CN111507314A - Artificial intelligence image data acquisition system of insect pest control facility - Google Patents
Artificial intelligence image data acquisition system of insect pest control facility Download PDFInfo
- Publication number
- CN111507314A CN111507314A CN202010505589.6A CN202010505589A CN111507314A CN 111507314 A CN111507314 A CN 111507314A CN 202010505589 A CN202010505589 A CN 202010505589A CN 111507314 A CN111507314 A CN 111507314A
- Authority
- CN
- China
- Prior art keywords
- insect
- data
- image data
- image
- uploading
- 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
- 241000238631 Hexapoda Species 0.000 title claims abstract description 206
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 68
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 34
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 13
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 239000003814 drug Substances 0.000 description 4
- 235000013305 food Nutrition 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000011176 pooling Methods 0.000 description 4
- 241000255925 Diptera Species 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241001674044 Blattodea Species 0.000 description 1
- 206010027146 Melanoderma Diseases 0.000 description 1
- 241000699670 Mus sp. Species 0.000 description 1
- 241000257226 Muscidae Species 0.000 description 1
- 241000256626 Pterygota <winged insects> Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011059 hazard and critical control points analysis Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Library & Information Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Catching Or Destruction (AREA)
Abstract
The invention relates to an artificial intelligence image data acquisition system for a pest control facility, and belongs to the field of artificial intelligence. The system comprises a data acquisition device, a data uploading device, a data preprocessing device, a data identification device, a data metering device, a data generation device and a database platform; the data acquisition device is used for acquiring insect image data and uploading the insect image data to the data uploading device; the uploading device is used for uploading the acquired insect image data to the data uploading data preprocessing device; the data preprocessing device is used for denoising and data normalizing the insect image data from the data acquisition device and extracting the characteristics of the image; the data identification device is used for rapidly identifying the insect image data; the data metering device is used for counting the identified insects; the data generation device: for generating insect profile reports; the artificial intelligence technology replaces the current artificial naked eye counting, the PCO working time is saved, and the service efficiency is improved.
Description
Technical Field
The invention relates to an artificial intelligence image data acquisition system for a pest control facility, and belongs to the field of artificial intelligence.
Background
With the progress of society, people pay high attention to the safety of foods and medicines, but in the manufacturing and packaging processes of foods and medicines, harmful organisms such as cockroaches, mice, mosquitoes, flies, greening insects and the like inevitably cause pollution risks, so that the safety of the foods and the medicines is seriously harmed, particularly, insect organisms are easy to breed, and the potential greater pollution is possibly caused. Therefore, higher requirements are put on the pest control service industry, and the pest control service changes are as follows:
the original mode of wide-range application of chemical pesticides completely depending on the polluted environment in a service site is changed into a mode of capturing and controlling harmful organisms by using a large amount of environment-friendly and harmless physical methods, for example, the purpose of controlling insect pests while ensuring environmental protection and safety is achieved by applying various insect killing lamps, physical insect killers and the like.
Secondly, in order to achieve a good pest control effect and prevent the product from being polluted by pests, the quantity of the pests captured on the various physical pest killers is required to be monitored, the types of the pests and the number of the pests of each type are counted and recorded by naked eyes, and finally, a quantity trend analysis report is formed.
The above records of pest number monitoring, recording and species discrimination classification and data analysis have the following importance:
1. the pest control service effect can be scientifically evaluated through the change analysis of pest quantity data captured by pest control equipment distributed at each position by each service (usually compared with the quantity of the last pest control service, the quantity of the same year and the same period), and meanwhile, whether a property structure, a sanitary condition, personnel habits and the like favorable for pest breeding activities exist in a pest control site or not can be judged through the abnormal change of the data, and finally, corresponding deviation rectifying measures are taken according to the judgment. It is also common to refer to historical data of the past year, establish an "alert threshold" for each pest control device, and when the recorded data exceeds the "alert threshold", it is necessary to find the reason for the excess and take corresponding action.
2. The pest captured by the pest control equipment distributed at each position is distinguished by type through each service, and the data analysis is recorded in a classified manner, so that the reason for triggering can be rapidly found out according to the biological habits (such as breeding places, conditions, activity rules and the like) of different types of insects, and corresponding control measures are taken.
In addition to the above service requirements of the customers using pest control services, industry audit standards of food, medicine, packaging and the like such as HACCP, GMP, AIB, BRC and FDA also define that: the quantity and classification data of the pests captured by the pest control device are required to be clearly recorded, accurately described and accurately recorded, and an analysis report is formed. The requirements of insect control equipment for capturing insect pest records and identifying and classifying have become one of the universal and necessary service standards of the whole insect control service industry at home and abroad.
All in all are based on data, and speaking with data has been a trend in the field of pest control. However, due to the pest control of all current pest control service field facilities (such as sticking type flying pest killing lamps and sticking boards), data recording work is completed by PCO (personal computer-controlled insect pest control) operators. The following obvious disadvantages are often caused in the practical operation process:
1. the service efficiency is low: as the insect killing device, such as a deinsectization lamp, the pest sticking paper (usually the pest sticking paper is 1/2A4 paper in size) can capture more flying insects, wherein the smallest flying insects such as flea flies are only 3-4 mm, PCO can visually see a small black spot, and the larger houseflies are only 5-8 mm. Generally, 20-30 flying insects are captured on the paper stuck in an unclean area, and 50-100 flying insects can be captured on equipment close to an outdoor area. In the pest control service, the PCO is required to count by naked eyes to accurately record the total number of various winged insects, a large amount of time is consumed, and the service efficiency is very low.
2. Insect pest quantity recording accuracy is extremely poor: because the captured flying insects are tiny and many are small black dots, the accuracy rate is very poor when the PCO is used for counting on a piece of sticky paper stuck with many flying insects by naked eyes, and the real situation of the insect pest activity around the equipment cannot be objectively reflected.
3. Inaccurate insect pest identification and classification: due to the professional knowledge or discrimination ability of the PCO, when the insect pest species captured on the pest sticking paper are various and the quantity is large, the classification and counting after accurate identification of the PCO by naked eyes are required to be almost impossible.
Disclosure of Invention
In order to solve the problems, the invention provides an artificial intelligence image data acquisition system of a pest control facility, which replaces the current artificial naked eye counting with artificial intelligence AI science and technology, identifies and can be directly input into service software through wireless transmission data, and finally forms a specialized analysis report through AI data acquisition and calculation, changes the original artificial data information acquisition mode, saves the PCO working time, improves the service efficiency, improves the accuracy of pest monitoring data, improves the specialty of identification and classification, and establishes a reliable data basis for finally forming a more specialized and credible pest activity analysis report.
The technical scheme provided by the invention is as follows: an artificial intelligence image data acquisition system of a pest control facility comprises a data acquisition device, a data uploading device, a data preprocessing device, a data identification device, a data metering device, a data generation device and a database platform.
A data acquisition device: the device is used for acquiring insect image data and uploading the insect image data to the data uploading device.
An uploading device: the data uploading device is used for uploading the acquired insect image data to the data uploading data preprocessing device.
A data preprocessing device: the device is used for carrying out noise reduction and data normalization processing on insect image data from the data acquisition device and carrying out feature extraction on the image.
The data identification device: the method is used for quickly identifying the insect image data.
A data metering device: for counting the identified insects.
The data generation device: for generating insect basic data reports.
A database platform: and the device is connected with all the devices and used for establishing insect image data storage and retrieval, continuously collecting newly added image data and providing the online updating capability of the insect image model.
The device of making pest control facility artificial intelligence image data acquisition system includes: the artificial intelligence vision main frame is used for carrying out training of a recognition model based on the insect sample image data so as to generate an artificial intelligence image data acquisition system of a pest control facility.
The scheme is further improved: the camera comprises an anti-shake high-definition camera, and serial numbers of shot photos can be marked by the anti-shake high-definition camera in sequence. Adopt anti-shake high definition camera, the insect sample photo that can the at utmost obtains the high definition improves the definition of the insect model in the insect database, is convenient for carry out the feature extraction, also provides the condition for the improvement of subsequent feature comparison success rate. The serial number marked on the photo is the same as the equipment number of the source of the photo, so that the source of the photo is easy to determine.
The scheme is further improved: the anti-shake high definition camera has a WIFI data transmission function. The obtained photos are conveniently uploaded to the terminal equipment for manual labeling, and the method is convenient and fast.
The scheme is further improved: the data identification device specifically utilizes a convolutional neural network to carry out deep learning on insect image data.
A method for collecting image data by using an artificial intelligence image data collecting system of a pest control facility, which comprises the following steps:
the method comprises the following steps: the system is built by adopting a device for manufacturing an artificial intelligent image data acquisition system of the insect pest control facility, namely, artificial intelligent insect recognition and counting functional software is built.
Step two: and collecting the image data of the insect to be identified.
Step three: and comparing the characteristics of the insect image data to be identified with the image models in the insect image database, and finally obtaining an insect basic data report.
The scheme is further improved: the method comprises the following steps that data in an insect image database are derived from insects captured in insect control equipment, the insects are attached to insect sticking paper, the insect control equipment is distributed at different positions, and the insect control equipment comprises an insect killing lamp or a physical sticking device.
The scheme is further improved: establishing artificial intelligent insect identification and counting functional software in the first step comprises the following steps:
s1: and (3) taking pictures of the insects attached to the insect sticking paper by using an anti-shake high-definition camera to obtain a large number of insect samples and form insect image data.
S2: insect image data are uploaded to the terminal equipment through a WIFI data transmission function of the anti-shake high-definition camera, each insect in the insect image data is manually segmented and labeled in the terminal equipment, and preprocessed insect image data are formed.
S3: the data acquisition device is used for acquiring the preprocessed insect image data, uploading the preprocessed insect image data to the data uploading device, uploading the preprocessed insect image data to the data preprocessing device through the data bed loading device, and the data preprocessing device is used for denoising and data normalizing the preprocessed insect image data, extracting the characteristics of the insect image and specifically extracting the shape and the type of the insect on the insect sticking paper.
S4: transmitting the insect image after the characteristic extraction to a data recognition device, and in the data recognition device, repeatedly and deeply learning and training the insect image after the characteristic extraction by using a convolutional neural network to establish a database for completing insect image parameters; specifically, to identify the categories of insects, the shape of each insect in each category, which appears on the sticky paper, is identified, wherein the shape includes the size of the insect body, the body and limb characteristics of the insect body, and the like.
S5: the data metering device counts the image parameters in the database software, specifically, the number of insects in each kind and the number of insects in all kinds are calculated;
s6: the data generating device forms an insect basic data report for the insects which finish the category identification and counting.
S7: the database platform stores and calls the data of each device, and continuously collects the data added by each device so as to expand the insect image data in the database platform, provide the online updating capability of the model and finally form the artificial intelligent insect identification and counting functional software.
The scheme is further improved: and in the third step, the image data of the insect to be identified is compared with the image model in the insect image parameter database, specifically, each insect form on the insect sample to be identified is compared with a large number of samples stored in the insect image database, so that the insect form is matched with the closest model form in the insect image identification model.
Compared with the prior art, the invention has the following beneficial effects:
1. the names of the same kind of insects can be accurately identified.
2. The number of the same kind of insects can be accurately calculated.
3. The monitoring report can be displayed at the PC terminal, namely the number and the name of different insects captured on the same device are monitored each time, the total number of the insects is calculated, and the trend curve of the captured number of various insects of each insect-proof device is automatically drawn.
Drawings
Fig. 1 is a schematic diagram of an artificial intelligence image data acquisition system of a pest control facility according to the present invention.
Fig. 2 is a schematic diagram of the steps of image data acquisition by using the artificial intelligence image data acquisition system of the pest control facility according to the preferred embodiment of the invention.
FIG. 3 is a schematic diagram of the steps of creating artificial intelligence insect identification and counting function software.
Detailed Description
According to the artificial intelligence image data acquisition system of the pest control facility, the artificial intelligence technology is applied to data acquisition of pest images, so that the accuracy of pest monitoring data can be realized, the specialty of identification and classification is improved, the reliability of pest activity analysis report data basis is established, and errors caused by manual operation are reduced.
As shown in fig. 1, the system comprises a data acquisition device (1), a data uploading device (2), a data preprocessing device (3), a data recognition device (4), a data metering device (5), a data generation device (6) and a database platform (7);
(1) a data acquisition device: the device is used for acquiring insect image data and uploading the insect image data to the data uploading device.
(2) An uploading device; the data uploading device is used for uploading the acquired insect image data to the data uploading data preprocessing device.
(3) A data preprocessing device: the device is used for carrying out noise reduction and data normalization processing on insect image data from the data acquisition device and carrying out feature extraction on the image.
(4) The data identification device: the method is used for quickly identifying the insect image data; specifically, a convolutional neural network is used for deep learning of insect image data.
(5) A data metering device: for counting the identified insects.
(6) The data generation device: for generating insect basic data reports.
(7) A database platform: and the device is connected with all the devices and used for establishing insect image data storage and retrieval, continuously collecting newly added image data and providing the online updating capability of the insect image model.
The device of making pest control facility artificial intelligence image data acquisition system includes: the artificial intelligence vision main frame is used for carrying out training of a recognition model based on the insect sample image data so as to generate an artificial intelligence image data acquisition system of a pest control facility. The camera comprises an anti-shake high-definition camera, the anti-shake high-definition camera can mark serial numbers of shot photos in sequence, and the camera has a WIFI data transmission function.
As shown in fig. 2, a method for collecting image data by using an artificial intelligence image data collection system of a pest control facility is characterized in that: the method comprises the following steps:
the method comprises the following steps: the system is built by adopting a device for manufacturing an artificial intelligent image data acquisition system of the insect pest control facility, namely, artificial intelligent insect recognition and counting functional software is built.
Step two: and collecting the image data of the insect to be identified.
Step three: and comparing the characteristics of the insect image data to be identified with the image models in the insect image database, and finally obtaining an insect basic data report. Specifically, each insect form on the insect sample to be identified is compared with a large number of samples stored in an insect image database to enable the insect form to be matched with the nearest model form in the insect image identification model.
Establishing artificial intelligent insect identification and counting functional software in the first step, as shown in fig. 3, specifically comprising the following steps:
s1: and (3) taking pictures of the insects attached to the insect sticking paper by using an anti-shake high-definition camera to obtain a large number of insect samples and form insect image data.
S2: insect image data are uploaded to the terminal equipment through a WIFI data transmission function of the anti-shake high-definition camera, each insect in the insect image data is manually segmented and labeled in the terminal equipment, and preprocessed insect image data are formed.
S3: the data acquisition device is used for acquiring the preprocessed insect image data, uploading the preprocessed insect image data to the data uploading device, uploading the preprocessed insect image data to the data preprocessing device through the data bed loading device, and the data preprocessing device is used for denoising and data normalizing the preprocessed insect image data, extracting the characteristics of the insect image and specifically extracting the shape and the type of the insect on the insect sticking paper.
S4: and transmitting the insect image after the characteristic extraction to a data recognition device, and repeatedly and deeply learning and training the insect image after the characteristic extraction by using a convolutional neural network in the data recognition device to establish a database for completing insect image parameters.
S5: the data metering device counts the image parameters in the database software, and specifically calculates the number of insects in each kind and the number of insects in all kinds.
S6: the data generating device forms an insect basic data report for the insects which finish the category identification and counting.
S7: the database platform stores and calls the data of each device, and continuously collects the data added by each device so as to expand the insect image data in the database platform, provide the online updating capability of the model and finally form the artificial intelligent insect identification and counting functional software.
The first step comprises two core points, one is the preprocessing of the image data, and the quality of the image quality directly influences the precision of the design and the effect of the recognition algorithm in the image analysis, so that the preprocessing is needed before the image analysis, namely, the feature extraction, the segmentation, the matching, the recognition and the like of the image. The main purposes of image preprocessing are to eliminate irrelevant information in images, recover useful real information, enhance the detectability of relevant information, and simplify data to the maximum extent, thereby improving the reliability of feature extraction, image segmentation, matching and recognition. The general pretreatment process is as follows: graying- > geometric transformation- > image enhancement. The other is to carry out deep learning on the insects marked with names in the insect image data through a convolutional neural network, the convolutional neural network is a multilayer neural network, the convolutional network successfully reduces the dimension of the image identification problem with huge data volume through a series of methods, and finally can be trained, the most typical convolutional network consists of a convolutional layer, a pooling layer and a full connection layer, wherein the convolutional layer is matched with the pooling layer to form a plurality of convolutional groups, the characteristics are extracted layer by layer, classification is finished through a plurality of fully-connected layers, the operation finished by the convolutional layer can be considered as inspired by a local receptive field concept, while the pooling layer is mainly to reduce data dimensionality, in summary, CNN models feature differentiation by convolution, and the order of magnitude of network parameters is reduced through weight sharing and pooling of convolution, and finally classification and other tasks are completed through a traditional neural network.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. Should the skilled person in the industry
It should be understood that the above-mentioned embodiments do not limit the present invention in any way, and all technical solutions obtained by means of equivalent substitution or equivalent transformation fall within the protection scope of the present invention.
Claims (8)
1. The utility model provides a pest control facility artificial intelligence image data acquisition system which characterized in that: the system comprises a data acquisition device, a data uploading device, a data preprocessing device, a data identification device, a data metering device, a data generation device and a database platform;
a data acquisition device: the device is used for acquiring insect image data and uploading the insect image data to the data uploading device;
an uploading device: the data uploading device is used for uploading the acquired insect image data to the data uploading data preprocessing device;
a data preprocessing device: the system is used for carrying out noise reduction and data normalization processing on insect image data from the data acquisition device and carrying out feature extraction on the image;
the data identification device: the method is used for quickly identifying the insect image data;
a data metering device: for counting the identified insects;
the data generation device: for generating insect profile reports;
a database platform: the device is connected with all the devices and used for establishing insect image data storage and retrieval, continuously collecting newly added image data and providing online updating capability of an insect image model;
the device of making pest control facility artificial intelligence image data acquisition system includes: the artificial intelligence vision main frame is used for carrying out training of a recognition model based on the insect sample image data so as to generate an artificial intelligence image data acquisition system of a pest control facility.
2. The pest control facility artificial intelligence image data acquisition system of claim 1, wherein: the camera comprises an anti-shake high-definition camera, and serial numbers of shot photos can be marked by the anti-shake high-definition camera in sequence.
3. A pest control facility artificial intelligence image data acquisition system according to claim 3, wherein: the anti-shake high definition camera has a WIFI data transmission function.
4. An insect pest control facility artificial intelligence image data acquisition system according to claim 1, wherein: the data identification device specifically utilizes a convolutional neural network to carry out deep learning on insect image data.
5. A method for collecting image data by using an artificial intelligence image data collecting system of a pest control facility is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: establishing an artificial intelligent insect recognition and counting functional software by adopting a device for manufacturing an artificial intelligent image data acquisition system of a pest control facility;
step two: collecting insect image data to be identified;
step three: and comparing the characteristics of the insect image data to be identified with the image models in the insect image database, and finally obtaining an insect basic data report.
6. The method for image data acquisition by using an artificial intelligence image data acquisition system of a pest control facility according to claim 5, wherein: the method comprises the following steps that data in an insect image database are derived from insects captured in insect control equipment, the insects are attached to insect sticking paper, the insect control equipment is distributed at different positions, and the insect control equipment comprises an insect killing lamp or a physical sticking device.
7. The method for image data acquisition by using the artificial intelligence image data acquisition system of the pest control facility as claimed in claim 4, wherein: establishing artificial intelligent insect identification and counting functional software in the first step comprises the following steps:
s1: using an anti-shake high-definition camera to photograph the insects attached to the insect sticking paper so as to obtain a large number of insect samples and form insect image data;
s2: uploading the insect image data to terminal equipment through a WIFI data transmission function of the anti-shake high-definition camera, manually dividing each insect in the insect image data in the terminal equipment, and marking a name to form preprocessed insect image data;
s3: acquiring preprocessed insect image data through a data acquisition device, uploading the preprocessed insect image data to a data uploading device, uploading the preprocessed insect image data to a data preprocessing device through a data bed loading device, carrying out noise reduction and data normalization processing on the preprocessed insect image data through the data preprocessing device, and carrying out feature extraction on insect images, specifically extracting the forms and the types of insects on insect sticking paper;
s4: transmitting the insect image after the characteristic extraction to a data recognition device, and in the data recognition device, repeatedly and deeply learning and training the insect image after the characteristic extraction by using a convolutional neural network to establish a database for completing insect image parameters;
s5: the data metering device counts the image parameters in the database software, specifically, the number of insects in each kind and the number of insects in all kinds are calculated;
s6: the data generating device forms an insect basic data report for the insects which finish the category identification and counting;
s7: the database platform stores and calls the data of each device, and continuously collects the data added by each device so as to expand the insect image data in the database platform, provide the online updating capability of the model and finally form the artificial intelligent insect identification and counting functional software.
8. The method for image data acquisition by using an artificial intelligence image data acquisition system of a pest control facility according to claim 5, wherein: and in the third step, the image data of the insect to be identified is compared with the image model in the insect image parameter database, specifically, each insect form on the insect sample to be identified is compared with a large number of samples stored in the insect image database, so that the insect form is matched with the closest model form in the insect image identification model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505589.6A CN111507314A (en) | 2020-06-05 | 2020-06-05 | Artificial intelligence image data acquisition system of insect pest control facility |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505589.6A CN111507314A (en) | 2020-06-05 | 2020-06-05 | Artificial intelligence image data acquisition system of insect pest control facility |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111507314A true CN111507314A (en) | 2020-08-07 |
Family
ID=71870462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010505589.6A Pending CN111507314A (en) | 2020-06-05 | 2020-06-05 | Artificial intelligence image data acquisition system of insect pest control facility |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507314A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7400035B1 (en) | 2022-07-27 | 2023-12-18 | 日本農薬株式会社 | Programs and pest inspection equipment for pest inspection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578089A (en) * | 2017-09-13 | 2018-01-12 | 中国水稻研究所 | A kind of crops lamp lures the automatic identification and method of counting for observing and predicting insect |
| CN109740627A (en) * | 2018-11-27 | 2019-05-10 | 南京邮电大学 | A kind of insect image identification identifying system and its method based on parallel-convolution neural network |
| CN110659659A (en) * | 2018-07-19 | 2020-01-07 | 清华珠三角研究院 | Method and system for intelligently identifying and early warning pests |
| CN110674805A (en) * | 2019-10-11 | 2020-01-10 | 杭州睿琪软件有限公司 | Insect identification method and system |
-
2020
- 2020-06-05 CN CN202010505589.6A patent/CN111507314A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107578089A (en) * | 2017-09-13 | 2018-01-12 | 中国水稻研究所 | A kind of crops lamp lures the automatic identification and method of counting for observing and predicting insect |
| CN110659659A (en) * | 2018-07-19 | 2020-01-07 | 清华珠三角研究院 | Method and system for intelligently identifying and early warning pests |
| CN109740627A (en) * | 2018-11-27 | 2019-05-10 | 南京邮电大学 | A kind of insect image identification identifying system and its method based on parallel-convolution neural network |
| CN110674805A (en) * | 2019-10-11 | 2020-01-10 | 杭州睿琪软件有限公司 | Insect identification method and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7400035B1 (en) | 2022-07-27 | 2023-12-18 | 日本農薬株式会社 | Programs and pest inspection equipment for pest inspection |
| WO2024024434A1 (en) * | 2022-07-27 | 2024-02-01 | 日本農薬株式会社 | Program for pest inspection and pest inspection device |
| JP2024017319A (en) * | 2022-07-27 | 2024-02-08 | 日本農薬株式会社 | Program for inspection of pest and pest inspection device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Seng et al. | Computer vision and machine learning for viticulture technology | |
| CN109726700B (en) | Insect pest recognition early warning method and device based on multiple features | |
| CN112464971A (en) | Method for constructing pest detection model | |
| US11636701B2 (en) | Method for calculating deviation relations of a population | |
| CN107808139A (en) | A kind of real-time monitoring threat analysis method and system based on deep learning | |
| CN108829762B (en) | Vision-based small target identification method and device | |
| CN114818909A (en) | Weed detection method and device based on crop growth characteristics | |
| WO2018120634A1 (en) | Method and apparatus for identifying disease and insect damage | |
| CN108874910B (en) | Vision-based small target recognition system | |
| CN113379769A (en) | Intelligent defense platform for crop diseases and insect pests | |
| CN112150498B (en) | Method and device for determining body state information, storage medium and electronic device | |
| CN113312999A (en) | High-precision detection method and device for diaphorina citri in natural orchard scene | |
| CN116630663A (en) | Intelligent pesticide application method and system based on Internet of things | |
| CN110245604B (en) | Mosquito identification method based on convolutional neural network | |
| CN110472596A (en) | It is a kind of agricultural fining plantation and disaster prevention control system | |
| CN116543347A (en) | Intelligent insect condition on-line monitoring system, method, device and medium | |
| CN116300608A (en) | Intelligent agriculture remote monitoring system based on big data | |
| CN114581948A (en) | Animal face identification method | |
| CN111507314A (en) | Artificial intelligence image data acquisition system of insect pest control facility | |
| CN116824626A (en) | Artificial intelligent identification method for abnormal state of animal | |
| CN114511801A (en) | Insect pest recognition model training method, insect pest monitoring method and electronic equipment | |
| CN118261488A (en) | Intelligent management system based on digital farm | |
| CN115439935A (en) | Food processing safety management method and system based on machine vision | |
| CN113947780B (en) | Sika face recognition method based on improved convolutional neural network | |
| CN116013502A (en) | Initial detection method for sheep diseases |
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: 20200807 |
|
| RJ01 | Rejection of invention patent application after publication |