Image processing method, device, storage medium and computer equipment

By using branching techniques of image recognition models, combined with the identification of net cages and water bodies, the problem of misidentification of aquaculture net cages has been solved, achieving higher identification accuracy.

CN113836982BActive Publication Date: 2024-11-08ALIBABA GROUP HOLDING LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010588381.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-06-24
Publication Date
2024-11-08
Estimated Expiration
2040-06-24

AI Technical Summary

Technical Problem

Existing technologies suffer from misidentification when identifying aquaculture cages from images, leading to incorrect identification of the target object.

Method used

Using the branching technique of the image recognition model, the net cages and water bodies in the image are identified separately, and the relationship between the two is combined to output the identification result of whether the net cage is an aquaculture net cage in the water body.

Benefits of technology

This improved the accuracy of identifying aquaculture cages and reduced misidentification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113836982B_ABST
    Figure CN113836982B_ABST
Patent Text Reader

Abstract

The present invention discloses an image processing method, device, storage medium and computer equipment. The method comprises: receiving a first image to be identified; identifying a cage in the first image to be identified by a first branch of an image recognition model, and identifying a water body in the first image to be identified by a second branch of the image recognition model; and outputting a first recognition result, wherein the first recognition result includes the relationship between the cage and the water body. The present invention solves the technical problem of misidentification of aquaculture cages when identifying aquaculture cages from images in the related art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to an image processing method, device, storage medium and computer equipment. Background Art

[0002] In the related art, when recognizing an image, the target object in the image is not the target object actually required. For example, the target object recognized is not the target object in the predetermined target environment, thus resulting in a large number of misidentifications of the target object. For example, when recognizing aquaculture cages from an image, that is, when recognizing the cages used for aquaculture in the image, since aquaculture is generally carried out in a water body, sometimes the recognized cages are on land, thus resulting in misidentification of the aquaculture cages.

[0003] Therefore, in the related art, when identifying aquaculture cages from images, there is a problem of misidentification of aquaculture cages.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide an image processing method, apparatus, storage medium and computer equipment to at least solve the technical problem of misidentification of aquaculture cages when identifying aquaculture cages from images in the related art.

[0006] According to one aspect of an embodiment of the present invention, there is provided an image processing method, comprising: receiving a first image to be identified; identifying a fish cage in the first image to be identified by a first branch of an image recognition model, and identifying a water body in the first image to be identified by a second branch of the image recognition model; and outputting a first recognition result, wherein the first recognition result includes a relationship between the fish cage and the water body.

[0007] According to another aspect of an embodiment of the present invention, there is also provided an image processing method, comprising: receiving a second image to be identified, wherein the second image to be identified includes a cage; identifying a water body in the second image to be identified by using an image recognition model; and outputting a second recognition result, wherein the second recognition result is used to identify whether the cage is a breeding cage in the water body.

[0008] According to one aspect of an embodiment of the present invention, there is also provided an image processing device, comprising: a first receiving module for receiving a first image to be identified; a first identification module for identifying a fish cage in the first image to be identified through a first branch of an image recognition model, and identifying a water body in the first image to be identified through a second branch of the image recognition model; and a first output module for outputting a first identification result, wherein the first identification result includes the relationship between the fish cage and the water body.

[0009] According to another aspect of an embodiment of the present invention, there is also provided an image processing device, comprising: a second receiving module, used to receive a second image to be identified, wherein the second image to be identified includes a cage; a second identification module, used to identify a water body in the second image to be identified by means of an image recognition model; and a second output module, used to output a second identification result, wherein the second identification result is used to identify whether the cage is a breeding cage in the water body.

[0010] According to one aspect of an embodiment of the present invention, a storage medium is further provided, wherein the storage medium stores a program, wherein when the program is executed by a processor, the processor is controlled to execute any one of the above-mentioned image processing methods.

[0011] According to another aspect of an embodiment of the present invention, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program; and the processor is used to execute the computer program stored in the memory, wherein when the computer program is executed, the processor executes any one of the above-mentioned image processing methods.

[0012] In the embodiment of the present invention, the water body in the image to be identified is identified by an image recognition model. By combining the identification of cages with the identification of water bodies, the purpose of identifying the relationship between cages and water bodies, that is, identifying whether the cage is a aquaculture cage in the water body, is achieved, thereby achieving the technical effect of improving the recognition rate of accurate identification of aquaculture cages, and further solving the technical problem of misidentification of aquaculture cages when identifying aquaculture cages from images in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0014] Figure 1 A hardware structure block diagram of a computer terminal for implementing an image processing method is shown;

[0015] Figure 2is a flowchart of an image processing method 1 according to Embodiment 1 of the present invention;

[0016] Figure 3 is a flowchart of a second image processing method according to embodiment 1 of the present invention;

[0017] Figure 4 is a structural schematic diagram of an image recognition model according to a preferred embodiment of the present invention;

[0018] Figure 5 is a structural block diagram of an image processing device 1 according to Embodiment 2 of the present invention;

[0019] Figure 6 is a structural block diagram of an image processing device 2 according to Embodiment 3 of the present invention;

[0020] Figure 7 It is a structural block diagram of a computer terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] According to an embodiment of the present invention, a method embodiment of an image processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] The method embodiment provided in Embodiment 1 of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing an image processing method. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (shown as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0026] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0027] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the image processing method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, to implement the vulnerability detection method of the above-mentioned application program. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0028] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0029] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0030] Under the above operating environment, this application provides Figure 2 The image processing method shown. Figure 2 is a flowchart of an image processing method 1 according to Embodiment 1 of the present invention. Figure 2 As shown, the process includes the following steps:

[0031] Step S202, receiving a first image to be recognized;

[0032] Step S204, identifying the cage in the first image to be identified by using the first branch of the image recognition model, and identifying the water body in the first image to be identified by using the second branch of the image recognition model;

[0033] Step S206, outputting a first recognition result, wherein the first recognition result includes the relationship between the cage and the water body.

[0034] Through the above steps, the water body in the image to be identified is identified by the image recognition model. By combining the identification of cages with the identification of water bodies, the purpose of identifying the relationship between cages and water bodies, that is, identifying whether the cage is a breeding cage in the water body, is achieved, thereby achieving the technical effect of improving the recognition rate of accurate identification of breeding cages, and further solving the technical problem of misidentification of breeding cages when identifying breeding cages from images in related technologies.

[0035] As an optional embodiment, the execution subject of the above steps may be a computer device for image processing, a terminal, a server, or other computing devices for processing parallel computing.

[0036] As an optional embodiment, when receiving the first image to be identified, the first image to be identified may be obtained in a variety of ways, for example, it may be directly obtained by photographing with a photographing device, it may be a monitoring screen captured from a monitoring device, it may be an image processed by a predetermined image processing device, etc. When receiving the first image to be identified, it may be received through an interface connected to other devices, or it may be received through any wireless communication technology that can achieve communication, which is not limited here.

[0037] As an optional embodiment, after receiving the first image to be identified, when identifying the cages and water bodies in the first image to be identified, multiple methods can be used. For example, the following methods can be used to implement: using the first branch of the image recognition model to identify the cages in the first image to be identified; using the second branch of the image recognition model to identify the water body in the first image to be identified; wherein the structures of the first branch and the second branch of the image recognition model can be different. Since different identification targets have different characteristics, the cages and water bodies are identified respectively through different branches, which effectively improves the recognition accuracy.

[0038] It should be noted that the combination of "identifying the cages in the first image to be identified through the first branch of the image recognition model" and "identifying the water body in the first image to be identified through the second branch of the image recognition model" can be flexibly selected according to specific needs.

[0039] For example, "identify the cages in the first image to be identified through the first branch of the image recognition model" and "identify the water body in the first image to be identified through the second branch of the image recognition model" are performed in parallel, that is, the two are executed separately and do not affect each other. Moreover, when the two are executed separately, the execution order can be multiple, for example, "identify the cages in the first image to be identified through the first branch of the image recognition model" can be performed first, and then "identify the water body in the first image to be identified through the second branch of the image recognition model"; or "identify the water body in the first image to be identified through the second branch of the image recognition model" can be performed first, and then "identify the cages in the first image to be identified through the first branch of the image recognition model" can be performed; or both can be performed at the same time.

[0040] For another example, "identifying the fish cages in the first image to be identified through the first branch of the image recognition model" and "identifying the water body in the first image to be identified through the second branch of the image recognition model" can also be executed in series, that is, the two are executed one after the other, and the result of the first execution affects the later execution. For example, "identifying the fish cages in the first image to be identified through the first branch of the image recognition model" can be executed first, and when the fish cages are identified, "identifying the water body in the first image to be identified through the second branch of the image recognition model" can be executed; or "identifying the water body in the first image to be identified through the second branch of the image recognition model" can be executed first, and when the water body is identified, "identifying the fish cages in the first image to be identified through the first branch of the image recognition model" can be executed.

[0041] As an optional embodiment, before identifying the cage in the first image to be identified by the first branch of the image recognition model, and identifying the water body in the first image to be identified by the second branch of the image recognition model, the first branch and the second branch of the image recognition model can be obtained by machine training. For example, the first type of multiple groups of data can be used for machine training to obtain the first branch of the image recognition model, wherein each group of data in the first type of multiple groups of data includes: an image, and a cage in the image; and the second type of multiple groups of data can be used for machine training to obtain the second branch of the image recognition model, wherein each group of data in the second type of multiple groups of data includes: an image, and a water body in the image. Therefore, when training the model, multiple groups of classified data can be used, and different branches of the model can be optimized and adjusted according to the multiple groups of data of different classifications, so as to achieve the benefit of improving the efficiency of model training. It should be noted that the different branches of the above-mentioned model can be independent model branches, and the independent model branches are used to achieve different recognition functions. For example, it can be the first branch used to identify the cage in the first image to be identified, or it can be the second branch used to identify the water body in the first image to be identified. In addition, the above-mentioned first category multiple groups of data and the above-mentioned second category multiple groups of data can be different data, or they can be the same group of data, but the same group of data is used for training different branches of the image recognition model. When the same group of data is used for training different branches of the image recognition model, it can not only realize the reuse of training samples, but also effectively improve the recognition accuracy when it is necessary to identify the recognition results of the cages appearing in the water body.

[0042] As an optional embodiment, the relationship between the cage and the water body may include:

[0043] When the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that appears in the water body; or,

[0044] When the similarity between the cage and the reference cage is greater than or equal to the first similarity threshold, and the similarity between the water body and the reference water body is less than the second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that does not appear in the water body. That is, through the first similarity threshold and the second similarity threshold, the cage identified by the first branch of the image recognition model and the water body identified by the second branch of the image recognition model can be determined to determine whether the identified cage is a breeding cage in the identified water body.

[0045] It should be noted that the above-mentioned reference cage can be a cage fitted after extracting the features of multiple specific aquaculture cages, which can be understood as a cage used to characterize aquatic products cultured in a water area. The reference cage can be a virtual cage, not a specific cage. The above-mentioned reference water body can also be a water body fitted after extracting the features of multiple specific water bodies, which can be understood as a water area used for aquatic products culture. The reference water body can also be a virtual water body, not a specific water area. The above-mentioned reference cage has more comprehensive characteristics of aquaculture cages than specific aquaculture cages, and the above-mentioned reference water body also has more comprehensive characteristics of water bodies than specific water areas.

[0046] As an optional embodiment, the method may further include: receiving first feedback information, wherein the first feedback information is used to provide feedback on whether the first recognition result is correct. For example, the first recognition result may be displayed through an interactive interface, and the user may determine whether the first recognition result identified by the image recognition model is correct based on the recognition of the first object to be identified. Based on the user's feedback, the first recognition image and the corresponding first recognition result may be used as a marked sample for subsequent optimization of the image recognition model, etc.

[0047] In an embodiment of the present invention, an image processing method is also provided. Figure 3 is a flowchart of the second image processing method according to the first embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0048] Step S302, receiving a second image to be identified, wherein the second image to be identified includes a cage;

[0049] Step S304, identifying a water body in the second image to be identified by using an image recognition model;

[0050] Step S306, outputting a second recognition result, wherein the second recognition result is used to identify whether the cage is a breeding cage in a water body.

[0051] Through the above steps, for the second image to be identified that includes the cages, an image recognition model is used to identify the water body in the second image to be identified, and by determining whether the cages in the second image to be identified are aquaculture cages in the water body, accurate identification of aquaculture cages is achieved during the image recognition process, thereby effectively improving the efficiency of accurately identifying images.

[0052] As an optional embodiment, the second image to be identified may be an image in which the existence of a cage is determined by a predetermined recognition model. The predetermined recognition model may be any model for identifying cages; or it may be the image recognition model for identifying water bodies. Since the recognition targets are different, it may be a branch in the image recognition model that is different from the branch for identifying water bodies. For example, in the same image recognition model, one branch is used to identify the cages, and the other branch is used to identify the water bodies.

[0053] As an optional embodiment, after the second recognition result is output, second feedback information may also be received, wherein the second feedback information is used to provide feedback on whether the second recognition result is correct. For example, the second recognition result may be displayed through an interactive interface, and the user may determine whether the second recognition result identified by the image recognition model is correct based on the recognition of the second object to be identified. Based on the user's feedback, the second recognition image and the corresponding second recognition result may be used as a marked sample for subsequent optimization of the image recognition model, etc.

[0054] Based on the above embodiments and optional embodiments, a preferred implementation manner is provided by taking whether the aquaculture cage is a cage in the water body as an example.

[0055] Cage farming generally only occurs in water areas, but the current recognition model (i.e., algorithm) cannot constrain the location of cages used for farming, resulting in a large number of false detections in land areas. Based on this, in this preferred embodiment, when using the recognition model to predict (i.e., identify) cages, a branch is added for water body prediction to generate prior information between the water body and the cages.

[0056] Figure 4 is a schematic diagram of the structure of an image recognition model according to a preferred embodiment of the present invention. Figure 4As shown, the input of the image recognition model can be an image to be recognized, and the output of the image recognition model can be different depending on whether the model is in the training stage or the application stage. For example, in the model training stage, three results can be output (which may include: outputting the cage, outputting the water body, and the result after the cage and the water body are related), so as to calculate the loss; while in the test stage (i.e., the application stage), only the result after the relationship can be output. In addition, because the characteristics of the cage and the water body are different, the network structure of the two heads used to identify the cage and the water body can be different. Specifically, the result after the output relationship can be (water body>threshold1)*(cage>threshold2), where water body>threshold1 means that the similarity between the identified water body and the predetermined water body (similar to the above-mentioned reference water body) is greater than the first predetermined threshold, and cage>threshold2 means that the similarity between the identified cage and the predetermined cage (similar to the above-mentioned reference cage) is greater than the second predetermined threshold.

[0057] In the above preferred embodiment, each head (of the model) used for different recognition targets has a different network structure. In addition, through this preferred embodiment, the output of relationships can be achieved, for example, the relationship between water bodies and cages can be output, that is, the cages only appear in the water body.

[0058] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0059] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0060] Example 2

[0061] According to an embodiment of the present invention, there is also provided an image processing device 1 for implementing the above-mentioned image processing method 1. Figure 5is a structural block diagram of an image processing device according to Embodiment 2 of the present invention. Figure 5 As shown, the image processing device 50 includes: a first receiving module 52, a first recognition module 54 and a first output module 56. The image processing device 50 is described below.

[0062] A first receiving module 52 is used to receive a first image to be identified; a first identification module 54 is connected to the first receiving module 52 and is used to identify the fish cages in the first image to be identified through a first branch of the image recognition model, and to identify the water body in the first image to be identified through a second branch of the image recognition model; a first output module 56 is connected to the first identification module 54 and is used to output a first identification result, wherein the first identification result includes the relationship between the fish cages and the water body.

[0063] It should be noted that the first receiving module 52, the first identification module 54 and the first output module 56 correspond to steps S202 to S206 in Example 1, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the modules as part of the device can be run in the computer terminal 10 provided in Example 1.

[0064] Example 3

[0065] According to an embodiment of the present invention, there is also provided an image processing device 2 for implementing the above-mentioned image processing method 2. Figure 6 is a structural block diagram of an image processing device 2 according to Embodiment 3 of the present invention. Figure 6 As shown, the second image processing device 60 includes: a second receiving module 62, a second recognition module 64 and a second output module 66. The second image processing device 60 is described below.

[0066] The second receiving module 62 is used to receive a second image to be identified, wherein the second image to be identified includes a cage; the second identification module 64 is connected to the second receiving module 62 and is used to identify the water body in the second image to be identified by using an image recognition model; the second output module 66 is connected to the second identification module 64 and is used to output a second identification result, wherein the second identification result is used to identify whether the cage is a breeding cage in the water body

[0067] It should be noted that the second receiving module 62, the second identification module 64 and the second output module 66 correspond to steps S302 to S306 in Example 1, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in Example 1. It should be noted that the modules as part of the device can be run in the computer terminal 10 provided in Example 1.

[0068] Example 4

[0069] The embodiment of the present invention can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal can also be replaced by a terminal device such as a mobile terminal.

[0070] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of the computer network.

[0071] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the image processing method of the application: receiving a first image to be identified; identifying the cages in the first image to be identified through the first branch of the image recognition model, and identifying the water body in the first image to be identified through the second branch of the image recognition model; outputting a first recognition result, wherein the first recognition result includes the relationship between the cages and the water body.

[0072] Optionally, Figure 7 is a structural block diagram of a computer terminal according to an embodiment of the present invention. Figure 7 As shown, the computer terminal may include: one or more (only one is shown in the figure) processors, memory, etc.

[0073] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the image processing method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned image processing method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0074] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receive a first image to be identified; identify the cages in the first image to be identified through the first branch of the image recognition model, and identify the water body in the first image to be identified through the second branch of the image recognition model; output a first recognition result, wherein the first recognition result includes the relationship between the cages and the water body.

[0075] Optionally, the processor may also execute program code of the following steps: the structures of the first branch and the second branch are different.

[0076] Optionally, the processor may also execute program codes of the following steps: performing machine training using multiple sets of data of the first category to obtain a first branch of the image recognition model, wherein each set of data in the multiple sets of data of the first category includes: an image, and a cage in the image; and performing machine training using multiple sets of data of the second category to obtain a second branch of the image recognition model, wherein each set of data in the multiple sets of data of the second category includes: an image, and a water body in the image.

[0077] Optionally, the processor may also execute the program code of the following steps: the relationship between the cage and the water body includes: when the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that appears in the water body; or, when the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is less than a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that does not appear in the water body.

[0078] Optionally, the processor may also execute program code of the following steps: receiving first feedback information, wherein the first feedback information is used to provide feedback on whether the first recognition result is correct.

[0079] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: receiving a second image to be identified, wherein the second image to be identified includes a cage; identifying the water body in the second image to be identified through an image recognition model; and outputting a second recognition result, wherein the second recognition result is used to identify whether the cage is a breeding cage in the water body.

[0080] Optionally, the processor may also execute program code of the following steps: the second image to be identified is an image in which a cage is determined to exist through a predetermined identification model.

[0081] Optionally, the processor may also execute program code of the following steps: receiving second feedback information, wherein the second feedback information is used to provide feedback on whether the second recognition result is correct.

[0082] The embodiment of the present invention provides an image processing solution. By using an image recognition model to identify the water body in the image to be identified, the purpose of identifying the relationship between the cage and the water body, that is, identifying whether the cage is a breeding cage in the water body, is achieved by combining the identification of the cage with the identification of the water body, thereby achieving the technical effect of improving the recognition rate of accurately identifying the breeding cage, and further solving the technical problem of misidentification of the breeding cage when identifying the breeding cage from the image in the related art.

[0083] It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 7 It does not limit the structure of the above electronic device. For example, the computer terminal 7 may also include Figure 7 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 7 Different configurations shown.

[0084] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0085] Example 5

[0086] The embodiment of the present invention further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the image processing method provided in the embodiment 1 above.

[0087] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0088] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: receiving a first image to be identified; identifying a fish cage in the first image to be identified through a first branch of an image recognition model, and identifying a water body in the first image to be identified through a second branch of the image recognition model; and outputting a first recognition result, wherein the first recognition result includes the relationship between the fish cage and the water body.

[0089] Optionally, in this embodiment, the storage medium is further configured to store program codes for executing the following steps: the structures of the first branch and the second branch are different.

[0090] Optionally, in this embodiment, the storage medium is also configured to store program codes for executing the following steps: performing machine training using multiple groups of data of the first category to obtain a first branch of the image recognition model, wherein each group of data in the first category of multiple groups of data includes: an image, and a cage in the image; and performing machine training using multiple groups of data of the second category to obtain a second branch of the image recognition model, wherein each group of data in the second category of multiple groups of data includes: an image, and a water body in the image.

[0091] Optionally, in this embodiment, the storage medium is also configured to store program code for executing the following steps: the relationship between the cage and the water body includes: when the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that appears in the water body; or, when the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is less than a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that does not appear in the water body.

[0092] Optionally, in this embodiment, the storage medium is further configured to store program codes for executing the following steps: receiving first feedback information, wherein the first feedback information is used to provide feedback on whether the first recognition result is correct.

[0093] Optionally, in this embodiment, the storage medium is configured to store program code for executing the following steps: receiving a second image to be identified, wherein the second image to be identified includes a cage; identifying a water body in the second image to be identified by an image recognition model; and outputting a second recognition result, wherein the second recognition result is used to identify whether the cage is a breeding cage in the water body.

[0094] Optionally, in this embodiment, the storage medium is further configured to store program codes for executing the following steps: the second image to be identified is an image in which a cage is determined to exist through a predetermined identification model.

[0095] Optionally, in this embodiment, the storage medium is further configured to store a program code for executing the following steps: receiving second feedback information, wherein the second feedback information is used to provide feedback on whether the second recognition result is correct.

[0096] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0097] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0102] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An image processing method, It is characterized in that include: Receiving a first image to be recognized; identifying a cage in the first image to be identified by a first branch of an image recognition model, and identifying a water body in the first image to be identified by a second branch of the image recognition model; Outputting a first recognition result, wherein the first recognition result includes a relationship between the cage and the water body, wherein the image recognition model supports outputting three results: outputting the cage, outputting the water body, and outputting the first recognition result of the relationship between the cage and the water body; Wherein, the relationship between the cage and the water body includes: In the case where the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that appears in the water body, wherein the reference cage is a virtual cage fitted after feature extraction of multiple specific breeding cages, and is used to characterize the cage for breeding aquatic products in the water area, and the reference water body is a virtual water body fitted after feature extraction of multiple specific water bodies, and is used to characterize the water area for breeding aquatic products; or, When the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is less than a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that does not appear in the water body; The first branch and the second branch have different structures.

2. The method according to claim 1, It is characterized in that Also includes: The first branch of the image recognition model is obtained by performing machine training using the first plurality of data sets, wherein each of the first plurality of data sets includes: an image, and a cage in the image; and, The second type of multiple sets of data are used for machine training to obtain the second branch of the image recognition model, wherein each set of data in the second type of multiple sets of data includes: an image, and a water body in the image.

3. The method according to claim 1, It is characterized in that Also includes: First feedback information is received, wherein the first feedback information is used to provide feedback on whether the first recognition result is correct.

4. An image processing method, It is characterized in that include: receiving a second image to be identified, wherein the second image to be identified includes a cage; identifying a cage in the second image to be identified by using a first branch of the image recognition model, and identifying a water body in the second image to be identified by using a second branch of the image recognition model; Outputting a second recognition result, wherein the second recognition result is used to identify whether the cage is a breeding cage in the water body, wherein the image recognition model supports outputting three results: outputting a breeding cage, outputting a water body, and outputting the second recognition result of the relationship between the breeding cage and the water body; The second recognition result is: In the case where the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the second recognition result is: the cage is a breeding cage that appears in the water body, wherein the reference cage is a virtual cage fitted after feature extraction of a plurality of specific breeding cages, and is used to characterize cages for breeding aquatic products in water areas, and the reference water body is a virtual water body fitted after feature extraction of a plurality of specific water bodies, and is used to characterize water areas for breeding aquatic products; or, When the similarity between the cage and the reference cage is greater than or equal to the first similarity threshold, and the similarity between the water body and the reference water body is less than the second similarity threshold, the second recognition result is: the cage is a breeding cage that does not appear in the water body; The first branch and the second branch have different structures.

5. The method according to claim 4, It is characterized in that The second image to be recognized is an image in which the cage is determined to exist through a predetermined recognition model.

6. The method according to claim 4, It is characterized in that Also includes: Second feedback information is received, wherein the second feedback information is used to provide feedback on whether the second recognition result is correct.

7. An image processing device, It is characterized in that include: A first receiving module, used for receiving a first image to be recognized; a first recognition module, configured to recognize the cages in the first image to be recognized by using a first branch of an image recognition model, and to recognize the water body in the first image to be recognized by using a second branch of the image recognition model; A first output module, configured to output a first recognition result, wherein the first recognition result includes a relationship between the cage and the water body, wherein the image recognition model supports outputting three results: outputting the cage, outputting the water body, and outputting the first recognition result of the relationship between the cage and the water body; Wherein, the relationship between the cage and the water body includes: In the case where the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that appears in the water body, wherein the reference cage is a virtual cage fitted after feature extraction of multiple specific breeding cages, and is used to characterize the cage for breeding aquatic products in the water area, and the reference water body is a virtual water body fitted after feature extraction of multiple specific water bodies, and is used to characterize the water area for breeding aquatic products; or, When the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is less than a second similarity threshold, the relationship between the cage and the water body is: the cage is a breeding cage that does not appear in the water body; The first branch and the second branch have different structures.

8. An image processing device, It is characterized in that include: A second receiving module, used for receiving a second image to be identified, wherein the second image to be identified includes a cage; a second recognition module, configured to recognize the cages in the second image to be recognized by using the first branch of the image recognition model, and to recognize the water body in the second image to be recognized by using the second branch of the image recognition model; A second output module, configured to output a second recognition result, wherein the second recognition result is used to identify whether the cage is a breeding cage in the water body, wherein the image recognition model supports outputting three results: outputting a breeding cage, outputting a water body, and outputting the second recognition result of the relationship between the breeding cage and the water body; The second recognition result is: In the case where the similarity between the cage and the reference cage is greater than or equal to a first similarity threshold, and the similarity between the water body and the reference water body is greater than or equal to a second similarity threshold, the second recognition result is: the cage is a breeding cage that appears in the water body, wherein the reference cage is a virtual cage fitted after feature extraction of a plurality of specific breeding cages, and is used to characterize cages for breeding aquatic products in water areas, and the reference water body is a virtual water body fitted after feature extraction of a plurality of specific water bodies, and is used to characterize water areas for breeding aquatic products; or, When the similarity between the cage and the reference cage is greater than or equal to the first similarity threshold, and the similarity between the water body and the reference water body is less than the second similarity threshold, the second recognition result is: the cage is a breeding cage that does not appear in the water body; The first branch and the second branch have different structures.

9. A storage medium, It is characterized in that The storage medium stores a program, wherein when the program is executed by a processor, the processor is controlled to execute the image processing method according to any one of claims 1 to 6.

10. A computer device, It is characterized in that include: Memory and processor, The memory stores a computer program; The processor is used to execute the computer program stored in the memory, and when the computer program is run, the processor executes the image processing method according to any one of claims 1 to 6.