stores the trained scoring model, and can output corresponding advertisement putting suitability scores according to the display data of the input image blocks and the corresponding extraction positions. The input item of the advertisement putting suitability scoring model is display data of a complete frame of video image.
Fig. 1 is a flowchart of a method for determining an advertisement delivery area in a video segment according to an embodiment of the present disclosure, where as shown in fig. 1, the video segment includes: the method for determining the advertising region of at least one frame of video image comprises the following steps:
and step S1, aiming at each frame of video image contained in the video clip, inputting the display data of the video image into a pre-trained advertisement putting suitability degree scoring model so that the advertisement putting suitability degree scoring model outputs the advertisement putting suitability degree of each extraction position in the video image.
Before step S1, an advertisement placement suitability scoring model that can be used to score the advertisement placement suitability of each extracted position in one frame of video image needs to be trained, and the specific training process can be referred to in the foregoing.
In step S1, when a certain frame of video image needs to be processed, the display data of the frame of video image is simply input to the advertisement delivery suitability score model trained in advance.
And an image block extraction module in the advertisement delivery suitability degree scoring model adopts a preset image block extraction algorithm to extract the display data of the corresponding image block from each extraction position in the frame video image. It should be noted that, when image block extraction is performed from the same frame of video image, there may be overlap between extracted partial image blocks, which does not affect the present common technical solution.
For each image block extracted by the image block extraction module, a scoring module (a scoring module is stored in the scoring module) in the advertisement putting suitability degree scoring model can calculate the corresponding score of the advertisement putting suitability degree based on the display data and the corresponding extraction position of the image block.
It should be noted that the division of the video segments in the present disclosure may be determined according to the video display content or determined artificially. For example, each frame of video image may be regarded as one video clip, or a plurality of consecutive needles of video images may be regarded as one video clip, which all fall within the scope of the present disclosure.
When the video clip includes one frame of video image, the display data need only be input once to the advertisement delivery suitability scoring model in step S1; when the video segment includes a plurality of frames of video images, it is necessary to sequentially input the display data of each frame of video image to the advertisement delivery suitability score model in step S1.
It should be noted that the higher the advertisement placement suitability score of the extraction position determined in step S1, the less influence on the overall viewing experience of the video image when the extraction position is covered with another image (advertisement), and the more suitable the extraction position is for advertisement placement.
Step S2, determining an advertisement placement area for the video segment according to the advertisement placement suitability of each extracted position in each frame of video image included in the video segment.
In step S2, based on the suitability of advertisement placement at each extraction position in each frame of video image included in the video clip determined in step S1, an advertisement placement area for the video clip can be determined. When playing the video segment, the advertisement may be placed in the advertisement placeable area determined in step S2, so as to reduce the probability that the advertisement placement will adversely affect the overall viewing experience of the video segment.
The technical scheme of the disclosure can determine a suitable advertisement putting area according to the display content of the video clip for advertisement putting; compared with the prior art, the technical scheme of the disclosure can effectively reduce the probability of adverse effect of advertisement putting on the overall watching experience of the video clip.
As a specific alternative in the present disclosure, the video segment includes a frame of video image, and the step S2 specifically includes:
step S201a, comparing the advertisement placement suitability of each extraction position in one frame of video image included in the video segment with a first predetermined suitability threshold, and selecting the extraction position with the advertisement placement suitability greater than the first predetermined suitability threshold, wherein the area covered by all the selected extraction positions is used as the advertisement placeable area of the video segment.
In step S201a, the extracted positions with the suitability for advertisement placement greater than the first predetermined suitability threshold (e.g., 0.7) can be regarded as positions with less influence on the overall viewing experience of the user when placing advertisements at the selected positions, and these positions can be regarded as advertisement placeable areas.
The first predetermined fitness threshold may be set or adjusted according to actual needs.
As another particular alternative in the present disclosure, a video clip comprises N frames of video images, each video image having M extraction positions, N and M both being integers greater than 1; wherein, the jth extraction position is recorded as (x)j,yj) And the suitability of advertisement placement at the jth extraction position in the ith frame of video image is recorded as
I is more than or equal to 1 and less than or equal to N, and j is more than or equal to 1 and less than or equal to M; step S2 specifically includes:
step S201b, calculating the average suitability of advertisement delivery of each extraction position aiming at each of M extraction positions according to the suitability of advertisement delivery of each extraction position in each frame of video image contained in the video clip; wherein, the average suitability of the advertisement delivery of the jth extraction position is recorded as
Step S202b, comparing the average suitability of advertisement placement at each extraction position with a second predetermined suitability threshold, and selecting the extraction position with the average suitability of advertisement placement greater than the second predetermined suitability threshold, wherein the area covered by all the selected extraction positions is extracted as the advertisement placeable area of the video segment.
In step S201a, the extracted positions with the average suitability for advertisement placement greater than the second predetermined suitability threshold (e.g., 0.7) can be regarded as positions with less influence on the overall viewing experience of the user when placing advertisements at the selected positions, and these positions can be regarded as advertisement placeable areas.
The size of the second predetermined fitness threshold may be set or adjusted according to actual needs.
Fig. 2 is a flowchart of another method for determining an advertisement delivery area in a video segment according to an embodiment of the present disclosure, and as shown in fig. 2, the method for determining an advertisement delivery area shown in fig. 2 includes step S1 and step S2 in the foregoing embodiment, and further includes step S3 after step S2, and only step S3 is described in detail below.
And step S3, determining a local optimal extraction position in the advertisement putting area by adopting a non-maximum suppression algorithm to be used as a preferred position for advertisement putting.
And determining a local optimal extraction position in the advertisement putting area by adopting a Non-Maximum Suppression (NMS) algorithm, wherein the local optimal extraction position is substantially the position of a local Maximum value for determining the advertisement putting suitability in the advertisement putting area.
Specifically, a functional relationship between the suitability of advertisement placement and the extraction position in the advertisement placement area (when the video segment includes multiple frames, a functional relationship between the average suitability of advertisement placement and the extraction position) may be fitted based on a predetermined fitting algorithm, and is represented by f (x, y). Here, the advertisement placement suitability (advertisement placement average suitability) of the extraction position (x, y) may be represented as f (x, y).
The position of the local maximum value of the advertisement putting suitability can be determined by solving the position corresponding to the maximum value point of the function f (x, y). The process of solving the position corresponding to the maximum point of the function f (x, y) can be regarded as a process of determining whether the position (x, y) satisfies the following formula:
f(x,y)＝max{f(x,y),f(x+1,y),f(x-1,y),f(x,y+1),f(x,y-1)}
if yes, the position is a local maximum value point; otherwise, the location is not a local maximum point.
It should be noted that, in order to remove the influence of the local noise interference, smooth filtering (such as gaussian filtering) may be performed on the data of the advertisement delivery suitability in the advertisement delivery area, and then the non-maximum suppression operation may be performed. The specific operation process of the non-maximum suppression operation is conventional in the art and will not be described in detail here.
In addition, the local optimum extraction positions (local maximum points) determined by step S3 may be 1 or more, which does not limit the technical solution of the present disclosure.
Advertising at the local optimal extraction location determined in step S3 can further reduce the probability that advertising will adversely affect the overall viewing experience of the video clip.
Fig. 3 is a block diagram of a structure of an advertisement delivery area determining system in a video segment according to an embodiment of the present disclosure, and as shown in fig. 3, the advertisement delivery area determining system may be used to implement the advertisement delivery area determining method provided in the foregoing embodiment, and the advertisement delivery area determining system includes: a suitability determination module 1 and a delivery area determination module 2.
The suitability determination module 1 is configured to, for each frame of video image included in the video segment, input display data of the video image into a pre-trained advertisement delivery suitability scoring model, so that the advertisement delivery suitability scoring model outputs advertisement delivery suitability of each extraction position in the video image.
The placement area determination module 2 is configured to determine an advertisement placement area for the video segment according to advertisement placement suitability of each extraction position in each frame of video image included in the video segment.
It should be noted that the suitability determination module 1 in this embodiment may be configured to execute step S1 in the foregoing embodiment, and the launch area determination module 2 may be configured to execute step S2 in the foregoing embodiment.
Fig. 4 is a block diagram of a drop zone determination module according to the present disclosure, as shown in fig. 4, in some embodiments, a video segment includes a frame of video image, and the drop zone determination module 2 includes: and the first comparison and selection unit 21 is configured to compare the advertisement delivery suitability of each extraction position in one frame of video image included in the video segment with a first predetermined suitability threshold, select an extraction position with an advertisement delivery suitability greater than the first predetermined suitability threshold, and use an area covered by all the selected extraction positions as an advertisement deliverable area of the video segment.
It should be noted that the first comparing and selecting unit 21 in the present embodiment may be configured to perform step S201a in the foregoing embodiment.
Fig. 5 is another block diagram of a drop zone determining module in the disclosure, and as shown in fig. 5, in some embodiments, a video segment includes N frames of video images, each video image has M extraction positions, and N and M are both integers greater than 1; wherein, the jth extraction position is recorded as (x)j,yj) And the suitability of advertisement placement at the jth extraction position in the ith frame of video image is recorded as
1≤i≤N，1≤j≤M；
The placement area determination module 2 includes: a calculation unit 22 and a second comparison and selection unit 23.
The calculating unit 22 is configured to calculate, for each of the M extraction positions, an average suitability of advertisement delivery at the extraction position according to the suitability of advertisement delivery at each extraction position in each frame of video image included in the video segment; wherein, the average suitability of the advertisement delivery of the jth extraction position is recorded as
The second comparison and selection unit 23 is configured to compare the average suitability of advertisement placement at each extraction position with a second predetermined suitability threshold, and select an extraction position where the average suitability of advertisement placement is greater than the second predetermined suitability threshold, where the coverage area of all the selected extraction positions is extracted as an advertisement placeable area of the video segment.
It should be noted that the calculating unit 22 in the present embodiment may be configured to perform the step S201b in the foregoing embodiment, and the second comparing and selecting unit 23 in the present embodiment may be configured to perform the step S202b in the foregoing embodiment.
With continued reference to fig. 3, in some embodiments, the advertisement delivery area determination system further comprises: the optimal position determining module 3, the optimal position determining module 3 is configured to determine a local optimal extraction position in the advertisement placeable area by using a non-maximum suppression algorithm, so as to serve as a preferred position for advertisement placement.
It should be noted that the optimal position determining module 3 in the present embodiment may be used to execute step S3 in the foregoing embodiment.
For the specific description of each module and each unit, reference may be made to corresponding contents in the foregoing advertisement delivery area determining method, and details are not described here again.
An embodiment of the present disclosure further provides a server, including: one or more processors and a storage device having one or more programs stored thereon; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement a method for determining an advertising placement area in a video clip as provided by the foregoing embodiments.
The embodiment of the present disclosure also provides a computer readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for determining an advertisement placement area in a video segment is implemented as provided in the foregoing embodiment.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods disclosed above, functional modules/units in the apparatus, may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted in a generic and descriptive sense only and not for purposes of limitation. In some instances, features, characteristics and/or elements described in connection with a particular embodiment may be used alone or in combination with features, characteristics and/or elements described in connection with other embodiments, unless expressly stated otherwise, as would be apparent to one skilled in the art. Accordingly, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the scope of the disclosure as set forth in the appended claims.
Claims (8)
1. A method for determining an advertisement placement area in a video clip is characterized in that the video clip comprises: at least one frame of video image, wherein the advertisement placement area determination method comprises the following steps:
step S1, aiming at each frame of video image contained in the video clip, inputting the display data of the video image into a pre-trained advertisement putting suitability degree scoring model so that the advertisement putting suitability degree scoring model outputs the advertisement putting suitability degree of each extraction position in the video image;
step S2, determining an advertisement putting available area aiming at the video clip according to the advertisement putting suitability of each extraction position in each frame of the video image contained in the video clip;
wherein the video segment comprises a frame of video image;
step S2 specifically includes:
step S201a, comparing the advertisement placement suitability of each extraction position in one frame of the video image included in the video segment with a first predetermined suitability threshold, and selecting an extraction position with an advertisement placement suitability greater than the first predetermined suitability threshold, where the coverage area of all the selected extraction positions is used as the advertisement placeable area of the video segment.
2. The method according to claim 1, wherein the video segment comprises N frames of video images, each video image has M extraction positions, and wherein the jth extraction position is marked as (x)j,yj) And the suitability of advertisement placement at the jth extraction position in the ith frame of video image is recorded as
1≤i≤N，1≤j≤M；
Step S2 specifically includes:
step S201b, calculating the average suitability of advertisement delivery of each extraction position aiming at each of M extraction positions according to the suitability of advertisement delivery of each extraction position in each frame of video image contained in the video clip; wherein, the average suitability of the advertisement delivery of the jth extraction position is recorded as
Step S202b, comparing the average suitability of advertisement placement at each extraction position with a second predetermined suitability threshold, and selecting the extraction position with the average suitability of advertisement placement greater than the second predetermined suitability threshold, wherein the area covered by all the selected extraction positions is extracted as the advertisement placeable area of the video segment.
3. The method for determining advertising placement areas in video clips according to claim 1 or 2, further comprising after step S2:
and step S3, determining a local optimal extraction position in the advertisement putting area by adopting a non-maximum suppression algorithm to be used as a preferred position for advertisement putting.
4. A system for determining an advertisement placement area in a video clip, the video clip comprising: at least one frame of video image, the advertisement placement area determination system comprising:
the suitability determination module is used for inputting display data of the video image into a pre-trained advertisement putting suitability scoring model aiming at each frame of video image contained in the video clip, so that the advertisement putting suitability scoring model outputs the advertisement putting suitability of each extraction position in the video image;
a placement area determination module, configured to determine, according to advertisement placement suitability of each extracted position in each frame of the video image included in the video segment, an advertisement placeable area for the video segment;
wherein the video segment comprises a frame of video image;
the delivery area determination module comprises:
and the first comparison and selection unit is used for comparing the advertisement putting suitability of each extraction position in one frame of video image contained in the video clip with a first preset suitability threshold value respectively, selecting the extraction position with the advertisement putting suitability larger than the first preset suitability threshold value, and taking the area covered by all the selected extraction positions as the advertisement putting-able area of the video clip.
5. The system according to claim 4, wherein the video segment comprises N frames of video images, each video image having M extraction positions, N and M being integers greater than 1;
wherein, the jth extraction position is recorded as (x)j,yj) And the suitability of advertisement placement at the jth extraction position in the ith frame of video image is recorded as
1≤i≤N，1≤j≤M，
The delivery area determination module comprises:
a calculating unit, configured to calculate, for each of M extraction positions, an average suitability of advertisement delivery for the extraction position according to the suitability of advertisement delivery for each extraction position in each frame of the video image included in the video clip; wherein, the average suitability of the advertisement delivery of the jth extraction position is recorded as
And the second comparison and selection unit is used for comparing the average suitability of advertisement putting at each extraction position with a second preset suitability threshold value respectively, selecting the extraction position with the average suitability of advertisement putting larger than the second preset suitability threshold value, and extracting the area covered by all the selected extraction positions as the advertisement putting-possible area of the video clip.
6. The system for determining advertising placement area in video clip according to claim 4 or 5, further comprising:
and the optimal position determining module is used for determining a local optimal extraction position in the advertisement putting area by adopting a non-maximum suppression algorithm to serve as a preferred position for advertisement putting.
7. A server, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for determining advertising placement areas in a video clip as recited in any of claims 1-3.
8. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out a method for determining an advertisement placement area in a video clip according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910244476.2A CN109993579B (en) | 2019-03-28 | 2019-03-28 | Advertisement delivery area determination method, system, server and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910244476.2A CN109993579B (en) | 2019-03-28 | 2019-03-28 | Advertisement delivery area determination method, system, server and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109993579A CN109993579A (en) | 2019-07-09 |
| CN109993579B true CN109993579B (en) | 2021-04-02 |
Family
ID=67131679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910244476.2A Active CN109993579B (en) | 2019-03-28 | 2019-03-28 | Advertisement delivery area determination method, system, server and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993579B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10957085B2 (en) * | 2019-08-15 | 2021-03-23 | International Business Machines Corporation | Methods and systems for adding content to images based on negative space recognition |
| CN110570253B (en) * | 2019-09-11 | 2021-12-28 | 合肥常春藤移动科技有限公司 | Advertisement putting and popularizing system based on big data |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930460A (en) * | 2012-11-01 | 2013-02-13 | 青岛海信传媒网络技术有限公司 | Electronic commerce system and advertisement video play method thereof |
| US9467750B2 (en) * | 2013-05-31 | 2016-10-11 | Adobe Systems Incorporated | Placing unobtrusive overlays in video content |
| EP2819095A1 (en) * | 2013-06-24 | 2014-12-31 | Thomson Licensing | Method and apparatus for inserting a virtual object in a video |
| CN104519371B (en) * | 2014-12-31 | 2017-10-20 | 北京酷云互动科技有限公司 | Method for pushing, pusher and server |
| CN107948721B (en) * | 2017-11-23 | 2020-07-10 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information |
| CN108985229A (en) * | 2018-07-17 | 2018-12-11 | 北京果盟科技有限公司 | A kind of intelligent advertisement replacement method and system based on deep neural network |
-
2019
- 2019-03-28 CN CN201910244476.2A patent/CN109993579B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109993579A (en) | 2019-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9600744B2 (en) | Adaptive interest rate control for visual search | |
| WO2017076040A1 (en) | Image processing method and device for use during continuous shooting operation | |
| US9390475B2 (en) | Backlight detection method and device | |
| CN104066003B (en) | Method and device for playing advertisement in video | |
| CN108229290B (en) | Video object segmentation method and device, electronic equipment and storage medium | |
| EP3800878A1 (en) | Cascaded camera motion estimation, rolling shutter detection, and camera shake detection for video stabilization | |
| CN110121098B (en) | Video playing method and device, storage medium and electronic device | |
| CN109993579B (en) | Advertisement delivery area determination method, system, server and computer readable medium | |
| US20200218901A1 (en) | System and method for automated video processing of an input video signal using tracking of a single moveable bilaterally-targeted game-object | |
| CN111145114B (en) | Image enhancement method and device and computer readable storage medium | |
| WO2014044158A1 (en) | Identification method and device for target object in image | |
| US20100128181A1 (en) | Seam Based Scaling of Video Content | |
| CN108923853B (en) | Display method and device, and visible light communication transmission method and device | |
| US8983188B1 (en) | Edge-aware smoothing in images | |
| CN110969673B (en) | Live broadcast face-changing interaction realization method, storage medium, equipment and system | |
| WO2021008205A1 (en) | Image processing | |
| CN110996183B (en) | Video abstract generation method, device, terminal and storage medium | |
| CN110876079A (en) | Video processing method, device and equipment | |
| CN111179159B (en) | Method and device for eliminating target image in video, electronic equipment and storage medium | |
| CN107333027A (en) | A kind of method and apparatus of video image enhancement | |
| US20170161232A1 (en) | Method and electronic device for configuring a video player in a web page | |
| CN105100895B (en) | The matching process and device of video and screen resolution without video resolution information | |
| US20180122052A1 (en) | Method for deblurring a video, corresponding device and computer program product | |
| CN111291668A (en) | Living body detection method, living body detection device, electronic equipment and readable storage medium | |
| US9672423B2 (en) | Object tracking apparatus and method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |