Image transmission method, system and equipment of underwater wireless sensor network and medium

Abstract

The invention provides an image transmission method, system and device of an underwater wireless sensor network, and a medium. The method comprises the following steps: acquiring an original image; taking the original image as an image block selected during the first screening, screening based on a target condition, processing the image block which does not meet the target condition into N sub-blocks, and taking the N sub-blocks as image blocks selected during the next screening for re-screening until the last screening is completed; obtaining hierarchical information of each sub-block in the original image; coding the sub-blocks meeting the target condition to obtain each coded sub-block; and the coding module is used for transmitting a coding information stream to the central node by using the trained deep learning joint source channel model coding according to the sequence from the first layer to the last layer based on the hierarchical information. According to the invention, high-quality image transmission of the underwater wireless sensor network can be realized.

Description

Technical Field

[0001] The present application relates to the field of underwater acoustic communication, and in particular to an image transmission method, system, device and medium for an underwater wireless sensor network. Background Art

[0002] In order to fully understand marine resources, we need to deploy observation equipment in the ocean to sense and monitor the various complex processes that drive changes in the marine environment, and transmit the collected data to the data analysis center for analysis and processing. Especially in the process of deep-sea resource development, in order to monitor deep-sea environmental information in real time, deep-sea images taken by underwater observation nodes equipped with cameras must be transmitted back to the base station in real time through acoustic signals.

[0003] In recent years, radio communication technology has been widely used in daily life and has become an important part of wireless sensor networks, greatly promoting data collection. However, most wireless communication technologies rely on high-frequency electromagnetic waves, which have the problems of rapid attenuation and limited communication distance on and under the sea surface. In contrast, although underwater wired networks are stable and reliable, with the advantages of high speed and low latency, their high cost and difficulty in deployment and maintenance make large-scale deployment in vast sea areas impractical. Although sound waves propagate fast and have long transmission distances underwater, due to the narrow bandwidth of underwater acoustic communication and high transmission power consumption, it is difficult to support real-time transmission of high-quality images. Therefore, when transmitting images in underwater environments, technical measures such as compression and encoding are needed to reduce the amount of data to adapt to bandwidth limitations and reduce power consumption.

[0004] Therefore, the present application provides an image transmission method, system, device and medium for an underwater wireless sensor network to solve one of the above technical problems. Summary of the invention

[0005] The purpose of the present application is to provide an image transmission method, system, device and medium for an underwater wireless sensor network, which can solve at least one of the technical problems mentioned above.

[0006] The specific plan is as follows:

[0007] According to a specific implementation of the present application, in a first aspect, the present application provides an image transmission method for an underwater wireless sensor network, which is applied to a detection node, comprising:

[0008] Acquire an original image; use the original image as an image block selected in the first screening, and perform screening based on a target condition to process the image block that does not meet the target condition into N sub-blocks, and use the N sub-blocks as the image blocks selected in the next screening for re-screening until the last screening is completed; wherein the target condition includes that the sub-block meets a uniformity condition and that the size of the sub-block is less than a preset size; in the last screening, each sub-block meets at least one of the target conditions, and N is a positive integer greater than or equal to 4; acquire hierarchical information of each sub-block in the original image; wherein the hierarchical information includes the number of layers to which the sub-block belongs and the original image block to which the sub-block belongs; wherein the number of layers to which the sub-block belongs is characterized based on the size of the sub-block, the sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer; encode the sub-blocks that meet the target condition to obtain the encoded sub-blocks; based on the hierarchical information, in the order from the first layer to the last layer, use the trained deep learning joint source channel model encoding to transmit the encoded information stream to the central node; wherein the encoded information stream is used to transmit the encoded sub-blocks layer by layer.

[0009] In one embodiment, encoding the sub-blocks that meet the target condition to obtain the encoded sub-blocks includes: data encoding the sub-blocks that meet the target condition according to color values ​​or pixel values ​​to obtain the data-encoded sub-blocks; wherein the data-encoded sub-blocks jointly represent the data-encoded original image; re-encoding the data-encoded original image according to a joint source-channel coding method to obtain the re-encoded original image; wherein the re-encoded original image is jointly represented by the re-encoded sub-blocks; and the re-encoded sub-blocks are used as the encoded sub-blocks.

[0010] In one implementation, the hierarchical information is identified based on a flag bit; the method further comprises: encoding and compressing the flag bit and the sub-block after the data is encoded based on a prefix encoding method or an arithmetic encoding method.

[0011] In one embodiment, the data-encoded original image is re-encoded according to a joint source channel coding method to obtain a re-encoded original image, including: preprocessing the data-encoded original image to obtain a preprocessed original image; wherein the preprocessing includes scaling and / or normalization; and the preprocessed original image is re-encoded according to a joint source channel coding method based on deep learning to obtain a re-encoded original image.

[0012] In one embodiment, based on the layered information, in the order from the first layer to the last layer, the trained deep learning joint source channel model encoding is used to transmit the encoded information stream to the central node, including: based on the layered information, in the order from the first layer to the last layer, and according to a preset restricted number of layers, the trained deep learning joint source channel model encoding is used to transmit the encoded information stream to the central node; wherein the preset restricted number of layers is used to limit the number of layers that can be transmitted.

[0013] According to a specific implementation of the present application, in a second aspect, the present application provides an image transmission method for an underwater wireless sensor network, which is applied to a central node and includes:

[0014] Receive a coded information stream transmitted by a detection node; wherein the coded information stream includes each coded sub-block transmitted layer by layer by the detection node in the order from the first layer to the last layer; wherein the each sub-block is used to jointly constitute an original image collected by the detection node, and the layer number to which the sub-block belongs is characterized based on the sub-block size, the sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer; according to the transmission order of the coded information stream, decode the image blocks one by one, and perform image splicing according to the decoding order; monitor the image clarity after the image splicing; in response to monitoring that the image clarity after the image splicing is greater than or equal to a preset clarity threshold, terminate the transmission of the coded information stream.

[0015] In one embodiment, the decoding of image blocks is performed one by one according to the transmission order of the encoded information stream, including: a joint source-channel decoding method based on deep learning, decoding image blocks one by one according to the transmission order of the encoded information stream.

[0016] According to a specific implementation of the present application, in a third aspect, the present application provides an image transmission system for an underwater wireless sensor network, comprising:

[0017] A detection node is used to obtain an original image; use the original image as an image block selected during the first screening, and screen based on a target condition to process the image blocks that do not meet the target condition into N sub-blocks, and use the N sub-blocks as the image blocks selected during the next screening for re-screening until the last screening is completed, wherein N is a positive integer greater than or equal to 4; obtain hierarchical information of each sub-block in the original image; encode the sub-blocks that meet the target condition to obtain each encoded sub-block; and based on the hierarchical information, in the order from the first layer to the last layer, use the trained deep learning joint source channel model encoding to transmit a coded information stream to a central node; the central node is used to receive the coded information stream transmitted by the detection node; decode the image blocks one by one in the transmission order of the coded information stream, and perform image splicing in the decoding order; monitor the image clarity after the image splicing; and terminate the transmission of the coded information stream when it is monitored that the image clarity after the image splicing is greater than or equal to a preset clarity threshold.

[0018] According to the specific implementation of the present application, in the third aspect, the present application provides an underwater acoustic device, including a memory, a processor and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the method described in any one of the first aspects, or executes the computer program to implement the method described in any one of the second aspects.

[0019] According to the specific implementation of the present application, in a fourth aspect, the present application provides a computer-readable storage medium having a computer program / instruction stored thereon, characterized in that when the computer program / instruction is executed by a processor, it implements the method described in any one of the first aspects, or implements the method described in any one of the second aspects.

[0020] Compared with the prior art, the above solution of the embodiment of the present application has at least the following beneficial effects:

[0021] The method provided by the present application is to gradually divide the original image into sub-blocks that meet the homogeneity condition and are smaller than the preset size, and obtain the hierarchical information of each sub-block. In this way, only the sub-blocks that meet the conditions will be encoded and transmitted. Since the image data is compressed into multiple sub-blocks, the amount of data transmitted can be significantly reduced, thereby improving the transmission efficiency in an underwater environment with limited bandwidth. Among them, the method of recursively dividing the image and transmitting the encoded information stream layer by layer significantly reduces the amount of data transmitted. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart showing an image transmission method for an underwater wireless sensor network is shown;

[0023] Figure 2 A decomposition flow chart of a quadtree image is shown;

[0024] Figure 3 A quadtree diagram after image decomposition is shown;

[0025] Figure 4 A flow chart showing an image transmission method for an underwater wireless sensor network according to an embodiment of the present application is shown;

[0026] Figure 5 A flow chart of a method for re-encoding an original image after data encoding according to a joint source-channel encoding method is shown;

[0027] Figure 6 A flow chart showing another method for transmitting images in an underwater wireless sensor network is shown;

[0028] Figure 7 A flow chart showing an image transmission method for an underwater wireless sensor network is shown;

[0029] Figure 8 A flow chart showing an image transmission method for an underwater wireless sensor network is shown;

[0030] Fig. 9 A schematic diagram of an image transmission system of an underwater wireless sensor network is shown;

[0031] Fig.10 The overall flow chart of image transmission in underwater wireless sensor network scenario is shown;

[0032] Fig.11 shows a flow chart of information transmission based on coded data stream;

[0033] Fig.12 The joint source channel coding flow chart of the present application is shown;

[0034] Fig.13 The figure is a block diagram of an underwater acoustic device for image transmission according to an exemplary embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0036] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0037] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0038] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0039] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0040] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0041] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0042] The present application is applied to underwater wireless detection scenarios, for example, it can be applied to underwater wireless sensor networks. Among them, detection nodes refer to those nodes located underwater and equipped with cameras or other sensing devices. The main task of these nodes is to detect the environment of the sea area where they are located, and transmit the captured images or other data to the central node in real time. The central node is a node that receives data from the detection node. The central node receives the image data transmitted by the detection node, is responsible for decoding the received data, and presents the image for analysis.

[0043] The following embodiments of the present application involve the representation of image blocks and sub-blocks, where image blocks are used to express image data before block processing, and sub-blocks are used to express image data after block processing. In some embodiments, an image data can be regarded as an image block and a sub-block at the same time. For example, an image block participating in the second screening can be regarded as one of the sub-blocks obtained after the block processing in the first screening.

[0044] The optional embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0045] The embodiment provided in this application is an embodiment of an image transmission method for an underwater wireless sensor network. Figure 1 The embodiments of the present application are described in detail.

[0046] Figure 1 A flow chart of an image transmission method for an underwater wireless sensor network is shown. Figure 1 As shown, the method is applied to a detection node, and includes the following steps S101 to S105.

[0047] Step S101, obtaining an original image.

[0048] The original image refers to the image initially acquired by the detection node without any processing, that is, the deep-sea image taken by the underwater observation node.

[0049] Step S102, using the original image as the image block selected in the first screening, and screening based on the target condition to process the image blocks that do not meet the target condition into N sub-blocks, and using the N sub-blocks as the image blocks selected in the next screening for screening again, until the last screening is completed.

[0050] Wherein, N is a positive integer greater than or equal to 4.

[0051] The target conditions include that the sub-blocks satisfy a uniformity condition and that the size of the sub-blocks is smaller than a preset size, and the preset size is predefined according to the underwater wireless sensor network situation.

[0052] For example, the following description is based on the case where N is 4. In the last screening, each sub-block satisfies at least one target condition.

[0053] Step S103, obtaining hierarchical information of each sub-block in the original image.

[0054] The hierarchical information includes the layer number to which the sub-block belongs and the original image block to which the sub-block belongs.

[0055] The layer number to which the sub-block belongs is characterized based on the sub-block size, where the sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer.

[0056] Step S104: Encode the sub-blocks that meet the target condition to obtain each encoded sub-block.

[0057] Step S105, based on the hierarchical information, in the order from the first layer to the last layer, use the trained deep learning joint source-channel model encoding to transmit the encoded information stream to the central node.

[0058] The coded information stream is used to transmit each coded sub-block layer by layer.

[0059] In this application, the uniformity condition refers to the standard used to determine whether an image block can be regarded as having the same or similar attributes (such as color, brightness, etc.) during the image segmentation process. For example, when checking an image block, if it is found that the pixel values ​​within the block do not change much, that is, the color variance is less than a predefined threshold, then the block is considered to meet the uniformity condition. If this condition is not met, the block is further divided into multiple small blocks, and the same check is continued on these small blocks. This process continues until all sub-blocks meet the uniformity condition or the predetermined minimum block size is reached. Blocks that meet the uniformity can directly encode their color values ​​or pixel values, while blocks that do not meet the uniformity need to record their segmentation information and further segment them. This strategy helps to reduce data redundancy and thus achieve image compression.

[0060] The method provided by the present application is to gradually divide the original image into sub-blocks that meet the homogeneity condition and are smaller than the preset size, and obtain the hierarchical information of each sub-block. In this way, only the sub-blocks that meet the conditions will be encoded and transmitted. Since the image data is compressed into multiple sub-blocks, the amount of data transmitted can be significantly reduced, thereby improving the transmission efficiency in an underwater environment with limited bandwidth. Among them, the method of recursively dividing the image and transmitting the encoded information stream layer by layer significantly reduces the amount of data transmitted.

[0061] Figure 2 A decomposition flow chart of a quadtree image is shown.

[0062] Figure 3A quadtree diagram after image decomposition is shown.

[0063] In the present application embodiment, Figure 2 As shown in FIG. 1 , the image blocks that do not meet the target conditions will be further subdivided into four small blocks for more fine-grained condition determination. Then, when each small block after the block processing meets the target conditions, the screening action is completed to obtain multiple small blocks that meet at least one of the target conditions and have the same or different sizes. Figure 3 As shown, the hierarchical information of each sub-block in the original image can be represented by a quadtree diagram. According to the branch direction of the diagram, it can be known which small-sized image blocks are obtained by dividing which large-sized image blocks, thereby facilitating subsequent encoding and decoding.

[0064] In the present application, the method of processing an image block into N sub-blocks can be characterized by a quadtree image decomposition process.

[0065] Figure 4 FIG. 4 is a flow chart showing an image transmission method for an underwater wireless sensor network according to an embodiment of the present application. Figure 4 As shown, it includes the following sub-steps S401 to S402.

[0066] Sub-step S401 , data encoding is performed on each sub-block that meets the target condition according to the color value or the pixel value to obtain each sub-block after data encoding.

[0067] The sub-blocks after data encoding together represent the original image after data encoding.

[0068] Sub-step S402, re-encoding the data-encoded original image according to the joint source-channel coding method to obtain a re-encoded original image.

[0069] The re-encoded original image is represented by the re-encoded sub-blocks.

[0070] The re-encoded sub-blocks are used as the encoded sub-blocks.

[0071] In the embodiment of the present application, the encoding steps are further refined, and it is proposed to first encode the color value or pixel value data of the sub-block that meets the conditions, and then use joint source channel coding to encode it again. This dual encoding mechanism can not only further compress the data, but also better adapt to changes in channel conditions during transmission. By first encoding the color value or pixel value data, the amount of data can be reduced. Re-encoding through JSCC can improve the robustness and stability of the transmission. This method ensures that the image can be accurately transmitted and restored even under harsh channel conditions.

[0072] In an example of the present application, the hierarchical information is based on a flag bit identifier.

[0073] In one embodiment of the present application, the sub-blocks after the flag bits and data encoding can be encoded and compressed by prefix coding or arithmetic coding. This method can not only effectively reduce the space occupied by the flag bits, but also further compress the amount of data, thereby improving the efficiency of underwater acoustic transmission. At the same time, through this method, image data can be managed more efficiently during the transmission process, reducing unnecessary information transmission, and further improving bandwidth utilization.

[0074] Figure 5 A flow chart of a method for re-encoding an original image after data encoding according to a joint source channel coding method is shown. Figure 5 As shown, it includes the following sub-steps S501 to S502.

[0075] Sub-step S501, preprocessing the original image after data encoding to obtain a preprocessed original image.

[0076] The preprocessing includes scaling and / or normalization.

[0077] Sub-step S502, re-encoding the pre-processed original image according to a joint source-channel coding method based on deep learning to obtain a re-encoded original image.

[0078] In the embodiment of the present application, the implementation method of joint source channel coding is improved, and the quality of the encoded image is ensured by preprocessing the original image before encoding. Among them, the preprocessing step can improve the statistical characteristics of the image, making it more suitable for subsequent encoding processing. In this way, not only the efficiency of encoding can be improved, but also the quality of the decoded image can be enhanced. This method can maintain the high quality of the image during the transmission process, while reducing the amount of data transmission, and adapting to the underwater environment with limited bandwidth.

[0079] Figure 6 A flowchart of another image transmission method for underwater wireless sensor networks is shown. Figure 6 As shown, the method is applied to a detection node, and includes the following steps S601 to S605.

[0080] Step S601, obtaining an original image.

[0081] Step S602, using the original image as the image block selected in the first screening, and screening based on the target condition to process the image blocks that do not meet the target condition into N sub-blocks, and using the N sub-blocks as the image blocks selected in the next screening for screening again, until the last screening is completed.

[0082] The target conditions include that the sub-blocks meet a uniformity condition and that the size of the sub-blocks is smaller than a preset size.

[0083] For example, in the last screening, each sub-block satisfies at least one target condition.

[0084] Step S603, obtaining hierarchical information of each sub-block in the original image, wherein the hierarchical information includes the layer number to which the sub-block belongs and the original image block to which the sub-block belongs.

[0085] The layer number to which the sub-block belongs is characterized based on the sub-block size, where the sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer.

[0086] Step S604: Encode the sub-blocks that meet the target condition to obtain each encoded sub-block.

[0087] Step S605: Based on the hierarchical information, in the order from the first layer to the last layer and according to the preset limited number of layers, the encoded information stream is transmitted to the central node using the trained deep learning joint source channel model encoding.

[0088] The preset restricted number of layers is used to restrict the number of layers that can be transmitted.

[0089] The present application also provides another image transmission method of an underwater wireless sensor network, which is applied to a central node and is used to cooperate with the detection node mentioned in the above embodiment to complete image transmission. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, and will not be repeated here.

[0090] Figure 7 A flow chart of an image transmission method for an underwater wireless sensor network is shown. Figure 7 As shown, the method is applied to a central node, and includes the following steps S701 to S704.

[0091] Step S701: receiving a coded information stream transmitted by a detection node.

[0092] The coded information stream includes the coded sub-blocks transmitted layer by layer by the detection node in the order from the first layer to the last layer.

[0093] Among them, each sub-block is used to jointly form the original image collected by the detection node. The layer number to which the sub-block belongs is characterized based on the sub-block size. The sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer.

[0094] Step S702: decode the image blocks one by one according to the transmission order of the coded information stream, and stitch the images according to the decoding order.

[0095] Step S703, monitoring the clarity of the image after the image is stitched.

[0096] Step S704, in response to monitoring that the clarity of the image after the image splicing is greater than or equal to a preset clarity threshold, terminating the transmission of the coded information stream.

[0097] Figure 8 A flow chart of an image transmission method for an underwater wireless sensor network is shown. Figure 8 As shown, the method is applied to a central node, and includes the following steps S801 to S805.

[0098] Step S801: receiving a coded information stream transmitted by a detection node.

[0099] The coded information stream includes the coded sub-blocks transmitted layer by layer by the detection node in the order from the first layer to the last layer.

[0100] Among them, each sub-block is used to jointly form the original image collected by the detection node. The layer number to which the sub-block belongs is characterized based on the sub-block size. The sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer.

[0101] Step S802, based on the deep learning joint source channel decoding method, image blocks are decoded one by one according to the transmission order of the encoded information stream, and images are spliced ​​in the decoding order.

[0102] Step S803, monitoring the clarity of the image after the image is stitched.

[0103] Step S804, in response to monitoring that the clarity of the image after the image splicing is greater than or equal to a preset clarity threshold, terminating the transmission of the coded information stream.

[0104] The present application also provides a system embodiment that is based on the above embodiment, which is used to implement the method steps of the above embodiment. The explanation based on the same name meaning is the same as the above embodiment, and has the same technical effect as the above embodiment, which will not be repeated here.

[0105] Fig. 9 A schematic diagram of an image transmission system of an underwater wireless sensor network is shown in FIG. Fig. 9 As shown, the system 900 includes a detection node 901 and a central node 902 .

[0106] The detection node 901 is used to obtain the original image. The original image is used as the image block selected in the first screening, and the image block that does not meet the target condition is screened based on the target condition to process the image block into N sub-blocks, and the N sub-blocks are used as the image blocks selected in the next screening for re-screening until the last screening is completed. The hierarchical information of each sub-block in the original image is obtained. The sub-blocks that meet the target condition are encoded to obtain the encoded sub-blocks. And based on the hierarchical information, in the order from the first layer to the last layer, the trained deep learning joint source channel model encoding is used to transmit the encoded information stream to the central node.

[0107] The central node 902 is used to receive the coded information stream transmitted by the detection node, decode the image blocks one by one according to the transmission order of the coded information stream, and splice the images according to the decoding order, monitor the image clarity after the image splicing, and terminate the transmission of the coded information stream when the image clarity after the image splicing is detected to be greater than or equal to a preset clarity threshold.

[0108] Fig.10 The overall flow chart of image transmission in an underwater wireless sensor network scenario is shown.

[0109] For example, Fig.10 As shown, x represents each sub-block with a quadtree structure, y represents the original image after joint source channel coding, represents the original image after transmission through the physical channel and after joint source channel coding. Represents the original image restored by the central node. First, the original image is recursively divided into multiple sub-blocks until each sub-block meets the homogeneity condition or reaches the predetermined minimum block size. The hierarchical information of these sub-blocks is recorded to form a quadtree structure. Next, these sub-blocks are encoded using joint source channel coding (JSCC) to adapt to the bandwidth-constrained underwater transmission environment. The encoded image data is transmitted to the central node through a physical channel. During the transmission process, the JSCC encoder converts the image data into a signal suitable for physical channel transmission. After the central node receives the signal, it recovers the encoded data through demodulation of the physical channel, and then uses the JSCC decoder to decode the data and finally restore the original image. The entire process is implemented through hierarchical transmission, ensuring that the image data can be transmitted efficiently and with high quality under bandwidth-constrained conditions.

[0110] Fig.11 A flow chart of information transmission based on coded data stream is shown.

[0111] For example, Fig.11As shown, the detection node recursively divides the original image into multiple sub-blocks according to the quadtree hierarchical coding, and encodes the sub-blocks that meet the uniformity condition. The encoded image information is transmitted to the central node layer by layer in the order from the first layer to the last layer. After each transmission of the depth layer (for example, depth represents the number of layers), the central node will evaluate the clarity of the received image. If the central node determines that the image is clear enough, it will send a stop transmission instruction to the detection node, and the detection node will stop further transmitting deeper information. In this way, the system can effectively utilize bandwidth resources while ensuring image quality.

[0112] Fig.12 The joint source channel coding flow chart of the present application is shown.

[0113] For example, Fig.12 As shown, x represents each sub-block with a quadtree structure, y represents the original image after joint source channel coding, represents the original image after transmission through the physical channel and after joint source channel coding. Represents the original image restored by the central node. At the sending end (i.e., the detection node), the original image is first preprocessed, including operations such as scaling and normalization, to meet the input requirements of the encoder. The preprocessed image data is sent to the joint source channel encoder for efficient encoding processing. The encoded data is transmitted through a physical channel, which may contain noise and interference, affecting the signal quality. After receiving the signal, the receiving end (i.e., the central node) first demodulates and recovers the encoded data. Then, the data is decoded using the joint source channel decoder to restore the original image. Finally, the received image is post-processed, such as denoising and sharpening, to improve the image quality. The entire process ensures that image data can be transmitted efficiently and with high quality under conditions of limited bandwidth and interference.

[0114] In this application, considering the bandwidth limitation of underwater acoustic communication, this application proposes an image transmission coding algorithm for underwater wireless sensor networks, which combines the advantages of progressive image coding and joint source channel image transmission algorithm. When designing, the complexity of the image and the variability of the underwater environment are comprehensively considered. Specifically, the overall process first uses quadtree hierarchical coding technology to process the original image to generate an image of a specific level, and then compresses and encodes it through the JSCC encoder, and finally transmits the encoded data to the receiving end, and the JSCC decoder at the receiving end decodes and restores the image.

[0115] In this application, the progressive image coding algorithm focuses on processing the color information of each pixel of the image, and divides the image into smaller and smaller square blocks by using the similarities and differences of local areas in the image through image block-based technology. Among them, quadtree hierarchical coding is an effective compression method, which recursively divides the image into N sub-blocks until each sub-block meets the uniformity condition or reaches a predetermined minimum block size, thereby reducing data redundancy and achieving efficient compression. This process includes four basic steps: image segmentation, recursive segmentation, encoding, and decoding. It aims to transmit image information hierarchically and progressively through depth-first traversal, ensuring that the central node can decide whether to continue to receive deeper data based on the quality of the received information.

[0116] Correspondingly, the joint source channel coding algorithm is committed to maximizing the performance of the communication system by jointly designing source coding and channel coding. In the field of image transmission, JSCC technology can effectively combine the statistical characteristics of the source and the transmission characteristics of the channel to optimize the image quality and efficiency during the transmission process. In particular, it can overcome the "cliff effect" existing in the traditional separate source coding and channel coding system, that is, when the channel conditions are below a certain threshold, the performance will drop sharply. Based on this, the present application introduces a JSCC image transmission scheme based on deep learning, which includes three parts: the transmitter, the physical channel and the receiver, and realizes the whole process from image preprocessing to the final decoding output. The transmitter encodes the image through an encoder based on deep learning, and performs joint source channel coding considering the channel characteristics. The receiver uses a decoder also based on deep learning to decode the encoded data, restore the original image, and improve the image quality through post-processing. This scheme not only improves the quality and efficiency of image transmission, but also enhances the system's ability to resist channel noise and interference.

[0117] Fig.13 is a block diagram of an underwater acoustic device 1300 for image transmission according to an exemplary embodiment.

[0118] like Fig.13As shown, an embodiment of the present application provides an underwater acoustic device 1300. The underwater acoustic device 1300 includes a memory 1301, a processor 1302, and an input / output (I / O) interface 1303. The memory 1301 is used to store instructions. The processor 1302 is used to call the instructions stored in the memory 1301 to execute the image transmission method of the underwater wireless sensor network in the embodiment of the present application. The processor 1302 is connected to the memory 1301 and the I / O interface 1303 respectively, for example, through a bus system and / or other forms of connection mechanisms (not shown). The memory 1301 can be used to store programs and data, including the program of the image transmission method of the underwater wireless sensor network involved in the embodiment of the present application. The processor 1302 executes various functional applications and data processing of the underwater acoustic device 1300 by running the program stored in the memory 1301.

[0119] In the embodiment of the present application, the processor 1302 can be implemented in at least one hardware form of a digital signal processor (Digital Signal Processing, DSP), a field programmable gate array (Field Programmable Gate Array, FPGA), and a programmable logic array (Programmable Logic Array, PLA). The processor 1302 can be a central processing unit (Central Processing Unit, CPU) or one or a combination of other forms of processing units with data processing capabilities and / or instruction execution capabilities.

[0120] The memory 1301 in the embodiment of the present application may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD), etc.

[0121] In the embodiment of the present application, the I / O interface 1303 may be used to receive input instructions (such as digital or character information, and to generate key signal input related to user settings and function control of the underwater acoustic device 1300, etc.), and may also output various information to the outside (such as images or sounds, etc.). In the embodiment of the present application, the I / O interface 1303 may include one or more of a physical keyboard, a function key (such as a volume control key, a switch key, etc.), a mouse, a joystick, a trackball, a microphone, a speaker, and a touch panel, etc.

[0122] In some embodiments, the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, any of the methods described above is performed.

[0123] In some embodiments, the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, any of the methods described above is performed.

[0124] Although operations are described in a particular order in the drawings, this should not be understood as requiring that the operations be performed in the particular order shown or in serial order, or that all shown operations be performed to achieve desired results. In certain circumstances, multitasking and parallel processing may be advantageous.

[0125] The methods and devices of the present application can be implemented using standard programming techniques, using rule-based logic or other logic to implement various method steps. It should also be noted that the words "device" and "module" used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving input.

[0126] Any steps, operations or procedures described herein may be performed or implemented using one or more hardware or software modules, either alone or in combination with other devices. In one embodiment, the software module is implemented using a computer program product including a computer-readable medium containing computer program code, which can be executed by a computer processor to perform any or all of the described steps, operations or procedures.

[0127] The foregoing description of the implementation of the present application has been given for the purpose of illustration and description. The foregoing description is not exhaustive nor is it intended to limit the present application to the exact form disclosed, and various variations and modifications may exist according to the above teachings or may be obtained from the practice of the present application. These embodiments are selected and described in order to illustrate the principles of the present application and its practical application, so that those skilled in the art can utilize the present application in various embodiments and various modifications suitable for the specific purpose contemplated.

[0128] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0129] It can be further understood that, unless otherwise specified, “connection” includes a direct connection without other components between the two, and also includes an indirect connection with other components between the two.

[0130] It is further understood that, although the operations are described in a specific order in the drawings in the embodiments of the present application, it should not be understood as requiring the operations to be performed in the specific order or serial order shown, or requiring the execution of all the operations shown to obtain the desired results. In certain environments, multitasking and parallel processing may be advantageous.

[0131] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to encompass any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the field of the present application that are not disclosed in the present application. The specification and embodiments are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following scope of rights.

[0132] It should be understood that the present application is not limited to the precise structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the scope of the appended claims.

[0133] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An image transmission method for an underwater wireless sensor network, characterized in that: Applied to a detection node, the method comprises: Get the original image; The original image is used as the image block selected in the first screening, and the screening is performed based on the target condition, so as to process the image block that does not meet the target condition into N sub-blocks, and the N sub-blocks are used as the image blocks selected in the next screening for re-screening until the last screening is completed; wherein the target condition includes that the sub-block meets the uniformity condition, and the size of the sub-block is less than the preset size; in the last screening, each sub-block meets at least one of the target conditions, and N is a positive integer greater than or equal to 4; Obtaining hierarchical information of each of the sub-blocks in the original image; wherein the hierarchical information includes the number of layers to which the sub-blocks belong and the original image block to which the sub-blocks belong; wherein the number of layers to which the sub-blocks belong is characterized based on the size of the sub-blocks, the sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer; Encoding the sub-blocks that meet the target condition to obtain encoded sub-blocks; Based on the hierarchical information, in the order from the first layer to the last layer, a coded information stream is transmitted to a central node using a trained deep learning joint source-channel model encoding; wherein the coded information stream is used to transmit each of the coded sub-blocks layer by layer.

2. The method according to claim 1, characterized in that The step of encoding the sub-blocks that meet the target condition to obtain the encoded sub-blocks includes: According to the color value or the pixel value, data encoding is performed on each sub-block that meets the target condition to obtain each sub-block after data encoding; wherein each sub-block after data encoding collectively represents the original image after data encoding; According to the joint source channel coding method, the original image after the data encoding is re-encoded to obtain the re-encoded original image; wherein the re-encoded original image is jointly represented by the re-encoded sub-blocks; The re-encoded sub-blocks are used as the encoded sub-blocks.

3. The method according to claim 2, characterized in that The hierarchical information is based on a flag bit identification; The method further comprises: Based on a prefix coding method or an arithmetic coding method, the sub-block after the flag bit and the data are encoded is encoded and compressed.

4. The method according to claim 2, characterized in that: The step of re-encoding the data-encoded original image according to the joint source-channel coding method to obtain the re-encoded original image includes: Preprocessing the original image after data encoding to obtain a preprocessed original image; wherein the preprocessing includes scaling processing and / or normalization processing; According to a joint source-channel coding method based on deep learning, the preprocessed original image is re-encoded to obtain a re-encoded original image.

5. The method according to claim 1, characterized in that The method of transmitting the encoded information stream to the central node using the trained deep learning joint source-channel model encoding in the order of the first layer to the last layer based on the hierarchical information includes: Based on the hierarchical information, in the order of the first layer to the last layer and according to a preset limited number of layers, using the trained deep learning joint source-channel model encoding to transmit the encoded information stream to the central node; The preset restricted number of layers is used to restrict the number of transmittable layers.

6. An image transmission method for an underwater wireless sensor network, characterized in that: Applied to the central node, the method includes: Receive a coded information stream transmitted by a detection node; wherein the coded information stream includes each coded sub-block transmitted layer by layer by the detection node in the order from the first layer to the last layer; wherein each sub-block is used to jointly constitute an original image collected by the detection node, and the number of layers to which the sub-block belongs is characterized based on the sub-block size, the sub-block with the largest size corresponds to the first layer, and the sub-block with the smallest size corresponds to the last layer; Decoding the image blocks one by one according to the transmission order of the coded information stream, and splicing the images according to the decoding order; Monitoring the clarity of the image after the image is stitched; In response to monitoring that the clarity of the image after the image splicing is greater than or equal to a preset clarity threshold, the transmission of the encoded information stream is terminated.

7. The method according to claim 6, characterized in that The step of decoding the image blocks one by one according to the transmission order of the coded information stream comprises: The joint source-channel decoding method based on deep learning decodes image blocks one by one according to the transmission order of the encoded information stream.

8. An image transmission system for an underwater wireless sensor network, characterized in that: The system comprises: A detection node, used to obtain an original image; use the original image as an image block selected during the first screening, and perform screening based on a target condition to process the image blocks that do not meet the target condition into N sub-blocks, and use the N sub-blocks as image blocks selected during the next screening for re-screening until the last screening is completed, wherein N is a positive integer greater than or equal to 4; obtain hierarchical information of each sub-block in the original image; encode the sub-blocks that meet the target condition to obtain each encoded sub-block; and transmit a coded information stream to a central node based on the hierarchical information in the order of the first layer to the last layer using a trained deep learning joint source-channel model encoding; A central node is used to receive a coded information stream transmitted by a detection node; decode image blocks one by one in the transmission order of the coded information stream, and perform image splicing in the decoding order; monitor the image clarity after the image splicing; and terminate the transmission of the coded information stream when it is monitored that the image clarity after the image splicing is greater than or equal to a preset clarity threshold.

9. An underwater acoustic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 5, and / or executes the computer program to implement the method according to any one of claims 6 to 7.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the method described in any one of claims 1 to 5 is implemented, and / or the method described in any one of claims 6 to 7 is implemented.

Images