Insect situation monitoring method and device and medium

Abstract

The invention relates to an insect pest situation monitoring method and device and a medium, and belongs to the technical field of tobacco insect monitoring. The method comprises the steps that tobacco insect moving images are collected by means of a short-focus AI camera arranged on an insect sticking plate, and the insect sticking plate is provided with a light-emitting component used for luring tobacco insects and a sex luring core; the tobacco insect activity image is input into an insect condition monitoring large model, and the insect condition monitoring large model is constructed by preprocessing a plurality of insect condition historical monitoring pictures into sample pictures; inputting the plurality of sample pictures into an object detection model in a one-stop open training platform of a Haikangwei AI model; testing the object detection model; the object detection model is perfected until the monitoring requirement is met, and the large insect situation monitoring model is obtained; and generating a tobacco insect monitoring report containing the increase and decrease conditions of the tobacco insects. The insect condition can be accurately monitored, and the defect that the insect condition is monitored manually is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of tobacco insect monitoring, and in particular relates to an insect monitoring method, device and medium. Background Art

[0002] The traditional method of monitoring insect infestation is to set up traps and use pheromone trapping devices to trap tobacco insects, and then manually count the number of trapped tobacco insects. According to the overall idea of ​​sample estimation, the number of tobacco insects and the damage situation in the reservoir area are estimated. This method is labor-intensive and due to the poor trapping effect of traditional traps, the results of manual estimation are inaccurate. Summary of the invention

[0003] The present disclosure provides an insect monitoring method, device and medium to solve the above technical problems.

[0004] According to a first aspect of the present disclosure, a method for monitoring an insect infestation is provided, the method comprising: collecting images of tobacco insect activity by means of a short-focus AI camera arranged on an insect sticky board, wherein the insect sticky board is provided with a luminous component and a sex attractant core for luring tobacco insects; inputting the images of tobacco insect activity into a large insect infestation monitoring model, wherein the construction of the large insect infestation monitoring model comprises: preprocessing a plurality of historical monitoring images of insect infestation into sample images; inputting a plurality of sample images into an object detection model in the Hikvision AI model one-stop open training platform; testing the object detection model; improving the object detection model until the monitoring requirements are met to obtain the large insect infestation monitoring model; and generating a tobacco insect monitoring report including the increase or decrease of tobacco insects.

[0005] In some embodiments, the preprocessing of multiple historical monitoring images of insect conditions into sample images includes: marking the historical monitoring images according to the color, size, shape, and posture of the tobacco insects in the historical monitoring images, and the historical monitoring images after being marked are sample images.

[0006] In some embodiments, after generating the tobacco insect monitoring report including the increase and decrease of tobacco insects, the method further includes: when it is detected that the year-on-year growth rate representing the increase and decrease is greater than the growth rate threshold, using an alarm system to issue a warning.

[0007] According to a second aspect of the present disclosure, there is provided an insect monitoring device, comprising: a tobacco insect activity image acquisition module, for acquiring tobacco insect activity images by means of a short-focus AI camera arranged on a sticky insect board, wherein the sticky insect board is provided with a luminous component and a sex attractant core for luring tobacco insects; a tobacco insect activity image input module, for inputting the tobacco insect activity image into an insect monitoring large model, wherein the construction of the insect monitoring large model comprises: preprocessing a plurality of historical monitoring images of insect conditions into sample images; inputting a plurality of sample images into an object detection model in the Hikvision AI model one-stop open training platform; testing the object detection model; improving the object detection model until the monitoring requirements are met to obtain the insect monitoring large model; and a tobacco insect monitoring report generation module, for generating a tobacco insect monitoring report including the increase or decrease of tobacco insects.

[0008] According to a third aspect of the present disclosure, there is provided an insect monitoring device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the insect monitoring method as described above based on instructions stored in the memory.

[0009] According to a fourth aspect of the present disclosure, a computer storable medium is provided, on which computer program instructions are stored, and when the instructions are executed by a processor, the insect monitoring method as described above is implemented.

[0010] By adopting the above technical solution, the embodiments of the present disclosure can achieve the beneficial technical effect: the method can be used to accurately monitor the insect situation, avoiding the shortcomings of monitoring the insect situation through manpower. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0012] Figure 1 The present invention is a flowchart showing a method of monitoring insect infestation according to some embodiments of the present disclosure.

[0013] Figure 2 It is a schematic diagram showing a historical monitoring screen of insect conditions according to some embodiments of the present disclosure.

[0014] Figure 3 is a schematic diagram showing a Hikvision one-stop training platform according to some embodiments of the present disclosure.

[0015] Figure 4 It is a schematic diagram showing uploading sample images on the Hikvision one-stop training platform according to some embodiments of the present disclosure.

[0016] Figure 5 is a schematic diagram showing the identification of tobacco insects according to some embodiments of the present disclosure.

[0017] Figure 6 It is a schematic diagram showing the completion of the training of a large insect monitoring model according to some embodiments of the present disclosure.

[0018] Figure 7 is a schematic diagram showing the year-on-year growth rate of tobacco insects according to some embodiments of the present disclosure.

[0019] Figure 8 A block diagram of an insect monitoring device according to some embodiments of the present disclosure is shown.

[0020] Fig. 9 is a block diagram showing an insect monitoring device according to some other embodiments of the present disclosure.

[0021] Fig.10 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0022] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0023] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0024] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0025] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0026] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0027] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0028] At present, the traditional method of monitoring insect conditions is to set up traps and use pheromone trapping devices to trap tobacco insects, and then manually count the number of trapped tobacco insects. According to the overall idea of ​​sample estimation, the number of tobacco insects and the damage situation in the reservoir area are estimated. This method is manpower-consuming, and due to the poor trapping effect of traditional traps, the results of manual estimation are inaccurate.

[0029] In view of this, the present disclosure proposes an insect monitoring method, device and medium, which can accurately monitor the insect situation and avoid the shortcomings of monitoring the insect situation by manpower.

[0030] Figure 1 is a flow chart showing a method for monitoring insect pests according to some embodiments of the present disclosure. Figure 1 As shown, the method for monitoring insect pests includes steps 110 to 130.

[0031] In step 110, a short-focus AI camera disposed on a sticky insect board is used to collect images of tobacco insect activities, wherein the sticky insect board is provided with a light-emitting component and a sex attractant core for attracting tobacco insects.

[0032] In each warehouse unit, sticky insect boards that combine sex attractants and light attractants are laid out, and short-focus AI cameras are placed on the sticky insect boards.

[0033] In step 120, the tobacco insect activity image is input into a large insect monitoring model, wherein the construction of the large insect monitoring model includes: preprocessing multiple historical monitoring images of insect conditions into sample images; inputting multiple sample images into an object detection model in the Hikvision AI model one-stop open training platform; testing the object detection model; and improving the object detection model until the monitoring requirements are met to obtain the large insect monitoring model.

[0034] like Figure 2 As shown, by deploying ultraviolet-light tobacco insect trapping devices, high-definition video acquisition equipment, hard disk recorders, AI computing servers and other equipment, insect monitoring images are collected on a daily basis to enrich the sample library.

[0035] like Figure 3 As shown in the figure, after collecting a sufficient number of material pictures, AI model training begins. The model training platform used in this project is Hikvision's one-stop open training platform for AI models. According to the actual needs of the project, the insect monitoring model selects the object detection model.

[0036] like Figure 4 As shown in the figure, upload the historical monitoring images to the one-stop open training platform to create a training set.

[0037] like Figure 5 As shown in the figure, the tobacco insects in the historical monitoring images are marked, and a recognition model is established according to the color, size, shape, and posture of the tobacco insects. A large number of pre-processed image samples are marked, and the model is trained using the marked historical monitoring images. Then, the model is tested and improved. Figure 6 As shown, the final insect monitoring model is obtained.

[0038] like Figure 7As shown, the insect monitoring model is finally applied to input the real-time database images into the insect monitoring model, and a tobacco insect monitoring report including the increase and decrease of tobacco insects is automatically generated. For example, when the year-on-year growth rate is -3.03%, no alarm is given, and when the year-on-year growth rate is 10.71%, an alarm is given.

[0039] In step 130, a tobacco insect monitoring report including the increase and decrease of tobacco insects is generated.

[0040] Since the large insect monitoring model is trained using more than 1,000 historical monitoring images and has been repeatedly tested and improved, it ensures accurate monitoring of insect infestation and avoids the shortcomings of manual monitoring of insect infestation.

[0041] like Figure 8 As shown, the insect monitoring device 800 includes a tobacco insect activity image acquisition module 810 , a tobacco insect activity image input module 820 , and a tobacco insect monitoring report generation module 830 .

[0042] The tobacco insect activity image acquisition module 810 is configured to acquire tobacco insect activity images by means of a short-focus AI camera disposed on an insect sticky board, wherein the insect sticky board is provided with a luminous component and a sex attractant core for attracting tobacco insects;

[0043] The tobacco insect activity image input module 820 is configured to input the tobacco insect activity image into the insect monitoring model, wherein the construction of the insect monitoring model includes: preprocessing a plurality of historical monitoring images of insect conditions into sample images; inputting a plurality of sample images into the object detection model in the Hikvision AI model one-stop open training platform; testing the object detection model; improving the object detection model until the monitoring requirements are met, and obtaining the insect monitoring model;

[0044] The tobacco insect monitoring report generating module 830 is configured to generate a tobacco insect monitoring report including the increase or decrease of tobacco insects.

[0045] In the device of the embodiment of the present disclosure, the device can be used to accurately monitor the insect situation, avoiding the shortcomings of monitoring the insect situation through manpower.

[0046] like Fig. 9 As shown, the insect monitoring device 900 includes a memory 910; and a processor 920 coupled to the memory 910. The memory 910 is used to store instructions for executing the corresponding embodiments of the insect monitoring method. The processor 920 is configured to execute the insect monitoring method in any of the embodiments of the present disclosure based on the instructions stored in the memory 910.

[0047] Fig.10 is a block diagram showing a computer system for implementing some embodiments of the present disclosure. Fig.10As shown, the computer system 1000 may be embodied in the form of a general-purpose computing device. The computer system 1000 includes a memory 1010, a processor 1020, and a bus 1030 that connects various system components.

[0048] The memory 1010 may include, for example, a system memory, a non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs. The system memory may include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium may store, for example, instructions for executing at least one corresponding embodiment of the insect monitoring method. The non-volatile storage medium includes, but is not limited to, a disk memory, an optical memory, a flash memory, etc.

[0049] The processor 1020 can be implemented by a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistors, etc. Discrete hardware components. Accordingly, each module such as the tobacco insect activity image acquisition module, the tobacco insect activity image input module, and the tobacco insect monitoring report generation module can be implemented by the central processing unit (CPU) running the instructions in the memory to execute the corresponding steps, or can be implemented by a dedicated circuit to execute the corresponding steps.

[0050] The bus 1030 may use any of a variety of bus architectures, including, but not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.

[0051] The computer system 1000 may also include an input / output interface 1040, a network interface 1050, a storage interface 1060, etc. These interfaces 1040, 1050, 1060, the memory 1010, and the processor 1020 may be connected via a bus 1030. The input / output interface 1040 may provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 1050 provides a connection interface for various networked devices. The storage interface 1060 provides a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.

[0052] Here, various aspects of the present disclosure are described with reference to flowcharts and / or block diagrams of methods, devices, and computer program products according to embodiments of the present disclosure. It should be understood that each frame of the flowchart and / or block diagram and the combination of frames can be implemented by computer-readable program instructions.

[0053] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable device to produce a machine, so that the processor executes the instructions to produce means for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0054] These computer-readable program instructions may also be stored in a computer-readable memory, which cause the computer to work in a specific manner to produce an article of manufacture, including instructions for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0055] The present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.

[0056] The method provided by the present invention can accurately monitor the insect infestation, avoiding the shortcomings of monitoring the insect infestation by manpower.

[0057] So far, the insect monitoring method, device and medium according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0058] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for monitoring insect pests, characterized in that: The method comprises: The activity images of tobacco insects are collected by means of a short-focus AI camera arranged on a sticky insect board, wherein the sticky insect board is provided with a luminous component and a sex attractant core for attracting tobacco insects; The tobacco insect activity image is input into a large insect monitoring model, wherein the construction of the large insect monitoring model includes: Preprocess multiple historical monitoring images of insect conditions into sample images; Input multiple sample images into the object detection model in Hikvision’s one-stop open training platform for AI models; Test the object detection model; Improve the object detection model until it meets the monitoring requirements and obtains the insect monitoring model; Generate tobacco insect monitoring reports including the increase and decrease of tobacco insects.

2. The insect monitoring method according to claim 1, characterized in that: The preprocessing of multiple historical monitoring images of insect conditions into sample images includes: The historical monitoring pictures are marked according to the colors, sizes, shapes and postures of the tobacco insects in the historical monitoring pictures. The marked historical monitoring pictures are the sample pictures.

3. The insect monitoring method according to claim 1, characterized in that: After the tobacco insect monitoring report including the increase and decrease of tobacco insects is generated, the following steps are also included: When it is detected that the year-on-year growth rate representing the increase or decrease is greater than the growth rate threshold, the alarm system is used to issue a warning.

4. An insect monitoring device, characterized in that: include: A tobacco insect activity image acquisition module, used to collect tobacco insect activity images by means of a short-focus AI camera arranged on an insect sticky board, wherein the insect sticky board is provided with a luminous component and a sex attractant core for attracting tobacco insects; The tobacco insect activity image input module is used to input the tobacco insect activity image into the insect monitoring model, wherein the construction of the insect monitoring model includes: preprocessing multiple historical monitoring images of insect conditions into sample images; inputting multiple sample images into the object detection model in the Hikvision AI model one-stop open training platform; testing the object detection model; improving the object detection model until the monitoring requirements are met to obtain the insect monitoring model; The tobacco insect monitoring report generation module is used to generate a tobacco insect monitoring report including the increase and decrease of tobacco insects.

5. An insect monitoring device, characterized in that: include: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the insect monitoring method according to any one of claims 1 to 3 based on instructions stored in the memory.

6. A computer storable medium, characterized in that: Computer program instructions are stored thereon, and when the instructions are executed by a processor, the insect monitoring method as described in any one of claims 1 to 3 is implemented.

Images