Image transmission method, electronic device, storage medium and computer program product

Abstract

The embodiment of the invention provides an image transmission method, an image transmission device, electronic equipment, a chip, a storage medium and a computer program product, and the image transmission method is applied to a sending end, and comprises the steps: carrying out the coding of an image information source through a plurality of coding models, and obtaining a plurality of coding results; the plurality of coding models are in one-to-one correspondence with the plurality of coding results, and the training signal-to-noise ratios (SNRs) of the plurality of coding models are different; obtaining a first coding result based on the plurality of coding results; the first coding result comprises a part of feature vectors in each coding result in the plurality of coding results; and transmitting the first coding result to a receiving end through a plurality of subcarriers.

Description

Technical Field

[0001] This application relates to the field of image transmission technology, specifically to an image transmission method, an image transmission device, an electronic device, a chip, a storage medium, and a computer program product. Background Technology

[0002] Currently, image transmission is achieved by inputting the image source into an encoding model to generate an encoding vector, and then encrypting it with a key. Although this method can ensure that the ciphertext cannot be successfully cracked by eavesdroppers, it is difficult to cope with harsh channel environments, resulting in poor image recovery performance at legitimate receiving ends. Summary of the Invention

[0003] This application provides an image transmission method, an image transmission device, an electronic device, a chip, a storage medium, and a computer program product.

[0004] The image transmission method provided in this application embodiment is applied at the sending end and includes: The image source is encoded by multiple encoding models to obtain multiple encoding results; the multiple encoding models correspond one-to-one with the multiple encoding results, and the training signal-to-noise ratio (SNR) of the multiple encoding models is different; Based on the multiple encoding results, a first encoding result is obtained; the first encoding result includes a portion of the feature vector from each of the multiple encoding results. The first encoding result is transmitted to the receiving end via multiple subcarriers.

[0005] The image transmission method provided in this application embodiment is applied at the receiving end and includes: The receiver sends a first encoding result; the first encoding result includes a partial feature vector from each of the multiple encoding results; the multiple encoding results are obtained by encoding the image source using multiple encoding models, and the training SNR of the multiple encoding models is different.

[0006] The image transmission device provided in this application embodiment is applied at the sending end and includes: First transmission unit: used to encode the image source through multiple coding models to obtain multiple coding results; the multiple coding models correspond one-to-one with the multiple coding results, and the training SNR of the multiple coding models is different; The first transmission unit is further configured to obtain a first encoding result based on the plurality of encoding results; the first encoding result includes a portion of the feature vector in each of the plurality of encoding results; The first transmission unit is also used to transmit the first encoding result to the receiving end via multiple subcarriers.

[0007] The image transmission device provided in this application embodiment is applied at the receiving end and includes: The second transmission unit is used to receive the first encoding result sent by the transmitting end; the first encoding result includes a partial feature vector of each of the multiple encoding results; the multiple encoding results are obtained by encoding the image source through multiple encoding models, and the training SNR of the multiple encoding models is different.

[0008] The electronic device provided in this application includes a processor and a memory. The memory is used to store computer programs, and the processor is used to call and run the computer programs stored in the memory to execute the image transmission method provided in any embodiment of this application.

[0009] The chip provided in this application includes a processor for calling and running a computer program from a memory, causing a device equipped with the chip to execute the image transmission method provided in any embodiment of this application.

[0010] The storage medium provided in this application embodiment is used to store a computer program, which causes a computer to execute the image transmission method provided in any embodiment of this application.

[0011] The computer program product provided in the embodiments of this application includes a computer program that, when executed by a processor, implements the image transmission method provided in any embodiment of this application.

[0012] The image transmission method, image transmission device, electronic device, chip, storage medium, and computer program product provided in the embodiments of this application encode an image using multiple coding models with different trained SNRs to obtain multiple coding results. Based on the multiple coding results, a first coding result corresponding to the image source is obtained. The first coding result includes a partial feature vector from each of the multiple coding results. The first coding result is transmitted using multiple subcarriers, thereby improving the robustness against multipath channels during image transmission and enhancing the image recovery performance of the legitimate receiver. Attached Figure Description

[0013] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram of the implementation process of the image transmission method provided in the embodiments of this application. Figure 1 ; Figure 2 This is a schematic diagram of skip mode encoding provided in an embodiment of this application; Figure 3 A schematic diagram of the implementation process of the image transmission method provided in the embodiments of this application. Figure 2 ; Figure 4 A schematic diagram of the implementation process of the image transmission method provided in the embodiments of this application. Figure 3 ; Figure 5 A schematic diagram of the implementation process of the image transmission method provided in the embodiments of this application. Figure 4 ; Figure 6 This is a schematic diagram of the eavesdropper decoder recovery result provided in an embodiment of this application; Figure 7 This is a comparative diagram of image restoration results provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of the image transmission device 800 provided in the embodiments of this application; Figure 9 This is a schematic diagram of the structure of the image transmission device 900 provided in the embodiments of this application; Figure 10 A schematic structural diagram of an electronic device provided in the embodiments of this application; Figure 11 This is a schematic structural diagram of the chip provided in an embodiment of this application. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0015] It should be noted that, in the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, in the embodiments of this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0016] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0017] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0018] In related technologies, neural networks are used to generate random keys during image transmission. Although this method can ensure that the ciphertext cannot be successfully cracked by eavesdroppers, it is difficult to cope with the harsh channel environment, resulting in poor image recovery performance at the legitimate receiving end.

[0019] refer to Figure 1 , Figure 1 A schematic diagram of the implementation flow of the image transmission method provided in the embodiments of this application. Figure 1 ,like Figure 1 As shown, the image transmission method provided in this embodiment of the application, applied to the sending end, includes the following steps: Step 101: Encode the image source using multiple coding models to obtain multiple coding results; the multiple coding models correspond one-to-one with the multiple coding results, and the training SNR of the multiple coding models is different.

[0020] In this embodiment, the number of coding models can be selected according to the actual situation. The more coding models there are, the more complex the calculation process becomes, which is more conducive to improving the robustness against multipath effects during image transmission.

[0021] In this embodiment of the application, each of the multiple coding models encodes the image source to obtain the coding result corresponding to each coding model; the number of feature channels in the coding result output by each of the multiple coding models is the same.

[0022] In this embodiment, the training SNR of multiple coding models is different, and the training SNR of a coding model is related to the multipath channel and the number of coding models. For example, the equivalent SNR of each subcarrier in the multipath channel is calculated. Based on the equivalent SNR of each subcarrier, the multiple subcarriers are divided into multiple SNR ranges. The number of SNR ranges is the same as the number of coding models, and each SNR range corresponds one-to-one with a coding model. The upper limit of each SNR range is the same as the training SNR of its corresponding coding model.

[0023] Step 102: Based on the multiple encoding results, obtain a first encoding result; the first encoding result includes a partial feature vector from each of the multiple encoding results.

[0024] In this embodiment, the first encoding result is the encoding result corresponding to the image source; the first encoding result includes a partial feature vector from each of the multiple encoding results. This can be understood as selecting partial feature vectors from each of the multiple encoding results to form the first encoding result. The partial feature vectors selected from different encoding results are different.

[0025] In this embodiment, based on the importance of the feature vectors and the first rule, a portion of the feature vectors in each encoding result can be selected from multiple encoding results. Alternatively, any encoding result can be randomly selected from multiple encoding results, and the feature vectors in that encoding result can be sorted by importance to obtain a sorting result. The sorting result represents the importance of different feature vectors of the image source. Based on the sorting result and the first rule, a portion of the feature vectors in each encoding result can be selected from multiple encoding results.

[0026] Based on this, in an optional embodiment of this application, obtaining the first encoding result based on the plurality of encoding results includes: The feature vectors in the encoding results are sorted by importance to obtain the sorting results; Based on the sorting results and the first rule, a portion of the feature vectors from each of the multiple encoding results are selected to obtain the first encoding result.

[0027] In this embodiment of the application, the first rule can be a preset rule.

[0028] In this embodiment of the application, the first rule includes one or more of the following: feature vectors with lower importance are matched with encoding models with lower training SNR; and the feature vectors of each encoding result in the first encoding result have the same proportion.

[0029] For example, refer to Figure 2 , Figure 2 This is a schematic diagram of the skip mode encoding provided in the embodiments of this application, such as... Figure 2As shown, the encoding model has 4 features and 32 feature channels. Feature channel C1 corresponds to feature vector 1, feature channel C2 corresponds to feature vector 2, ..., feature channel C32 corresponds to feature vector 32. After sorting the 32 feature vectors by average importance, the ranking results are as follows: the importance of the 32 feature channels from low to high is C15, C10, C8, C25, C2, C6, C9, C20, C7, C11, C12, C13, C17, C23, C22, C14, C19, C5, C21, C18, C20, C31, C24, C27, C32, C4, C30, C29, C28, C16, C3, C1. The training SNR of encoding model 1 is 0, the training SNR of encoding model 2 is 10, the training SNR of encoding model 3 is 20, and the training SNR of encoding model 4 is 40. Then, feature vectors from channels C15, C10, C8, C25, C2, C6, C9, and C20 in the encoding result corresponding to encoding model 1, feature vectors from channels C7, C11, C12, C13, C17, C23, C22, and C14 in the encoding result corresponding to encoding model 2, feature vectors from channels C19, C5, C21, C18, C20, C31, C24, and C27 in the encoding result corresponding to encoding model 3, and feature vectors from channels C32, C4, C30, C29, C28, C16, C3, and C1 in the encoding result corresponding to encoding model 4 are selected. The feature vectors of these 32 selected channels form the first encoding result. In this embodiment, the process of obtaining the first encoding result can also be called mode-hopping encoding.

[0030] In this embodiment, the number of feature channels of the encoding model is related to the number of encoding models. For example, the number of feature channels of the encoding model = a * the number of encoding models, where a is a positive integer.

[0031] Step 103: Transmit the first encoding result to the receiving end through multiple subcarriers.

[0032] In this embodiment, the equivalent SNR of each subcarrier in a multipath channel is calculated. Based on the equivalent SNR of each subcarrier, the multiple subcarriers are divided into multiple SNR ranges. The number of the multiple SNR ranges is the same as the number of the multiple coding models. According to a second rule, the first coding result is transmitted to the receiving end. The second rule includes that the feature vectors obtained by the same coding model in the first coding result are transmitted through subcarriers within the same SNR range.

[0033] Based on this, in an optional embodiment of this application, transmitting the first encoding result to the receiving end via multiple subcarriers includes: Calculate the equivalent SNR of each subcarrier among the multiple subcarriers in the multipath channel; Based on the equivalent SNR of each subcarrier, the plurality of subcarriers are divided into a plurality of SNR ranges; the number of the plurality of SNR ranges is the same as the number of the plurality of coding models; Based on the second rule, the first encoding result is transmitted to the receiving end; the second rule includes: the feature vectors obtained by encoding the first encoding result using the same encoding model are transmitted through subcarriers within the same SNR range.

[0034] In this embodiment of the application, the second rule can be a preset rule.

[0035] Multiple SNR ranges correspond one-to-one with multiple coding models, and the upper limit of the corresponding SNR range is equal to the training SNR of the coding model. In the first coding result, the feature vectors encoded by the same coding model are transmitted through subcarriers within the SNR range corresponding to that coding model.

[0036] Based on this, in an optional embodiment of this application, the plurality of SNR ranges correspond one-to-one with the plurality of coding models, and the upper limit of the SNR of the SNR range is equal to the training SNR of the coding model corresponding to the SNR range. The feature vectors obtained by the same coding model in the first coding result are transmitted through subcarriers within the SNR range corresponding to the coding model.

[0037] For example, refer to Figure 2 , Figure 2 It includes four coding models: coding model 1 with a training SNR of 0, coding model 2 with a training SNR of 10, coding model 3 with a training SNR of 20, and coding model 4 with a training SNR of 40. This divides the multiple subcarriers into four SNR ranges. The equivalent SNR range for SNR range 1 is... The equivalent SNR range for SNR range 2 is (0, 10], the equivalent SNR range for SNR range 3 is (10, 20], and the equivalent SNR range for SNR range 4 is (20, 40]. Coding model 1 corresponds to SNR range 1, coding model 2 corresponds to SNR range 2, coding model 3 corresponds to SNR range 3, and coding model 4 corresponds to SNR range 4. In the first coding result, the feature vectors of channels C15, C10, C8, C25, C2, C6, C9, and C20 pass through subcarriers within SNR range 1. In the first encoding result, the feature vectors of channels C7, C11, C12, C13, C17, C23, C22, and C14 are transmitted via subcarriers within the SNR range of 2. The feature vectors of channels C19, C5, C21, C18, C20, C31, C24, and C27 are transmitted via subcarriers within the SNR range of 3. The feature vectors of channels C32, C4, C30, C29, C28, C16, C3, and C1 are transmitted via subcarriers within the SNR range of 4.

[0038] In an optional embodiment of this application, before transmitting the first encoding result to the receiving end, the image transmission method further includes: The physical layer key (PLK) binary sequence is negotiated with the receiving end. Based on the binary sequence, a scrambling matrix and a shared key are generated; Based on the scrambling matrix, the signals allocated to each subcarrier are scrambled and sorted. The shared key is transmitted to the receiving end.

[0039] In this embodiment, the randomness of PLK is used to scramble the signals allocated to each subcarrier to achieve encryption.

[0040] In this embodiment, the transmitting end and the receiving end negotiate to obtain a mutually agreed-upon PLK binary sequence. Based on the number of valid signals for each subcarrier, the binary sequence is converted into a decimal sequence, and duplicate elements are removed. The valid signals for each subcarrier are then scrambled according to the size of the elements in the decimal sequence. This decimal sequence is a scrambling matrix. The decimal sequence is input into a hash function to generate a fixed-length shared key, which is then transmitted to the receiving end.

[0041] refer to Figure 3 , Figure 3 A schematic diagram of the implementation flow of the image transmission method provided in the embodiments of this application. Figure 2 ,like Figure 3 As shown, the image transmission method provided in this application embodiment, applied to the receiving end, includes the following steps: Step 301: Receive the first encoding result sent by the sending end; the first encoding result includes a partial feature vector from each of the multiple encoding results; the multiple encoding results are obtained by encoding the image source through multiple encoding models, and the training SNR of the multiple encoding models is different.

[0042] In this embodiment, the number of coding models can be selected according to the actual situation. The more coding models there are, the more complex the calculation process becomes, which is more conducive to improving the robustness against multipath effects during image transmission.

[0043] In this embodiment of the application, each of the multiple coding models encodes the image source to obtain the coding result corresponding to each coding model; the number of feature channels in the coding result output by each of the multiple coding models is the same.

[0044] In this embodiment, the training SNR of multiple coding models is different, and the training SNR of a coding model is related to the multipath channel and the number of coding models. For example, the equivalent SNR of each subcarrier in the multipath channel is calculated. Based on the equivalent SNR of each subcarrier, the multiple subcarriers are divided into multiple SNR ranges. The number of SNR ranges is the same as the number of coding models, and each SNR range corresponds one-to-one with a coding model. The upper limit of each SNR range is the same as the training SNR of its corresponding coding model.

[0045] In this embodiment, the first encoding result is encrypted based on PLK. The receiving end and the transmitting end negotiate to obtain a consistent PLK binary sequence. The transmitting end converts the binary sequence into a decimal sequence based on the number of valid signals for each subcarrier, removes duplicate elements from the decimal sequence, and scrambles the valid signals of each subcarrier according to the size of the elements in the decimal sequence. This decimal sequence is a scrambling matrix. The transmitting end inputs the decimal sequence into a hash function to generate a fixed-length shared key and transmits the shared key to the receiving end. The receiving end receives the shared key, solves for the scrambling matrix, decrypts the first encoding result, and inputs it into the decoder to obtain the recovered image. The decoder is trained end-to-end.

[0046] refer to Figure 4 ,refer to Figure 4 , Figure 4 A schematic diagram of the implementation flow of the image transmission method provided in the embodiments of this application. Figure 3 ,like Figure 4 As shown, the image transmission method provided in this application embodiment includes the following steps: Step 401: Perform mode-hopping coding on the image source.

[0047] The receiver uses coding models with different trained SNRs to perform mode-hopping coding on the image source. The number of models used in mode-hopping coding determines the computational complexity of the scheme and affects the final recovery performance. The trained SNR selected for each coding model is determined by the number of multipath channels and the number of models used in mode-hopping coding. After mode-hopping coding, the image yields multiple feature vectors encoded by different trained SNR models. The number of channels in these vectors is determined by the number of models used in mode-hopping coding; these are referred to as mode-hopping coding vectors. Specifically, the image source is input into coding models with different trained SNRs, generating feature vectors with the same number of channels. The coding vectors of any model are randomly selected, and the average importance of the feature vectors for each channel is calculated and sorted according to the average importance. Based on the principle of matching feature vectors with lower importance to coding models with lower trained SNRs, feature vectors encoded by different trained SNR models are selected proportionally to form mode-hopping coding vectors, corresponding to the first coding result in the aforementioned embodiment. The dimension of the mode-hopping coding vector is the same as the dimension of the feature vector encoded by any coding model.

[0048] Step 402: Allocate subcarriers to the mode-hopping coding vector.

[0049] Calculate the equivalent SNR of different subcarriers in a multipath channel and divide the ranges. The number of ranges is the same as the number of models in the mode-hopping coding. The upper limit of each SNR range is the training SNR of the corresponding coding model. Feature vectors encoded by the same model in the mode-hopping coding vector are assigned to subcarriers with the training SNR of that model as the upper limit of the range for transmission.

[0050] Step 403: Implement PLK-based subcarrier scrambling encryption.

[0051] In this step, the randomness of the PLK (Programmable Logic Controller) is used to scramble the signals allocated to each subcarrier, achieving encryption. Specifically, a PLK binary sequence agreed upon by legitimate transceivers is obtained. Based on the number of valid signals for each subcarrier, the binary sequence is converted into a decimal sequence, and duplicate elements are removed. The valid signals for each subcarrier are then scrambled and sorted according to the size of the elements in this decimal sequence. This decimal sequence is treated as a scrambling matrix and input into a hash function to generate a fixed-length shared key. This shared key is shared with legitimate receivers through lossless transmission.

[0052] Step 404: The receiving end performs decryption and mode-hopping decoding to recover the image.

[0053] The receiver uses a shared key to solve for the scrambling matrix, and then decrypts the mode-hopping encoded vector sent by the transmitter. This vector is then input into the mode-hopping decoder to obtain the recovered image. The mode-hopping decoder is trained end-to-end.

[0054] refer to Figure 5 , Figure 5A schematic diagram of the implementation flow of the image transmission method provided in the embodiments of this application. Figure 4 ,like Figure 5 As shown, the image transmission method provided in this application embodiment includes the following steps: inputting a source image into four coding models to obtain four coding results, each coding model corresponding to a different training SNR, where the training SNR of coding model 1 is 0, the training SNR of coding model 2 is 10, the training SNR of coding model 3 is 20, and the training SNR of coding model 4 is 40; selecting a portion of the feature vectors from each of the four coding results according to the importance ranking result of the feature vectors and a first rule to obtain the first coding result; the first rule includes one or more of the following: matching feature vectors with lower importance to coding models with lower training SNR; and ensuring that the proportion of feature vectors in each coding result in the first coding result is the same; calculating the equivalent SNR of each subcarrier under a multipath channel, dividing it into multiple SNR ranges, and allocating the first coding result to different subcarriers according to a second rule. Transmission is performed on the same wave, and the second rule includes: feature vectors encoded by the same coding model in the first coding result are transmitted through subcarriers within the same SNR range; multiple SNR ranges correspond one-to-one with the multiple coding models, and the upper limit of the SNR range is equal to the training SNR of the coding model corresponding to the SNR range; feature vectors encoded by the same coding model in the first coding result are transmitted through subcarriers within the SNR range corresponding to the coding model; a scrambling matrix is ​​obtained based on PLK, and the subcarriers are encrypted using the scrambling matrix, and a shared key is generated using a hash function; the encrypted subcarriers are transmitted through orthogonal frequency division multiplexing, which can effectively combat multipath interference; the receiving end decrypts the received signal using the shared key to recover the first coding result, and then decodes it using a decoder, combining the decoded data from each subcarrier to recover the original image.

[0055] The image transmission method provided in this application increases the difficulty for an eavesdropper's decoder to recover the image by performing mode-hopping encoding, subcarrier allocation, subcarrier scrambling encryption, and receiving-end decryption and decoding of the image source. It achieves reliable image transmission under different signal-to-noise ratio conditions and improves the security and robustness of data transmission by utilizing mode-hopping and PLK encryption technologies.

[0056] refer to Figure 6 , Figure 6 This is a schematic diagram of the eavesdropper decoder recovery result provided in the embodiments of this application, as shown below. Figure 6 As shown, the visualization results of the eavesdropper decoder recovering the image under different parameters are presented. From left to right, the number of mode skips are 14, 10, 12, 8, 6, 4, and 2, respectively. It can be seen that the similarity between the eavesdropper's recovery result and the original image remains at a low value, and the eavesdropper decoder has difficulty recovering effective information.

[0057] refer to Figure 7 , Figure 7 This is a comparative diagram of image restoration results provided in the embodiments of this application, such as... Figure 7 As shown, Figure 7 The image above is a schematic diagram of the image restoration result using relevant techniques. Figure 7 The following figure is a schematic diagram of the image restoration result using the image transmission method of this application, as shown below. Figure 7 As shown, the proposed solution achieves higher image restoration accuracy and exhibits good robustness to multipath channels, thereby improving the image recovery effect at legitimate receivers.

[0058] This application also provides an image transmission device 800, see reference. Figure 8 , Figure 8 This is a schematic diagram of the structure of the image transmission device 800 provided in an embodiment of this application. The image transmission device 800 in this embodiment is applied at the transmitting end and includes: First transmission unit: used to encode the image source through multiple coding models to obtain multiple coding results; the multiple coding models correspond one-to-one with the multiple coding results, and the training SNR of the multiple coding models is different; The first transmission unit is used to obtain a first encoding result based on the plurality of encoding results; the first encoding result includes a partial feature vector from each of the plurality of encoding results; The first transmission unit is used to transmit the first encoding result to the receiving end via multiple subcarriers.

[0059] In this embodiment of the application, the first transmission unit is further configured to: sort the feature vectors in the encoding result by importance to obtain a sorting result; and select a portion of the feature vectors in each of the plurality of encoding results based on the sorting result and the first rule to obtain the first encoding result.

[0060] In this embodiment of the application, the first rule includes one or more of the following: feature vectors with lower importance are matched with encoding models with lower training SNR; and the feature vectors of each encoding result in the first encoding result have the same proportion.

[0061] In this embodiment of the application, the first transmission unit is further configured to: calculate the equivalent SNR of each subcarrier among the plurality of subcarriers under the multipath channel; divide the plurality of subcarriers into a plurality of SNR ranges based on the equivalent SNR of each subcarrier; the number of the plurality of SNR ranges is the same as the number of the plurality of coding models; and transmit the first coding result to the receiving end based on a second rule; the second rule includes: the feature vectors in the first coding result encoded by the same coding model are transmitted through subcarriers within the same SNR range.

[0062] In this embodiment of the application, the plurality of SNR ranges correspond one-to-one with the plurality of coding models, and the upper limit of the SNR of the SNR range is equal to the training SNR of the coding model corresponding to the SNR range; the feature vectors in the first coding result encoded by the same coding model are transmitted through subcarriers within the SNR range corresponding to the coding model.

[0063] In this embodiment of the application, before transmitting the first encoding result to the receiving end, the first transmission unit is further configured to: negotiate with the receiving end to obtain a physical layer key PLK binary sequence; generate a scrambling matrix and a shared key based on the binary sequence; scramble and sort the signals allocated to each subcarrier based on the scrambling matrix; and transmit the shared key to the receiving end.

[0064] Those skilled in the art should understand that Figure 8 The functions of each unit in the image transmission device 800 shown can be understood by referring to the relevant description of the aforementioned method. Figure 8 The functions of each unit in the image transmission device 800 shown can be implemented by a program running on a processor or by specific logic circuits.

[0065] This application also provides an image transmission device 900, see reference. Figure 9 , Figure 9 This is a schematic diagram of the structure of the image transmission device 900 provided in an embodiment of this application. The image transmission device 900 in this embodiment is applied at the receiving end and includes: The second transmission unit is used to receive the first encoding result sent by the transmitting end; the first encoding result includes a partial feature vector of each of the multiple encoding results; the multiple encoding results are obtained by encoding the image source through multiple encoding models, and the training SNR of the multiple encoding models is different.

[0066] In this embodiment of the application, the second transmission unit is further configured to decrypt the first encoding result using a shared key; the shared key is transmitted from the sending end to the receiving end; and to decode the decrypted first encoding result using a decoder to obtain a restored image of the first encoding result.

[0067] Those skilled in the art should understand that Figure 9 The functions of each unit in the image transmission device 900 shown can be understood by referring to the relevant description of the aforementioned method. Figure 9 The functions of each unit in the image transmission device 900 shown can be implemented by a program running on a processor or by specific logic circuits.

[0068] Figure 10 This is a schematic structural diagram of an electronic device provided in an embodiment of this application. Figure 10 The electronic device shown includes a processor 1010, which can call and run computer programs from memory to implement the image transmission method provided in the embodiments of this application.

[0069] Optionally, such as Figure 10 As shown, the electronic device may also include a memory 1020. The processor 1010 can retrieve and run computer programs from the memory 1020 to implement the image transmission method provided in this embodiment.

[0070] The memory 1020 can be a separate device independent of the processor 1010, or it can be integrated into the processor 1010.

[0071] Optionally, such as Figure 10 As shown, the electronic device may also include a transceiver 1030, and the processor 1010 can control the transceiver 1030 to transmit images with other devices. Specifically, it can send information or data to other devices or receive information or data sent by other devices.

[0072] The transceiver 1030 may include a transmitter and a receiver. The transceiver 1030 may further include an antenna, and the number of antennas may be one or more.

[0073] The electronic device may specifically be the image transmission device 800 / image transmission device 900 in the embodiments of this application, and the electronic device may implement the corresponding processes implemented by the image transmission device 800 / image transmission device 900 in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0074] For example, embodiments of this application also provide a computer program product, including a computer program that can be executed by a processor 1010 of an electronic device to perform the steps described in any of the foregoing methods.

[0075] Figure 11 This is a schematic structural diagram of the chip according to an embodiment of this application. Figure 11The chip 1100 shown includes a processor 1110, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0076] Optionally, such as Figure 11 As shown, chip 1100 may further include memory 1120. Processor 1110 can retrieve and run computer programs from memory 1120 to implement the methods described in this embodiment.

[0077] The memory 1120 can be a separate device independent of the processor 1110, or it can be integrated into the processor 1110.

[0078] Optionally, the chip 1100 may also include an input interface 1130. The processor 1110 can control the input interface 1130 to transmit images to other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0079] Optionally, the chip 1100 may also include an output interface 1140. The processor 1110 can control the output interface 1140 to transmit images to other devices or chips; specifically, it can output information or data to other devices or chips.

[0080] This chip can be applied to the electronic devices in the embodiments of this application, and the chip can implement the corresponding processes implemented by the electronic devices in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0081] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0082] It should be understood that the processor in the embodiments of this application may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0083] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0084] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0085] This application also provides a storage medium for storing a computer program. This storage medium can be applied to the electronic device in this application embodiment, and the computer program causes the computer to execute the corresponding processes implemented by the electronic device in the various methods of this application embodiment; for brevity, these will not be elaborated further here.

[0086] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0087] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0091] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or electronic device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An image transmission method, characterized in that, Applied to the sending end, including: The image source is encoded using multiple coding models to obtain multiple coding results; each coding model corresponds one-to-one with the multiple coding results, and the training signal-to-noise ratio (SNR) of each coding model is different. Based on the multiple encoding results, a first encoding result is obtained; the first encoding result includes a portion of the feature vector from each of the multiple encoding results. The first encoding result is transmitted to the receiving end via multiple subcarriers.

2. The method according to claim 1, characterized in that, The process of obtaining a first encoding result based on the multiple encoding results includes: The feature vectors in the encoding results are sorted by importance to obtain the sorting results; Based on the sorting results and the first rule, a portion of the feature vectors from each of the multiple encoding results are selected to obtain the first encoding result.

3. The method according to claim 2, characterized in that, The first rule includes one or more of the following: Lower importance feature vectors are matched with encoding models that have lower training SNR; and, In the first encoding result, the feature vectors of each encoding result have the same proportion.

4. The method according to any one of claims 1 to 3, characterized in that, The transmission of the first encoding result to the receiving end via multiple subcarriers includes: Calculate the equivalent SNR of each subcarrier among the multiple subcarriers in the multipath channel; Based on the equivalent SNR of each subcarrier, the plurality of subcarriers are divided into a plurality of SNR ranges; the number of the plurality of SNR ranges is the same as the number of the plurality of coding models; Based on the second rule, the first encoding result is transmitted to the receiving end; the second rule includes: the feature vectors obtained by encoding the first encoding result using the same encoding model are transmitted through subcarriers within the same SNR range.

5. The method according to claim 4, characterized in that, The plurality of SNR ranges correspond one-to-one with the plurality of coding models, and the upper limit of the SNR range is equal to the training SNR of the coding model corresponding to the SNR range. The feature vectors obtained by the same coding model in the first coding result are transmitted through subcarriers within the SNR range corresponding to the coding model.

6. The method according to claim 5, characterized in that, Before transmitting the first encoded result to the receiving end, the method further includes: The physical layer key PLK binary sequence is obtained through negotiation with the receiving end; Based on the binary sequence, a scrambling matrix and a shared key are generated; Based on the scrambling matrix, the signals allocated to each subcarrier are scrambled and sorted. The shared key is transmitted to the receiving end.

7. An image transmission method, characterized in that, Applied to the receiving end, including: The receiver sends a first encoding result; the first encoding result includes a partial feature vector from each of the multiple encoding results; the multiple encoding results are obtained by encoding the image source using multiple encoding models, and the training SNR of the multiple encoding models is different.

8. An electronic device, characterized in that, include: A processor and a memory, the memory for storing a computer program, the processor for calling and running the computer program stored in the memory to perform the image transmission method as described in any one of claims 1 to 6, or the image transmission method as described in claim 7.

9. A storage medium, characterized in that, Used to store a computer program that causes a computer to perform the image transmission method as described in any one of claims 1 to 6, or the image transmission method as described in claim 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the image transmission method as described in any one of claims 1 to 6, or the image transmission method as described in claim 7.

Images