Image transmission method, transmitting device, receiving device and image transmission system

Abstract

The invention relates to the technical field of image transmission, and discloses an image transmission method, transmitting equipment, receiving equipment and an image transmission system.The method is applied to the transmitting equipment, the transmitting equipment is connected with the receiving equipment through a transmission channel, and the method comprises the steps that a to-be-transmitted image is obtained, semantic feature extraction is conducted on the to-be-transmitted image, and the to-be-transmitted image is obtained; obtaining semantic features to be transmitted; obtaining a channel feature of the transmission channel, determining a corresponding preset coding strategy based on the channel feature, and performing channel coding on the to-be-transmitted semantic feature through the preset coding strategy; and sending a channel coding result to the receiving equipment, so that the receiving equipment performs image reconstruction based on the channel coding result to obtain the to-be-transmitted image. The channel characteristics of the transmission channel can be obtained so as to determine the corresponding preset coding strategy to perform channel coding on the to-be-transmitted image, so that the integrity of the to-be-transmitted image during transmission through the complex transmission channel is ensured.

Description

Technical Field

[0001] The present application relates to the field of image transmission technology, and in particular to an image transmission method, a transmitting device, a receiving device and an image transmission system. Background Art

[0002] Due to the urgent need for efficient and high-quality image transmission in the modern communication field. With the popularization of the Internet and mobile devices, the proportion of image data in communication is increasing. Traditional image transmission technology has problems such as large data volume, low transmission efficiency, and susceptibility to network fluctuations. To this end, researchers have proposed an image transmission technology based on semantic feature extraction and reconstruction. This technology analyzes the semantic information of the image, extracts key features, and then reconstructs them at the receiving end, effectively reducing the amount of transmitted data, improving transmission efficiency, and ensuring the visual quality of the image.

[0003] Existingly, when sending an image to be transmitted, it is necessary to perform channel encoding on the semantic information of the image to be transmitted before sending it. During encoding, redundant information is generally added to the semantic information and then encoded using a fixed encoding method. When the channel conditions are not ideal, the fixed encoding method cannot be flexibly and dynamically adjusted when transmitting through a wireless channel with complex interference, resulting in distortion of local features and details of the image to be transmitted, leading to the problem of incompleteness of the reconstructed image to be transmitted. Summary of the invention

[0004] The main purpose of the present application is to provide an image transmission method, aiming to solve the existing problem that the image to be transmitted cannot be flexibly and dynamically adjusted when facing complex transmission channels, resulting in incomplete reconstructed images.

[0005] To achieve the above object, the present application proposes an image transmission method, which is applied to a transmitting device, the transmitting device is connected to a receiving device through a transmission channel, and the method includes:

[0006] Acquire an image to be transmitted, and extract semantic features of the image to be transmitted to obtain semantic features to be transmitted;

[0007] Acquire channel characteristics of the transmission channel, determine a corresponding preset coding strategy based on the channel characteristics, and perform channel coding on the semantic features to be transmitted using the preset coding strategy;

[0008] The channel coding result is sent to the receiving device, so that the receiving device performs image reconstruction based on the channel coding result to obtain the image to be transmitted.

[0009] In one embodiment, the step of performing channel coding on the semantic feature to be transmitted by using the preset coding strategy includes:

[0010] Acquire a corresponding preset filtering condition based on the channel characteristics;

[0011] Filtering the semantic features to be transmitted according to the preset filtering conditions to obtain target semantic features;

[0012] Channel coding is performed on the target semantic feature using the preset coding strategy.

[0013] In one embodiment, the step of filtering the semantic features to be transmitted according to the preset filtering condition to obtain the target semantic features includes:

[0014] Obtaining a preset semantic feature priority table, and prioritizing the semantic features to be transmitted based on the semantic feature priority table;

[0015] Acquire a transmission data volume threshold corresponding to the transmission channel from the preset filtering condition;

[0016] The sorted semantic features to be transmitted are filtered according to the transmission data volume threshold to obtain target semantic features.

[0017] In one embodiment, the step of extracting semantic features from the image to be transmitted to obtain the semantic features to be transmitted includes:

[0018] Performing channel analysis on the image to be transmitted to obtain a color channel corresponding to the image to be transmitted;

[0019] Preprocessing the image to be transmitted, and extracting features of the preprocessed image to be transmitted based on each of the color channels;

[0020] The feature extraction results are classified according to each of the color channels to obtain semantic features to be transmitted.

[0021] In addition, to achieve the above purpose, the present application also proposes an image transmission method, which is applied to a receiving device, the receiving device is connected to a transmitting device through a transmission channel, and the method includes:

[0022] When receiving a channel coding result sent by the transmitting device, acquiring a channel characteristic of the transmission channel, the channel coding result being obtained by performing channel coding on the image to be transmitted by the transmitting device;

[0023] Determine a corresponding preset decoding strategy based on the channel characteristics, and perform channel decoding on the channel coding result by using the preset decoding strategy;

[0024] Image reconstruction is performed according to the channel decoding result to obtain the image to be transmitted.

[0025] In one embodiment, the step of performing channel decoding on the channel coding result by using the preset decoding strategy includes:

[0026] Acquire a corresponding preset noise reduction strategy based on the channel characteristics;

[0027] The encoding result is denoised based on the preset denoising strategy, and the denoising result is channel-decoded according to the preset decoding strategy.

[0028] In one embodiment, the step of performing image reconstruction according to the channel decoding result to obtain the image to be transmitted includes:

[0029] Acquire the semantic features to be transmitted of the image to be transmitted according to the channel decoding result;

[0030] Reconstructing the image according to the semantic features to be transmitted by using a preset image reconstruction algorithm;

[0031] Perform image enhancement on the image reconstruction result to obtain the image to be transmitted.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a transmitting device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the image transmission method described above.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a receiving device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the image transmission method described above.

[0034] In addition, in order to achieve the above-mentioned purpose, the present application also proposes an image transmission system, which includes: a transmitting device and a receiving device as described above, and the transmitting device is connected to the receiving device via a transmission channel.

[0035] The present application proposes an image transmission method, a transmitting device, a receiving device and an image transmission system. The method is applied to a transmitting device, wherein the transmitting device is connected to a receiving device through a transmission channel. The method includes: obtaining an image to be transmitted, and extracting semantic features of the image to be transmitted to obtain semantic features to be transmitted; obtaining channel features of the transmission channel, determining a corresponding preset coding strategy based on the channel features, and channel coding the semantic features to be transmitted through the preset coding strategy; sending the channel coding result to the receiving device so that the receiving device reconstructs the image based on the channel coding result to obtain the image to be transmitted. Since the present application extracts semantic features of the acquired image to be transmitted through a transmitting device to obtain semantic features to be transmitted, and obtains the channel features of the transmission channel to determine the corresponding preset coding strategy through the channel features, then channel codes the image to be transmitted through the preset coding strategy, and sends the channel coding result to the receiving device so that the receiving device can reconstruct the image according to the coding result to obtain the image to be transmitted, so as to complete the image transmission, and the integrity of the image to be transmitted when transmitting through a complex transmission channel is ensured by determining the corresponding coding strategy according to the characteristics of the channel. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 This is a flow chart of a first embodiment of the image transmission method proposed in this embodiment;

[0039] Figure 2 This is a diagram of device connections in the image transmission method proposed in this embodiment;

[0040] Figure 3 This is a flow chart of a second embodiment of the image transmission method proposed in this embodiment;

[0041] Figure 4 A schematic diagram of the structure of a transmitting device suitable for implementing an embodiment of the present application;

[0042] Figure 5 A schematic diagram of the structure of a receiving device suitable for implementing an embodiment of the present application;

[0043] Figure 6This is a diagram of the image transmission system in the image transmission method proposed in this embodiment.

[0044] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0048] Understandably, in the field of modern communications, the demand for efficient and high-quality image transmission is becoming increasingly urgent. The widespread popularity of the Internet and mobile devices has led to an increasing proportion of image data in communication traffic. Traditional image transmission technology faces many challenges, such as large data volume, low transmission efficiency, and sensitivity to network fluctuations. In order to solve these problems, researchers have innovatively proposed an image transmission technology based on semantic feature extraction and reconstruction.

[0049] This technology first conducts an in-depth analysis of the semantic information of the image, identifies and extracts the key features of the image. At the sending end, these features are encoded and transmitted, and at the receiving end, the image is restored to a quality close to the original through a reconstruction algorithm. This method significantly reduces the amount of transmitted data, improves transmission efficiency, and achieves effective transmission of images without sacrificing the visual quality of the image.

[0050] In the existing process of image transmission through semantic feature extraction and reconstruction, it is usually necessary to channel code the semantic information of the image. In this process, in order to enhance the reliability of transmission, redundant information is usually added to the semantic information and a fixed coding method is used. This approach works normally when the channel conditions are ideal, but it exposes its limitations when the channel conditions are not ideal, especially in a wireless channel environment with complex interference. The fixed coding method cannot flexibly and dynamically adjust the feature extraction and channel coding process to adapt to real-time channel interference, which leads to a problem in the transmission process: the local features and details of the image to be transmitted are easily distorted when passing through a wireless channel with complex interference.

[0051] Therefore, in order to solve the existing problem that the image to be transmitted cannot be adjusted flexibly and dynamically when facing a complex transmission channel, resulting in an incomplete reconstructed image to be transmitted, this embodiment proposes an image transmission method, which is applied to a transmitting device, wherein the transmitting device is connected to a receiving device through a transmission channel, and the method includes: obtaining an image to be transmitted, and extracting semantic features of the image to be transmitted to obtain semantic features to be transmitted; obtaining channel features of the transmission channel, determining a corresponding preset coding strategy based on the channel features, and channel coding the semantic features to be transmitted through the preset coding strategy; sending the channel coding result to the receiving device, so that the receiving device reconstructs the image based on the channel coding result to obtain the image to be transmitted. Since the present application extracts semantic features of the acquired image to be transmitted through the transmitting device to obtain the semantic features to be transmitted, and obtains the channel features of the transmission channel to determine the corresponding preset coding strategy through the channel features, then channel codes the image to be transmitted through the preset coding strategy, and sends the channel coding result to the receiving device, so that the receiving device can reconstruct the image according to the coding result to obtain the image to be transmitted, so as to complete the image transmission, and the corresponding coding strategy is determined according to the characteristics of the channel to ensure the integrity of the image to be transmitted when transmitting through a complex transmission channel.

[0052] For ease of understanding, the following combination Figures 1 to 6 The image transmission method provided in the embodiment of the present application and the image transmission method, transmitting device, receiving device and image transmission system provided in the following embodiments are specifically introduced.

[0053] The present application embodiment provides an image transmission method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the image transmission method proposed in this embodiment.

[0054] like Figure 1 As shown, the method includes:

[0055] Step S10: Acquire an image to be transmitted, and extract semantic features from the image to be transmitted to obtain semantic features to be transmitted.

[0056] refer to Figure 2 , Figure 2 This is a device connection diagram in the image transmission method proposed in this embodiment. It should be noted that the execution subject of this embodiment can be a computing service device with image transmission, network communication and program running functions, such as an image sending device and an image receiving device, or an electronic device capable of realizing the above functions. This embodiment uses a sending device for illustration, and the sending device can be connected to a receiving device through a transmission channel.

[0057] In addition, it should be noted that the above-mentioned image to be transmitted may be an image that the user needs to transmit, and the image may be stored in a storage device connected to the above-mentioned transmitting device or may be directly uploaded to the above-mentioned transmitting device by the user, and this embodiment does not impose specific restrictions. The above-mentioned semantic features to be transmitted may be features that describe key objects, scenes, textures, colors and other information in the image, such as key objects such as vehicles, pedestrians, roads, and key information such as the width of the road and the color of the traffic light.

[0058] In a specific implementation, first, the above-mentioned transmitting device can obtain the image to be transmitted from the built-in memory or the memory connected to the transmitting device and pre-process the image. Secondly, the transmitting device can use a deep learning model, such as a convolutional neural network (CNN) or a transformer, to extract features from the pre-processed image. Among them, CNN can capture local features of the image, while Transformer is good at capturing global dependencies. In order to make full use of the advantages of both, the above-mentioned transmitting device can adopt a hybrid model, such as using CNN for preliminary feature extraction, and then using Transformer for further feature fusion and refinement.

[0059] Furthermore, in order to facilitate the above-mentioned transmitting device to extract data from the image to be transmitted, the step of extracting semantic features from the image to be transmitted to obtain the semantic features to be transmitted includes:

[0060] Performing channel analysis on the image to be transmitted to obtain a color channel corresponding to the image to be transmitted;

[0061] Preprocessing the image to be transmitted, and extracting features of the preprocessed image to be transmitted based on each of the color channels;

[0062] The feature extraction results are classified according to each of the color channels to obtain semantic features to be transmitted.

[0063] It should be noted that the above-mentioned color channel can be a channel represented by an independent data stream containing different color information in the image. In a specific implementation, the above-mentioned transmitting device can first perform channel analysis on the acquired image to be transmitted to obtain the color channel corresponding to the image to be transmitted. Channel analysis refers to the process of decomposing an image into different color channels. For example, a red-green-blue (RGB) image can be decomposed into three channels: red, green, and blue. By analyzing each channel, image features can be extracted more finely and personalized processing can be performed for different channels.

[0064] Next, the transmitting device may preprocess the image to be transmitted and perform feature extraction. The preprocessing step includes operations such as scaling and normalization to ensure that the image data is suitable for subsequent processing, and classify the feature extraction results based on each color channel to obtain the semantic features to be transmitted.

[0065] Finally, the transmitting device can use a pre-trained semantic segmentation model or a specially designed model to classify the features of each channel and identify the key semantic information in the image. For example, the image can be segmented into multiple regions and each region can be classified to determine its corresponding category, such as road, building, vehicle, etc.

[0066] Through the above steps, the transmitting device can effectively extract key semantic features from the image to be transmitted and use them for subsequent image transmission and processing tasks. These semantic features can be used to compress images, optimize transmission strategies, perform target detection, etc., thereby improving the efficiency and robustness of image transmission.

[0067] At the same time, when the transmitting device is performing feature extraction, it can perform personalized processing based on the characteristics of different color channels. For example, for the RGB channel, the red channel can be used to extract vehicle and pedestrian features, the green channel can be used to extract road and vegetation features, and the blue channel can be used to extract sky and water features. This can more effectively extract key information from the image and improve the accuracy of classification.

[0068] In addition, the transmitting device can also selectively transmit the characteristic information of certain color channels according to the characteristics of the transmission channel. For example, when the bandwidth is limited, only the characteristic information of the red channel can be transmitted, because the red channel usually contains important semantic information, such as vehicles and pedestrians. This can effectively reduce the amount of transmitted data and improve transmission efficiency.

[0069] Step S20: Acquire channel characteristics of the transmission channel, determine a corresponding preset coding strategy based on the channel characteristics, and perform channel coding on the semantic features to be transmitted using the preset coding strategy.

[0070] It should be noted that the above-mentioned channel characteristics may be parameters describing the state and performance of the transmission channel, such as bandwidth, noise, attenuation, multipath effect and interference, etc. The above-mentioned preset coding strategy may be a coding scheme selected from a group of pre-designed coding schemes, which is used to select the most appropriate coding method according to the channel characteristics to improve the reliability of signal transmission.

[0071] In a specific implementation, when performing an image transmission task, the transmitting device can first obtain the channel characteristics of the transmission channel through advanced channel monitoring technology. Based on these channel characteristics, the transmitting device can determine the corresponding preset coding strategy to ensure the anti-interference ability and error correction ability of the semantic features during the transmission process.

[0072] Secondly, the above-mentioned transmitting device uses the selected preset coding strategy to perform channel coding on the semantic features to be transmitted. This process involves converting the semantic information of the image into a signal form that can be stably transmitted under specific channel conditions. In this process, the coding technologies that may be used include but are not limited to convolutional coding, turbo coding, low-density parity check (LDPC) coding, etc. These coding technologies can improve the transmission reliability of the signal by adding redundant information. At the same time, the transmitting device will also dynamically adjust the coding parameters such as coding rate, code block size and interleaving depth according to the channel characteristics to adapt to the real-time changes of the channel.

[0073] In addition, in order to further improve the robustness of transmission, the above-mentioned transmitting equipment may also implement modulation strategies in combination with channel coding technology, such as quadrature amplitude modulation (QAM), frequency shift keying (FSK) or orthogonal frequency division multiplexing (OFDM), etc. These modulation technologies can adjust the signal transmission method according to the channel characteristics to optimize the signal transmission performance in the channel. Through such a comprehensive coding and modulation strategy, the transmitting equipment can effectively overcome the instability and interference of the channel and ensure the accurate transmission of image semantic features in complex communication environments.

[0074] Furthermore, in the face of a transmission channel with strong interference or poor quality, in order to transmit the image to be transmitted more completely, the step of performing channel coding on the semantic features to be transmitted by using the preset coding strategy includes:

[0075] Acquire a corresponding preset filtering condition based on the channel characteristics;

[0076] Filtering the semantic features to be transmitted according to the preset filtering conditions to obtain target semantic features;

[0077] Channel coding is performed on the target semantic feature using the preset coding strategy.

[0078] It should be noted that the preset filtering conditions may be screening criteria pre-set according to channel characteristics, and are used to select the most critical information for image reconstruction from the semantic features to be transmitted. The target semantic features may be a set of semantic features that are critical for image reconstruction obtained after filtering by the filtering conditions, and are the core part of the content to be transmitted.

[0079] In the specific implementation process, the above-mentioned transmitting device first determines a set of corresponding preset filtering conditions based on the acquired channel characteristics during the image transmission process. These filtering conditions are formulated based on the specific characteristics of the channel, such as noise level, signal attenuation and multipath effect, etc., with the purpose of filtering out information that is critical to image reconstruction from the semantic features to be transmitted, while excluding information that may cause transmission errors or redundancy under specific channel conditions. This step ensures that the most critical semantic features are transmitted, thereby improving transmission efficiency and robustness.

[0080] Subsequently, the transmitting device filters the semantic features to be transmitted according to these preset filtering conditions, and extracts the target semantic features from the original semantic feature set through a series of algorithm processing. This process may involve techniques such as feature selection, feature dimensionality reduction or feature weighting to optimize the feature set to make it more suitable for transmission under the current channel conditions. The acquisition of target semantic features not only reduces the amount of data, but also improves the pertinence of the transmission content, laying a solid foundation for subsequent channel coding. Finally, the transmitting device performs channel coding on the target semantic features using the preset coding strategy determined previously.

[0081] Further, the filtering condition may be an upper limit of the amount of transmission data (or a transmission data threshold) of the transmission channel, and the step of filtering the semantic features to be transmitted according to the preset filtering condition to obtain the target semantic features includes:

[0082] Obtaining a preset semantic feature priority table, and prioritizing the semantic features to be transmitted based on the semantic feature priority table;

[0083] Acquire a transmission data volume threshold corresponding to the transmission channel from the preset filtering condition;

[0084] The sorted semantic features to be transmitted are filtered according to the transmission data volume threshold to obtain target semantic features.

[0085] It should be noted that the above-mentioned preset semantic feature priority table can be a predefined list for specifying the priority order of different semantic features in image transmission to guide feature selection when resources are limited. The above-mentioned transmission data volume threshold can be a maximum transmission data volume limit set according to channel characteristics, which is used to ensure that the amount of data transmitted does not exceed the capacity of the channel under channel conditions.

[0086] In a specific implementation, before preparing for image transmission, the above-mentioned transmitting device can first obtain a semantic feature priority table preset by the user. Based on the priority table, the above-mentioned transmitting device will prioritize the semantic features to be transmitted to ensure that when channel conditions are limited, the features that have the greatest impact on image reconstruction are transmitted first. Secondly, the above-mentioned transmitting device extracts the transmission data volume threshold corresponding to the current transmission channel from the preset filtering conditions. Through this threshold, the transmitting device can effectively control the transmission data volume to avoid transmission failures due to data overload.

[0087] Finally, according to the obtained transmission data volume threshold, the transmitting device filters the sorted semantic features to be transmitted. This process involves selectively retaining or discarding features according to the data volume threshold to achieve the extraction of target semantic features. Through the above method steps, the transmitting device ensures that while meeting the transmission data volume limit, the key semantic information of the image is retained to the maximum extent, so that the receiving end can reconstruct the image with the highest possible quality.

[0088] Step S30: Send the channel coding result to the receiving device, so that the receiving device performs image reconstruction based on the channel coding result to obtain the image to be transmitted.

[0089] In a specific implementation, after the transmitting device performs channel coding on the semantic features to be transmitted, the channel coding result is sent to the receiving device connected to the transmitting device through the transmission channel. After receiving the channel coding result, the receiving device decodes the channel coding and reconstructs the image to be transmitted through the decoding result to complete the image transmission function.

[0090] This embodiment proposes an image transmission method, which is applied to a transmitting device, wherein the transmitting device is connected to a receiving device through a transmission channel, and the method includes: obtaining an image to be transmitted, and extracting semantic features of the image to be transmitted to obtain the semantic features to be transmitted; obtaining channel features of the transmission channel, determining a corresponding preset coding strategy based on the channel features, and channel coding the semantic features to be transmitted through the preset coding strategy; sending the channel coding result to the receiving device, so that the receiving device reconstructs the image based on the channel coding result to obtain the image to be transmitted. Since the present application extracts semantic features of the acquired image to be transmitted through the transmitting device to obtain the semantic features to be transmitted, and obtains the channel features of the transmission channel to determine the corresponding preset coding strategy through the channel features, then channel codes the image to be transmitted through the preset coding strategy, and sends the channel coding result to the receiving device, so that the receiving device can reconstruct the image according to the coding result to obtain the image to be transmitted, so as to complete the image transmission, and the corresponding coding strategy is determined according to the characteristics of the channel to ensure the integrity of the image to be transmitted when transmitting through a complex transmission channel.

[0091] Based on the first embodiment, in the second embodiment, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be described in detail later. Figure 3 , Figure 3 This is a flow chart of the second embodiment of the image transmission method proposed in this embodiment.

[0092] It should be noted that this embodiment uses a receiving device for illustration, and the transmitting device can be connected to the above transmitting device through a transmission channel.

[0093] refer to Figure 3 , the method comprising:

[0094] Step S40: when receiving the channel coding result sent by the transmitting device, the channel characteristics of the transmission channel are acquired, wherein the channel coding result is obtained by performing channel coding on the image to be transmitted by the transmitting device.

[0095] It should be understood that when the above-mentioned receiving device receives the channel coding result from the transmitting device, it will first monitor the characteristics of the transmission channel in real time to obtain accurate channel characteristics. The above-mentioned receiving device uses these channel characteristics to evaluate the signal damage that may be encountered during the transmission process, thereby providing necessary information for the subsequent decoding process. The channel coding result is obtained by the transmitting device after encoding the semantic features of the image to be transmitted. It contains the key information of the image and the redundant code for error detection and correction to ensure the reliable reception of image data in a complex transmission environment.

[0096] Step S50: determining a corresponding preset decoding strategy based on the channel characteristics, and performing channel decoding on the channel coding result using the preset decoding strategy.

[0097] It should be understood that the above-mentioned preset decoding strategy can be a decoding scheme pre-designed according to the channel characteristics and the above-mentioned preset coding strategy, which is used to guide the receiving device on how to recover the original data from the channel coding result. In a specific implementation, after the above-mentioned receiving device analyzes the channel characteristics of the transmission channel in detail, it begins to determine the corresponding preset decoding strategy. The selection of this strategy is based on channel characteristics such as bandwidth, noise type and signal strength, so as to ensure that the decoding process can adapt to the channel conditions to the greatest extent and improve the accuracy and efficiency of decoding. Then, the receiving device uses this preset decoding strategy to perform channel decoding on the channel coding result. This process involves removing redundant information in the encoded data and correcting possible transmission errors, thereby restoring the original semantic features of the image. This series of operations ensures that the image data can be effectively restored even in a complex transmission environment.

[0098] Furthermore, in order to remove interference during channel transmission, the step of performing channel decoding on the channel coding result by using the preset decoding strategy includes:

[0099] Acquire a corresponding preset noise reduction strategy based on the channel characteristics;

[0100] The encoding result is denoised based on the preset denoising strategy, and the denoising result is channel-decoded according to the preset decoding strategy.

[0101] It should be understood that the above-mentioned preset noise reduction strategy can be a set of pre-designed noise reduction solutions to reduce the impact of noise on the signal during transmission (for example, when the channel noise is mainly Gaussian white noise, the preset noise reduction strategy may use a Wiener filter for noise reduction).

[0102] In a specific implementation, after receiving the channel coding result, the above-mentioned receiving device first obtains the corresponding preset noise reduction strategy based on the channel characteristics. These strategies are customized according to the channel noise type, intensity and other related characteristics, aiming to reduce the noise introduced during the transmission process and improve the signal quality. The receiving device uses these strategies to perform noise reduction on the coding result, and eliminates noise interference as much as possible through technical means such as filtering and signal enhancement. After completing the noise reduction, the receiving device performs channel decoding on the noise reduction result according to the preset decoding strategy. This step involves error detection and correction, ensuring the accurate restoration of the semantic features of the original image. Such a processing flow not only improves the transmission efficiency of the image, but also guarantees the visual effect of the image.

[0103] Step S60: Reconstruct the image according to the channel decoding result to obtain the image to be transmitted.

[0104] It should be understood that the above-mentioned image reconstruction can be a process of reconstructing an image based on the decoded data (for example, using the inverse discrete cosine transform (IDCT) to reconstruct a spatial domain image from frequency domain data). In a specific implementation, after completing the channel decoding, the above-mentioned receiving device reconstructs the image according to the decoding result, recombines and transforms the semantic features obtained by decoding to restore the original image to be transmitted. Through an efficient reconstruction algorithm, the receiving device can ensure that the clarity and details of the image are as close as possible to the state before transmission, thereby achieving accurate restoration of the image.

[0105] Furthermore, in order to obtain a reconstructed image of the image to be transmitted, the step of performing image reconstruction according to the channel decoding result to obtain the image to be transmitted includes:

[0106] Acquire the semantic features to be transmitted of the image to be transmitted according to the channel decoding result;

[0107] Reconstructing the image according to the semantic features to be transmitted by using a preset image reconstruction algorithm;

[0108] Perform image enhancement on the image reconstruction result to obtain the image to be transmitted.

[0109] It should be noted that the above-mentioned preset image algorithm can be a mathematical method for recovering images from semantic features. For example, a convolutional neural network (CNN) in deep learning can be used as an image reconstruction algorithm to generate images from features or use a Swin transformer to perform image recovery.

[0110] Since the use of SwinTransformer for image restoration can make full use of the hierarchical feature extraction capabilities and sliding window mechanism. Through the hierarchical structure, it can adapt to images of different scales, process high-resolution images with linear complexity, and capture the multi-scale information of the image. The design of local non-overlapping window calculation self-attention and cross-window connection enables the model to pay attention to local details and global context information at the same time. Therefore, this embodiment is explained by using SwinTransformer for image restoration, but no specific limitation is made to this embodiment.

[0111] After receiving the channel decoding result, the receiving device first extracts the semantic features of the image to be transmitted. These features are the core information of the image content and are crucial for the accurate reconstruction of the image to be transmitted. Subsequently, the receiving device uses a preset image reconstruction algorithm to reconstruct the image based on these semantic features. This process includes converting the decoded feature data back to the pixel format of the image to reproduce the original structure and details of the image.

[0112] In addition, after completing the image reconstruction, the above-mentioned receiving device will also perform image enhancement processing on the reconstruction result, and further improve the visual effect of the image by adjusting parameters such as contrast, brightness, and sharpness, and finally obtain a high-quality image to be transmitted.

[0113] This embodiment provides a transmitting device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the image transmission method in the above-mentioned first embodiment.

[0114] Reference below Figure 4 , Figure 4 Schematic diagram of the structure of a transmitting device suitable for implementing the embodiment of the present application. The transmitting device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The transmitting device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0115] like Figure 4As shown, the transmitting device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the transmitting device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the transmitting device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a transmitting device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0116] In particular, according to the present embodiment, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present embodiment includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present embodiment are executed.

[0117] The transmitting device provided in this embodiment adopts the image transmission method in the above embodiment, which can solve the existing problem that the image to be transmitted after reconstruction is incomplete due to the inability to flexibly and dynamically adjust when facing a complex transmission channel. Compared with the prior art, the beneficial effects of the transmitting device provided in this embodiment are the same as the beneficial effects of the image transmission method provided in the above embodiment, and the other technical features in the transmitting device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0118] In addition, this embodiment provides a receiving device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the image transmission method in the above-mentioned second embodiment.

[0119] Reference below Figure 5 , Figure 5 Schematic diagram of the structure of a receiving device suitable for implementing the embodiment of the present application. The receiving device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The receiving device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0120] like Figure 5 As shown, the receiving device may include a processing device 1011 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1012 or a program loaded from a storage device 1013 to a random access memory (RAM: Random Access Memory) 1014. In RAM1014, various programs and data required for the operation of the receiving device are also stored. The processing device 1011, ROM1012, and RAM1014 are connected to each other through a bus 1015. An input / output (I / O) interface 1016 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1016: an input device 1017 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1018 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1013 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1019. The communication device 1019 can allow the receiving device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a receiving device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0121] In particular, according to the present embodiment, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present embodiment includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device, or installed from the storage device 1013, or installed from the ROM 1012. When the computer program is executed by the processing device 1011, the above-mentioned functions defined in the method of the embodiment disclosed in the present embodiment are executed.

[0122] The receiving device provided in this embodiment adopts the image transmission method in the above embodiment, which can solve the existing problem that the image to be transmitted after reconstruction is incomplete due to the inability to flexibly and dynamically adjust when facing a complex transmission channel. Compared with the prior art, the beneficial effects of the receiving device provided in this embodiment are the same as the beneficial effects of the image transmission method provided in the above embodiment, and other technical features in the receiving device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0123] refer to Figure 6 , Figure 6 This is a diagram of an image transmission system in the image transmission method proposed in this embodiment. This embodiment also provides an image transmission system, which includes: a transmitting device and a receiving device as described above, wherein the transmitting device is connected to the receiving device via a transmission channel.

[0124] It should be understood that the various parts disclosed in this embodiment can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0125] The above is only a specific implementation of this embodiment, but the protection scope of this embodiment is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this embodiment, which should be included in the protection scope of this embodiment. Therefore, the protection scope of this embodiment should be based on the protection scope of the claims.

[0126] The above descriptions are only some embodiments, and are not intended to limit the patent scope of this embodiment. All equivalent structural changes made using the contents of the specification and drawings of this application under the technical concept of this application, or directly / indirectly applied in other related technical fields are included in the patent protection scope of this application.

Claims

1. An image transmission method, characterized in that: The method is applied to a transmitting device, the transmitting device is connected to a receiving device via a transmission channel, and the method comprises: Acquire an image to be transmitted, and extract semantic features of the image to be transmitted to obtain semantic features to be transmitted; Acquire channel characteristics of the transmission channel, determine a corresponding preset coding strategy based on the channel characteristics, and perform channel coding on the semantic features to be transmitted using the preset coding strategy; The channel coding result is sent to the receiving device, so that the receiving device performs image reconstruction based on the channel coding result to obtain the image to be transmitted.

2. The method according to claim 1, characterized in that The step of performing channel coding on the semantic feature to be transmitted by using the preset coding strategy comprises: Acquire a corresponding preset filtering condition based on the channel characteristics; Filtering the semantic features to be transmitted according to the preset filtering conditions to obtain target semantic features; Channel coding is performed on the target semantic feature using the preset coding strategy.

3. The method according to claim 2, characterized in that The step of filtering the semantic features to be transmitted according to the preset filtering conditions to obtain target semantic features includes: Obtaining a preset semantic feature priority table, and prioritizing the semantic features to be transmitted based on the semantic feature priority table; Acquire a transmission data volume threshold corresponding to the transmission channel from the preset filtering condition; The sorted semantic features to be transmitted are filtered according to the transmission data volume threshold to obtain target semantic features.

4. The method according to claim 1, characterized in that The step of extracting semantic features from the image to be transmitted to obtain the semantic features to be transmitted comprises: Performing channel analysis on the image to be transmitted to obtain a color channel corresponding to the image to be transmitted; Preprocessing the image to be transmitted, and extracting features of the preprocessed image to be transmitted based on each of the color channels; The feature extraction results are classified according to each of the color channels to obtain semantic features to be transmitted.

5. An image transmission method, characterized in that: The method is applied to a receiving device, the receiving device is connected to a transmitting device via a transmission channel, and the method comprises: When receiving a channel coding result sent by the transmitting device, acquiring a channel characteristic of the transmission channel, the channel coding result being obtained by performing channel coding on the image to be transmitted by the transmitting device; Determine a corresponding preset decoding strategy based on the channel characteristics, and perform channel decoding on the channel coding result by using the preset decoding strategy; Image reconstruction is performed according to the channel decoding result to obtain the image to be transmitted.

6. The method according to claim 5, characterized in that The step of performing channel decoding on the channel coding result by using the preset decoding strategy comprises: Acquire a corresponding preset noise reduction strategy based on the channel characteristics; The encoding result is denoised based on the preset denoising strategy, and the denoising result is channel-decoded according to the preset decoding strategy.

7. The method according to claim 5, characterized in that The step of reconstructing the image according to the channel decoding result to obtain the image to be transmitted comprises: Acquire the semantic features to be transmitted of the image to be transmitted according to the channel decoding result; Reconstructing the image according to the semantic features to be transmitted by using a preset image reconstruction algorithm; Perform image enhancement on the image reconstruction result to obtain the image to be transmitted.

8. A transmitting device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the image transmission method according to any one of claims 1 to 4.

9. A receiving device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the image transmission method according to any one of claims 5 to 7.

10. An image transmission system, characterized in that: The system comprises: the transmitting device as claimed in claim 8 and the receiving device as claimed in claim 9, wherein the transmitting device is connected to the receiving device via a transmission channel.

Images