Marine organism monitoring buoy identification result transmission method and device, medium and product

Abstract

The invention discloses a marine organism monitoring buoy recognition result transmission method and device, a medium and a product, and relates to the field of data transmission, and the method comprises the steps: obtaining a marine organism monitoring buoy recognition result; determining a judgment result according to the confidence coefficient and the confidence coefficient threshold value of the target recognition result in the json format file; when the judgment result is that the confidence coefficient of the target recognition result is greater than or equal to a confidence coefficient threshold value, cutting a picture of the recognition result by utilizing coordinate information of the target region, and extracting a detected target picture; and a shore manual analysis module is adopted to judge the detection target picture, and when the detection target picture is a detection target, the picture of the identification result is compressed and coded, and then the coded picture is sent. According to the invention, real-time performance and reliability of neural network identification result transmission of the marine biological monitoring buoy can be provided, and characteristics of low power consumption and low cost are possessed.

Description

Technical Field

[0001] The present application relates to the field of data transmission, and in particular to a method, device, medium and product for transmitting identification results of marine biological monitoring buoys. Background Art

[0002] With the development of electronic technology, it has become possible to deploy biological monitoring buoys equipped with neural network edge computing nodes in the near sea or ocean. However, due to limitations in communication technology or cost, the recognition results of edge computing nodes are difficult to transmit back.

[0003] At present, the neural network calculation results of edge computing nodes usually include recognition results in text form and recognition content mainly in the form of pictures, which are usually transmitted using the following methods: 1. Local storage of recognition results: The recognition results are recorded by installing a dedicated memory in the device, and the memory is manually recovered after a specific period of time, which consumes a lot of manpower, is difficult to locate, and cannot guarantee timeliness; 2. Use cellular networks for data transmission: The traditional cellular network is used with a communication module to achieve remote data transmission. The traditional cellular network has low tariffs, high transmission stability, and a transmission speed that can support multimedia file transmission. However, this method requires that the terminal node be deployed at a location with GPRS or 4G network coverage. It is only suitable for use in offshore areas or near islands where there are mobile network signals, and cannot cover deep sea environments; 3. Use low-orbit communication satellite constellations (such as StarLink): Using low-orbit communication constellations for data transmission can achieve faster transmission speeds, but it consumes more power and has higher tariffs.

[0004] Therefore, based on the above problems, there is an urgent need to provide a method for transmitting marine biological monitoring buoy identification results with low power consumption, high real-time performance, low fees and high transmission reliability. Summary of the invention

[0005] The purpose of this application is to provide a method, device, medium and product for transmitting the identification results of a marine biological monitoring buoy, which can provide real-time and reliability of the transmission of the neural network identification results of the marine biological monitoring buoy, as well as the characteristics of low power consumption and low charges.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for transmitting identification results of a marine biological monitoring buoy, the method comprising:

[0008] Obtaining the marine biological monitoring buoy identification result; the marine biological monitoring buoy identification result includes: a json format file and a corresponding identification result picture; the json format file includes: the confidence of the target identification result and the coordinate information of the target area;

[0009] Determine the judgment result according to the confidence and confidence threshold of the target recognition result in the JSON format file;

[0010] When the judgment result is that the confidence of the target identification result is less than the confidence threshold, the identification result of the marine biological monitoring buoy is re-obtained;

[0011] When the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold, the image of the recognition result is cropped using the coordinate information of the target area to extract the detection target image;

[0012] The onshore manual analysis module is used to judge the detection target image, and when the detection target image is the detection target, the image of the recognition result is compressed and encoded, and then the encoded image is sent.

[0013] Optionally, the step of obtaining the marine biological monitoring buoy identification result also includes:

[0014] The trained neural network is deployed on the edge computing terminal of the marine biological monitoring buoy.

[0015] Optionally, the edge computing terminal is a camera.

[0016] Optionally, the onshore manual analysis module is used to judge the detection target image, and when the detection target image is the detection target, the image of the recognition result is compressed and encoded, and then the encoded image is sent, which specifically includes:

[0017] Use JPG compression algorithm to compress the image of recognition result;

[0018] According to the compressed picture, re-encode using progressive loading encoding;

[0019] According to the re-encoded picture, Base64 encoding is used for transcoding to obtain the encoded picture.

[0020] Optionally, a JPG compression algorithm is used to compress the image of the recognition result, specifically including:

[0021] Use the JPG compression algorithm to compress the image of the recognition result once;

[0022] Determine whether the compressed image meets the set image size;

[0023] If it does not match, the JPG compression algorithm is used to perform secondary compression on the image of the recognition result.

[0024] Optionally, according to the re-encoded picture, Base64 encoding is used for transcoding to obtain an encoded picture, and then the following steps are further included:

[0025] The Reed-Solomon coding method is used to correct errors based on the encoded image.

[0026] In a second aspect, the present application provides a marine biological monitoring buoy identification result transmission device, the marine biological monitoring buoy identification result transmission device comprising:

[0027] A result acquisition unit is used to acquire the identification result of the marine biological monitoring buoy; the identification result of the marine biological monitoring buoy includes: a json format file and a corresponding image of the identification result; the json format file includes: the confidence of the target identification result and the coordinate information of the target area;

[0028] A judgment result determination unit, used to determine the judgment result according to the confidence and confidence threshold of the target recognition result in the JSON format file;

[0029] The identification result updating unit is used to re-acquire the identification result of the marine biological monitoring buoy when the confidence of the target identification result is less than the confidence threshold;

[0030] A detection target image extraction unit, used to crop the image of the recognition result using the coordinate information of the target area to extract the detection target image when the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold;

[0031] The image sending unit is used to use the onshore manual analysis module to judge the detection target image, and when the detection target image is the detection target, compress and encode the image of the recognition result, and then send the encoded image.

[0032] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for transmitting identification results of a marine biological monitoring buoy.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for transmitting identification results of a marine biological monitoring buoy.

[0034] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for transmitting identification results of a marine biological monitoring buoy.

[0035] According to the specific embodiments provided in this application, this application has the following technical effects:

[0036] The present application provides a method, device, medium and product for transmitting the identification results of a marine biological monitoring buoy. Before the image is transmitted, the detection target image is first extracted, and the image containing only the detection target is sent to an onshore manual analysis module. The onshore manual analysis module is used to pre-judge the detection target image, effectively reducing the possibility of erroneous results being transmitted, thereby effectively reducing unnecessary transmission resource consumption caused by false alarms of neural networks, and further reducing power consumption and charges; when it is determined to be a detection target, the image of the identification result is compressed and encoded, and then the encoded image is sent, ensuring the reliability and real-time nature of the transmission. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0038] Figure 1 This is a flow chart of a method for transmitting identification results of a marine biological monitoring buoy in one embodiment of the present application;

[0039] Figure 2 This is a schematic diagram of the overall process of a method for transmitting identification results of a marine biological monitoring buoy in one embodiment of the present application;

[0040] Figure 3 This is a schematic diagram of the structure of a marine biological monitoring buoy;

[0041] Figure 4 This is a schematic diagram of the picture transmission process. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0044] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a method for transmitting identification results of marine biological monitoring buoys is provided, and the method includes the following S101 to S105. Among them:

[0045] S101, obtaining the identification result of the marine biological monitoring buoy; the identification result of the marine biological monitoring buoy includes: a json format file and a corresponding image of the identification result; the json format file includes: the confidence of the target identification result and the coordinate information of the target area; the coordinate information is the position coordinates of the four corners of the target area in the image;

[0046] like Figure 3 As shown, the marine biological monitoring buoy includes: a float, an electronic compartment, a solar panel, related brackets and a camera equipped with a neural network processing chip; wherein, the float is used to carry the electronic compartment; the electronic compartment includes a neural network auxiliary processing host, an embedded main controller, etc., and the processing host is connected to the embedded main controller through a network port; the solar panel is located on the upper surface of the float and is used to provide power; the solar panel is connected to the battery management module in the electronic compartment through cables; the battery management module is symmetrically placed in the electronic compartment; there is a bracket above the float, which includes a weather sensor and three cameras, each camera is equipped with an embedded neural network computing chip, which can be used for neural network computing, and the three cameras are connected to the neural network auxiliary processing host in the electronic compartment through a network port; there is also a bracket for stabilizing the center of gravity under the buoy, and if necessary, other scientific research equipment or instruments can be carried on the upper or lower bracket.

[0047] The marine biological monitoring buoy runs the trained neural network through the neural network computing chip in the three cameras, and outputs the marine biological monitoring buoy recognition results including json format files and corresponding recognition result pictures;

[0048] S102, determining a judgment result according to the confidence level and confidence threshold of the target recognition result in the json format file;

[0049] S103, when the judgment result is that the confidence of the target recognition result is less than the confidence threshold, the marine biological monitoring buoy recognition result is re-acquired; that is, the current marine biological monitoring buoy recognition result is not adopted and needs to be re-acquired;

[0050] S104, when the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold, the image of the recognition result is cropped using the coordinate information of the target area to extract the detection target image;

[0051] Among them, when the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold, the image of the recognition result is first stored and an identification serial number is generated; then the detection target contained in the image is cropped, the actual target range is extracted, and only the detected target image is uploaded for manual verification;

[0052] S105, using an onshore manual analysis module to judge the detection target image, and when the detection target image is the detection target, compressing and encoding the image of the recognition result, and then sending the encoded image.

[0053] The detection target is pre-judged in advance through manual judgment in the onshore manual analysis module, and the pre-judgment can effectively reduce the possibility of erroneous results being transmitted, thereby effectively reducing unnecessary transmission resource consumption caused by false alarms of neural networks, etc.

[0054] like Figure 4 As shown, S501 specifically includes:

[0055] S51, compressing the image of the recognition result using a JPG compression algorithm;

[0056] Use the JPG compression algorithm to compress the image of the recognition result once;

[0057] Determine whether the compressed image meets the set image size;

[0058] If it does not match, the JPG compression algorithm is used to perform secondary compression on the image of the recognition result.

[0059] S52, re-encoding the compressed image by using progressive loading encoding;

[0060] Using the progressive loading format ensures that even if there are problems with subsequent satellite transmission, part of the image can be displayed. Progressive loading encoding describes the overall structure of the image package in the first frame and splits all subsequent packages to ensure that even if there is partial data, the final result is still available to a certain extent.

[0061] S53, transcoding is performed using Base64 encoding according to the re-encoded image to obtain an encoded image.

[0062] Base64 can encode the pixel information of the image into character information that can be represented by ASCII code, thus meeting the transmission requirements of most short message satellite communication systems (such as Beidou short message communication);

[0063] S53 and later also include:

[0064] The Reed-Solomon coding method is used to correct errors based on the coded images, and errors caused by the instability of satellite communications can be automatically corrected during the transmission process;

[0065] After receiving the corresponding data on shore, the data is first decoded using Reed-Solomon. Based on the quality of the data packet, the first N complete data packets are selected. Based on the segmentation description information contained in the first data packet, these data packets are re-encoded using Base64 to obtain the image information, and the image is then reassembled and displayed.

[0066] Based on the same inventive concept, the embodiment of the present application also provides a marine biological monitoring buoy identification result transmission device for implementing the marine biological monitoring buoy identification result transmission method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more marine biological monitoring buoy identification result transmission device embodiments provided below can refer to the limitations of the marine biological monitoring buoy identification result transmission method above, and will not be repeated here.

[0067] In an exemplary embodiment, a marine biological monitoring buoy identification result transmission device is provided, comprising:

[0068] A result acquisition unit is used to acquire the identification result of the marine biological monitoring buoy; the identification result of the marine biological monitoring buoy includes: a json format file and a corresponding image of the identification result; the json format file includes: the confidence of the target identification result and the coordinate information of the target area;

[0069] A judgment result determination unit, used to determine the judgment result according to the confidence and confidence threshold of the target recognition result in the JSON format file;

[0070] The identification result updating unit is used to re-acquire the identification result of the marine biological monitoring buoy when the confidence of the target identification result is less than the confidence threshold;

[0071] A detection target image extraction unit, used to crop the image of the recognition result using the coordinate information of the target area to extract the detection target image when the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold;

[0072] The image sending unit is used to use the onshore manual analysis module to judge the detection target image, and when the detection target image is the detection target, compress and encode the image of the recognition result, and then send the encoded image.

[0073] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for transmitting identification results of a marine biological monitoring buoy is implemented.

[0074] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0075] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0076] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0077] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0078] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0079] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0080] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for transmitting identification results of marine biological monitoring buoys, characterized in that: The method for transmitting the identification result of the marine biological monitoring buoy comprises: Obtaining the marine biological monitoring buoy identification result; the marine biological monitoring buoy identification result includes: a json format file and a corresponding identification result picture; the json format file includes: the confidence of the target identification result and the coordinate information of the target area; Determine the judgment result according to the confidence and confidence threshold of the target recognition result in the JSON format file; When the judgment result is that the confidence of the target identification result is less than the confidence threshold, the identification result of the marine biological monitoring buoy is re-obtained; When the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold, the image of the recognition result is cropped using the coordinate information of the target area to extract the detection target image; The onshore manual analysis module is used to judge the detection target image, and when the detection target image is the detection target, the image of the recognition result is compressed and encoded, and then the encoded image is sent.

2. The method for transmitting identification results of marine biological monitoring buoys according to claim 1, characterized in that: The obtaining of the marine biological monitoring buoy identification result also includes: The trained neural network is deployed on the edge computing terminal of the marine biological monitoring buoy.

3. The method for transmitting the identification results of marine biological monitoring buoys according to claim 2, characterized in that: The edge computing terminal is a camera.

4. The method for transmitting identification results of marine biological monitoring buoys according to claim 1, characterized in that: The onshore manual analysis module is used to judge the detection target image, and when the detection target image is the detection target, the image of the recognition result is compressed and encoded, and then the encoded image is sent, which specifically includes: Use JPG compression algorithm to compress the image of recognition result; According to the compressed picture, re-encode using progressive loading encoding; According to the re-encoded picture, Base64 encoding is used for transcoding to obtain the encoded picture.

5. The method for transmitting the identification results of marine biological monitoring buoys according to claim 4, characterized in that: The JPG compression algorithm is used to compress the image of the recognition result, including: Use the JPG compression algorithm to compress the image of the recognition result once; Determine whether the compressed image meets the set image size; If it does not match, the JPG compression algorithm is used to perform secondary compression on the image of the recognition result.

6. The method for transmitting the identification results of marine biological monitoring buoys according to claim 4, characterized in that: According to the re-encoded picture, Base64 encoding is used for transcoding to obtain the encoded picture, and then the following is included: The Reed-Solomon coding method is used to correct errors based on the encoded image.

7. A marine biological monitoring buoy identification result transmission device, characterized in that: The marine biological monitoring buoy identification result transmission device includes: A result acquisition unit is used to acquire the identification result of the marine biological monitoring buoy; the identification result of the marine biological monitoring buoy includes: a json format file and a corresponding image of the identification result; the json format file includes: the confidence of the target identification result and the coordinate information of the target area; A judgment result determination unit, used to determine the judgment result according to the confidence and confidence threshold of the target recognition result in the JSON format file; The identification result updating unit is used to re-acquire the identification result of the marine biological monitoring buoy when the confidence of the target identification result is less than the confidence threshold; A detection target image extraction unit, used to crop the image of the recognition result using the coordinate information of the target area to extract the detection target image when the judgment result is that the confidence of the target recognition result is greater than or equal to the confidence threshold; The image sending unit is used to use the onshore manual analysis module to judge the detection target image, and when the detection target image is the detection target, compress and encode the image of the recognition result, and then send the encoded image.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for transmitting identification results of a marine biological monitoring buoy as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for transmitting the identification results of a marine biological monitoring buoy described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for transmitting the identification results of a marine biological monitoring buoy described in any one of claims 1 to 6 is implemented.

Images