Image transmission method, device, equipment, medium and product

Abstract

The invention discloses an image transmission method, system and device, a medium and a product, and relates to the technical field of communication, and the method comprises the steps: carrying out the target detection of a to-be-transmitted image, and obtaining a target group of the to-be-transmitted image; obtaining relation information among the target groups according to the target groups; obtaining a scene semantic graph of the to-be-transmitted image according to the target group and the relation information; when the scene semantic graph is received, analyzing the scene semantic graph to obtain image scene description; and according to the image scene description, generating a reconstructed image by adopting a graph generation algorithm. By adopting the embodiment of the invention, the efficient transmission of the image can be realized through semantic expression and semantic reconstruction based on the image semantics, the data volume in the transmission process is reduced, and the method and the device can be effectively applied to the condition of limited bandwidth.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an image transmission method, system, device, medium and product. Background Art

[0002] With the development and widespread application of information technology, images, as an important information carrier, have become an indispensable part of people's daily life and work. However, the amount of image data is huge, and its transmission and storage costs are high. In the traditional communication process, image compression and transmission technology is used to compress images to reduce bandwidth and improve image transmission efficiency.

[0003] However, current image compression technology mainly focuses on reducing image data redundancy and improving compression ratio. Common methods include static image compression algorithms such as JPEG and PNG and video compression algorithms such as H.264 and H.265.

[0004] The existing technology has at least the following technical problems: although the compression algorithm can reduce data redundancy, it cannot fundamentally reduce the basic data volume of image transmission, and the algorithm with a high compression ratio often leads to a decrease in image quality and causes information loss. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide an image transmission method, system, device, medium and product, which can achieve efficient transmission of images based on image semantics through semantic expression and semantic reconstruction, reduce the amount of data in the transmission process, and can be effectively applied under conditions of limited bandwidth.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides an image transmission method, comprising:

[0007] Performing target detection on the image to be transmitted to obtain a target group of the image to be transmitted;

[0008] According to the target groups, obtaining relationship information between the target groups;

[0009] Obtaining a scene semantic graph of the image to be transmitted according to the target group and the relationship information;

[0010] When the scene semantic graph is received, parsing the scene semantic graph to obtain an image scene description;

[0011] According to the image scene description, a graphics generation algorithm is used to generate a reconstructed image.

[0012] As an improvement of the above solution, the step of performing target detection on the image to be transmitted and obtaining a target group of the image to be transmitted includes:

[0013] Performing instance segmentation on the image to be transmitted to obtain instance objects in the image to be transmitted;

[0014] The properties of the instance object are acquired to obtain the target group of the image to be transmitted.

[0015] As an improvement of the above solution, obtaining the relationship information between the target groups according to the target groups includes:

[0016] According to the target group, a pre-trained relational reasoning network model is used to process the target group to obtain preliminary relational information;

[0017] A knowledge-assisted verifier is used to semantically adjust the preliminary relationship information to obtain the relationship information between the target groups.

[0018] As an improvement of the above solution, obtaining the scene semantic graph of the image to be transmitted according to the target group and the relationship information includes:

[0019] Using a natural language processing algorithm, the target group and the relationship information are analyzed and integrated to generate a scene overview of the image to be transmitted;

[0020] A scene semantic graph of the image to be transmitted is generated according to the scene overview, the target group and the relationship information.

[0021] As an improvement of the above solution, generating a scene semantic graph of the image to be transmitted according to the scene overview, the target group and the relationship information includes:

[0022] Provide an overview of the scenario as the first level;

[0023] The target group is used as the second level;

[0024] The relationship information is used as the third level;

[0025] A scene semantic graph of the transmission image is generated according to the first level, the second level and the third level.

[0026] As an improvement of the above solution, when the scene semantic graph is received, parsing the scene semantic graph to obtain an image scene description includes:

[0027] When receiving the scene semantic graph, parsing the scene semantic graph to obtain scene overview, target group and relationship information;

[0028] Taking the scene overview as a theme, the target group and the relationship information are integrated to generate an image scene description.

[0029] The embodiment of the present invention further provides an image transmission device, comprising:

[0030] A target detection module, used to perform target detection on the image to be transmitted, and obtain a target group of the image to be transmitted;

[0031] A relationship information generating module, used for obtaining relationship information between the target groups according to the target groups;

[0032] A scene semantic graph construction module, used to obtain a scene semantic graph of the image to be transmitted according to the target group and the relationship information;

[0033] A reconstruction target group generation module is used to parse the scene semantic graph when receiving the scene semantic graph to obtain an image scene description;

[0034] The image reconstruction module is used to generate a reconstructed image using a graphics generation algorithm according to the image scene description.

[0035] An embodiment of the present invention further provides an image transmission device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements an image transmission method as described above when executing the computer program.

[0036] An embodiment of the present invention further provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute an image transmission method as described in any one of the above.

[0037] An embodiment of the present invention further provides a computer program product, characterized in that the computer program product includes a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, an image transmission method as described in any one of the above is executed.

[0038] Compared with the prior art, the image transmission method, system, device, medium and product disclosed in the present invention obtain a target group of the image to be transmitted by performing target detection on the image to be transmitted; obtain relationship information between the target groups according to the target group; obtain a scene semantic graph of the image to be transmitted according to the target group and the relationship information; when the scene semantic graph is received, the scene semantic graph is parsed to obtain an image scene description; and a reconstructed image is generated using a graphics generation algorithm according to the image scene description. By using the embodiments of the present invention, efficient transmission of images can be achieved based on image semantics through semantic expression and semantic reconstruction, reducing the amount of data in the transmission process, and can be effectively applied under conditions of limited bandwidth. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the steps of an image transmission method provided by an embodiment of the present invention;

[0040] Figure 2 It is a structural schematic diagram of an image transmission device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In the description of the specification and claims, it is to be understood that the terms first, second, etc. in the specification and claims are only used for the purpose of describing the same technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated, nor necessarily describing the order or time sequence. The terms are interchangeable where appropriate. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features.

[0043] In the prior art, in order to reduce the bandwidth occupied by streaming media transmission, static image compression algorithms such as JPEG and PNG and video compression algorithms such as H.264 and H.265 are generally used, which can improve transmission efficiency to a certain extent, but the existing compression algorithms only reduce data redundancy and cannot fundamentally reduce the basic data volume of image transmission; in addition, algorithms with high compression ratios often reduce image quality, which in turn leads to information loss. Users are unable to receive accurate information, which reduces the accuracy of information transmission.

[0044] Based on the above considerations, an embodiment of the present invention provides an image transmission method. It should be noted that the image transmission method described in the embodiment of the present invention can process the image to be transmitted so that it can be transmitted in a low data volume and high accuracy manner; it can also parse the received scene semantic graph to reconstruct the image and restore the semantic information of the image, and the execution steps can be selected according to the workflow of image transmission.

[0045] See also Figure 1 In this embodiment, the image transmission method is specifically performed through steps S1 to S5:

[0046] S1. Perform target detection on the image to be transmitted to obtain a target group of the image to be transmitted.

[0047] It should be noted that when performing target detection, you can use the target detection algorithm that has been trained with the existing large model, or you can improve and adjust the large model according to the specific field of the image to be transmitted to obtain a target detection algorithm that is more in line with the field of the image to be transmitted. The specific target detection method used does not affect the beneficial effects achieved by the present invention.

[0048] As a preferred implementation, step S1 specifically includes:

[0049] Performing instance segmentation on the image to be transmitted to obtain instance objects in the image to be transmitted;

[0050] The properties of the instance object are acquired to obtain the target group of the image to be transmitted.

[0051] In the above scheme, by performing target detection on the image to be transmitted, the instance object in the image to be transmitted can be obtained, and the attribute value of the instance object, such as the behavior, posture and category of the instance object, can be obtained. Subsequently, the image semantics of the image to be transmitted can be further analyzed according to the target group.

[0052] In some embodiments, Mask R-CNN is used as a target detector to perform instance segmentation on the image to be transmitted to obtain instance objects, and obtain instance name information, pixel position information and main attribute information of the instance objects, wherein the main attribute information includes behavior, appearance and posture, so as to obtain the target group of the image to be transmitted.

[0053] S2. According to the target groups, obtain relationship information between the target groups.

[0054] It should be noted that each of the target groups is an instance object and its attributes in the image to be transmitted. Step S2 is equivalent to predicting the relationship between the instance objects based on the instance objects and their attributes to obtain relationship information. The relationship information can lay the foundation for the complete semantic expression of the image to be transmitted.

[0055] Preferably, step S2 specifically includes:

[0056] According to the target group, a pre-trained relational reasoning network model is used to process the target group to obtain preliminary relational information;

[0057] A knowledge base auxiliary verifier is used to semantically adjust the preliminary relationship information to obtain the relationship information between the target groups.

[0058] It should be noted that the pre-trained relational reasoning network model has certain limitations. It may lack the ability to reason about relations in specific fields or proprietary and other non-public content, and may give fictitious information when it is beyond its understanding. Therefore, in an embodiment of the present invention, a knowledge base assisted verifier is used to correct the preliminary relational information.

[0059] It should also be noted that, in an embodiment of the present invention, the knowledge base auxiliary verifier relies on a structured knowledge base, which contains a large number of facts, data, rules and / or associations, and judges the authenticity and reliability of the content by accessing and querying the information stored in the knowledge base. In practical applications, according to the field to which the image to be transmitted belongs, it is linked to the corresponding knowledge base auxiliary verifier to obtain more accurate relationship information. For example, if the preliminary relationship information is "a man behind the basket and basketball", it is linked to the knowledge base auxiliary verifier in the "sports" field, and the preliminary relationship information is semantically adjusted to obtain the relationship information of "a man dribbling towards the basket".

[0060] In some embodiments, a pre-trained relational reasoning network model is used to process the target group, and the preliminary relational information obtained is in the form of a knowledge graph. Then, a knowledge-assisted verifier is used to perform relational confidence analysis on each connection in the knowledge graph to obtain the relational information between the target groups.

[0061] Exemplarily, in an embodiment of the present invention, the target groups are processed using an R-GCN relational reasoning network to obtain relational information between the target groups.

[0062] S3. Obtain a scene semantic graph of the image to be transmitted according to the target group and the relationship information.

[0063] It should be noted that the format of the scene semantic graph is different from that of the image to be transmitted, and is not a picture format in the traditional sense. In an embodiment of the present invention, the scene semantic graph stores a description of the semantic information of the image to be transmitted. Compared with the image to be transmitted, the data volume of the scene semantic graph is effectively reduced, further reducing the bandwidth requirement.

[0064] In the above scheme, by generating a scene semantic graph of the image to be transmitted, the target group and the relationship information of the image to be transmitted can be analyzed and integrated. When transmitting an image, it is not necessary to transmit the complete image data, but the scene semantic graph is transmitted. The scene semantic graph includes the main semantic information of the image to be transmitted, and the data volume is lower. By transmitting the scene semantic graph, the semantic transfer of the image to be transmitted is realized, and image data can be efficiently transmitted even in a bandwidth-constrained environment.

[0065] As a preferred implementation, step S3 specifically includes:

[0066] Using a natural language processing algorithm, the target group and the relationship information are analyzed and integrated to generate a scene overview of the image to be transmitted;

[0067] A scene semantic graph of the image to be transmitted is generated according to the scene overview, the target group and the relationship information.

[0068] In some embodiments, the target group and the relationship information are integrated to obtain a single sentence of text that can summarize the subject of the image to be transmitted as a scene summary.

[0069] For example, the scene overview "A baseball game is in progress with a batter, catcher and umpire at home plate" is the theme of the image to be transmitted, which describes a baseball game in progress, with a batter, catcher and umpire at home plate. For each target group corresponding instance object, it includes three attributes: name, position and attribute. Name describes the category name of the instance object, such as "umpire", position describes the pixel area of ​​the instance object in the original image, and the four key values ​​of x, y, w and h respectively represent the position coordinates and the frame size, and attribute describes other attributes of the instance object, such as "black shirt" indicates that the umpire is wearing a black T-shirt. In general, the instance object describes various semantic attributes, not only distinguishing categories, but also describing various detailed information of the object in detail. The relationship information stores the relationship between the instance objects in the form of triples, such as the triple relationship of "umpire"-"standing behind"-"catcher" describes the content information that the umpire stands behind the catcher. The semantic relationship between the instance objects is supplemented by the storage form of triples.

[0070] Further, as a preferred implementation, generating a scene semantic graph of the image to be transmitted according to the scene overview, the target group and the relationship information includes:

[0071] Provide an overview of the scenario as the first level;

[0072] The target group is used as the second level;

[0073] The relationship information is used as the third level;

[0074] A scene semantic graph of the transmission image is generated according to the first level, the second level and the third level.

[0075] Exemplarily, in an embodiment of the present invention, fully automatic JSON data generation based on Python and JSON is used to generate a hierarchical semantic scene graph from top to bottom.

[0076] In the above scheme, the scene semantic graph includes three levels, namely, scene overview, target group and relationship information from top to bottom, and the image to be transmitted is serialized and integrated into the scene semantic graph. It can be understood that the scene semantic graph retains the main semantic information of the image to be transmitted, and screens out a large number of invalid pixels. By transmitting the scene semantic graph, the image to be transmitted can be efficiently transmitted and reconstructed.

[0077] S4. When the scene semantic graph is received, the scene semantic graph is parsed to obtain an image scene description.

[0078] It should be noted that the scene semantic graph participates in the actual transmission. When the scene semantic graph is received, the scene semantic graph is parsed using the method corresponding to the generation of the scene semantic graph, so as to completely restore the semantic information of the image to be transmitted. In an embodiment of the present invention, the scene semantic graph is restored to the level of the target group to obtain a reconstructed target group and an overview of the second scene.

[0079] As a preferred implementation, step S4 specifically includes:

[0080] When receiving the scene semantic graph, parsing the scene semantic graph to obtain scene overview, target group and relationship information;

[0081] Taking the scene overview as the theme, the target group and the relationship information are integrated and extracted to generate an image scene description.

[0082] It should be noted that the scene semantic graph includes a scene overview, a target group and relationship information. However, in order to generate a reconstructed image, it is necessary to further integrate the target group and the relationship information, improve the details of the instance objects in the target group, and generate an image scene description. The image scene description contains all the semantic information in the scene semantic graph.

[0083] S5. Generate a reconstructed image using a graphics generation algorithm according to the image scene description.

[0084] Exemplarily, in an embodiment of the present invention, by training the DALL-E model or the Stable Diffusion model, it is enabled to generate images according to text descriptions, and the model is continuously trained using samples from different fields to obtain a mature graphics generation algorithm, and then the graphics generation algorithm is applied to the present method to generate a reconstructed image according to the image scene description. The reconstructed image includes all semantic information of the image to be transmitted, and the instance objects and the relationships between the instance objects in the reconstructed image are consistent with the image to be transmitted, thereby ensuring the accuracy of data transmission.

[0085] An image transmission method provided by an embodiment of the present invention is adopted. By performing object detection and attribute recognition on the image to be transmitted, a target group is obtained, and the main objects and their attribute information in the image to be transmitted can be extracted. Then, by reasoning the relationship between the target groups, the relationship information can be obtained. By constructing a scene semantic graph, a new image transmission method is provided, which does not need to transmit the complete image information, but instead transmits its main semantic information. When the scene semantic graph is received, the semantic information of the image to be transmitted is restored by generating an image scene description, which can effectively reduce the amount of data in the image transmission process and realize efficient transmission of the image.

[0086] See also Figure 2 , an embodiment of the present invention provides a schematic diagram of the structure of an image transmission device. The image transmission device includes a target detection module 11, a relationship information generation module 12, a scene semantic graph construction module 13, an image scene description generation module 14 and an image reconstruction module 15, wherein:

[0087] The target detection module 11 is used to perform target detection on the image to be transmitted and obtain a target group of the image to be transmitted;

[0088] A relationship information generating module 12, configured to obtain relationship information between the target groups according to the target groups;

[0089] A scene semantic graph construction module 13, used to obtain a scene semantic graph of the image to be transmitted according to the target group and the relationship information;

[0090] An image scene description generating module 14 is used to parse the scene semantic graph when receiving the scene semantic graph to obtain an image scene description;

[0091] The image reconstruction module 15 is used to generate a reconstructed image using a graphics generation algorithm according to the image scene description.

[0092] As a preferred implementation, the target detection module 11 includes:

[0093] An instance segmentation unit, used to perform instance segmentation on the image to be transmitted to obtain instance objects in the image to be transmitted;

[0094] The target group acquisition unit is used to acquire the attributes of the instance object to obtain the target group of the image to be transmitted.

[0095] As a preferred implementation, the relationship information generating module 12 includes:

[0096] A preliminary relationship information prediction unit, configured to process the target group using a pre-trained relationship reasoning network model according to the target group to obtain preliminary relationship information;

[0097] The semantic adjustment unit is used to use a knowledge-assisted verifier to perform semantic adjustment on the preliminary relationship information to obtain the relationship information between the target groups.

[0098] As a preferred implementation, the scene semantic graph construction module 13 includes:

[0099] A scene overview generating unit, configured to analyze and integrate the target group and the relationship information using a natural language processing algorithm to generate a scene overview of the image to be transmitted;

[0100] A scene semantic graph generating unit is used to generate a scene semantic graph of the image to be transmitted according to the scene overview, the target group and the relationship information.

[0101] Further, preferably, the scene semantic graph generating unit comprises:

[0102] A first level generating unit, configured to use the scenario overview as a first level;

[0103] A second level generating unit, configured to use the target group as a second level;

[0104] A third level generating unit, configured to use the relationship information as a third level;

[0105] A hierarchical integration unit is used to generate a scene semantic graph of the transmission image according to the first hierarchical level, the second hierarchical level and the third hierarchical level.

[0106] As a preferred implementation, the image scene description generating module 14 includes:

[0107] A scene semantic graph parsing unit, configured to parse the scene semantic graph upon receiving the scene semantic graph, and obtain a scene overview, a target group, and relationship information;

[0108] The image scene description generating unit is used to integrate the target group and the relationship information with the scene overview as the theme to generate an image scene description.

[0109] An image transmission device provided by an embodiment of the present invention performs object detection and attribute recognition on the image to be transmitted to obtain a target group, which can extract the main objects in the image to be transmitted and their attribute information, and then obtain relationship information by inferring the relationship between the target groups; by constructing a scene semantic graph, a new image transmission method is provided, which does not require the transmission of complete image information, but rather transmits its main semantic information; when the scene semantic graph is received, the semantic information of the image to be transmitted is restored by generating an image scene description, which can effectively reduce the amount of data in the image transmission process and achieve efficient image transmission.

[0110] It should be noted that the working process of each module in an image transmission device described in an embodiment of the present invention can refer to the working process of an image transmission method described in the above embodiment, and the technical effect achieved is the same as that of an image transmission method described in the above embodiment, which will not be repeated here.

[0111] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0112] An embodiment of the present invention also provides an image transmission device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, an image transmission method as described above is implemented. The working principles and beneficial effects of the two correspond one to one, and thus will not be repeated herein.

[0113] The present invention may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0114] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. An image transmission method, characterized in that: include: Performing target detection on the image to be transmitted to obtain a target group of the image to be transmitted; According to the target groups, obtaining relationship information between the target groups; Obtaining a scene semantic graph of the image to be transmitted according to the target group and the relationship information; When the scene semantic graph is received, parsing the scene semantic graph to obtain an image scene description; According to the image scene description, a graphics generation algorithm is used to generate a reconstructed image.

2. An image transmission method as claimed in claim 1, characterized in that: The performing target detection on the image to be transmitted and obtaining the target group of the image to be transmitted comprises: Performing instance segmentation on the image to be transmitted to obtain instance objects in the image to be transmitted; The properties of the instance object are acquired to obtain the target group of the image to be transmitted.

3. An image transmission method as claimed in claim 1, characterized in that: The obtaining, according to the target groups, relationship information between the target groups includes: According to the target group, a pre-trained relational reasoning network model is used to process the target group to obtain preliminary relational information; A knowledge-assisted verifier is used to semantically adjust the preliminary relationship information to obtain the relationship information between the target groups.

4. An image transmission method as claimed in claim 1, characterized in that: The step of obtaining a scene semantic graph of the image to be transmitted according to the target group and the relationship information includes: Using a natural language processing algorithm, the target group and the relationship information are analyzed and integrated to generate a scene overview of the image to be transmitted; A scene semantic graph of the image to be transmitted is generated according to the scene overview, the target group and the relationship information.

5. An image transmission method as claimed in claim 4, characterized in that: The step of generating a scene semantic graph of the image to be transmitted according to the scene overview, the target group and the relationship information includes: Provide an overview of the scenario as the first level; The target group is used as the second level; The relationship information is used as the third level; A scene semantic graph of the transmission image is generated according to the first level, the second level and the third level.

6. An image transmission method as claimed in claim 4 or 5, characterized in that: When the scene semantic graph is received, parsing the scene semantic graph to obtain an image scene description includes: When receiving the scene semantic graph, parsing the scene semantic graph to obtain scene overview, target group and relationship information; Taking the scene overview as a theme, the target group and the relationship information are integrated to generate an image scene description.

7. An image transmission device, characterized in that: include A target detection module, used to perform target detection on the image to be transmitted, and obtain a target group of the image to be transmitted; A relationship information generating module, used for obtaining relationship information between the target groups according to the target groups; A scene semantic graph construction module, used to obtain a scene semantic graph of the image to be transmitted according to the target group and the relationship information; A reconstruction target group generation module is used to parse the scene semantic graph when receiving the scene semantic graph to obtain an image scene description; The image reconstruction module is used to generate a reconstructed image using a graphics generation algorithm according to the image scene description.

8. An image transmission device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, an image transmission method as claimed in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute an image transmission method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program or a computer instruction, and when the computer program or the computer instruction is executed by a processor, an image transmission method according to any one of claims 1 to 6 is executed.

Images