CN116543347A - Intelligent insect condition on-line monitoring system, method, device and medium - Google Patents
Intelligent insect condition on-line monitoring system, method, device and medium Download PDFInfo
- Publication number
- CN116543347A CN116543347A CN202310522526.5A CN202310522526A CN116543347A CN 116543347 A CN116543347 A CN 116543347A CN 202310522526 A CN202310522526 A CN 202310522526A CN 116543347 A CN116543347 A CN 116543347A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- pest
- data
- monitoring point
- information
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 146
- 241000238631 Hexapoda Species 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 title claims abstract description 37
- 241000607479 Yersinia pestis Species 0.000 claims abstract description 98
- 238000001514 detection method Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000007613 environmental effect Effects 0.000 claims abstract description 16
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 3
- 241000208125 Nicotiana Species 0.000 description 10
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 10
- 238000012549 training Methods 0.000 description 10
- 238000007726 management method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 241001177117 Lasioderma serricorne Species 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002354 daily effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- 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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention provides an intelligent insect condition on-line monitoring method, which comprises the following steps: acquiring a monitoring image of at least one monitoring point; determining pest information based on the processing of the monitoring image by the detection model; the detection model is a machine learning model; acquiring environmental data of the at least one monitoring point; generating warning data of the at least one monitoring point based on the environmental data of the at least one monitoring point and the pest information.
Description
Technical Field
The invention relates to the field of intelligent insect condition online monitoring, in particular to an intelligent insect condition online monitoring method, an intelligent insect condition online monitoring system, an intelligent insect condition online monitoring device and a storage medium.
Background
At present, insect conditions in the tobacco processing process are accurately mastered, a great promotion effect is achieved on the quality improvement of cigarette products, most insect condition monitoring in the industry currently adopts a manual inspection mode, insect condition monitoring staff check once a day, and a scanning code is input into a tobacco storage insect pest management system of a company to form a production area insect condition monitoring record table. The trap has the effects of large human monitoring error, low efficiency and great labor consumption, and the insect condition early warning and the like are all carried out by manual inspection, so that the early warning and alarming informatization means in the insect condition monitoring process are relatively lacking, and the phenomena of lag of insect condition monitoring information and untimely response exist.
The conventional insect pest control flow has the following problems:
(1) As more than 100 insect condition monitoring points exist in the factory production range, the insect condition is manually distinguished by detection, insect condition monitoring personnel need to scan codes and upload the data of the insect condition monitoring points every day, and return to the port management department to recheck the insect condition of the trapper, the inspection is not timely due to the fact that the manual inspection error is large and the inspection frequency is not high, the data is difficult to provide a basis for decision making, is one of process quality control blind points, is easy to form quality risks, and belongs to the common problem of the tobacco processing industry.
(2) At present, no systematic method capable of detecting and analyzing insect pest situation in real time exists in the industry, and a method for strengthening manual inspection and assessment is mainly adopted to monitor insect pest situation; and (3) making week and month analysis, finding a pest situation change trend, and optimizing and improving a pest comprehensive control method.
Therefore, an intelligent insect condition on-line monitoring method and system capable of achieving on-line monitoring, automatic identification and insect condition early warning is needed.
Disclosure of Invention
The invention aims to provide an intelligent insect condition on-line monitoring method. In order to solve the technical problems existing in the background art.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an intelligent insect condition on-line monitoring method comprises the following steps:
acquiring a monitoring image of at least one monitoring point;
determining pest information based on the processing of the monitoring image by the detection model; the detection model is a machine learning model;
acquiring environmental data of the at least one monitoring point;
generating warning data of the at least one monitoring point based on the environmental data of the at least one monitoring point and the pest information.
In some embodiments, the generating alert data for the at least one monitoring point based on the environmental data for the at least one monitoring point, the pest information includes:
determining pest variation information of the at least one monitoring point based on the pest information and historical data of the at least one monitoring point;
determining the early warning level of the at least one monitoring point based on the pest change information and a preset early warning rule;
and generating warning data of the at least one monitoring point based on the early warning grade and the environment data in response to the early warning grade meeting a preset grade requirement.
In some embodiments, the target area includes a plurality of the monitoring points, the method further comprising:
and generating pest management data of the target area based on the warning data of the monitoring points.
In some embodiments, the method further comprises determining pest prediction data for the at least one monitoring point based on the pest information and historical data for the at least one monitoring point.
In some embodiments, the determining pest information based on the processing of the monitoring image by the detection model includes:
carrying out preset treatment on the monitoring image;
determining pest information based on the processing of the preset monitoring image by the detection model; the pest information includes the number of pests, the kind of pests.
Meanwhile, the invention also discloses an intelligent insect condition on-line monitoring system, which comprises
The first acquisition module is used for acquiring a monitoring image of at least one monitoring point;
the first determining module is used for determining pest information based on the processing of the detection model on the monitoring image; the detection model is a machine learning model;
the second acquisition module is used for acquiring the environmental data of the at least one monitoring point;
the first generation module is used for generating warning data of the at least one monitoring point based on the environment data of the at least one monitoring point and the pest information.
Meanwhile, the invention also discloses an intelligent insect condition on-line monitoring device, which comprises at least one processor and at least one memory;
the at least one memory is configured to store computer instructions;
the at least one processor is configured to execute at least some of the computer instructions to implement the intelligent insect condition on-line monitoring method described above.
The invention also discloses a computer readable storage medium storing computer instructions which when executed by a processor implement the above method.
Advantageous effects
Compared with the prior art, the invention has the remarkable advantages that:
the technical scheme of the invention can complete on-line monitoring, automatic identification and insect condition early warning. The invention has the beneficial effects that the insect pest situation in the insect pest trap is monitored, analyzed and early-warned in real time, the human reduction and synergy are realized, the insect pest monitoring cost is reduced, the insect pest monitoring accuracy is improved, and the insect pest situation is guided or prompted to be rapidly treated by management staff;
meanwhile, the self-monitoring of the whole process can be realized, and the tobacco beetles can be accurately identified by adopting an AI artificial intelligent image identification technology; and the number of the tobacco insects can be counted automatically, and the ambient temperature, humidity, time and the like can be collected and displayed on a large screen. And the number of the insect conditions can be statistically analyzed to form an insect condition distribution early warning model, the insect condition trend change is analyzed, and when the insect conditions occur, relevant responsible persons can be timely reminded in a short message mode and the like, so that the real-time performance is high.
Drawings
FIG. 1 is a schematic diagram of an intelligent insect condition on-line monitoring system according to the embodiment;
FIG. 2 is a flow chart of an intelligent insect condition online monitoring method according to the embodiment;
fig. 3 is a schematic diagram of a detection model according to the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
On the contrary, the application is intended to cover any alternatives, modifications, equivalents, and variations that may be included within the spirit and scope of the application as defined by the appended claims. Further, in the following detailed description of the present application, specific details are set forth in order to provide a more thorough understanding of the present application. The present application will be fully understood by those skilled in the art without a description of these details.
An online intelligent insect condition monitoring method according to the embodiments of the present application will be described in detail with reference to fig. 1 to 3. It is noted that the following examples are only for explaining the present application and are not limiting of the present application.
Example 1
As shown in fig. 1, the present invention also discloses an intelligent insect condition online monitoring system 100, which comprises:
the first acquiring module 110 is configured to acquire a monitoring image of at least one monitoring point. For example, the first acquisition module 110 may be an image or video acquisition device such as a monitoring camera. The monitoring point may refer to a point where pest conditions need to be monitored, for example, a corresponding point location may be selected randomly or selected as required in the target area to install the trap, and the point location is used as the monitoring point.
In some embodiments, first acquisition module 110 may acquire insect pest pictures or videos after attracting tobacco pests to the acquisition board by the trap and transmit to first determination module 120 using communication techniques such as 5G or WIFI.
A first determining module 120 for determining pest information based on the processing of the monitoring image by the detection model; the detection model is a machine learning model.
In some embodiments, the first determination module 120 is further to:
carrying out preset treatment on the monitoring image;
determining pest information based on the processing of the preset monitoring image by the detection model; the pest information includes the number of pests, the kind of pests.
In some embodiments, the detection model may be a CNNs, GNN, or other intelligent model. The detection model can learn various insect pest shapes through an AI algorithm, and after insect pest images or videos are collected, the information such as dust, sundries and the like can be automatically removed by combining the data model through AI artificial intelligent calculation, and insect pest quantity and the like can be accurately counted. For further description of the detection model see the corresponding contents of fig. 2 and 3.
A second obtaining module 130, configured to obtain environmental data of the at least one monitoring point. Environmental data may refer to temperature, humidity, current time, etc. data surrounding the trap. May be acquired based on the corresponding sensing device.
A first generating module 140, configured to generate alert data of the at least one monitoring point based on the environmental data of the at least one monitoring point and the pest information. For example, the first generating module 140 may display the generated warning data on a corresponding display module, so that the staff can check the warning data in time, or send the warning data to the staff through a short message, a phone, or the like.
In some embodiments, the first generation module is further to:
determining pest variation information of the at least one monitoring point based on the pest information and historical data of the at least one monitoring point;
determining the early warning level of the at least one monitoring point based on the pest change information and a preset early warning rule;
and generating warning data of the at least one monitoring point based on the early warning grade and the environment data in response to the early warning grade meeting a preset grade requirement.
For example, the first generation module may determine the number of newly added tobacco beetles on the current day based on the current total number of tobacco beetles at each point and compare the current total number of tobacco beetles with the yesterday.
In some embodiments, the preset pre-alarm rules may include a mode of weekly monitoring, a mild (cumulative increase in single-point weeks < 3), moderate (3. Ltoreq. Cumulative increase in single-point weeks < 7), severe pre-alarm (cumulative increase in single-point weeks. Ltoreq. 7) against the pre-alarm classification treatment requirements.
The production area monitoring points are executed according to the daily monitoring mode, and are compared with the early warning grading treatment requirements, the early warning grading treatment requirements are light (1 head is newly increased on a single day), moderate (2 heads are newly increased on a single day or 2 days are continuously increased, the average number of area single Zhou Shandian traps is less than 0.7 head and less than 0.3 heads), and the severe early warning (3 heads are newly increased on a single day or 3 days are continuously increased, and the average number of area single Zhou Shandian traps is more than or equal to 0.7 head).
In some embodiments, when the pest reaches a preset number, the system may automatically push pest status alert information to the relevant manager to perform pest management work.
In some embodiments, the system further comprises a second generation module 150:
the second generation module is used for generating pest management data of the target area based on the warning data of the monitoring points. For example, the second generation module can generate a global point position plan view of the target area, so that a view is quickly browsed, and detailed information of tobacco beetles at each monitoring point position of the production storage area can be intuitively and comprehensively known.
The system further includes a second determination module 160, the second determination module 160 configured to determine pest prediction data for the at least one monitoring point based on the pest information and historical data for the at least one monitoring point. For example, the second determination module 160 may generate trend analysis curves in conjunction with the daily data to further assist the staff in predicting future pest data.
As shown in fig. 2, the present invention further discloses an intelligent insect condition online monitoring method, which is executed based on the intelligent insect condition online monitoring system 100, and the method 200 includes:
step 210, acquiring a monitoring image of at least one monitoring point.
For example, a picture of the trap containing debris and insects is taken by the camera device.
Step 220, determining pest information based on the processing of the monitoring image by the detection model; the detection model is a machine learning model.
In some embodiments, step 220 comprises:
step 221, performing preset processing on the monitoring image;
step 222, determining pest information based on the processing of the preset monitoring image by the detection model; the pest information includes the number of pests, the kind of pests.
In some embodiments, the preset processing may include performing gridding processing according to a distance Z between the terminal camera and the insect board and a position X, Y of the trap from the terminal to the inside, positioning the insect through X, Y, Z coordinates, and enhancing the shape of the identified insect by performing pixel amplification on the image of the insect, so as to facilitate the calculation of the next step.
In some embodiments, the detection model may interleave the integration layers (modeling layers) using convolution calculations (convolution), and CNNs may implement automatic extraction of feature information, forming a series of fully connected network layers that may complete the final classification. ) And identifying, self-comparing and storing the tobacco insects through the model, and generating a tobacco insect identifying sample.
In some embodiments, the algorithm formula of the model algorithm of the detection model includes:wherein M is a fixed value constant (x, y coordinate variable) of the feature map, M is defined for the insect species, tanh, i, j are specific calculation methods in the algorithm formula, k is a feature map variable, and is obtained by decomposition according to the pixel density value of the picture, and W is a weight of similarity, wherein b is a deviation term (obtained by simulation according to a neural network CNNs).
The algorithm formula is characterized in that the Tanh, i and j are subjected to simulation calculation to finally obtain M characteristic diagrams, and the number of insects is checked by the number of the M characteristic diagrams. The insect condition sample can be continuously updated through continuous collection, and according to a preset early warning rule, the detection accuracy can be improved, and the false alarm rate can be reduced. See the corresponding discussion of fig. 3 for a training description of the detection model.
Step 230, acquiring environmental data of the at least one monitoring point;
step 240, generating warning data of the at least one monitoring point based on the environmental data of the at least one monitoring point and the pest information. For example, after the most recently acquired tobacco image is identified, the most recently acquired tobacco image is output through a monitoring system, and finally, an early warning-processing-reporting process is formed. When insect conditions appear at the detection points of the traps, relevant responsible persons are timely reminded in a short message mode and the like, and the real-time performance is high.
In some embodiments, step 240 comprises:
step 241, determining pest variation information of the at least one monitoring point based on the pest information and history data of the at least one monitoring point;
step 242, determining an early warning level of the at least one monitoring point based on the pest variation information and a preset early warning rule;
and step 243, generating warning data of the at least one monitoring point based on the early warning level and the environmental data in response to the early warning level meeting a preset level requirement.
In some embodiments, the method of the embodiment can realize the functions of warning and early warning of the preset number of insect pests, and when the number of insect pests reaches the preset number, the platform automatically pushes the insect pest situation warning information to relevant management staff to carry out insect pest control work.
In some embodiments, the target area includes a plurality of the monitoring points, the method further comprising step 250: and generating pest management data of the target area based on the warning data of the monitoring points.
In some embodiments, the method further comprises step 260: pest prediction data for the at least one monitoring point is determined based on the pest information and historical data for the at least one monitoring point. For example, it is possible to implement a process of killing insects in advance based on the predicted development trend, and the like.
Fig. 3 is a schematic diagram of the detection model disclosed in the present embodiment.
In some embodiments, the detection model may be a machine learning model, such as a neural network model or other model built by an intelligent learning network.
In some embodiments, the input to the detection model 320 is a monitoring image 310 of each of the target regions. The output of the detection model is pest information 330, such as the number, type, etc. of pests.
In some embodiments, the detection model may be trained based on a plurality of first training data 340 (including a first training sample with a first label). The first training sample may be a historical monitoring image of each of the target areas over a historical period of time. The first label may be pest information corresponding to the sample.
In some embodiments, training of the detection model includes: the first training sample is input into the initial detection model 350, and an abnormal region corresponding to the first training sample is obtained. In the training process, the detection model can construct a loss function based on the labels and the output results. Meanwhile, parameters of the detection model are updated based on the loss function until preset conditions are met, and training is completed. The preset condition may include one or more of the loss function being less than a threshold, converging, or the training period reaching a threshold, etc.
In summary, the scheme can realize real-time monitoring, analysis and early warning of each insect pest trapping point, and display insect pest information through a large screen so as to guide or prompt monitoring, manage personnel to quickly find the insect pest situation of each point, timely process tobacco insect pests, realize insect pest early warning through big data statistics and analysis, and complete real-time insect pest detection, automatic statistics and overrun warning; and collecting and uploading the temperature, humidity, time and insect condition number of each trap point so as to guide or prompt operation and manage personnel to rapidly handle abnormal conditions.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. An intelligent insect condition on-line monitoring method is characterized by comprising the following steps:
acquiring a monitoring image of at least one monitoring point;
determining pest information based on the processing of the monitoring image by the detection model; the detection model is a machine learning model;
acquiring environmental data of the at least one monitoring point;
generating warning data of the at least one monitoring point based on the environmental data of the at least one monitoring point and the pest information.
2. The intelligent insect condition online monitoring method according to claim 1, wherein the generating warning data of the at least one monitoring point based on the environmental data of the at least one monitoring point and the insect pest information comprises:
determining pest variation information of the at least one monitoring point based on the pest information and historical data of the at least one monitoring point;
determining the early warning level of the at least one monitoring point based on the pest change information and a preset early warning rule;
and generating warning data of the at least one monitoring point based on the early warning grade and the environment data in response to the early warning grade meeting a preset grade requirement.
3. The intelligent insect condition online monitoring method according to claim 2, wherein a target area includes a plurality of the monitoring points, the method further comprising:
and generating pest management data of the target area based on the warning data of the monitoring points.
4. The intelligent pest situation online monitoring method of claim 2, further comprising determining pest prediction data for the at least one monitoring point based on the pest information and historical data for the at least one monitoring point.
5. The intelligent pest situation online monitoring method according to claim 1, wherein the determining pest information based on the processing of the monitoring image by the detection model comprises:
carrying out preset treatment on the monitoring image;
determining pest information based on the processing of the preset monitoring image by the detection model; the pest information includes the number of pests, the kind of pests.
6. An intelligent insect condition on-line monitoring system is characterized by comprising
The first acquisition module is used for acquiring a monitoring image of at least one monitoring point;
the first determining module is used for determining pest information based on the processing of the detection model on the monitoring image; the detection model is a machine learning model;
the second acquisition module is used for acquiring the environmental data of the at least one monitoring point;
the first generation module is used for generating warning data of the at least one monitoring point based on the environment data of the at least one monitoring point and the pest information.
7. The intelligent insect condition online monitoring system of claim 6, wherein the first generation module is further configured to:
determining pest variation information of the at least one monitoring point based on the pest information and historical data of the at least one monitoring point;
determining the early warning level of the at least one monitoring point based on the pest change information and a preset early warning rule;
and generating warning data of the at least one monitoring point based on the early warning grade and the environment data in response to the early warning grade meeting a preset grade requirement.
8. The intelligent insect condition online monitoring system of claim 7, wherein a target area includes a plurality of the monitoring points, the system further comprising a second generation module:
the second generation module is used for generating pest management data of the target area based on the warning data of the monitoring points.
9. An intelligent insect condition on-line monitoring device is characterized by comprising at least one processor and at least one memory;
the at least one memory is configured to store computer instructions;
the at least one processor is configured to execute at least some of the computer instructions to implement the intelligent insect condition on-line monitoring method of any one of claims 1-5.
10. A computer readable storage medium storing computer instructions which when executed by a processor implement the intelligent insect condition on-line monitoring method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310522526.5A CN116543347A (en) | 2023-05-10 | 2023-05-10 | Intelligent insect condition on-line monitoring system, method, device and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310522526.5A CN116543347A (en) | 2023-05-10 | 2023-05-10 | Intelligent insect condition on-line monitoring system, method, device and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116543347A true CN116543347A (en) | 2023-08-04 |
Family
ID=87446631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310522526.5A Pending CN116543347A (en) | 2023-05-10 | 2023-05-10 | Intelligent insect condition on-line monitoring system, method, device and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116543347A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117237820A (en) * | 2023-09-26 | 2023-12-15 | 中化现代农业有限公司 | Method and device for determining pest hazard degree, electronic equipment and storage medium |
CN117523617A (en) * | 2024-01-08 | 2024-02-06 | 陕西安康玮创达信息技术有限公司 | Insect pest detection method and system based on machine learning |
-
2023
- 2023-05-10 CN CN202310522526.5A patent/CN116543347A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117237820A (en) * | 2023-09-26 | 2023-12-15 | 中化现代农业有限公司 | Method and device for determining pest hazard degree, electronic equipment and storage medium |
CN117523617A (en) * | 2024-01-08 | 2024-02-06 | 陕西安康玮创达信息技术有限公司 | Insect pest detection method and system based on machine learning |
CN117523617B (en) * | 2024-01-08 | 2024-04-05 | 陕西安康玮创达信息技术有限公司 | Insect pest detection method and system based on machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11723344B2 (en) | Agricultural monitoring system using image analysis | |
CN116543347A (en) | Intelligent insect condition on-line monitoring system, method, device and medium | |
JP2021514548A (en) | Target object monitoring methods, devices and systems | |
CN109922310A (en) | The monitoring method of target object, apparatus and system | |
US10729117B2 (en) | Pest monitoring method based on machine vision | |
CN114972843B (en) | Agricultural pest diagnosis and early warning system based on big data | |
CN106332855A (en) | Automatic early warning system for pests and diseases | |
CN108829762A (en) | The Small object recognition methods of view-based access control model and device | |
CN108874910B (en) | Vision-based small target recognition system | |
US20220414795A1 (en) | Crop disease prediction and treatment based on artificial intelligence (ai) and machine learning (ml) models | |
CN117114913A (en) | Intelligent agricultural data acquisition system based on big data | |
Hamilton et al. | When you can't see the koalas for the trees: Using drones and machine learning in complex environments | |
CN113273555A (en) | Artificial intelligence insect situation prediction system and prediction method | |
CN113792715B (en) | Granary pest monitoring and early warning method, device, equipment and storage medium | |
CN114708438A (en) | Target pest monitoring and identifying system and method | |
FAISAL | A pest monitoring system for agriculture using deep learning | |
Majewski et al. | Prediction of the remaining time of the foraging activity of honey bees using spatio-temporal correction and periodic model re-fitting | |
Teixeira et al. | Evaluating YOLO Models for Grape Moth Detection in Insect Traps | |
TWI804060B (en) | Surveillance method for plant disease and pest and surveillance system for plant disease and pest | |
Savitha et al. | Smart Greenhouse and Warehouse Monitoring with Disease Detection using Machine Learning | |
Amarendra et al. | CNN Based Animal Repelling Device for Crop Protection | |
Zhigang et al. | Tobacco pests monitoring system based on time sequence pattern mining | |
CN117670829A (en) | Tobacco plant diseases and insect pests early warning and preventing and controlling system and method | |
Kohila et al. | An extensive survey on machine and deep learning algorithms for air quality analysis | |
Putra et al. | Vision-Based Object Detection for Efficient Monitoring in Smart Hydroponic Systems |
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 |