CN117061698B - Hidden immersion type teleconference channel establishment method and system - Google Patents
Hidden immersion type teleconference channel establishment method and system Download PDFInfo
- Publication number
- CN117061698B CN117061698B CN202311316933.7A CN202311316933A CN117061698B CN 117061698 B CN117061698 B CN 117061698B CN 202311316933 A CN202311316933 A CN 202311316933A CN 117061698 B CN117061698 B CN 117061698B
- Authority
- CN
- China
- Prior art keywords
- video
- acquisition
- matching degree
- definition
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000007654 immersion Methods 0.000 title description 6
- 230000005540 biological transmission Effects 0.000 claims abstract description 34
- 230000008569 process Effects 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 18
- 230000002776 aggregation Effects 0.000 claims description 12
- 238000004220 aggregation Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000003213 activating effect Effects 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 230000006872 improvement Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1069—Session establishment or de-establishment
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/40—Support for services or applications
- H04L65/403—Arrangements for multi-party communication, e.g. for conferences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/80—Responding to QoS
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
- H04N7/15—Conference systems
- H04N7/155—Conference systems involving storage of or access to video conference sessions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention relates to the technical field of video transmission, and particularly discloses a method and a system for establishing a hidden immersive teleconference channel, wherein the method comprises the steps of acquiring the position of a video acquisition end based on positioning equipment at fixed time, and adjusting the acquisition definition of the video acquisition end in real time according to the position; receiving a scene video containing a scene name uploaded by a video acquisition terminal, identifying the scene video based on a scene feature library, and updating the matching degree; and carrying out secondary adjustment on the acquisition definition according to the matching degree, and determining the video priority according to the acquisition definition after secondary adjustment. The method and the device preliminarily determine the video acquisition definition by analyzing the position of the acquisition end, query scene characteristics on the basis, predict video content, compare a prediction result with an actual video, calculate matching degree, secondarily adjust the definition according to the calculated matching degree, and re-determine the processing priority according to the final definition, thereby ensuring the video quality and optimizing the transmission process.
Description
Technical Field
The invention relates to the technical field of video transmission, in particular to a method and a system for establishing a hidden immersive teleconference channel.
Background
The existing remote conference setting-up service is mostly an instant messaging service, and the video conference requests of both sides are received, so that a video transmission channel is established, and the channel needs to be completed by both sides together. In some cases, the video transaction process does not need to ensure real-time performance, for example, one party sends a live video and does not need to receive the live video in real time, the video transaction process can be a packaged video, the other party can inquire the video in a space-time manner, the service is also related in the prior art, for example, in daily social software, the video file can be sent and stored in a local or cloud side, and the other party can autonomously determine the inquiry time.
For this scheme, if there is a one-to-one transmission process, too many discussions are not needed, but if there is a one-to-many scenario, then the analysis priority of multiple field videos is an important problem, under the existing device performance, the data volume of the acquired videos is very large, and the processing resources of the master control end are limited, how to determine the priority of each video under the one-to-many scenario is a technical problem that the technical scheme of the present invention wants to solve.
Disclosure of Invention
The invention aims to provide a hidden immersive teleconference channel establishment method and system, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a hidden immersive teleconferencing channel establishment method, the method comprising:
s100: the method comprises the steps of acquiring the position of a video acquisition end based on positioning equipment at regular time, and adjusting the acquisition definition of the video acquisition end in real time according to the position;
s200: receiving a scene video containing a scene name uploaded by a video acquisition terminal, and reading a scene feature library based on the scene name;
s300: identifying the field video based on the scene feature library, and updating the matching degree;
s400: performing secondary adjustment on the acquisition definition according to the matching degree, and determining video priority according to the acquisition definition after secondary adjustment; wherein, the video priority is inversely proportional to the acquisition definition;
s500: and creating a transmission channel according to the video priority, and forwarding the live video based on the transmission channel.
As a further scheme of the invention: the step of timely acquiring the position of the video acquisition end based on the positioning equipment and adjusting the acquisition definition of the video acquisition end in real time according to the position comprises the following steps:
activating positioning equipment in the video acquisition end and establishing a transmission channel with the positioning equipment when binding a user and the video acquisition end;
receiving and counting the position reported by the positioning equipment based on the transmission channel timing; when receiving the position, calculating the movement speed according to the position, and judging the effectiveness of the position according to the movement speed;
reading a position according to a preset frequency, and updating a position representation according to the position; the updating process is to increment a preset numerical value at the position;
and traversing the position representation in a timing way, and determining the acquisition definition of the current position based on the position representation.
As a further scheme of the invention: the step of determining the acquisition definition of the current position based on the position representation comprises the steps of:
the timing reading position representation is converted into a numerical matrix;
traversing the numerical matrix, and calculating the data density and the data aggregation degree in a preset range;
determining an acquisition level according to the data density and the data aggregation degree, and inquiring acquisition definition in a preset parameter table according to the acquisition level; the parameter table comprises level items and parameter items;
the calculation formula of the data density is as follows:
the calculation formula of the data uniformity is as follows:
in the method, in the process of the invention,for data density, N is the total number of rows in the preset range, M is the total number of columns in the preset range, +.>The numerical value at the j-th column of the i-th row, S is the area of the preset range; />Data uniformity>A vector formed by the points of the ith row and the jth column and the center; />For adjusting the coefficients.
As a further scheme of the invention: the step of identifying the field video based on the scene feature library and updating the matching degree comprises the following steps:
reading a live video, and extracting images from the live video according to a preset interval duration to obtain an image group;
reading scene features from a scene feature library, traversing the image group according to the scene features, and recording the times that the similarity reaches a preset threshold value;
updating the matching degree according to the times;
the similarity calculation process adopts a pearson correlation coefficient, and a calculation formula of the pearson correlation coefficient comprises:
in the method, in the process of the invention,similarity between regions to be compared for a certain block of a certain image in scene feature and live video, +.>For the total number of points in the scene feature, +.>For the pixel mean in the scene feature, +.>For the kth pixel value in the scene feature, < +.>Pixel mean value of region to be aligned for a certain block of a certain image in live video, ++>The k pixel value in the region to be aligned for a certain block of a certain image in the live video.
As a further scheme of the invention: the step of secondarily adjusting the acquisition definition according to the matching degree and determining the video priority according to the secondarily adjusted acquisition definition comprises the following steps:
counting the matching degree based on the updating times, and fitting a matching degree change curve;
calculating a derivative curve of the matching degree change curve;
intercepting curve segments in a matching degree change curve according to preset backtracking time, and calculating a matching degree mean value;
reading derivative curve segments corresponding to the curve segments, and calculating a derivative mean value;
and carrying out secondary adjustment on the acquisition definition according to the average value of the matching degree and the average value of the derivative, and determining the video priority according to the acquisition definition after secondary adjustment.
As a further scheme of the invention: the step of secondarily adjusting the acquisition definition according to the average value of the matching degree and the average value of the derivative, and determining the video priority according to the secondarily adjusted acquisition definition comprises the following steps:
when the matching degree mean value is smaller than a preset matching degree threshold value and the derivative mean value is larger than a preset derivative threshold value, the acquisition definition is improved based on the first improvement rate;
when the matching degree mean value is smaller than a preset matching degree threshold value and the derivative mean value is smaller than a preset derivative threshold value, the acquisition definition is improved based on the second improvement rate; wherein the second rate of increase is greater than the first rate of increase;
step S400 is circularly executed until a preset jump-out condition is reached; the jump-out condition comprises that the average value of the matching degree reaches a preset matching degree threshold value and the acquisition definition reaches a preset definition threshold value;
recording acquisition definition when the circulation is jumped out, and determining video priority according to a preset inverse relation.
The technical scheme of the invention also provides a hidden immersive teleconference channel establishment system, which comprises:
the definition setting module is used for acquiring the position of the video acquisition end based on the timing of the positioning equipment and adjusting the acquisition definition of the video acquisition end in real time according to the position;
the feature library inquiry module is used for receiving the scene video containing the scene name uploaded by the video acquisition end and reading a scene feature library based on the scene name;
the matching degree updating module is used for identifying the field video based on the scene feature library and updating the matching degree;
the priority determining module is used for secondarily adjusting the acquisition definition according to the matching degree and determining the video priority according to the acquisition definition after the secondary adjustment; wherein, the video priority is inversely proportional to the acquisition definition;
and the video transmission module is used for creating a transmission channel according to the video priority and forwarding the field video based on the transmission channel.
As a further scheme of the invention: the definition setting module includes:
the channel activating unit is used for activating the positioning equipment in the video acquisition end and establishing a transmission channel with the positioning equipment when the user and the video acquisition end are bound;
the position statistics unit is used for receiving and counting the position reported by the positioning equipment based on the transmission channel timing; when receiving the position, calculating the movement speed according to the position, and judging the effectiveness of the position according to the movement speed;
a representation updating unit for reading the position according to a preset frequency and updating the position representation according to the position; the updating process is to increment a preset numerical value at the position;
and the traversing unit is used for traversing the position representation in a timing way, and determining the acquisition definition of the current position based on the position representation.
As a further scheme of the invention: the matching degree updating module comprises:
the image extraction unit is used for reading the live video, extracting images from the live video according to the preset interval duration and obtaining an image group;
the frequency recording unit is used for reading scene characteristics from the scene characteristic library, traversing the image group according to the scene characteristics, and recording the frequency of the similarity reaching a preset threshold value;
the matching degree updating unit is used for updating the matching degree according to the times;
the similarity calculation process adopts a pearson correlation coefficient, and a calculation formula of the pearson correlation coefficient comprises:
in the method, in the process of the invention,similarity between regions to be compared for a certain block of a certain image in scene feature and live video, +.>For the total number of points in the scene feature, +.>For the pixel mean in the scene feature, +.>For the kth pixel value in the scene feature, < +.>Pixel mean value of region to be aligned for a certain block of a certain image in live video, ++>The k pixel value in the region to be aligned for a certain block of a certain image in the live video.
As a further scheme of the invention: the priority determining module includes:
the curve fitting unit is used for counting the matching degree based on the updating times and fitting a matching degree change curve;
the derivative calculation unit is used for calculating a derivative curve of the matching degree change curve;
the first calculation unit is used for intercepting curve segments in the matching degree change curve according to the preset backtracking time and calculating a matching degree mean value;
the second calculation unit is used for reading derivative curve segments corresponding to the curve segments and calculating a derivative mean value;
and the execution unit is used for secondarily adjusting the acquisition definition according to the matching degree mean value and the derivative mean value, and determining the video priority according to the acquisition definition after the secondary adjustment.
Compared with the prior art, the invention has the beneficial effects that: the method and the device preliminarily determine the video acquisition definition by analyzing the position of the acquisition end, on the basis, query scene characteristics based on scene names, predict video contents, compare a prediction result with actual videos, calculate matching degree, secondarily adjust the definition according to the calculated matching degree, and finally, re-determine the processing priority according to the definition, thereby ensuring the video quality and optimizing the transmission process.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 is a flow diagram of a hidden immersive teleconferencing channel establishment method.
Fig. 2 is a block diagram of the components of a hidden immersive teleconferencing channel-building system.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 shows a flow chart of a method for establishing a hidden immersion type teleconference channel, and in an embodiment of the present invention, a method for establishing a hidden immersion type teleconference channel includes:
s100: the method comprises the steps of acquiring the position of a video acquisition end based on positioning equipment at regular time, and adjusting the acquisition definition of the video acquisition end in real time according to the position;
s200: receiving a scene video containing a scene name uploaded by a video acquisition terminal, and reading a scene feature library based on the scene name;
s300: identifying the field video based on the scene feature library, and updating the matching degree;
s400: performing secondary adjustment on the acquisition definition according to the matching degree, and determining video priority according to the acquisition definition after secondary adjustment; wherein, the video priority is inversely proportional to the acquisition definition;
s500: and creating a transmission channel according to the video priority, and forwarding the live video based on the transmission channel.
The video acquisition end is an electronic device with a video acquisition function, the electronic device comprises positioning equipment, the position of the electronic device can be acquired in real time and reported to a platform (an operation main body of the method, generally a server cluster), the position of the electronic device is analyzed, an initial definition can be determined, and under the general condition, the initial definition is very low; the position is analyzed, so that the current situation of the user can be judged, and the definition is distinguished in a lower definition range based on the situation; the reference logic is distinguished in that in areas which are not frequently present, the sharpness is slightly higher and in areas which are frequently present, the sharpness is slightly lower.
The video acquisition end acquires the field video under the condition of acquisition definition, on the basis, staff can synchronously upload scene names through the video acquisition end, and the platform can read a scene feature library according to the scene names; in one working process, the scene is limited, and scene characteristics are limited, so that the pre-statistics can be performed; in view of convenience, face features may be employed as scene features, i.e. under a certain scene name, which people need to appear.
Furthermore, the read scene feature library is used for carrying out traversal recognition on the field video, so that the matching degree can be calculated, the matching degree represents the matching degree between the field video and the theoretical prediction process, the higher the matching degree is, the more conventional the field video is, the lower the definition can be, if the matching degree is lower, the mismatch caused by the definition process is likely, and at the moment, the definition needs to be improved.
Finally, as can be seen from the logic, the higher the final definition, the less common the application scene (the less frequently occurring area and the lower the matching degree), the larger the data volume, and the effective information volume contained in the data volume may be very low, so that the application firstly performs forwarding analysis (high speed and more effective information volume) on the field video with lower definition, and better distributes the limited platform resources.
The on-site video is forwarded to the corresponding target user, and the process can have a certain time delay, similar to the existing instant messaging App, and query feedback is performed when the target user is available.
As a preferred embodiment of the present invention, the above-mentioned step S100 is defined as follows:
activating positioning equipment in the video acquisition end and establishing a transmission channel with the positioning equipment when binding a user and the video acquisition end;
receiving and counting the position reported by the positioning equipment based on the transmission channel timing; when receiving the position, calculating the movement speed according to the position, and judging the effectiveness of the position according to the movement speed;
reading a position according to a preset frequency, and updating a position representation according to the position; the updating process is to increment a preset numerical value at the position;
and traversing the position representation in a timing way, and determining the acquisition definition of the current position based on the position representation.
In an example of the technical scheme of the invention, the first distinguishing process of definition is specifically described, the principle is that the position is obtained, and whether the current video obtaining process is conventional or not is judged according to the position; the judgment mode is that the positions at different moments are counted in one image (map) to obtain a position representation image, the position representation image is analyzed, and the acquisition definition is distinguished according to the analysis result.
Specifically, the step of traversing the position representation at fixed time and determining the acquisition definition of the current position based on the position representation includes:
the timing reading position representation is converted into a numerical matrix;
traversing the numerical matrix, and calculating the data density and the data aggregation degree in a preset range;
determining an acquisition level according to the data density and the data aggregation degree, and inquiring acquisition definition in a preset parameter table according to the acquisition level; the parameter table comprises level items and parameter items;
the timing reading position representation diagram is an image and two-dimensional data, namely a matrix in nature, and the conversion process into a numerical matrix is very simple; then, traversing each row and column position, and calculating data density and data aggregation degree, wherein the data density is used for collecting the stay time (numerical value) of a video end in the vicinity (preset range) of the video end by taking the row and column position as the center; the data aggregation degree represents the numerical uniformity around the point location; taking the data density and the data aggregation degree as input and the acquisition level as output, and training a mapping from the data density and the data aggregation degree to the acquisition level; in the actual analysis, the mapping is applied.
The calculation formula of the data density is as follows:
the calculation formula of the data uniformity is as follows:
in the method, in the process of the invention,for data density, N is the total number of rows in the preset range, M is the total number of columns in the preset range, +.>The numerical value at the j-th column of the i-th row, S is the area of the preset range; />Data uniformity>A vector formed by the points of the ith row and the jth column and the center; />For adjusting the coefficients.
In the above description, the data density is the sum of all values and the data uniformity is the value multiplied by the current position vector, and then all the position vectors are summed to obtain a combined vector, and the modular length of the combined vector is inversely proportional to the data uniformity, so that the modular length of the combined vector needs to be inverted and multiplied by the adjustment coefficient.
As a preferred embodiment of the present invention, the step of identifying the live video based on the scene feature library and updating the matching degree includes:
reading a live video, and extracting images from the live video according to a preset interval duration to obtain an image group;
reading scene features from a scene feature library, traversing the image group according to the scene features, and recording the times that the similarity reaches a preset threshold value;
updating the matching degree according to the times;
the similarity calculation process adopts a pearson correlation coefficient, and a calculation formula of the pearson correlation coefficient comprises:
in the method, in the process of the invention,similarity between regions to be compared for a certain block of a certain image in scene feature and live video, +.>For the total number of points in the scene feature, +.>For the pixel mean in the scene feature, +.>For the kth pixel value in the scene feature, < +.>Pixel mean value of region to be aligned for a certain block of a certain image in live video, ++>The k pixel value in the region to be aligned for a certain block of a certain image in the live video.
In an example of the technical scheme of the invention, the field video is converted into the image group, the images are sequentially read, then the size of the region to be compared in the primary comparison process is determined according to the size of the scene feature, and the similarity can be calculated by comparing the image feature with the region to be compared.
Although the above k=1 to k=l are one-dimensional summation expressions, it is actually summation expressions for one region, and pixel values in one region are summed in a certain order (from left to right, from top to bottom).
As a preferred embodiment of the present invention, the step of secondarily adjusting the acquisition sharpness according to the matching degree, and determining the video priority according to the secondarily adjusted acquisition sharpness includes:
counting the matching degree based on the updating times, and fitting a matching degree change curve;
calculating a derivative curve of the matching degree change curve;
intercepting curve segments in a matching degree change curve according to preset backtracking time, and calculating a matching degree mean value;
reading derivative curve segments corresponding to the curve segments, and calculating a derivative mean value;
and carrying out secondary adjustment on the acquisition definition according to the average value of the matching degree and the average value of the derivative, and determining the video priority according to the acquisition definition after secondary adjustment.
Further, the step of secondarily adjusting the acquisition definition according to the matching degree mean value and the derivative mean value and determining the video priority according to the secondarily adjusted acquisition definition includes:
when the matching degree mean value is smaller than a preset matching degree threshold value and the derivative mean value is larger than a preset derivative threshold value, the acquisition definition is improved based on the first improvement rate;
when the matching degree mean value is smaller than a preset matching degree threshold value and the derivative mean value is smaller than a preset derivative threshold value, the acquisition definition is improved based on the second improvement rate; wherein the second rate of increase is greater than the first rate of increase;
step S400 is circularly executed until a preset jump-out condition is reached; the jump-out condition comprises that the average value of the matching degree reaches a preset matching degree threshold value and the acquisition definition reaches a preset definition threshold value;
recording acquisition definition when the circulation is jumped out, and determining video priority according to a preset inverse relation.
The above-mentioned content is an integrated scheme, the principle is that the average value of the matching degree and the average value of the derivative thereof in a period of time are calculated, if the average value of the matching degree is lower, the situation that the on-site video is not in conformity with the scene characteristics in the period of time is indicated, on the basis, if the derivative thereof is almost zero, the situation that the on-site video is not in conformity with the scene characteristics in a long time in the period of time is indicated, at the moment, the possibility that the scene has problems is higher, the definition needs to be improved at a higher speed, if the average value of the matching degree is still not in conformity with the requirement in the highest definition, the on-site video is acquired at the highest definition, and accordingly, the forwarding priority is lower, which means that the quality of the on-site video is high, but the processing sequence is later.
Further, if the mean value of the matching degree is lower, but the mean value of the derivative is higher, at this time, the likelihood that the sharpness is the cause of the mismatch is higher, and the sharpness is continuously improved at a lower speed until the mean value of the matching degree reaches the threshold value of the matching degree.
In summary, the above-mentioned scheme aims at improving the video quality when the scene video is not in conformity with the scene feature, but reducing its processing priority, the video quality guarantees the judgment accuracy of easy ordinary condition, the processing priority guarantees that the video of large data volume will not occupy too much transmission resource.
Fig. 2 is a component structure diagram of a hidden immersion teleconference channel establishment system, and the technical solution of the present invention further provides a hidden immersion teleconference channel establishment system, where the system 10 includes:
the definition setting module 11 is used for acquiring the position of the video acquisition end based on the timing of the positioning equipment and adjusting the acquisition definition of the video acquisition end in real time according to the position;
the feature library inquiry module 12 is used for receiving the scene video with the scene name uploaded by the video acquisition end and reading a scene feature library based on the scene name;
the matching degree updating module 13 is used for identifying the field video based on the scene feature library and updating the matching degree;
the priority determining module 14 is configured to secondarily adjust the acquisition sharpness according to the matching degree, and determine the video priority according to the secondarily adjusted acquisition sharpness; wherein, the video priority is inversely proportional to the acquisition definition;
the video transmission module 15 is configured to create a transmission channel according to the video priority, and forward the live video based on the transmission channel.
Further, the sharpness setting module 11 includes:
the channel activating unit is used for activating the positioning equipment in the video acquisition end and establishing a transmission channel with the positioning equipment when the user and the video acquisition end are bound;
the position statistics unit is used for receiving and counting the position reported by the positioning equipment based on the transmission channel timing; when receiving the position, calculating the movement speed according to the position, and judging the effectiveness of the position according to the movement speed;
a representation updating unit for reading the position according to a preset frequency and updating the position representation according to the position; the updating process is to increment a preset numerical value at the position;
and the traversing unit is used for traversing the position representation in a timing way, and determining the acquisition definition of the current position based on the position representation.
Specifically, the matching degree updating module 13 includes:
the image extraction unit is used for reading the live video, extracting images from the live video according to the preset interval duration and obtaining an image group;
the frequency recording unit is used for reading scene characteristics from the scene characteristic library, traversing the image group according to the scene characteristics, and recording the frequency of the similarity reaching a preset threshold value;
the matching degree updating unit is used for updating the matching degree according to the times;
the similarity calculation process adopts a pearson correlation coefficient, and a calculation formula of the pearson correlation coefficient comprises:
in the method, in the process of the invention,similarity between regions to be compared for a certain block of a certain image in scene feature and live video, +.>For the total number of points in the scene feature, +.>For the pixel mean in the scene feature, +.>For the kth pixel value in the scene feature, < +.>Pixel mean value of region to be aligned for a certain block of a certain image in live video, ++>The k pixel value in the region to be aligned for a certain block of a certain image in the live video.
Still further, the priority determining module 14 includes:
the curve fitting unit is used for counting the matching degree based on the updating times and fitting a matching degree change curve;
the derivative calculation unit is used for calculating a derivative curve of the matching degree change curve;
the first calculation unit is used for intercepting curve segments in the matching degree change curve according to the preset backtracking time and calculating a matching degree mean value;
the second calculation unit is used for reading derivative curve segments corresponding to the curve segments and calculating a derivative mean value;
and the execution unit is used for secondarily adjusting the acquisition definition according to the matching degree mean value and the derivative mean value, and determining the video priority according to the acquisition definition after the secondary adjustment.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. A method of establishing a hidden immersive teleconference channel, the method comprising:
s100: the method comprises the steps of acquiring the position of a video acquisition end based on positioning equipment at regular time, and adjusting the acquisition definition of the video acquisition end in real time according to the position;
s200: receiving a scene video containing a scene name uploaded by a video acquisition terminal, and reading a scene feature library based on the scene name;
s300: identifying the field video based on the scene feature library, and updating the matching degree;
s400: performing secondary adjustment on the acquisition definition according to the matching degree, and determining video priority according to the acquisition definition after secondary adjustment; wherein, the video priority is inversely proportional to the acquisition definition;
s500: creating a transmission channel according to the video priority, and forwarding the field video based on the transmission channel;
the step of timely acquiring the position of the video acquisition end based on the positioning equipment and adjusting the acquisition definition of the video acquisition end in real time according to the position comprises the following steps:
activating positioning equipment in the video acquisition end and establishing a transmission channel with the positioning equipment when binding a user and the video acquisition end;
receiving and counting the position reported by the positioning equipment based on the transmission channel timing; when receiving the position, calculating the movement speed according to the position, and judging the effectiveness of the position according to the movement speed;
reading a position according to a preset frequency, and updating a position representation according to the position; the updating process is to increment a preset numerical value at the position;
traversing the position representation in a timing manner, and determining the acquisition definition of the current position based on the position representation;
the step of determining the acquisition definition of the current position based on the position representation comprises the steps of:
the timing reading position representation is converted into a numerical matrix;
traversing the numerical matrix, and calculating the data density and the data aggregation degree in a preset range;
determining an acquisition level according to the data density and the data aggregation degree, and inquiring acquisition definition in a preset parameter table according to the acquisition level; the parameter table comprises level items and parameter items;
the calculation formula of the data density is as follows:
the calculation formula of the data uniformity is as follows:
in the method, in the process of the invention,for data density, N is the total number of rows in the preset range, M is the total number of columns in the preset range, +.>The numerical value at the j-th column of the i-th row, S is the area of the preset range; />Data uniformity>A vector formed by the points of the ith row and the jth column and the center; />For adjusting the coefficients.
2. The method of claim 1, wherein the step of identifying the live video based on the scene feature library and updating the matching degree comprises:
reading a live video, and extracting images from the live video according to a preset interval duration to obtain an image group;
reading scene features from a scene feature library, traversing the image group according to the scene features, and recording the times that the similarity reaches a preset threshold value;
updating the matching degree according to the times;
the similarity calculation process adopts a pearson correlation coefficient, and a calculation formula of the pearson correlation coefficient comprises:
in the method, in the process of the invention,similarity between regions to be compared for a certain block of a certain image in scene feature and live video, +.>For the total number of points in the scene feature, +.>For the pixel mean in the scene feature, +.>For the kth pixel value in the scene feature, < +.>Pixel mean value of region to be aligned for a certain block of a certain image in live video, ++>The k pixel value in the region to be aligned for a certain block of a certain image in the live video.
3. The method of claim 1, wherein the step of secondarily adjusting the acquisition sharpness according to the matching degree and determining the video priority according to the secondarily adjusted acquisition sharpness comprises:
counting the matching degree based on the updating times, and fitting a matching degree change curve;
calculating a derivative curve of the matching degree change curve;
intercepting curve segments in a matching degree change curve according to preset backtracking time, and calculating a matching degree mean value;
reading derivative curve segments corresponding to the curve segments, and calculating a derivative mean value;
and carrying out secondary adjustment on the acquisition definition according to the average value of the matching degree and the average value of the derivative, and determining the video priority according to the acquisition definition after secondary adjustment.
4. The method of claim 3, wherein the step of secondarily adjusting the acquisition sharpness according to the average value of the matching degree and the average value of the derivative, and determining the video priority according to the secondarily adjusted acquisition sharpness comprises:
when the matching degree mean value is smaller than a preset matching degree threshold value and the derivative mean value is larger than a preset derivative threshold value, the acquisition definition is improved based on the first improvement rate;
when the matching degree mean value is smaller than a preset matching degree threshold value and the derivative mean value is smaller than a preset derivative threshold value, the acquisition definition is improved based on the second improvement rate; wherein the second rate of increase is greater than the first rate of increase;
step S400 is circularly executed until a preset jump-out condition is reached; the jump-out condition comprises that the average value of the matching degree reaches a preset matching degree threshold value and the acquisition definition reaches a preset definition threshold value;
recording acquisition definition when the circulation is jumped out, and determining video priority according to a preset inverse relation.
5. A hidden immersive teleconferencing channel establishment system, the system comprising:
the definition setting module is used for acquiring the position of the video acquisition end based on the timing of the positioning equipment and adjusting the acquisition definition of the video acquisition end in real time according to the position;
the feature library inquiry module is used for receiving the scene video containing the scene name uploaded by the video acquisition end and reading a scene feature library based on the scene name;
the matching degree updating module is used for identifying the field video based on the scene feature library and updating the matching degree;
the priority determining module is used for secondarily adjusting the acquisition definition according to the matching degree and determining the video priority according to the acquisition definition after the secondary adjustment; wherein, the video priority is inversely proportional to the acquisition definition;
the video transmission module is used for creating a transmission channel according to the video priority and forwarding the field video based on the transmission channel;
the definition setting module includes:
the channel activating unit is used for activating the positioning equipment in the video acquisition end and establishing a transmission channel with the positioning equipment when the user and the video acquisition end are bound;
the position statistics unit is used for receiving and counting the position reported by the positioning equipment based on the transmission channel timing; when receiving the position, calculating the movement speed according to the position, and judging the effectiveness of the position according to the movement speed;
a representation updating unit for reading the position according to a preset frequency and updating the position representation according to the position; the updating process is to increment a preset numerical value at the position;
a traversing unit for traversing the position representation at regular time, and determining the acquisition definition of the current position based on the position representation;
the timing traversal of the position representation, the determining the content of the acquisition definition of the current position based on the position representation comprises:
the timing reading position representation is converted into a numerical matrix;
traversing the numerical matrix, and calculating the data density and the data aggregation degree in a preset range;
determining an acquisition level according to the data density and the data aggregation degree, and inquiring acquisition definition in a preset parameter table according to the acquisition level; the parameter table comprises level items and parameter items;
the calculation formula of the data density is as follows:
the calculation formula of the data uniformity is as follows:
in the method, in the process of the invention,for data density, N is the total number of rows in the preset range, M is the total number of columns in the preset range, +.>The numerical value at the j-th column of the i-th row, S is the area of the preset range; />Data uniformity>A vector formed by the points of the ith row and the jth column and the center; />For adjusting the coefficients.
6. The hidden immersive teleconference channel-building system of claim 5, wherein the matching update module comprises:
the image extraction unit is used for reading the live video, extracting images from the live video according to the preset interval duration and obtaining an image group;
the frequency recording unit is used for reading scene characteristics from the scene characteristic library, traversing the image group according to the scene characteristics, and recording the frequency of the similarity reaching a preset threshold value;
the matching degree updating unit is used for updating the matching degree according to the times;
the similarity calculation process adopts a pearson correlation coefficient, and a calculation formula of the pearson correlation coefficient comprises:
in the method, in the process of the invention,similarity between regions to be compared for a certain block of a certain image in scene feature and live video, +.>For the total number of points in the scene feature, +.>For the pixel mean in the scene feature, +.>For the kth pixel value in the scene feature, < +.>Pixel mean value of region to be aligned for a certain block of a certain image in live video, ++>The k pixel value in the region to be aligned for a certain block of a certain image in the live video.
7. The hidden immersive teleconference channel-building system of claim 5, wherein the priority determination module comprises:
the curve fitting unit is used for counting the matching degree based on the updating times and fitting a matching degree change curve;
the derivative calculation unit is used for calculating a derivative curve of the matching degree change curve;
the first calculation unit is used for intercepting curve segments in the matching degree change curve according to the preset backtracking time and calculating a matching degree mean value;
the second calculation unit is used for reading derivative curve segments corresponding to the curve segments and calculating a derivative mean value;
and the execution unit is used for secondarily adjusting the acquisition definition according to the matching degree mean value and the derivative mean value, and determining the video priority according to the acquisition definition after the secondary adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311316933.7A CN117061698B (en) | 2023-10-12 | 2023-10-12 | Hidden immersion type teleconference channel establishment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311316933.7A CN117061698B (en) | 2023-10-12 | 2023-10-12 | Hidden immersion type teleconference channel establishment method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117061698A CN117061698A (en) | 2023-11-14 |
| CN117061698B true CN117061698B (en) | 2023-12-22 |
Family
ID=88661296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311316933.7A Active CN117061698B (en) | 2023-10-12 | 2023-10-12 | Hidden immersion type teleconference channel establishment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117061698B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103841361A (en) * | 2014-03-25 | 2014-06-04 | 山西一建集团有限公司 | Communication method for integrating multiple conference systems under low bandwidth |
| CN108055481A (en) * | 2017-12-19 | 2018-05-18 | 北京欣远盈嘉信息科技有限公司 | A kind of method and device of definite signal source output |
| CN115397030A (en) * | 2022-08-16 | 2022-11-25 | 中国联合网络通信集团有限公司 | Method, device, equipment and storage medium for determining data transmission priority |
| CN115514918A (en) * | 2022-09-19 | 2022-12-23 | 深圳市拓普智造科技有限公司 | Remote video method, cloud platform, communication mobile platform and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5355108B2 (en) * | 2009-01-26 | 2013-11-27 | キヤノン株式会社 | Communication channel determination method and determination device |
| US20120309321A1 (en) * | 2011-05-31 | 2012-12-06 | Broadcom Corporation | Synchronized calibration for wireless communication devices |
-
2023
- 2023-10-12 CN CN202311316933.7A patent/CN117061698B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103841361A (en) * | 2014-03-25 | 2014-06-04 | 山西一建集团有限公司 | Communication method for integrating multiple conference systems under low bandwidth |
| CN108055481A (en) * | 2017-12-19 | 2018-05-18 | 北京欣远盈嘉信息科技有限公司 | A kind of method and device of definite signal source output |
| CN115397030A (en) * | 2022-08-16 | 2022-11-25 | 中国联合网络通信集团有限公司 | Method, device, equipment and storage medium for determining data transmission priority |
| CN115514918A (en) * | 2022-09-19 | 2022-12-23 | 深圳市拓普智造科技有限公司 | Remote video method, cloud platform, communication mobile platform and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117061698A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360028B (en) | Method and device for pushing information | |
| CN110751649B (en) | Video quality evaluation method and device, electronic equipment and storage medium | |
| US20200151514A1 (en) | Training and application method of neural network model, apparatus, system and storage medium | |
| US8903130B1 (en) | Virtual camera operator | |
| EP4137991A1 (en) | Pedestrian re-identification method and device | |
| WO2020098121A1 (en) | Method and device for training fast model, computer apparatus, and storage medium | |
| US11216924B2 (en) | Method and apparatus for processing image | |
| US20190114532A1 (en) | Apparatus and method for convolution operation of convolution neural network | |
| CN113610146B (en) | Method for realizing image classification based on knowledge distillation with enhanced intermediate layer feature extraction | |
| CN107527045A (en) | A kind of human body behavior event real-time analysis method towards multi-channel video | |
| CN110956059B (en) | Dynamic gesture recognition method and device and electronic equipment | |
| CN107040771A (en) | A kind of Encoding Optimization for panoramic video | |
| CN117061698B (en) | Hidden immersion type teleconference channel establishment method and system | |
| CN112703532A (en) | Image processing method, device, equipment and storage medium | |
| CN110555120A (en) | picture compression control method and device, computer equipment and storage medium | |
| CN117115595B (en) | Training method and device of attitude estimation model, electronic equipment and storage medium | |
| CN112804219B (en) | Low-delay real-time video analysis method based on edge calculation | |
| CN117372782A (en) | Small sample image classification method based on frequency domain analysis | |
| CN114529750A (en) | Image classification method, device, equipment and storage medium | |
| CN113901928A (en) | Target detection method based on dynamic super-resolution, and power transmission line component detection method and system | |
| CN116582693A (en) | Camera calling control method based on video resource pool | |
| CN116645268A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| CN113298112B (en) | Integrated data intelligent labeling method and system | |
| CN111143688B (en) | Evaluation method and system based on mobile news client | |
| CN114630139A (en) | Quality evaluation method of live video and related equipment 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 |