CN112926473A - Bee mite identification method and equipment based on image identification - Google Patents
Bee mite identification method and equipment based on image identification Download PDFInfo
- Publication number
- CN112926473A CN112926473A CN202110246273.4A CN202110246273A CN112926473A CN 112926473 A CN112926473 A CN 112926473A CN 202110246273 A CN202110246273 A CN 202110246273A CN 112926473 A CN112926473 A CN 112926473A
- Authority
- CN
- China
- Prior art keywords
- bee
- mite
- image
- mites
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 241000238876 Acari Species 0.000 claims abstract description 54
- 238000013135 deep learning Methods 0.000 claims abstract description 19
- 238000010186 staining Methods 0.000 claims abstract description 14
- 201000010099 disease Diseases 0.000 claims abstract description 12
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 12
- 230000002265 prevention Effects 0.000 claims abstract description 9
- 238000003672 processing method Methods 0.000 claims abstract description 6
- 241000257303 Hymenoptera Species 0.000 claims description 30
- 241000895650 Varroa jacobsoni Species 0.000 claims description 24
- 230000003071 parasitic effect Effects 0.000 claims description 13
- 210000000952 spleen Anatomy 0.000 claims description 10
- 241000895647 Varroa Species 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 241000256844 Apis mellifera Species 0.000 abstract 8
- 238000009395 breeding Methods 0.000 description 5
- 230000001488 breeding effect Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000000642 acaricide Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000009341 apiculture Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010059866 Drug resistance Diseases 0.000 description 1
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000003599 detergent Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/695—Preprocessing, e.g. image segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06M—COUNTING MECHANISMS; COUNTING OF OBJECTS NOT OTHERWISE PROVIDED FOR
- G06M11/00—Counting of objects distributed at random, e.g. on a surface
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Marketing (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
Abstract
The present disclosure provides a bee mite identification method and apparatus based on image identification, the bee mite identification method comprises the following steps: acquiring a honeycomb image; identifying the bee mite condition by adopting a deep learning method and combining an image processing method; and periodically executing the steps to count the bee mite-staining conditions to predict the disease incidence rule of the bee mites, and generating a bee mite prevention and control scheme according to the disease incidence rule. Through using computer visual identification technique, carry out the analysis statistics to the mite bee of dying, supplementary breed decision-making for the honeybee is bred and has more intelligent, more high-efficient, more accurate and easy operation's advantage.
Description
Technical Field
The disclosure relates to the technical field of bee breeding, in particular to a bee mite identification method and device based on image identification.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Bee mites are the most serious biological threat in global bee breeding and are mainly treated by chemical miticides at present. However, the miticide is often used in a mess in production, the drug resistance of the bee mites is increased by frequent and excessive use, the miticide effect cannot be achieved due to low dose and untimely use, and bee colonies are seriously lost. The main reasons for these problems are that the bee-keeping person cannot quickly and accurately detect the parasitic rate of the mites in the bee colony, predict the temporal-spatial law of the occurrence of the mites, and understand the relationship between the parasitic rate of the bees and the dosage of the drug, so that the proper and proper dosage of the drug cannot be taken timely, properly, and the accurate advanced prevention and control measures cannot be taken.
The inventor finds that the existing identification method is a method of visual identification generally adopted in bee breeding production, but bee mites are small in size, the number of bees in a colony is large, the bee mites cannot be identified one by one, the parasitic rate of the bee mites can be estimated only according to the frequency of the bee mites observed in the process of inspecting the bee colony and the body condition of the bees, accurate data cannot be given, and only rough grade evaluation can be carried out by high, medium and low. In research, in order to obtain describable data, a sampling survey method is generally adopted, namely 300 bees are randomly taken from each bee colony, bee mites are eluted from the bees by a detergent or alcohol rinsing method, the bee mites are artificially counted, and the parasitic rate of the bee mites (bee mite number/bee number) is calculated. The method is complex to operate, large in sampling error and system error and difficult to rapidly obtain accurate data. Therefore, an efficient, accurate and simple-operation method for counting the parasitic rate of the bee mites is lacked in both bee keeping production and scientific research of the bee mites at present.
Disclosure of Invention
In order to solve the problems, the disclosure provides a bee mite identification method and device based on image identification, and by using a computer vision identification technology, the bee mite-infected bees are analyzed and counted, and breeding decision is assisted, so that the bee breeding has the advantages of being more intelligent, more efficient, more accurate and simple to operate.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
one or more embodiments provide a bee mite identification method based on image identification, including the steps of:
acquiring a honeycomb image;
identifying the bee mite condition by adopting a deep learning method and combining an image processing method;
and periodically executing the steps to count the bee mite-staining conditions to predict the disease incidence rule of the bee mites, and generating a bee mite prevention and control scheme according to the disease incidence rule.
An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions, when executed by the processor, performing the steps of the above method.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the above method.
Compared with the prior art, the beneficial effect of this disclosure is:
(1) according to the bee mite recognition method, the deep learning method is combined with the image processing method through the deep learning algorithm to recognize the bee mite condition, the recognition efficiency is improved, and the intelligence of bee mite recognition can be improved.
(2) In the method, the yolo3 model and the MobileNet V2 model are set to identify the bee mite condition, and the combination of the two models not only ensures the accuracy, but also has the characteristics of high operation speed and light weight.
Advantages of additional aspects of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure and not to limit the disclosure.
Fig. 1 is a flowchart of a bee mite identification method according to embodiment 1 of the present disclosure;
fig. 2 is a fusion model structure diagram of embodiment 1 of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments in the present disclosure may be combined with each other. The embodiments will be described in detail below with reference to the accompanying drawings.
Example 1
In one or more embodiments, as shown in fig. 1-2, the bee mite identification method based on image identification includes the following steps:
step 1, acquiring a honeycomb image;
step 2, identifying the bee mite condition by adopting a deep learning method and combining an image processing method;
and 3, periodically executing the steps to count the bee mite-staining conditions and predict the disease incidence rule of the bee mites, and generating a bee mite prevention and control scheme according to the disease incidence rule.
In the embodiment, the deep learning method is combined with the image processing method through the deep learning algorithm to identify the bee mite condition, so that the identification efficiency is improved, and the intellectualization of bee mite identification can be improved.
In the step 1, a high-resolution camera is used for photographing the bees and collecting images. The operation is to take the honeycomb out of the beehive and take the honeycomb image by using a high-resolution camera.
In step 2, the infection condition may include the type of bees infected with bee mites, the number or proportion of each type of bees infected with bee mites, the type of bee mites infected with bee mites, and the proportion of each type of bee mites.
Optionally, identifying the mite-staining condition of the bees in the image includes the following steps:
2.1 preprocessing the honeycomb image, and identifying whether bees infect the bee mites by adopting a deep learning algorithm aiming at the preprocessed image;
2.2 if the bee mites are infected, continuously identifying the type of the bees by adopting a deep learning algorithm, and counting; wherein the bee types include worker bees, drone bees, etc.
2.3 adopting a deep learning counting method to identify whether the bee mites are varroa jacobsoni or varroa parvu, and calculating the proportion of the bee mites infecting the varroa jacobsoni.
Optionally, the deep learning method in the above steps 2.1 and 2.2 may be a convolution algorithm, and specifically, a yolo3 model may be adopted to fuse a MobileNetV2 model.
The yolo3 model and the MobileNet V2 model can be fused into a specific structure as shown in FIG. 2, and the specific structure comprises a yolov3 part and a MovileNet V2 part which are connected in sequence, and the recognition result of the yolov3 part is used as the input of a MovileNet V2 part.
Specifically, the yolov3 part comprises an input layer, a plurality of first convolution layers and a first output layer, and the detection result is an image matrix of a part framed by the bee; the MobileNet V2 part comprises a second convolution layer, a multilayer inverse residual error structure and a second output layer, wherein the multilayer inverse residual error structure firstly carries out dimension increasing on an image, then extracts features, finally carries out dimension reducing operation, and outputs bee types as identification results through the second output layer.
In this embodiment, the upper half is yolov3 part, and the lower half is MovileNetV2 part: each layer of the yovov3 part is a convolution layer, the detection result is an image matrix of the framed part of the bee, and then the lower half part receives the matrix to judge the bee type.
The MobileNet V2 part comprises a multilayer inverse residual error structure and is characterized in that dimension increasing is carried out on an image, then the feature is extracted, and finally dimension reducing operation is carried out.
The yolo3 model comprises a multilayer convolution, a residual error and an up-sampling structure, and the final model outputs a convolution calculation result; and the image recognition adopts models such as MobileNet V2 and the like, comprises a plurality of layers of convolution and full connection layers, and finally outputs a classification result.
Optionally, in step 2.3, a deep learning counting method is adopted to identify whether the bee mites are varroa jacobsoni or varroa parvus, and the proportion of the bee mites infecting the varroa jacobsoni is calculated, wherein the method for identifying the bee mites as varroa jacobsoni or varroa parvus specifically comprises the following steps: the method comprises the steps of synchronously obtaining morphology pictures of varroa jacobsoni and varroa jacobsoni, training a yolo3 model, inputting obtained bee spleen images into a trained yolo3 model, identifying whether the varroa jacobsoni is varroa jacobsoni or varroa jacobsoni through deep learning images, and calculating the proportion of the varroa jacobsoni infecting the varroa jacobsoni or the varroa jacobsoni infecting the varroa.
In the embodiment, the yolo3 model and the MobileNet V2 model are set to identify the bee mite condition, and the combination of the two models not only ensures the accuracy, but also has the characteristics of high operation speed and light weight.
The counting method can be as follows: and (5) setting marking frames at the positions of the mites in the image by adopting the yolo3 model, and identifying the number of the marking frames for counting.
The bee mite detection method has the advantages that the type and occupied proportion of bees infected with bee mites are simultaneously identified by adopting a machine algorithm, comprehensive analysis on the mite staining condition of the whole bee colony is facilitated, meanwhile, the marking frames are adopted for direct counting, the identification efficiency is high, the data processing speed is high, and the method is simple and convenient to operate.
Furthermore, after the mite staining condition of the bees in the image is identified, the bee mite staining condition is counted to predict the disease incidence rule of the bee mites, and the method comprises the following steps:
and acquiring the position data of the honeycomb while acquiring the image of the honeycomb, counting the relationship between the position of the honeycomb in a bee colony and the parasitic rate of the bee mites, and guiding the key area of the mite damage prevention and control pesticide.
Wherein the honeycomb position comprises a lateral spleen, a middle spleen and the like.
Furthermore, after the mite staining condition of the bees in the image is identified, the bee mite staining condition is counted to predict the disease incidence rule of the bee mites, and the method further comprises the following steps:
and synchronously acquiring bee colony parameters while acquiring all the bee spleen images of the whole swarm, counting the relationship between the bee mite parasitic rate and the bee colony parameters, predicting the optimal feeding management conditions, and guiding production.
Optionally, the swarm parameters include data such as swarm vigor, swarm internal temperature, queen age, and queen spawning capacity.
The method for predicting the disease incidence rule of the bee mites by counting the bee mite-staining conditions comprises the following specific steps:
3.1 obtaining the result of the number of mites on worker bees and male bees according to the identification and statistics of the types of the mite-infected bees and the number of the bee mites, and drawing a distribution map;
3.2 calculating the parasitic rate of the mite damage of the bee colony under different worker bee and drone proportions according to the distribution map, counting the correlation between the worker bee and drone proportions and the parasitic rate of the bee mites, and predicting the optimal worker-male proportion, so that the bee mite prevention and control scheme adopts the optimal proportion for configuration.
The embodiment realizes visual display through the distribution map, and is favorable for determining a bee mite prevention and control scheme.
This embodiment still provides bee mite identification equipment based on image recognition, its characterized by: the method comprises an image acquisition device and a processor, wherein the processor executes the steps of the method.
Example 2
The present embodiment provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method of embodiment 1.
Example 3
The present embodiment provides a computer readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of embodiment 1.
The electronic device provided by the present disclosure may be a mobile terminal and a non-mobile terminal, where the non-mobile terminal includes a desktop computer, and the mobile terminal includes a Smart Phone (such as an Android Phone and an IOS Phone), Smart glasses, a Smart watch, a Smart bracelet, a tablet computer, a notebook computer, a personal digital assistant, and other mobile internet devices capable of performing wireless communication.
It should be understood that in the present disclosure, the processor may be a central processing unit CPU, but may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The steps of a method disclosed in connection with the present disclosure may be embodied directly in a hardware processor, or in a combination of the hardware and software modules within the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here. Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is merely a division of one logic function, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some interfaces, and may be in an electrical, mechanical or other form.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Although the present disclosure has been described with reference to specific embodiments, it should be understood that the scope of the present disclosure is not limited thereto, and those skilled in the art will appreciate that various modifications and changes can be made without departing from the spirit and scope of the present disclosure.
Claims (10)
1. The bee mite identification method based on image identification is characterized by comprising the following steps of:
acquiring a honeycomb image;
identifying the bee mite condition by adopting a deep learning method and combining an image processing method;
and periodically executing the steps to count the bee mite-staining conditions to predict the disease incidence rule of the bee mites, and generating a bee mite prevention and control scheme according to the disease incidence rule.
2. The bee mite identification method based on image identification as claimed in claim 1, wherein: the full condition comprises the type of bees infected with the bee mites, the number or proportion of each type of bees infected with the bee mites, the type of the bee mites infected and the proportion of each type of bee mites.
3. The bee mite identification method based on image identification as claimed in claim 1, wherein: identifying the mite staining condition of the bees in the image, comprising the following steps:
preprocessing a bee spleen image, and identifying whether bees infect bee mites by adopting a deep learning algorithm aiming at the preprocessed image;
if the bee mites are infected, continuously identifying the type of the bees by adopting a deep learning algorithm, and counting; wherein the bee types include worker bee change and drone;
and identifying whether the bee mites are varroa jacobsoni or varroa parvu by adopting a deep learning counting method, and calculating the proportion of infecting the varroa jacobsoni and the varroa parvu.
4. The bee mite identification method based on image identification as claimed in claim 1, wherein: the deep learning method is a convolution algorithm, and specifically adopts a yolo3 model to fuse a Mobi LeNetV2 model;
or the specific structure of the yolo3 model fused with the MobileNet V2 model is as follows: the method comprises a yolov3 part and a MovileNetV2 part which are sequentially connected, wherein the identification result of the yolov3 part is used as the input of the Movi LeNetV2 part;
specifically, the yolov3 part comprises an input layer, a plurality of first convolution layers and a first output layer, and the detection result is an image matrix of a part framed by the bee; the MobileNet V2 part comprises a second convolution layer, a multilayer inverse residual error structure and a second output layer, wherein the multilayer inverse residual error structure firstly carries out dimension increasing on an image, then extracts features, finally carries out dimension reducing operation, and identifies a result through the second output layer.
5. The bee mite identification method based on image identification as claimed in claim 1, wherein: the method for identifying the bee mites as varroa jacobsoni or varroa parva specifically comprises the following steps: the method comprises the steps of synchronously obtaining morphology pictures of varroa jacobsoni and varroa jacobsoni, training a yolo3 model, inputting obtained bee spleen images into a trained yolo3 model, identifying whether the varroa jacobsoni is varroa jacobsoni or varroa jacobsoni through deep learning images, and calculating the proportion of the varroa jacobsoni infecting the varroa jacobsoni or the varroa jacobsoni infecting the varroa.
6. The bee mite identification method based on image identification as claimed in claim 1, wherein: the proportion of the bee mites infecting the big and small bees is calculated by counting, wherein the technical method specifically comprises the following steps: and (5) setting marking frames at the positions of the mites in the image by adopting the yolo3 model, and identifying the number of the marking frames for counting.
7. The bee mite identification method based on image identification as claimed in claim 1, wherein: after the mite staining condition of the bees in the image is identified, the bee mite staining condition is counted to predict the bee mite incidence rule, and the method comprises the following steps:
acquiring a bee spleen image, acquiring bee spleen position data, and counting the relationship between the position of a bee spleen in a bee colony and the parasitic rate of bee mites;
or, the method also comprises the following steps:
synchronously acquiring swarm parameters while acquiring all the bee spleen images of the whole swarm, and counting the relationship between the parasitic rate of bee mites and the swarm parameters;
or
The method for counting and predicting the disease incidence rule of the bee mites comprises the following steps:
obtaining the result of the number of mites on worker bees and male bees according to the identification and statistics of the types of the mite-infected bees and the number of the bee mites, and drawing a distribution map;
and calculating the parasitic rate of the mite damage of the bee colony under different worker bee and drone proportions according to the distribution diagram, counting the correlation between the worker bee and drone proportions and the parasitic rate of the bee mites, and predicting the optimal worker-male proportion, so that the optimal proportion is adopted for configuration in the bee mite prevention and control scheme.
8. Bee mite identification equipment based on image recognition, characterized by: comprising image acquisition means and a processor performing the steps of the method according to any one of claims 1 to 7.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executable on the processor, the computer instructions when executed by the processor performing the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110246273.4A CN112926473B (en) | 2021-03-05 | 2021-03-05 | Bee mite identification method and equipment based on image identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110246273.4A CN112926473B (en) | 2021-03-05 | 2021-03-05 | Bee mite identification method and equipment based on image identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112926473A true CN112926473A (en) | 2021-06-08 |
CN112926473B CN112926473B (en) | 2022-10-04 |
Family
ID=76173454
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110246273.4A Active CN112926473B (en) | 2021-03-05 | 2021-03-05 | Bee mite identification method and equipment based on image identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112926473B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113678794A (en) * | 2021-10-26 | 2021-11-23 | 中国农业科学院蜜蜂研究所 | Breeding method, device and application of bee mite-resistant bee species |
CN114155757A (en) * | 2021-12-03 | 2022-03-08 | 广东省健卫病媒预防控制中心(普通合伙) | Quality certificate level identification platform in pest control industry |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2858749A1 (en) * | 2003-08-14 | 2005-02-18 | Marcel Legris | Bee-house for apiculture, has sloping section that forms funnel cup for collecting and driving detritus and Varroa jacobsoni towards passage that leads towards exterior of body |
WO2013143552A2 (en) * | 2012-03-27 | 2013-10-03 | Humal Priit | An apparatus for diagnosis and control of honeybee varroatosis, image processing method and software for recognition of parasite |
CN106719463A (en) * | 2017-02-22 | 2017-05-31 | 中国农业科学院蜜蜂研究所 | The detection method and device of a kind of honeybee mite infestationss rate |
CN206933010U (en) * | 2017-06-23 | 2018-01-30 | 四川天府蜂谷科技有限公司 | The automatic intelligent beehive for carrying out honeybee and controlling mite |
CN108739719A (en) * | 2018-05-07 | 2018-11-06 | 杨波 | A kind of intelligent recognition laser bee mite kills robot and its killing method |
CN110502987A (en) * | 2019-07-12 | 2019-11-26 | 山东农业大学 | A kind of plant pest recognition methods and system based on deep learning |
CN111797934A (en) * | 2020-07-10 | 2020-10-20 | 北京嘉楠捷思信息技术有限公司 | Road sign identification method and device |
-
2021
- 2021-03-05 CN CN202110246273.4A patent/CN112926473B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2858749A1 (en) * | 2003-08-14 | 2005-02-18 | Marcel Legris | Bee-house for apiculture, has sloping section that forms funnel cup for collecting and driving detritus and Varroa jacobsoni towards passage that leads towards exterior of body |
WO2013143552A2 (en) * | 2012-03-27 | 2013-10-03 | Humal Priit | An apparatus for diagnosis and control of honeybee varroatosis, image processing method and software for recognition of parasite |
CN106719463A (en) * | 2017-02-22 | 2017-05-31 | 中国农业科学院蜜蜂研究所 | The detection method and device of a kind of honeybee mite infestationss rate |
CN206933010U (en) * | 2017-06-23 | 2018-01-30 | 四川天府蜂谷科技有限公司 | The automatic intelligent beehive for carrying out honeybee and controlling mite |
CN108739719A (en) * | 2018-05-07 | 2018-11-06 | 杨波 | A kind of intelligent recognition laser bee mite kills robot and its killing method |
CN110502987A (en) * | 2019-07-12 | 2019-11-26 | 山东农业大学 | A kind of plant pest recognition methods and system based on deep learning |
CN111797934A (en) * | 2020-07-10 | 2020-10-20 | 北京嘉楠捷思信息技术有限公司 | Road sign identification method and device |
Non-Patent Citations (3)
Title |
---|
SIMON BILIK ET AL: "Visual diagnosis of the Varroa destructor parasitic mite in honeybees using object detector techniques", 《ARXIV:2103.03133V1》 * |
刘劲军: "《蜜蜂生态养殖》", 31 May 2018 * |
刘璇昕: "基于深度学习的昆虫轻量级检测模型研究", 《中国优秀博硕士学位论文全文数据库(硕士)农业科技辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113678794A (en) * | 2021-10-26 | 2021-11-23 | 中国农业科学院蜜蜂研究所 | Breeding method, device and application of bee mite-resistant bee species |
CN114155757A (en) * | 2021-12-03 | 2022-03-08 | 广东省健卫病媒预防控制中心(普通合伙) | Quality certificate level identification platform in pest control industry |
Also Published As
Publication number | Publication date |
---|---|
CN112926473B (en) | 2022-10-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11798662B2 (en) | Methods for identifying biological material by microscopy | |
CN112926473B (en) | Bee mite identification method and equipment based on image identification | |
WO2021093451A1 (en) | Pathological section image processing method, apparatus, system, and storage medium | |
WO2021000423A1 (en) | Pig weight measurement method and apparatus | |
CN111260677B (en) | Cell analysis method, device, equipment and storage medium based on microscopic image | |
CN109964235A (en) | For carrying out the prediction model of vision sorter to insect | |
CN116051574A (en) | Semi-supervised segmentation model construction and image analysis method, device and system | |
CN106066934A (en) | A kind of Alzheimer based on Spark platform assistant diagnosis system in early days | |
CN111402217A (en) | Image grading method, device, equipment and storage medium | |
CN109784200A (en) | Milk cow behavior image based on binocular vision obtains and body condition intelligent monitor system | |
Li et al. | Cow individual identification based on convolutional neural network | |
Singh et al. | Performance evaluation of plant leaf disease detection using deep learning models | |
CN113902669A (en) | Method and system for reading urine exfoliative cell fluid-based smear | |
Vinicki et al. | Using convolutional neural networks for determining reticulocyte percentage in cats | |
CN113780145A (en) | Sperm morphology detection method, sperm morphology detection device, computer equipment and storage medium | |
CN107292340A (en) | Lateral line scales recognition methods based on convolutional neural networks | |
Qin et al. | Malaria cell detection using evolutionary convolutional deep networks | |
US20230245495A1 (en) | Face recognition systems data collection process | |
CN107194918B (en) | Data analysis method and device | |
Yoo et al. | BeeNet: An End-To-End Deep Network For Bee Surveillance | |
Singh et al. | Malaria parasite recognition in thin blood smear images using squeeze and excitation networks | |
Moen et al. | Age interpretation of cod otoliths using deep learning | |
Mishra et al. | Analysis of different Machine Learning and Deep Learning Techniques for Malaria Parasite Detection | |
CN117496274B (en) | Classification counting method, system and storage medium based on liquid drop images | |
CN113706449B (en) | Pathological image-based cell analysis method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |