CN113887595A - Garden pest identification method, system, computer equipment and storage medium - Google Patents
Garden pest identification method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113887595A CN113887595A CN202111116037.7A CN202111116037A CN113887595A CN 113887595 A CN113887595 A CN 113887595A CN 202111116037 A CN202111116037 A CN 202111116037A CN 113887595 A CN113887595 A CN 113887595A
- Authority
- CN
- China
- Prior art keywords
- pest
- image
- data
- identification
- user side
- 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.)
- Pending
Links
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 398
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000002265 prevention Effects 0.000 claims description 29
- 239000003814 drug Substances 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 15
- 230000003449 preventive effect Effects 0.000 claims description 9
- 229940079593 drug Drugs 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 8
- 238000012549 training Methods 0.000 description 12
- 241000238631 Hexapoda Species 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 9
- 238000013526 transfer learning Methods 0.000 description 9
- 241001465754 Metazoa Species 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 102220171488 rs760746448 Human genes 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a garden pest identification method, a system, computer equipment and a storage medium, wherein the method comprises the steps of obtaining pest images and extracting a plurality of pest characteristic data; sending the pest characteristic data to a pest identification model, wherein the pest identification model stores a plurality of pest sample data; respectively matching the pest characteristic data with pest sample data based on the pest identification model to obtain an image identification result; and sending the image recognition result to a user side associated with the inquiry user. The pest control method and the pest control system have the effect that the user can timely distinguish the types of the pests when finding the pests, so that the pest control work is convenient.
Description
Technical Field
The present application relates to the field of pest control technologies, and in particular, to a garden pest identification method, system, computer device, and storage medium.
Background
The ornamental and practical properties of garden plants are seriously affected by garden insect pests, and huge economic loss is brought to people; landscape plant pest kind is various, and different kinds of pest control mode differs moreover, and the user is difficult to in time to distinguish the pest kind when discovering the pest, and need expend time just to find the mode of preventing after studying the matching to the pest kind, has delayed the working progress of pest control, and garden economic loss aggravates.
Disclosure of Invention
In order to enable a user to timely distinguish the types of pests when finding the pests and enable the pest control work to be convenient, the application provides a garden pest identification method, a garden pest identification system, computer equipment and a storage medium.
The above object of the present invention is achieved by the following technical solutions:
a garden pest identification method comprises the following steps:
acquiring a pest image and extracting a plurality of pest characteristic data;
sending the pest characteristic data to a pest identification model, wherein the pest identification model stores a plurality of pest sample data;
based on the pest identification model, respectively carrying out similarity matching on a plurality of pest characteristic data and pest sample data to obtain an image identification result, wherein the image identification result comprises an identified pest image and academic name data thereof;
and sending the image recognition result to a user side associated with the inquiry user.
Through adopting above-mentioned technical scheme, the user is when carrying out the survey of pest on the spot in gardens, when discovering that certain plant has the pest, through the image of shooting the pest and extracting a plurality of pest characteristic data, then transmit a plurality of pest characteristic data to pest recognition model in, pest recognition model carries out the analysis according to a plurality of pest characteristic data received, and the sample data that individual and pest recognition model stored matches, thereby obtain a plurality of pest sample data that match, a plurality of sample data that match form image recognition result, obtain the image and the academic name data that match of discernment pest and send to the user end promptly, then the gardens trade staff can obtain the image and the academic name of discernment pest fast, and then can learn the prevention mode of this pest fast, make the work of pest control comparatively convenient.
The present application may be further configured in a preferred example to: before the step of sending the pest characteristic data to the pest identification model, the method comprises the following steps:
acquiring an auxiliary model storing auxiliary sample data;
and converting the auxiliary sample data based on the auxiliary model to generate a pest identification model with pest sample data.
By adopting the technical scheme, the original model obtained by training from other data sources can be applied to similar fields through certain modification and improvement by conversion, namely the characteristics stored in the original model can be applied to the pest recognition field after being modified and improved, the pest recognition model can obtain the same effect obtained by training a large amount of pest characteristic data from the beginning only by using fewer pest pictures, and the pest characteristic data of the pest recognition model is convenient to train.
The present application may be further configured in a preferred example to: after the step of sending the image recognition result to the user terminal associated with the query user, the method comprises the following steps:
and when a viewing instruction sent by a user side is received, based on the image recognition result, the introduction data, the prevention and treatment data and the prevention and treatment drug link are pushed to the user side.
By adopting the technical scheme, the user side can immediately send a viewing instruction after obtaining the image recognition result, and obtain the introduction information and the prevention and control method of the recognized pests, so that the workers can more timely and conveniently perform the next pest prevention and control work.
The present application may be further configured in a preferred example to: after the step of pushing the introduction data, the prevention and treatment data and the prevention and treatment drug link to the user terminal, the method further comprises the following steps:
based on the preventive medicine link, when a viewing request triggered by the user side is received, a sale page of the preventive medicine is pushed to the user side.
Through adopting above-mentioned technical scheme, make things convenient for the staff to the prevention and cure medicine of purchasing to this pest, improve the efficiency of preventing and curing this pest.
The present application may be further configured in a preferred example to: when the step of obtaining the pest image and extracting a plurality of pest characteristic data comprises the following steps:
acquiring the position information of a user side;
and binding the position information with the pest image.
Through adopting above-mentioned technical scheme, when the pest was shot, obtain the specific position that the pest was located, because pest characteristic data has been bound to specific position, can learn the distribution position of this pest promptly, consequently can learn the region of pest to the distribution condition of geographical position to user side propelling movement pest helps the prevention and cure of pest.
The present application may be further configured in a preferred example to: after the step of binding the location information with the pest image, the method includes the steps of:
screening a plurality of same or adjacent position information, integrating pest images bound by the position information, generating a regional pest damage report and pushing the regional pest damage report to the user side.
Through adopting above-mentioned technical scheme, will the pest image that the same or adjacent positioning information corresponds integrate, can obtain the main pest in every area, region, and then obtain the positional information that the pest distributes, with these information propelling movement to user, then the user in the same region can be according to the main pest type in this region, makes the precaution of prevention pest in advance, and the effect of pest control is better.
The present application may be further configured in a preferred example to: after the step of sending the image recognition result to the user side associated with the query user, the method further comprises the following steps:
and when receiving an application field service request sent by the user side, pushing introduction information and contact information data of the pest control team based on the positioning information of the user side.
Through adopting above-mentioned technical scheme, if the user has the demand of deinsectization as early as possible when discovering the pest, the accessible sends the request of applying for the field service, according to the pest control team in this region of positioning information propelling movement, contacts the pest control team through the phone and makes an appointment the time to arrive and carry out the pest and drive off for pest control is more efficient and convenient.
The second objective of the present invention is achieved by the following technical solutions:
a garden pest identification system, comprising:
the image acquisition module is used for acquiring a pest image and extracting a plurality of pest characteristic data;
the image sending module is used for sending the pest characteristic data to a pest identification model, and the pest identification model stores a plurality of pest sample data;
the image matching module is used for performing similarity matching on a plurality of pest characteristic data and pest sample data respectively based on the pest identification model to obtain an image identification result, and the image identification result comprises an identified pest image and academic name data thereof;
and the user side module is used for sending the image identification result to a user side associated with the inquiry user.
Through adopting above-mentioned technical scheme, the user is when carrying out the survey of pest on the spot in gardens, when discovering that certain plant has the pest, through the image of shooting the pest and extracting a plurality of pest characteristic data, then transmit a plurality of pest characteristic data to pest recognition model in, pest recognition model carries out the analysis according to a plurality of pest characteristic data received, and the sample data that individual and pest recognition model stored matches, thereby obtain a plurality of pest sample data that match, a plurality of sample data that match form image recognition result, obtain the image and the academic name data that match of discernment pest and send to the user end promptly, then the gardens trade staff can obtain the image and the academic name of discernment pest fast, and then can learn the prevention mode of this pest fast, make the work of pest control comparatively convenient.
The third purpose of the present application is achieved by the following technical solutions:
a computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned garden pest identification method when executing the computer program.
The fourth purpose of the present application is achieved by the following technical solutions:
a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the garden pest identification method described above.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the matched image and the academic name data of the identified pests are obtained and sent to the user side, so that the garden change staff can quickly obtain the image and the academic name of the identified pests, and can further quickly know the pest prevention mode, so that the pest prevention work is more convenient;
2. the pest recognition model can obtain the same effect obtained by training a large amount of pest characteristic data from the beginning only by using fewer pest photos, and the pest characteristic data of the pest recognition model is more convenient to train;
3. after the user side obtains the image recognition result, the user side can immediately send a viewing instruction to obtain introduction information and a prevention and control method of the recognized pests, and workers can perform the following pest prevention and control work more timely and conveniently.
4. Because pest characteristic data has been bound to specific position, can learn the distribution position of this pest promptly, consequently can learn the region of pest to the distribution condition of pest is pushed to the user side to geographical position, the prevention and cure of pest is helped.
Drawings
FIG. 1 is a flowchart of a garden pest identification method in one embodiment of the present application;
fig. 2 is another implementation flowchart of the garden pest identification method in step S10 according to an embodiment of the application;
fig. 3 is another implementation flowchart before step S20 in the garden pest identification method in one embodiment of the present application;
fig. 4 is another implementation flowchart after step S40 in the garden pest identification method in one embodiment of the application;
fig. 5 is another implementation flowchart after step S40 in the garden pest identification method in one embodiment of the application;
FIG. 6 is another implementation diagram of the garden pest identification method in one embodiment of the present application;
FIG. 7 is a schematic block diagram of a garden pest identification system in an embodiment of the present application;
fig. 8 is a schematic diagram of an apparatus in an embodiment of the present application.
Detailed Description
The present application is described in further detail below with reference to figures 1-8.
In an embodiment, as shown in fig. 1, the present application discloses a garden pest identification method, which specifically includes the following steps:
s10: acquiring a pest image and extracting a plurality of pest characteristic data;
in the present embodiment, the image of the pest refers to a photograph of the pest; pest characteristic data refers to images of various parts of a pest body, such as partial images of the head, tail, legs, wings, and the like of the pest;
specifically, when the picture of the pest is obtained, the picture can be obtained by photographing through mobile equipment such as a mobile phone or obtained from an album of the mobile phone or the mobile equipment, and then the obtained pest picture is uploaded to the pest identification model.
S20: sending the pest characteristic data to a pest identification model, wherein the pest identification model stores a plurality of pest sample data;
in this embodiment, the pest identification model refers to a model that can identify features of each part of a pest and perform similarity matching by repeated training;
the pest sample data refers to pest characteristic data of a plurality of pests.
S30: based on the pest identification model, respectively carrying out similarity matching on a plurality of pest characteristic data and pest sample data to obtain an image identification result, wherein the image identification result comprises an identified pest image and academic name data thereof;
in this embodiment, the similarity matching between the pest characteristic data and the pest sample data respectively means that a pest local image most similar to the pest characteristic data is searched and screened from the pest sample data;
the image recognition result is the recognized pest image and the scientific name of the pest.
Specifically, a pest local image which is most similar to pest characteristic data is searched and screened from pest sample data received by a pest identification model, then a plurality of most similar pest local images are traced back to a finished pest image of the pest local image respectively, a plurality of complete pest images are traced back, a pest image with the largest occurrence frequency is screened from the traced-back pest images to serve as an 'identified pest image' in an image identification result, and the academic name of the pest is identified.
For example, the head images of the caterpillar of a certain variety are matched with a large number of head images of the caterpillar in the pest identification model, the head images of the caterpillar which are most similar to the head images of the caterpillar of the variety are identified, and the head images of the caterpillar of the variety are identified by combining the most similar images of other parts of the caterpillar.
S40: and sending the image recognition result to a user side associated with the inquiry user.
In this embodiment, the user terminal is a user port used by a user to capture images of pests.
Specifically, the identified most approximate pest image and the pest name are sent to the user terminal.
S50: and storing the pest image acquired each time in a user side.
Specifically, the pest image obtained each time is stored, so that the user side can look up the record of identifying pests, and the pests can be conveniently looked up or identified again.
In this embodiment, the steps S10 to S50 may be performed without networking, the garden pest identification method provides an offline service, and a user can use the identification function of the system even in a field situation without a network.
In one embodiment, as shown in fig. 2, when performing step S10, the method further includes the steps of:
s11: acquiring the position information of a user side;
s12: and binding the position information with the pest image.
In this embodiment, the location information is the geographical location information of the user terminal when the pest image is acquired.
Specifically, when the pest image is acquired, the geographical position of the user side at the moment is acquired synchronously, the geographical position is bound with the pest image of the pest image, namely the distribution position of the pest can be acquired, so that the region of the pest can be acquired, and the distribution situation of the pest is pushed to the user side according to the geographical position, and the pest control is facilitated.
In an embodiment, as shown in fig. 2, after the step S12, the method further includes the steps of:
s13: screening a plurality of same or adjacent position information, integrating pest images bound by the position information, generating a regional pest damage report and pushing the regional pest damage report to the user side.
In this embodiment, the regional pest reports include the specific location of the region, images of pests present in the region, academic name data, and prevention tips.
Specifically, screening out a plurality of identical or adjacent position information, acquiring pest images corresponding to the position information, counting and classifying the acquired images, and generating a regional pest report by combining the pest control measures; the main pest types and the newly appeared pest types of each area and region can be obtained, and then the comparison is carried out according to the pests in different regions, so as to obtain the position information of the pest distribution.
Furthermore, the information is pushed to the user side in a text pushing mode, so that users in different areas can take preventive measures for preventing pests in advance according to main pest types in the areas, and pest control effects are better.
In one embodiment, after step S12, the method further includes the steps of:
S13A: when a position information viewing request sent by a user side is received, acquiring the position information or the bound pest image integration of the adjacent position information;
S14A: and generating an area pest insect report and pushing the report to the user terminal based on the bound pest image.
In this embodiment, the regional pest control report includes the region near the location of the user terminal, the image of the pest appearing in the region, the scholarly name data, and the prevention prompt.
Specifically, when the user side sends a viewing request of the position where the user side is located, the regional insect pest report of the specific position or the nearby position is generated, and the user side can independently know the insect pest situation nearby the position where the user side is located, so that prevention measures for preventing insect pests in advance can be taken, and the insect pest control effect is better.
In one embodiment, as shown in fig. 3, before step S20, the method further includes the steps of:
s21: acquiring an auxiliary model storing auxiliary sample data;
s22: and converting the auxiliary sample data based on the auxiliary model to generate a pest identification model with pest sample data.
In this embodiment, the auxiliary model is a convolutional neural network model; a Convolutional Neural Network (CNN) is an artificial Neural Network, which can automatically and adaptively learn an element space hierarchy from a low-level mode to a high-level mode, and is good at handling machine learning problems related to images, particularly large images. The CNN is different from the traditional LBP for extracting texture features, Canny for extracting edge features, HIS for extracting space features and other specific manual features, and the CNN is used for performing layered abstract processing on an original image of pests by simulating a human visual system and utilizing a convolution module, extracting image features of each part of the pests after continuously reducing the dimension of the image data with huge original data volume, and finally being trained to generate a classification result. The method adopts local receptive field, weight sharing and space sampling technology, so that training parameters of the network are greatly reduced compared with a neural network, and the image of the pests has translation, rotation and distortion invariance to a certain degree. It is currently believed that CNNs learn more powerful and expressive features than traditional manually extracted features.
The auxiliary sample data is converted by a method of 'Transfer Learning', wherein the Transfer Learning refers to an inclusion-V3 extracted feature + SVM/SoftMax structure based on 'CNN + other classifiers', and is called Transfer Learning (Transfer Learning). The transfer learning means that the original model is obtained by utilizing a large amount of image training and is applied to a new image field, so that the model training in the new image field can obtain the same effect as that of the model training which needs a large amount of image data from the beginning only by using a small number of pictures. Aiming at the problem of garden plant pests, the difficulty of finding sufficient training data is high. However, through transfer learning, the model obtained from training of other data sources can be applied to the field of pest identification after certain modification and improvement, so that the problem caused by insufficient data sources is greatly relieved.
Specifically, a convolutional neural network model trained by a large number of pictures in other fields is obtained, the convolutional neural network model is modified and perfectly applied to the field of pest recognition in a transfer learning mode to obtain a pest recognition model, the pest recognition model can reach a huge data source only by using a small number of pest pictures for training, and the training of the pest recognition model is more convenient.
For example, in an auxiliary model, how to quickly identify the pest feature model of the caterpillars is trained by uploading 100 photos of different parts of the caterpillars in different states, that is, auxiliary feature data, so that through transfer learning, only a small number of pictures of the caterpillars need to be uploaded, and photos of different parts of the caterpillars can be trained to be automatically acquired, that is, pest feature data of different parts of the caterpillars can be acquired.
In another embodiment, the auxiliary characteristic data refers to pest characteristic data of pests and animal characteristic data of other animals except the pests, the auxiliary model stores the pest characteristic data and the animal characteristic data, the pest characteristic data in the auxiliary model is transformed and migrated through screening and pairing to obtain a pest identification model containing partial pest characteristics, and the pest identification model is formed through transforming and migrating mutually different pest characteristic data in a plurality of auxiliary models;
for example, the auxiliary model A has 80% of pest characteristic data and 20% of animal characteristic data, 80% of the pest characteristic data are migrated and converted into a pest identification model containing 80% of pest characteristic data, the auxiliary model B has 20% of pest characteristic data and 80% of animal characteristic data, 10% of the pest characteristic data are repeated with the pest characteristic data in the auxiliary model A, after transformation, the pest identification model has 90% of pest characteristic data, and then 10% of pest characteristic data which are different from those in the auxiliary model A and the auxiliary model B are migrated and converted into the pest identification model, namely, a 100% pest characteristic model is formed.
In an embodiment, as shown in fig. 4, after the step S40, the method further includes the steps of:
s41: when a viewing instruction sent by a user side is received; based on the image recognition result, pushing introduction data, prevention and treatment data and prevention and treatment drug links to the user side;
in the embodiment, the viewing instruction is to click on the pest image identified in the image identification result;
the introduction data is the introduction data of the identified pests;
the control data is the control means data for the identified pest.
Specifically, if the user at the user end clicks the identified pest image, the user end pops up introduction data and control mode data about the identified pest. So that the user can quickly know the information of the pest and the control information.
In an embodiment, as shown in fig. 4, after the step S41, the method further includes the steps of:
s42: based on the preventive medicine link, when a viewing request triggered by the user side is received, a sale page of the preventive medicine is pushed to the user side.
In this embodiment, the page of the recommended page for prevention and treatment of drugs includes drugs for prevention and treatment of the identified pests, prices, and window identifiers for purchase.
Specifically, if the user clicks the link of the pest control medicine, the user side pops up a recommended page of the pest control medicine, the user can directly purchase the medicine on the recommended page to be used for pest control recognition, and pest control is more convenient.
In an embodiment, as shown in fig. 5, after step S40, the method further includes the steps of:
s43: and when receiving an application field service request sent by the user side, pushing introduction information and contact information data of the pest control team based on the positioning information of the user side.
In this embodiment, the application for the field service refers to a request for a pest control team to perform pest control at a shooting place of a user, and the introduction information of the pest control team refers to the main business, service range and charging mode of the team.
Specifically, a user at the user side sends a request for applying the field service, for example, the request for applying the field service is sent in a manner of clicking a software application interface, and the user side pops up a plurality of pest control teams close to a shooting place of the user and introduction information and contact information thereof. If the user wants to deinsectize as soon as possible after discovering the insect pest, the user can push the insect pest control team in the area according to the positioning information by sending a request for applying field service, and contact the insect pest control team to reserve time to remove the insect pest by telephone, so that the insect pest control is more efficient and convenient.
In an embodiment, as shown in fig. 6, the garden pest identification method further includes:
SA 1: if a help identification request sent by a user side is obtained, pest images and description information are obtained based on the help identification request;
SA 2: and the background server generates request information according to the pest image and the description information and shares the request information to each user side.
In the present embodiment, the request information refers to an image of a pest requested to be identified and a description of the image.
Specifically, because the number of pests stored in the pest identification model is still limited, when a user at a certain user side obtains an identification image through the pest identification model, but the pest identified by subjective judgment is still different from the photographed pest, the pest cannot be identified, at the moment, the user can send out a help identification request, the background server side sends a request to produce a shared message to all the user sides, namely, the user at all the user sides can see and comment the shared message, so that the users at other user sides can answer the help identification request by experience, and the pest identification modes are enriched.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
In one embodiment, a garden pest identification system is provided, which corresponds to the garden pest identification method in the above embodiments one to one. As shown in fig. 7, the garden pest recognition system includes:
the image acquisition module is used for acquiring a pest image and extracting a plurality of pest characteristic data;
the image sending module is used for sending the pest characteristic data to a pest identification model, and the pest identification model stores a plurality of pest sample data;
the image matching module is used for performing similarity matching on a plurality of pest characteristic data and pest sample data respectively based on the pest identification model to obtain an image identification result, and the image identification result comprises an identified pest image and academic name data thereof;
and the user side module is used for sending the image identification result to a user side associated with the inquiry user.
Optionally, the garden pest identification system further comprises:
and the storage module is used for storing the pest image which is sent to the pest identification model by the user side each time.
Optionally, the garden pest identification system further comprises:
the original model module is used for acquiring an auxiliary model stored with auxiliary sample data;
and the transfer learning module is used for converting the auxiliary sample data based on the auxiliary model and generating the pest identification model with the pest sample data.
Optionally, the garden pest identification system further comprises:
the viewing instruction module is used for receiving a viewing instruction sent by a user side; based on the image recognition result, pushing introduction data, prevention and treatment data and prevention and treatment drug links to the user side;
and the medicine link module is used for pushing a selling page of the preventive medicine to the user side when receiving a checking request triggered by the user side based on preventive medicine link.
Optionally, the garden pest identification system further comprises:
a positioning acquisition module for acquiring the position information of the user terminal,
and the positioning sending module is used for binding the position information with the pest image.
Optionally, the garden pest identification system further comprises:
and the report pushing module is used for screening a plurality of same or adjacent position information, integrating pest images bound by the position information, generating a regional pest damage report and pushing the regional pest damage report to the user side.
Optionally, the garden pest identification system further comprises:
and the field service request module is used for pushing introduction information and contact data of the pest control team based on the positioning information of the user side when receiving a field service application request sent by the user side.
Optionally, the garden pest identification system further comprises:
the identification request module is used for acquiring pest images and description information based on a help identification request sent by a user side if the help identification request is acquired;
and the shared information generating module is used for generating request information by the background server side according to the pest image and the description information and sharing the request information to each user side.
Specific limitations on the garden pest identification system can be found in the above limitations on the garden pest identification method, and are not described herein again. The respective modules in the above-described garden pest identification system may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing pest characteristic data, pest images, sample characteristic data, introduction information data, control information data and position information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement the garden pest identification method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring a pest image and extracting a plurality of pest characteristic data;
sending the pest characteristic data to a pest identification model, wherein the pest identification model stores a plurality of pest sample data;
based on the pest identification model, respectively carrying out similarity matching on a plurality of pest characteristic data and pest sample data to obtain an image identification result, wherein the image identification result comprises an identified pest image and academic name data thereof;
and sending the image recognition result to a user side associated with the inquiry user.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a pest image and extracting a plurality of pest characteristic data;
sending the pest characteristic data to a pest identification model, wherein the pest identification model stores a plurality of pest sample data;
based on the pest identification model, respectively carrying out similarity matching on a plurality of pest characteristic data and pest sample data to obtain an image identification result, wherein the image identification result comprises an identified pest image and academic name data thereof;
and sending the image recognition result to a user side associated with the inquiry user.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A garden pest identification method is characterized by comprising the following steps: the method comprises the following steps:
acquiring a pest image and extracting a plurality of pest characteristic data;
sending the pest characteristic data to a pest identification model, wherein the pest identification model stores a plurality of pest sample data;
based on the pest identification model, respectively carrying out similarity matching on a plurality of pest characteristic data and pest sample data to obtain an image identification result, wherein the image identification result comprises an identified pest image and academic name data thereof;
and sending the image recognition result to a user side associated with the inquiry user.
2. The garden pest identification method according to claim 1, wherein: before the step of sending the pest characteristic data to the pest identification model, the method comprises the following steps:
acquiring an auxiliary model storing auxiliary sample data;
and converting the auxiliary sample data based on the auxiliary model to generate a pest identification model with pest sample data.
3. The garden pest identification method according to claim 1, wherein: after the step of sending the image recognition result to the user terminal associated with the query user, the method comprises the following steps:
and when a viewing instruction sent by a user side is received, based on the image recognition result, the introduction data, the prevention and treatment data and the prevention and treatment drug link are pushed to the user side.
4. The garden pest identification method according to claim 3, wherein: after the step of pushing the introduction data, the prevention and treatment data and the prevention and treatment drug link to the user terminal, the method further comprises the following steps:
based on the preventive medicine link, when a viewing request triggered by the user side is received, a sale page of the preventive medicine is pushed to the user side.
5. The garden pest identification method according to claim 1, wherein: when the step of obtaining pest images and extracting a plurality of pest characteristic data comprises the following steps:
acquiring the position information of a user side;
and binding the position information with the pest image.
6. The garden pest identification method according to claim 5, wherein: after the step of binding the location information with the pest image, the method includes the steps of:
screening a plurality of same or adjacent position information, integrating pest images bound by the position information, generating a regional pest damage report and pushing the regional pest damage report to the user side.
7. The garden pest identification method according to claim 3, wherein: after the step of sending the image recognition result to the user side associated with the query user, the method further comprises the following steps:
and when receiving an application field service request sent by the user side, pushing introduction information and contact information data of the pest control team based on the positioning information of the user side.
8. A garden pest identification system which characterized in that: the garden pest recognition system includes:
the image acquisition module is used for acquiring a pest image and extracting a plurality of pest characteristic data;
the image sending module is used for sending the pest characteristic data to a pest identification model, and the pest identification model stores a plurality of pest sample data;
the image matching module is used for performing similarity matching on a plurality of pest characteristic data and pest sample data respectively based on the pest identification model to obtain an image identification result, and the image identification result comprises an identified pest image and academic name data thereof;
and the user side module is used for sending the image identification result to a user side associated with the inquiry user.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the garden pest identification method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the garden pest identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111116037.7A CN113887595A (en) | 2021-09-23 | 2021-09-23 | Garden pest identification method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111116037.7A CN113887595A (en) | 2021-09-23 | 2021-09-23 | Garden pest identification method, system, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113887595A true CN113887595A (en) | 2022-01-04 |
Family
ID=79010389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111116037.7A Pending CN113887595A (en) | 2021-09-23 | 2021-09-23 | Garden pest identification method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887595A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381156A (en) * | 2020-11-18 | 2021-02-19 | 重庆电子工程职业学院 | Chinese medicinal material pest and disease damage detection system based on image recognition |
| CN112528814A (en) * | 2020-12-04 | 2021-03-19 | 湖南高德联创环境管理有限公司 | Harmful organism monitoring and early warning method and system and storage medium |
| CN112966758A (en) * | 2021-03-12 | 2021-06-15 | 中化现代农业有限公司 | Crop disease, insect and weed identification method, device and system and storage medium |
| CN113313193A (en) * | 2021-06-15 | 2021-08-27 | 杭州睿胜软件有限公司 | Plant picture identification method, readable storage medium and electronic device |
-
2021
- 2021-09-23 CN CN202111116037.7A patent/CN113887595A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381156A (en) * | 2020-11-18 | 2021-02-19 | 重庆电子工程职业学院 | Chinese medicinal material pest and disease damage detection system based on image recognition |
| CN112528814A (en) * | 2020-12-04 | 2021-03-19 | 湖南高德联创环境管理有限公司 | Harmful organism monitoring and early warning method and system and storage medium |
| CN112966758A (en) * | 2021-03-12 | 2021-06-15 | 中化现代农业有限公司 | Crop disease, insect and weed identification method, device and system and storage medium |
| CN113313193A (en) * | 2021-06-15 | 2021-08-27 | 杭州睿胜软件有限公司 | Plant picture identification method, readable storage medium and electronic device |
Non-Patent Citations (1)
| Title |
|---|
| 姜梦洲: "基于深度学习的农业害虫图像智能识别系统的研究与实现", 《中国优秀博硕士学位论文全文数据库(硕士)农业科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Elias et al. | Where's the bear? automating wildlife image processing using IoT and edge cloud systems | |
| CN108922622B (en) | Animal health monitoring method, device and computer readable storage medium | |
| WO2018170663A1 (en) | Method and device for annotating image, and electronic apparatus | |
| Rahman et al. | Smartphone-based hierarchical crowdsourcing for weed identification | |
| Salunke et al. | A new approach for automatic face emotion recognition and classification based on deep networks | |
| US20180197287A1 (en) | Process of using machine learning for cannabis plant health diagnostics | |
| US11367196B2 (en) | Image processing method, apparatus, and storage medium | |
| CN108549909B (en) | Object classification method and object classification system based on crowdsourcing | |
| CN110377218B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN110610125A (en) | Ox face identification method, device, equipment and storage medium based on neural network | |
| CN106022467A (en) | Crop disease detection system based on neural network | |
| CN111753697B (en) | Intelligent pet management system and management method thereof | |
| CN112465038A (en) | Method and system for identifying disease and insect pest types of fruit trees | |
| CN110992500B (en) | Attendance checking method and device, storage medium and server | |
| CN110019916A (en) | Event-handling method, device, equipment and storage medium based on user's portrait | |
| Wong et al. | Development of species recognition models using Google teachable machine on shorebirds and waterbirds | |
| WO2020019457A1 (en) | User instruction matching method and apparatus, computer device, and storage medium | |
| CN112528978B (en) | Face key point detection method and device, electronic equipment and storage medium | |
| US11361032B2 (en) | Computer driven question identification and understanding within a commercial tender document for automated bid processing for rapid bid submission and win rate enhancement | |
| CN113887595A (en) | Garden pest identification method, system, computer equipment and storage medium | |
| CN104766080A (en) | Image multi-class feature recognizing and pushing method based on electronic commerce | |
| CN107679555A (en) | Processing method, computer program, storage medium and electronic equipment is immunized in livestock | |
| CN108664921B (en) | Image identification method and system based on bag-of-words model under android platform | |
| CN109493279B (en) | Large-scale unmanned aerial vehicle image parallel splicing method | |
| Dube et al. | Snake identification system using convolutional neural networks |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220104 |
|
| RJ01 | Rejection of invention patent application after publication |