CN115065855A - Live broadcast room dynamic cover generation method and device - Google Patents
Live broadcast room dynamic cover generation method and device Download PDFInfo
- Publication number
- CN115065855A CN115065855A CN202210933437.5A CN202210933437A CN115065855A CN 115065855 A CN115065855 A CN 115065855A CN 202210933437 A CN202210933437 A CN 202210933437A CN 115065855 A CN115065855 A CN 115065855A
- Authority
- CN
- China
- Prior art keywords
- pictures
- picture
- stillness
- live broadcast
- dynamic cover
- 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
Images
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]
- H04N21/40—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
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application discloses a method and a device for generating a dynamic cover of a live broadcast room, which relate to the technical field of deep learning, and the method comprises the following steps: the method comprises the steps of obtaining a plurality of first pictures, filtering low-frame pictures with brightness and/or definition smaller than a first threshold value in the plurality of first pictures, determining a plurality of second pictures with the stillness smaller than the stillness threshold value from the plurality of filtered first pictures, and generating a dynamic cover of a live broadcast room according to the plurality of second pictures. In the method, the low-frame pictures in the first picture can be filtered firstly, so that the pictures with too low brightness and definition in the first picture can be filtered, then a plurality of second pictures with the stillness smaller than the stillness threshold value are determined from the filtered first pictures, so that the stillness of the person in the determined second picture is ensured to be low, the figure outline can be clearly seen, and the situation that the picture is blurred due to rapid movement of the person in the picture is avoided. Therefore, the quality of the generated dynamic cover can be improved, and the display effect of the dynamic cover picture in the live broadcast room is optimized.
Description
Technical Field
The application relates to the technical field of deep learning, in particular to a method for generating a dynamic cover of a live broadcast room.
Background
With the development of internet technology, live broadcasting is becoming more and more popular with people. More and more people like live broadcasting through mobile phones, computers and other equipment. In the live broadcasting process, a high-quality live broadcasting cover can attract more users to enter a live broadcasting room to watch live broadcasting. Therefore, the live cover plays a crucial role for each anchor and each live room. Therefore, how to select the live cover is very important.
At present, a dynamic seal graph is generally generated by adopting a time point interception method, and the intercepted time point is generally fixed. Although some live broadcasting platforms inform the anchor, the anchor can actively ensure the current picture quality when the capture time of the cover, for example, the capture time is in the first few seconds of the live broadcasting. However, some time points in the live broadcasting process are inevitably adopted, and because the time points have certain randomness to live broadcasting contents, the picture quality and the content quality of the captured picture cannot be guaranteed. As a result, there is a problem in that the generated dynamic cover may be of poor quality.
Therefore, how to improve the quality of the generated live broadcast dynamic cover is a problem that needs to be solved urgently by those skilled in the art.
Disclosure of Invention
Based on the problems, the application provides a method and a device for generating a dynamic cover of a live broadcast room, so that the quality of the generated dynamic cover is improved, and the display effect of a dynamic cover map of the live broadcast room is optimized. The embodiment of the application discloses the following technical scheme.
In a first aspect, a method for generating a dynamic cover of a live broadcast room provided by the present application includes:
acquiring a plurality of first pictures, wherein the first pictures are pictures intercepted in a live broadcast process;
filtering brightness in the plurality of first pictures and/or low-frame pictures with definition smaller than a first threshold value;
determining a plurality of second pictures with the still degrees smaller than a still degree threshold value from the plurality of filtered first pictures, wherein the still degrees are used for representing the still degrees of the people in the pictures;
and generating a live broadcast room dynamic cover according to the plurality of second pictures.
Optionally, the determining, from the filtered plurality of first pictures, a plurality of second pictures whose stillness is less than a stillness threshold includes:
classifying the plurality of filtered first pictures according to the action characteristics of the human beings in the pictures to obtain a plurality of first picture sets;
determining a preset number of second pictures with the still degrees smaller than a still degree threshold value from each first picture set.
Optionally, after determining a plurality of second pictures with a degree of stillness smaller than a threshold value of the degree of stillness from the filtered plurality of first pictures, the method further includes:
inputting the second pictures into a preset training model for grading to obtain a plurality of grading results;
determining at least one third picture with a score result larger than a score threshold value from the plurality of second pictures;
and generating a dynamic cover according to the at least one third picture.
Optionally, the training model is obtained by:
constructing a feature vector for the plurality of second pictures, the feature vector comprising: human face characteristics, picture color characteristics and basic quality characteristics;
and inputting the second picture after the characteristic vector is constructed into a basic neural network model for training to obtain a training model.
Optionally, the generating a dynamic cover according to the plurality of second pictures includes:
synthesizing the plurality of second pictures into dynamic pictures;
and determining the dynamic picture as a dynamic cover of the live broadcast room.
In a second aspect, the present application provides a live broadcast room dynamic cover generation apparatus, including:
the device comprises a first acquisition unit, a second acquisition unit and a display unit, wherein the first acquisition unit is used for acquiring a plurality of first pictures, and the first pictures are pictures intercepted in a live broadcast process;
the first filtering unit is used for filtering the brightness in the first pictures and/or the low-frame pictures with the definition smaller than a first threshold value;
a first determining unit, configured to determine, from the filtered plurality of first pictures, a plurality of second pictures with a degree of stillness smaller than a threshold degree of stillness, where the degree of stillness is used to indicate a degree of stillness of a person in the pictures;
and the first generation unit is used for generating a dynamic cover of the live broadcast room according to the plurality of second pictures.
Optionally, the first determining unit is specifically configured to:
classifying the plurality of filtered first pictures according to the action characteristics of the human beings in the pictures to obtain a plurality of first picture sets;
determining a preset number of second pictures with the still degrees smaller than a still degree threshold value from each first picture set.
Optionally, the apparatus further comprises:
the scoring unit is used for inputting the second pictures into a preset training model for scoring to obtain a plurality of scoring results;
a second determining unit, configured to determine, from the plurality of second pictures, at least one third picture whose scoring result is greater than a score threshold;
and the second generating unit is used for generating a dynamic cover according to the at least one third picture.
Optionally, the training model is obtained by:
constructing a feature vector for the plurality of second pictures, the feature vector comprising: human face characteristics, picture color characteristics and basic quality characteristics;
and inputting the second picture after the characteristic vector is constructed into a basic neural network model for training to obtain a training model.
Optionally, the first generating unit is specifically configured to:
synthesizing the plurality of second pictures into dynamic pictures;
and determining the dynamic picture as a dynamic cover of the live broadcast room.
In a third aspect, an apparatus is provided in an embodiment of the present application, where the apparatus includes a memory for storing instructions or codes and a processor for executing the instructions or codes to cause the apparatus to perform the method of any one of the foregoing first aspects.
In a fourth aspect, an embodiment of the present application provides a computer storage medium, where codes are stored in the computer storage medium, and when the codes are executed, an apparatus executing the codes implements the method according to any one of the foregoing first aspects.
Compared with the prior art, the method has the following beneficial effects:
the method comprises the steps of obtaining a plurality of first pictures, filtering brightness in the first pictures, and/or determining a plurality of second pictures with the stillness smaller than a stillness threshold value from the filtered first pictures, and generating a live room dynamic cover according to the second pictures. In the method and the device, the low-frame pictures in the first picture can be filtered firstly, so that the pictures with too low brightness and/or definition in the first picture can be filtered, and then the plurality of second pictures with the stillness smaller than the stillness threshold value are determined from the plurality of filtered first pictures, so that the stillness of the person in the determined second picture is low, the figure outline can be seen clearly, and the figure in the picture is prevented from being blurred due to rapid movement. Therefore, a plurality of second pictures with relatively high quality are determined, and the dynamic cover of the live broadcast room is generated according to the plurality of second pictures, so that the problems that in the prior art, due to certain randomness of live broadcast contents corresponding to certain time points, the picture quality and the content quality of captured pictures cannot be guaranteed, and the generated dynamic cover possibly has poor quality are solved. The quality of the generated dynamic cover is improved, and the display effect of the dynamic cover map of the live broadcast room is optimized.
Drawings
To illustrate the technical solutions in the present embodiment or the prior art more clearly, the drawings needed to be used in the description of the embodiment or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for generating a dynamic cover of a live broadcast room according to an embodiment of the present application;
fig. 2 is a flowchart of another method for generating a dynamic cover of a live broadcast room according to the embodiment of the present application;
fig. 3 is a schematic structural diagram of a device for generating a dynamic cover of a live broadcast room according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
It should be noted that the method and apparatus for generating a dynamic cover of a live broadcast room provided by the present application are used in the field of deep learning, and the above description is only an example, and does not limit the application field of the names of the method and apparatus provided by the present application.
With the development of internet technology, live broadcasting is becoming more and more popular with people. More and more people like live broadcasting through mobile phones, computers and other equipment. In the live broadcasting process, a high-quality live broadcasting cover can attract more users to enter a live broadcasting room to watch live broadcasting. Therefore, the live cover plays a crucial role for each anchor and each live room. Therefore, how to select the live cover is very important.
At present, a dynamic seal graph is generally generated by adopting a time point interception method, and the intercepted time point is generally fixed. Although some live broadcasting platforms inform the anchor, the anchor can actively ensure the current picture quality when the capture time of the cover, for example, the capture time is in the first few seconds of the live broadcasting. However, some time points in the live broadcasting process are inevitably adopted, and because the time points have certain randomness to live broadcasting contents, the picture quality and the content quality of the captured picture cannot be guaranteed. As a result, there is a problem in that the generated dynamic cover may be of poor quality.
The inventor provides the technical scheme of the application through research. In the method and the device, the low-frame pictures in the first picture can be filtered firstly, so that the pictures with too low brightness and/or definition in the first picture can be filtered, and then the plurality of second pictures with the stillness smaller than the stillness threshold value are determined from the plurality of filtered first pictures, so that the stillness of the person in the determined second picture is low, the figure outline can be seen clearly, and the figure in the picture is prevented from being blurred due to rapid movement. Therefore, a plurality of second pictures with relatively high quality are determined, and the dynamic cover of the live broadcast room is generated according to the plurality of second pictures, so that the problems that in the prior art, due to certain randomness of live broadcast contents corresponding to certain time points, the picture quality and the content quality of captured pictures cannot be guaranteed, and the generated dynamic cover possibly has poor quality are solved. The quality of the generated dynamic cover is improved, and the display effect of the dynamic cover map of the live broadcast room is optimized.
The method provided by the embodiment of the application can be executed on the terminal equipment. The terminal device may be, for example, a mobile phone, a tablet computer, a computer, or the like.
In order that those skilled in the art will better understand the disclosure, the following detailed description will be given with reference to the accompanying drawings. The method provided by the embodiment of the present application is performed by the first device as an example.
Fig. 1 is a flowchart of a method for generating a dynamic cover of a live broadcast room according to an embodiment of the present application, and as shown in fig. 1, the method includes:
s101: a plurality of first pictures are acquired.
The first device acquires a plurality of first pictures. The first picture is a picture captured in a live broadcasting process.
It is understood that a plurality of time periods may be set, and a still picture is intercepted by a corresponding node in each time period. For example, a plurality of still pictures may be taken every 30S from the start of the live timing.
S102: and filtering the brightness and/or the low-frame pictures with the definition smaller than a first threshold value in the plurality of first pictures.
After the first device obtains the plurality of first pictures, the first device filters the plurality of first pictures to filter out brightness in the plurality of first pictures and/or low-frame pictures with definition smaller than a first threshold value.
Further, the pictures with brightness smaller than the first threshold value in the first picture or the pictures with sharpness smaller than the first threshold value in the first picture may be filtered, or only the pictures with brightness and sharpness smaller than the first threshold value at the same time may be filtered. Wherein the first threshold value can be set according to requirements. For example, 5 first pictures are obtained, which are numbered 1-5, picture No. 1 has a brightness of 10, a sharpness of 20, picture No. 2 has a brightness of 15, a sharpness of 15, picture No. 3 has a brightness of 5, a sharpness of 25, picture No. 4 has a brightness of 12, a sharpness of 16, picture No. 5 has a brightness of 8, and a sharpness of 17. The first threshold may be set to have a brightness of 12, and may filter out the picture No. 1 and the picture No. 3 having a brightness smaller than the first threshold, and may be set to have a resolution of 20, and may filter out the picture No. 2, the picture No. 4, and the picture No. 5 having a resolution smaller than the first threshold. The first threshold value can also be set to be 20 for brightness and 20 for sharpness, and picture No. 2, picture No. 4 and picture No. 5 which are simultaneously smaller than the first threshold value are filtered out.
S103: and determining a plurality of second pictures with the still degrees smaller than the still degree threshold value from the filtered plurality of first pictures.
The first device determines a plurality of second pictures with the still degree smaller than a still degree threshold value from the filtered plurality of first pictures. Wherein, the stillness is used to represent the still degree of a person in a picture, and may be the inverse of the square of the sum of pixel levels between successive frames per unit time.
To explain further, the first device may classify the filtered plurality of first pictures according to the motion characteristics of the person in the pictures to obtain a plurality of first picture sets, for example, the filtered plurality of first pictures includes pictures of drinking water, singing, and dancing of the person. The pictures of a person performing an action may be classified into a group to form a group, the first pictures may be divided into a plurality of picture groups, a preset number of second pictures with a degree of stillness smaller than a threshold value of the degree of stillness may be determined from each picture group, for example, the preset number may be 2, then 2 second pictures with a degree of stillness smaller than the threshold value of the degree of stillness may be determined from each group, and two pictures with a relatively lowest degree of stillness in each group may be determined as the second pictures.
S104: and generating a dynamic cover of the live broadcast room according to the plurality of second pictures.
The first device, after determining the plurality of second pictures, may synthesize the plurality of second pictures into a dynamic picture, and then determine the dynamic picture as a live room dynamic cover.
The method comprises the steps of obtaining a plurality of first pictures, filtering brightness in the first pictures, and/or determining a plurality of second pictures with the stillness smaller than a stillness threshold value from the filtered first pictures, and generating a live room dynamic cover according to the second pictures. In the method and the device, the low-frame pictures in the first picture can be filtered firstly, so that the pictures with too low brightness and/or definition in the first picture can be filtered, and then the plurality of second pictures with the stillness smaller than the stillness threshold value are determined from the plurality of filtered first pictures, so that the stillness of the person in the determined second picture is low, the figure outline can be seen clearly, and the figure in the picture is prevented from being blurred due to rapid movement. Therefore, a plurality of second pictures with relatively high quality are determined, and the dynamic cover of the live broadcast room is generated according to the plurality of second pictures, so that the problems that in the prior art, due to certain randomness of live broadcast contents corresponding to certain time points, the picture quality and the content quality of captured pictures cannot be guaranteed, and the generated dynamic cover possibly has poor quality are solved. The quality of the generated dynamic cover is improved, and the display effect of the dynamic cover map of the live broadcast room is optimized.
Fig. 2 is a flowchart of another live broadcast room dynamic cover generation method provided in the embodiment of the present application, and as shown in fig. 2, the method includes:
s201: a plurality of first pictures are acquired.
S202: and filtering the brightness and/or the low-frame pictures with the definition smaller than a first threshold value in the plurality of first pictures.
S203: and classifying the plurality of filtered first pictures according to the action characteristics of the human beings in the pictures to obtain a plurality of first picture sets.
S204: determining a preset number of second pictures with the still degrees smaller than a still degree threshold value from each first picture set.
S205: and inputting the second pictures into a preset training model for grading to obtain a plurality of grading results.
The first device can input the plurality of second pictures into a preset training model for scoring to obtain a plurality of scoring results.
It should be explained that the training model can be obtained by: and constructing feature vectors including face features, picture color features and basic quality features for the plurality of second pictures, and inputting the second pictures after the feature vectors are constructed into a basic neural network model for training to obtain a training model. Wherein the underlying neural network model may be a decision tree model. The face features may include: ASM-68 characteristic vector, 18-dimensional face distance characteristic and area characteristic. The picture color features may include: average HSV, center average HSV, HSV color histogram, HSV contrast. The base quality features may include: contrast balance, exposure balance, JPEG quality, and global sharpness.
The plurality of second pictures may then be input into a training model, which may score the pictures by their feature vectors. The score may be a percentage or a decimal.
S206: determining at least one third picture with a score result larger than a score threshold value from the plurality of second pictures.
The first device may sort the plurality of pictures according to the corresponding score results from large to small, and then determine at least one third picture with a score result larger than a score threshold from the plurality of second pictures, for example, the score threshold is set to 60 points, and the picture larger than 60 points may be determined as the third picture.
S207: and synthesizing the at least one third picture into a dynamic picture, and determining the dynamic picture as a live broadcast room dynamic cover.
Fig. 3 is a schematic structural diagram of a device for generating a dynamic cover of a live broadcast room according to an embodiment of the present application. As shown in fig. 3, the apparatus includes:
a first obtaining unit 300, configured to obtain a plurality of first pictures, where the first pictures are pictures captured in a live broadcast process;
a first filtering unit 310, configured to filter luminance in the plurality of first pictures, and/or a low-frame picture with sharpness smaller than a first threshold;
a first determining unit 320, configured to determine, from the filtered plurality of first pictures, a plurality of second pictures with a degree of stillness smaller than a threshold degree of stillness, where the degree of stillness is used to indicate a degree of stillness of a person in the pictures;
the first generating unit 330 is configured to generate a live-air live-room dynamic cover according to the plurality of second pictures.
Optionally, the first determining unit is specifically configured to:
classifying the plurality of filtered first pictures according to the action characteristics of the human beings in the pictures to obtain a plurality of first picture sets;
determining a preset number of second pictures with the still degrees smaller than a still degree threshold value from each first picture set.
Optionally, the apparatus further comprises:
the scoring unit is used for inputting the second pictures into a preset training model for scoring to obtain a plurality of scoring results;
a second determining unit, configured to determine, from the plurality of second pictures, at least one third picture whose scoring result is greater than a score threshold;
and the second generating unit is used for generating a dynamic cover according to the at least one third picture.
Optionally, the training model is obtained by:
constructing a feature vector for the plurality of second pictures, the feature vector comprising: human face characteristics, picture color characteristics and basic quality characteristics;
and inputting the second picture after the characteristic vector is constructed into a basic neural network model for training to obtain a training model.
Optionally, the first generating unit is specifically configured to:
synthesizing the plurality of second pictures into dynamic pictures;
and determining the dynamic picture as a dynamic cover of the live broadcast room.
In the device, a first obtaining unit 300 obtains a plurality of first pictures, a first filtering unit 310 filters brightness and/or low-frame pictures with definition smaller than a first threshold value in the plurality of first pictures, a first determining unit determines a plurality of second pictures with the stillness smaller than a stillness threshold value from the plurality of filtered first pictures, and a first generating unit generates a dynamic cover of a live broadcast room according to the plurality of second pictures. In the method and the device, the low-frame pictures in the first picture can be filtered firstly, so that the pictures with too low brightness and/or definition in the first picture can be filtered, and then the plurality of second pictures with the stillness smaller than the stillness threshold value are determined from the plurality of filtered first pictures, so that the stillness of the person in the determined second picture is low, the figure outline can be seen clearly, and the figure in the picture is prevented from being blurred due to rapid movement. Therefore, a plurality of second pictures with relatively high quality are determined, and the dynamic cover of the live broadcast room is generated according to the plurality of second pictures, so that the problems that in the prior art, due to certain randomness of live broadcast contents corresponding to certain time points, the picture quality and the content quality of captured pictures cannot be guaranteed, and the generated dynamic cover possibly has poor quality are solved. The quality of the generated dynamic cover is improved, and the display effect of the dynamic cover map of the live broadcast room is optimized.
The embodiment of the application also provides corresponding equipment and a computer storage medium, which are used for realizing the scheme provided by the embodiment of the application.
Wherein the apparatus comprises a memory for storing instructions or code and a processor for executing the instructions or code to cause the apparatus to perform the method of any embodiment of the present application.
The computer storage medium has code stored therein that, when executed, causes an apparatus that executes the code to implement a method as described in any of the embodiments of the present application.
In the embodiments of the present application, the names "first" and "second" (if present) in the names "first" and "second" are used for name identification, and do not represent the first and second in sequence.
As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by software plus a general hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a read-only memory (ROM)/RAM, a magnetic disk, an optical disk, or the like, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the method according to the embodiments or some parts of the embodiments of the present application.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only an exemplary embodiment of the present application, and is not intended to limit the scope of the present application.
Claims (10)
1. A live broadcast room dynamic cover generation method is characterized by comprising the following steps:
acquiring a plurality of first pictures, wherein the first pictures are pictures intercepted in a live broadcast process;
filtering brightness in the plurality of first pictures and/or low-frame pictures with definition smaller than a first threshold value;
determining a plurality of second pictures with the still degrees smaller than a still degree threshold value from the plurality of filtered first pictures, wherein the still degrees are used for representing the still degrees of the people in the pictures;
and generating a live broadcast room dynamic cover according to the plurality of second pictures.
2. The method of claim 1, wherein determining a plurality of second pictures from the filtered plurality of first pictures with a degree of stillness less than a threshold degree of stillness comprises:
classifying the filtered first pictures according to the action characteristics of the human beings in the pictures to obtain a plurality of first picture sets;
determining a preset number of second pictures with the still degrees smaller than a still degree threshold value from each first picture set.
3. The method of claim 1, wherein after the determining a plurality of second pictures with a degree of stillness less than a threshold degree of stillness from the filtered plurality of first pictures, the method further comprises:
inputting the second pictures into a preset training model for grading to obtain a plurality of grading results;
determining at least one third picture with a score result larger than a score threshold value from the plurality of second pictures;
and generating a dynamic cover according to the at least one third picture.
4. The method of claim 3, wherein the training model is obtained by:
constructing a feature vector for the plurality of second pictures, the feature vector comprising: face features, picture color features, and basic quality features;
and inputting the second picture after the characteristic vector is constructed into a basic neural network model for training to obtain a training model.
5. The method of claim 1, wherein generating a dynamic cover from the plurality of second pictures comprises:
synthesizing the plurality of second pictures into dynamic pictures;
and determining the dynamic picture as a dynamic cover of the live broadcast room.
6. A live room dynamic cover generation apparatus, comprising:
the device comprises a first acquisition unit, a second acquisition unit and a display unit, wherein the first acquisition unit is used for acquiring a plurality of first pictures, and the first pictures are pictures intercepted in a live broadcast process;
the first filtering unit is used for filtering the brightness in the first pictures and/or the low-frame pictures with the definition smaller than a first threshold value;
a first determining unit, configured to determine, from the filtered plurality of first pictures, a plurality of second pictures with a degree of stillness smaller than a threshold degree of stillness, where the degree of stillness is used to indicate a degree of stillness of a person in the pictures;
and the first generating unit is used for generating a live broadcast room dynamic cover according to the plurality of second pictures.
7. The apparatus according to claim 6, wherein the first determining unit is specifically configured to:
classifying the filtered first pictures according to the action characteristics of the human beings in the pictures to obtain a plurality of first picture sets;
determining a preset number of second pictures with the still degrees smaller than a still degree threshold value from each first picture set.
8. The apparatus of claim 6, further comprising:
the scoring unit is used for inputting the second pictures into a preset training model for scoring to obtain a plurality of scoring results;
a second determining unit, configured to determine, from the plurality of second pictures, at least one third picture whose scoring result is greater than a score threshold;
and the second generating unit is used for generating a dynamic cover according to the at least one third picture.
9. The apparatus of claim 8, wherein the training model is obtained by:
constructing a feature vector for the plurality of second pictures, the feature vector comprising: human face characteristics, picture color characteristics and basic quality characteristics;
and inputting the second picture after the characteristic vector is constructed into a basic neural network model for training to obtain a training model.
10. The apparatus according to claim 6, wherein the first generating unit is specifically configured to:
synthesizing the plurality of second pictures into dynamic pictures;
and determining the dynamic picture as a dynamic cover of the live broadcast room.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210933437.5A CN115065855A (en) | 2022-08-04 | 2022-08-04 | Live broadcast room dynamic cover generation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210933437.5A CN115065855A (en) | 2022-08-04 | 2022-08-04 | Live broadcast room dynamic cover generation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115065855A true CN115065855A (en) | 2022-09-16 |
Family
ID=83207868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210933437.5A Pending CN115065855A (en) | 2022-08-04 | 2022-08-04 | Live broadcast room dynamic cover generation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115065855A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10404923B1 (en) * | 2018-10-29 | 2019-09-03 | Henry M. Pena | Real time video special effects system and method |
| CN110879851A (en) * | 2019-10-15 | 2020-03-13 | 北京三快在线科技有限公司 | Video dynamic cover generation method and device, electronic equipment and readable storage medium |
| CN111918130A (en) * | 2020-08-11 | 2020-11-10 | 北京达佳互联信息技术有限公司 | Video cover determining method and device, electronic equipment and storage medium |
| CN112948612A (en) * | 2021-03-16 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Human body cover generation method and device, electronic equipment and storage medium |
| CN114741559A (en) * | 2022-03-21 | 2022-07-12 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, apparatus and storage medium for determining video cover |
| CN114845158A (en) * | 2022-04-11 | 2022-08-02 | 广州虎牙科技有限公司 | Video cover generation method, video publishing method and related equipment |
-
2022
- 2022-08-04 CN CN202210933437.5A patent/CN115065855A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10404923B1 (en) * | 2018-10-29 | 2019-09-03 | Henry M. Pena | Real time video special effects system and method |
| CN110879851A (en) * | 2019-10-15 | 2020-03-13 | 北京三快在线科技有限公司 | Video dynamic cover generation method and device, electronic equipment and readable storage medium |
| CN111918130A (en) * | 2020-08-11 | 2020-11-10 | 北京达佳互联信息技术有限公司 | Video cover determining method and device, electronic equipment and storage medium |
| CN112948612A (en) * | 2021-03-16 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Human body cover generation method and device, electronic equipment and storage medium |
| CN114741559A (en) * | 2022-03-21 | 2022-07-12 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, apparatus and storage medium for determining video cover |
| CN114845158A (en) * | 2022-04-11 | 2022-08-02 | 广州虎牙科技有限公司 | Video cover generation method, video publishing method and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109068056B (en) | Electronic equipment, filter processing method of image shot by electronic equipment and storage medium | |
| KR101479387B1 (en) | Methods and apparatuses for face detection | |
| CN105451029B (en) | A kind of processing method and processing device of video image | |
| CN111985281B (en) | Image generation model generation method and device and image generation method and device | |
| CN107172482B (en) | Method and device for generating image with interchangeable format | |
| CN113012081A (en) | Image processing method, device and electronic system | |
| CN108961260B (en) | Image binarization method and device and computer storage medium | |
| CN111183630B (en) | Photo processing method and processing device of intelligent terminal | |
| CN110958469A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN111445424B (en) | Image processing method, device, equipment and medium for processing mobile terminal video | |
| CN107958441A (en) | Image split-joint method, device, computer equipment and storage medium | |
| CN112818737A (en) | Video identification method and device, storage medium and terminal | |
| CN113038185B (en) | Bullet screen processing method and device | |
| CN113242392A (en) | Short video production method | |
| CN115482529A (en) | Method, equipment, storage medium and device for recognizing fruit image in near scene | |
| CN111144156B (en) | Image data processing method and related device | |
| CN111259907A (en) | Content identification method and device and electronic equipment | |
| CN113538304A (en) | Training method and device of image enhancement model, and image enhancement method and device | |
| CN115065855A (en) | Live broadcast room dynamic cover generation method and device | |
| CN112839167A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN109040778B (en) | Video cover determining method, user equipment, storage medium and device | |
| KR20230086999A (en) | A recording medium recording a virtual character content creation program | |
| KR20230086998A (en) | A computer program that creates virtual character contnet by adding noise to face segment regions | |
| KR20230086996A (en) | A computer program that performs the noise addition process | |
| CN111859022A (en) | Cover generation method, electronic device and computer-readable storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220916 |