CN117640898B - Monitoring self-adaptive adjusting method based on agricultural Internet of things technology - Google Patents
Monitoring self-adaptive adjusting method based on agricultural Internet of things technology Download PDFInfo
- Publication number
- CN117640898B CN117640898B CN202311785284.5A CN202311785284A CN117640898B CN 117640898 B CN117640898 B CN 117640898B CN 202311785284 A CN202311785284 A CN 202311785284A CN 117640898 B CN117640898 B CN 117640898B
- Authority
- CN
- China
- Prior art keywords
- farmland
- abnormal
- shooting
- camera
- area
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000005516 engineering process Methods 0.000 title claims abstract description 35
- 230000002159 abnormal effect Effects 0.000 claims abstract description 130
- 230000012010 growth Effects 0.000 claims abstract description 44
- 238000012271 agricultural production Methods 0.000 claims abstract description 14
- 230000008859 change Effects 0.000 claims description 27
- 230000005856 abnormality Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 230000004438 eyesight Effects 0.000 claims description 11
- 230000036541 health Effects 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000013506 data mapping Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 238000012876 topography Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 9
- 241000607479 Yersinia pestis Species 0.000 description 6
- 241000238631 Hexapoda Species 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008635 plant growth Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000029553 photosynthesis Effects 0.000 description 2
- 238000010672 photosynthesis Methods 0.000 description 2
- 208000002720 Malnutrition Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000006065 biodegradation reaction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000001071 malnutrition Effects 0.000 description 1
- 235000000824 malnutrition Nutrition 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000004297 night vision Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 208000015380 nutritional deficiency disease Diseases 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 230000001717 pathogenic effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000003900 soil pollution Methods 0.000 description 1
- 230000008719 thickening Effects 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which belongs to the technical field of monitoring self-adaptive adjustment and comprises the following steps: acquiring the type of a target farmland, and installing corresponding multiple types of cameras based on the type of the target farmland; acquiring a plurality of video data in an agricultural production environment in real time based on the plurality of types of cameras; determining the growth trend of plants in a target farmland according to the plurality of video data, and determining abnormal information; determining an abnormal area of plants in the target farmland according to the abnormal information; and monitoring and self-adapting adjusting the abnormal region based on the agricultural Internet of things technology according to the abnormal coverage and the abnormal coverage type of the abnormal region so as to effectively monitor the abnormal region. The problem that data are not timely and accurate easily occurs in a manual inspection mode is solved.
Description
Technical Field
The invention relates to the technical field of monitoring self-adaptive adjustment, in particular to a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things.
Background
At present, along with population growth and the influence of climate change, agricultural production becomes more and more important, in agricultural production, environmental factors such as temperature, humidity, illumination and the like can all influence crop growth, but traditional agricultural production monitoring methods often rely on manual inspection, and the problems of untimely and inaccurate data and the like easily occur in the mode.
Therefore, the invention provides a monitoring self-adaptive adjusting method based on the technology of the agricultural Internet of things.
Disclosure of Invention
The invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which is characterized in that a plurality of video data of an agricultural production environment are acquired through installing corresponding cameras according to the types of a target farmland, so that the growth trend of plants is determined, an abnormal area is determined, and the abnormal area is subjected to self-adaptive adjustment according to the abnormal coverage surface and the abnormal coverage type of the abnormal area, so that the problems that the data are not timely and accurate easily occur in a manual inspection mode in the background technology are solved.
The invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which comprises the following steps:
step 1: acquiring the type of a target farmland, and installing corresponding multiple types of cameras based on the type of the target farmland;
Step 2: acquiring a plurality of video data in an agricultural production environment in real time based on the plurality of types of cameras;
Step 3: determining the growth trend of plants in a target farmland according to the plurality of video data, and determining abnormal information;
Step 4: determining an abnormal area of plants in the target farmland according to the abnormal information;
Step 5: and monitoring and self-adapting adjusting the abnormal region based on the agricultural Internet of things technology according to the abnormal coverage and the abnormal coverage type of the abnormal region so as to effectively monitor the abnormal region.
Preferably, obtaining the type of the target farmland, installing corresponding multiple types of cameras based on the type of the target farmland, including:
Acquiring a remote sensing image of a target farmland, and extracting structural features of the farmland;
Determining the type of a camera to be installed in a farmland according to the structural characteristics of the farmland, wherein the type of the camera to be installed comprises: wide angle, ultra wide angle, long focal length, ultra long focal length;
Determining a camera mounting point position in the farmland according to the type of the camera to be mounted in the farmland and the structural characteristics of the farmland;
And installing corresponding multiple types of cameras at camera installation points in the farmland.
Preferably, the method for acquiring a plurality of video data in the agricultural production environment in real time based on the plurality of types of cameras comprises the following steps:
acquiring the shooting purpose of a target farmland;
And setting different parameters for the multiple types of cameras based on the shooting purpose, and acquiring multiple video data by using the multiple types of cameras with the parameters set.
Preferably, determining the growth trend of the plants in the target farmland according to the plurality of video data, determining the abnormality information includes:
Preprocessing the collected video data, analyzing the video data based on a computer vision technology, and extracting important information;
acquiring actual growth forms of plants in the corresponding unit area in the target farmland in different time periods based on the important information, and acquiring actual growth trend of the plants in the target farmland;
And extracting a standard growth trend matched with the plants in the corresponding unit area in the target farmland from a farmland database, analyzing the actual growth trend, and determining abnormal information in the corresponding unit area.
Preferably, determining the abnormal area of the plant in the target farmland according to the abnormal information comprises:
acquiring a farmland deployment diagram of the target farmland to establish a farmland health monitoring structure;
And synchronously inputting the first position of the unit area to which the abnormal information belongs and the abnormal information into a farmland health monitoring structure for position communication to obtain an abnormal area.
Preferably, the monitoring and self-adaptive adjustment of the abnormal area based on the technology of the agriculture internet of things according to the abnormal coverage and the abnormal coverage type of the abnormal area comprises the following steps:
confirming the distribution condition of cameras around the abnormal area;
determining available cameras in an abnormal area according to the distribution condition of the cameras;
Generating a camera array according to the dominable cameras of the abnormal area, and determining initial adjustment parameters of each dominable camera and the relative position relation between each dominable camera and the abnormal area according to the arrangement mode of the camera array;
And determining final adjusting parameters of each dominable camera according to the abnormal coverage surface, the abnormal coverage type and the relative position relation of the abnormal region to carry out self-adaptive adjustment on the dominable cameras so as to realize the important monitoring of the abnormal region.
Preferably, preprocessing the acquired video data includes:
determining current shooting setting parameters of a camera, and extracting shooting data samples consistent with the current shooting setting parameters from a video database;
classifying the shot data samples by using a self-organizing feature mapping neural network to obtain classification results;
extracting a first attribute characteristic value of each category in the classification result, and respectively storing the first attribute characteristic value into a corresponding data layer of an attribute characteristic database;
Extracting attribute parameters of the video data acquired based on the current shooting setting parameters according to a principal component analysis method to obtain a second attribute characteristic value;
Inputting the second attribute characteristic value into each data layer of an attribute characteristic database, and obtaining the matching degree output by each data layer;
Determining a plurality of data labels of the collected video data based on the matching degree output by each data layer, and screening matched target results from the collected video data based on the label data mapping relation of the data labels;
searching the target result to determine the data change rate between two adjacent result shooting data;
Counting possible factors influencing the change of video data, carrying out correlation analysis, and screening main factors;
determining the association relation between each result shooting data and the main factor, determining the change rule, and further determining the change trend in the acquisition process;
According to the change trend and the data change rate, determining an abnormal shooting result and a normal shooting result in the acquisition process;
And confirming and rejecting abnormal shooting results as shooting data which are not used for acquiring shooting conditions, and confirming and retaining normal shooting results as shooting data which are used for acquiring shooting conditions.
The reserved shooting data is the preprocessed video data.
Preferably, after installing corresponding multiclass cameras at camera mounting points in farmland, include:
acquiring a shooting area of a camera, and decomposing the shooting area of the camera into a plurality of subareas;
determining definition of each sub-area and shooting degree of the camera, drawing an expected shooting area of the camera according to the shooting degree and the definition of each sub-area, and calculating deviation degree of the expected shooting area and a target area:
; where k is represented as a degree of deviation of the desired photographing region from the target region, N is represented as the number of decomposed sub-regions,/> Definition expressed as the ith decomposition sub-region,/>Expressed as spatial frequency of camera vision, F (u) is expressed as a spatial frequency function of preset camera vision recognition definition,/>Expressed as the included angle between the straight line of sight of the camera looking directly at the target farmland and the vertical direction of the target farmland, and the angle is/isThe cosine value expressed as the included angle between the straight line of sight of the camera looking directly at the target farmland and the vertical direction of the screen of the target farmland is the value of the angle of the straight line of sight of the camera looking directly at the target farmlandExpressed as the degree of shooting by the camera,/>The value of the influence factor caused by the reflection coefficient of the target farmland is [0.15,0.2],/>Region characteristic factor expressed as target region,/>Region feature factors expressed as desired photographing regions;
Comparing the deviation degree of the expected shooting area and the target area with a preset threshold value to obtain a comparison result;
; wherein A is represented as a comparison result, and B is represented as a preset threshold;
and when the comparison result is 1, the expected shooting area and the target area are simultaneously presented and watched by the camera for the camera to select a final shooting area, and when the comparison result is 0, the target area is confirmed to be the final shooting area.
Compared with the prior art, the application has the following beneficial effects:
The corresponding multiple types of cameras are installed through the types of the target farmland, multiple video data of the agricultural production environment are obtained, so that the growth trend of plants is determined, the abnormal area is adaptively adjusted according to the abnormal coverage and the abnormal coverage type of the abnormal area, the abnormal condition of the plants can be timely and accurately obtained, the abnormal condition is improved, and the growth efficiency of crops is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a monitoring adaptive adjustment method based on the technology of the agricultural Internet of things in an embodiment of the invention;
Fig. 2 is a flowchart of installing a corresponding camera according to a farmland type in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1:
The invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which is shown in fig. 1 and comprises the following steps:
step 1: acquiring the type of a target farmland, and installing corresponding multiple types of cameras based on the type of the target farmland;
Step 2: acquiring a plurality of video data in an agricultural production environment in real time based on the plurality of types of cameras;
Step 3: determining the growth trend of plants in a target farmland according to the plurality of video data, and determining abnormal information;
Step 4: determining an abnormal area of plants in the target farmland according to the abnormal information;
Step 5: and monitoring and self-adapting adjusting the abnormal region based on the agricultural Internet of things technology according to the abnormal coverage and the abnormal coverage type of the abnormal region so as to effectively monitor the abnormal region.
In this embodiment, the types of the target farmland are classified according to soil type, moisture content, pH, including: paddy fields, dry lands, vegetable lands, fruit trees lands and livestock lands.
In this embodiment, the multiple camera types include: standard definition lens, ultra-high pixel lens, night vision lens, infrared lens.
In this embodiment, the video data refers to stored images and video information collected by the video monitoring system. Video data generally includes: video content, frame rate, resolution, number of color bits, dynamic range, encoder.
In this example, the growth trend of a plant refers to the growth process of the plant from seed to maturity per unit time, including growth rate, growth stage, and final yield.
In this embodiment, the abnormality information means, for example: abnormal plant growth, plant diseases and insect pests, insufficient water and insufficient photosynthesis.
In this example, the abnormal region of the plant in the target farmland refers to a plant region where problems such as slow growth, outbreak of plant diseases and insect pests, malnutrition and the like may occur. Such as: abnormally high plants, areas where pests are severe, areas where soil nutrients are insufficient.
In this embodiment, the abnormal coverage refers to how large the area of the target farmland is in which the abnormal situation exists, for example, the coverage is about 5 square.
In this embodiment, the abnormal coverage type includes:
Physical anomaly: such as insect pest and mechanical damage.
Biological abnormalities: such as abnormal plant growth and outbreak of plant diseases and insect pests.
Chemical abnormality: such as soil pollution, fertilizer or pesticide overdose.
Bio-chemical abnormalities: such as pathogen infection and biodegradation abnormality.
In this embodiment, effective monitoring means that useful information can be obtained from the monitoring video, for example, if the monitoring is all black screen, the effective monitoring is not effective.
The beneficial effects of the technical scheme are as follows: the corresponding multiple types of cameras are installed through the types of the target farmland, multiple video data of the agricultural production environment are obtained, so that the growth trend of plants is determined, the abnormal area is adaptively adjusted according to the abnormal coverage and the abnormal coverage type of the abnormal area, the abnormal condition of the plants can be timely and accurately obtained, the abnormal condition is improved, and the growth efficiency of crops is improved.
Example 2:
The invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, as shown in fig. 2, the type of a target farmland is obtained, and a plurality of corresponding cameras are installed based on the type of the target farmland, comprising the following steps:
s01: acquiring a remote sensing image of a target farmland, and extracting structural features of the farmland;
S02: determining the type of a camera to be installed in a farmland according to the structural characteristics of the farmland, wherein the type of the camera to be installed comprises: wide angle, ultra wide angle, long focal length, ultra long focal length;
s03: determining a camera mounting point position in the farmland according to the type of the camera to be mounted in the farmland and the structural characteristics of the farmland;
s04: and installing corresponding multiple types of cameras at camera installation points in the farmland.
In this embodiment, the remote sensing image refers to image data of a farmland area obtained by using a remote sensing technology, and includes data in aspects of shape, color, texture, spatial information and the like of the farmland. These data may reflect information on the ecology of the farmland, agricultural production, soil type, moisture status, and crop growth status.
In this embodiment, the structural features of the farmland include the shape, size, position, orientation, obstacles and topography of the farmland, which may be obtained by remote sensing image data, for example, the area and volume of the farmland may be estimated by measuring the shape and size of the farmland, the reasonable planning and layout of the farmland may be determined by analyzing the position and orientation of the farmland, and the soil, moisture and vegetation conditions of the farmland may be determined by detecting the obstacles and topography of the farmland.
The beneficial effects of the technical scheme are as follows: the remote sensing image through the target farmland draws the structural feature in farmland, can rationally plan the overall arrangement in farmland according to the characteristic, improves the productivity and the benefit in farmland, and is further, selects suitable camera to monitor the farmland, can acquire useful video data, is convenient for manage the farmland.
Example 3:
the invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which is based on the fact that a plurality of video data in an agricultural production environment are collected in real time by a plurality of cameras, and comprises the following steps:
acquiring the shooting purpose of a target farmland;
And setting different parameters for the multiple types of cameras based on the shooting purpose, and acquiring multiple video data by using the multiple types of cameras with the parameters set.
In this embodiment, the purpose of photographing is to photograph what is done, for example, to monitor whether someone damages the farmland, and the daily growth of the farmland.
In this embodiment, setting different parameters ensures that basic information such as type, size, and function of the camera matches the set parameters, such as type 1: size 1.5 times, parameter 1=120, parameter 2=0.3; type 2: size 1.3 times, parameter 1=150, parameter 2=0.2, and type 1 is suitable for far shooting, so parameter 1 is set large to obtain better image quality, type 2 is suitable for near shooting, and parameter 2 is set small to reduce image quality.
The beneficial effects of the technical scheme are as follows: through the shooting purpose that acquires the farmland, set up suitable camera parameter, can improve the acquisition to the shooting condition in farmland, avoid because the parameter is unsuitable, lead to shooting data not ideal, can't acquire useful information.
Example 4:
The invention provides a monitoring self-adaptive adjusting method based on the technology of the agricultural Internet of things, which determines the growth trend of plants in a target farmland according to a plurality of video data, determines abnormal information and comprises the following steps:
Preprocessing the collected video data, analyzing the video data based on a computer vision technology, and extracting important information;
acquiring actual growth forms of plants in the corresponding unit area in the target farmland in different time periods based on the important information, and acquiring actual growth trend of the plants in the target farmland;
And extracting a standard growth trend matched with the plants in the corresponding unit area in the target farmland from a farmland database, analyzing the actual growth trend, and determining abnormal information in the corresponding unit area.
In this embodiment, preprocessing refers to compressing, encoding, cropping, and converting video data.
In this embodiment, the computer vision technology refers to processing, analyzing and identifying visual information such as images, videos, and the like by using a computer, for example: image processing, video processing, pattern recognition.
In this embodiment, the important information means, for example, person identification, plant identification.
In this example, the growth morphology refers to morphological features exhibited by the plant during growth, such as height of the plant, shape and size of the leaves.
In this example, the growth trend refers to the directional change exhibited by plants during growth, which generally includes growing, thickening, and changing shape in a certain direction.
In this example, abnormality information means that, for example, on the tenth day of plant growth, it is required to grow to 10 cm, but the actual growth height is only 3 cm, which is an abnormality in which the cause of abnormality such as insufficient moisture or insufficient photosynthesis time is acquired.
The beneficial effects of the technical scheme are as follows: the video data is analyzed by utilizing a computer vision technology to obtain important information, and the actual growth form of a target farmland in different time periods is determined according to the important information, so that the actual growth trend is determined, and the actual growth trend is compared with the standard growth trend in a corresponding unit in a farmland database to determine abnormal information, so that abnormal conditions can be timely improved, and farmland productivity is improved.
Example 5:
The invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which determines an abnormal area of plants in a target farmland according to the abnormal information, and comprises the following steps:
acquiring a farmland deployment diagram of the target farmland to establish a farmland health monitoring structure;
And synchronously inputting the first position of the unit area to which the abnormal information belongs and the abnormal information into a farmland health monitoring structure for position communication to obtain an abnormal area.
In this embodiment, the plot of farmland deployment generally refers to the spatial arrangement of crops and other plants in the farmland.
In this embodiment, the farmland health monitoring structure is a real-time monitoring system for farmland pest and disease and growth conditions.
In this embodiment, the first position refers to a specific position having abnormality information.
In this embodiment, the abnormal area refers to an abnormal area generated by, for example, the temperature data of the temperature sensor in the farmland health monitoring structure continuously exceeding the normal range, or the illuminance of the light sensor exceeding the normal range.
The beneficial effects of the technical scheme are as follows: a farmland health monitoring structure is established through a farmland deployment diagram of a target farmland, the first position of a unit area corresponding to abnormal information and the abnormal information are input for position communication, and an abnormal area is determined, so that farmers can be helped to find and process the abnormal conditions in time, and the health of the farmland and the growth of crops are ensured.
Example 6:
The invention provides a monitoring self-adaptive adjustment method based on an agricultural Internet of things technology, which is used for monitoring self-adaptive adjustment of an abnormal region based on the agricultural Internet of things technology according to the abnormal coverage and the abnormal coverage type of the abnormal region, and comprises the following steps:
confirming the distribution condition of cameras around the abnormal area;
determining available cameras in an abnormal area according to the distribution condition of the cameras;
Generating a camera array according to the dominable cameras of the abnormal area, and determining initial adjustment parameters of each dominable camera and the relative position relation between each dominable camera and the abnormal area according to the arrangement mode of the camera array;
And determining final adjusting parameters of each dominable camera according to the abnormal coverage surface, the abnormal coverage type and the relative position relation of the abnormal region to carry out self-adaptive adjustment on the dominable cameras so as to realize the important monitoring of the abnormal region.
In this embodiment, the distribution refers to the positions and the number of cameras around the abnormal area.
In this embodiment, the available cameras refer to the number of cameras available in a certain period of time.
In this embodiment, the camera array is composed of a plurality of camera lenses, and each lens is responsible for capturing images at a specific angle.
In this embodiment, the initial adjustment parameters refer to parameters such as focal length, gain, exposure time, etc. of the camera.
In this embodiment, the relative positional relationship refers to where the available camera is located in the abnormal area, such as directly above.
In this embodiment, the final adjustment parameter refers to a parameter that adjusts the camera according to actual conditions, for example, when shooting at night, the exposure time needs to be increased; in the backlight case, the white balance needs to be adjusted.
In this embodiment, the adaptive adjustment refers to that in the shooting process of the camera, parameters such as exposure time and gain of the camera are automatically adjusted according to actual conditions of ambient light, in the adaptive adjustment, the camera automatically detects intensity and color temperature of the ambient light, and then corresponding parameter adjustment is performed according to actual conditions so as to adapt to different light environments and shooting objects.
The beneficial effects of the technical scheme are as follows: the controllable cameras are determined according to the distribution conditions of the cameras around the abnormal area, so that the monitoring effect of the cameras can be guaranteed, further, the camera array is generated according to the controllable cameras in the abnormal area, the initial adjusting parameters of the cameras and the relative position relation between the cameras and the abnormal area are determined, the parameters of the cameras can be adjusted according to actual conditions, the quality of monitoring video of the cameras is guaranteed, the shooting effect of the cameras is effectively improved, and shooting is more convenient and efficient.
Example 7:
the invention provides a monitoring self-adaptive adjustment method based on the technology of the agricultural Internet of things, which is used for preprocessing collected video data and comprises the following steps:
determining current shooting setting parameters of a camera, and extracting shooting data samples consistent with the current shooting setting parameters from a video database;
classifying the shot data samples by using a self-organizing feature mapping neural network to obtain classification results;
extracting a first attribute characteristic value of each category in the classification result, and respectively storing the first attribute characteristic value into a corresponding data layer of an attribute characteristic database;
Extracting attribute parameters of the video data acquired based on the current shooting setting parameters according to a principal component analysis method to obtain a second attribute characteristic value;
Inputting the second attribute characteristic value into each data layer of an attribute characteristic database, and obtaining the matching degree output by each data layer;
Determining a plurality of data labels of the collected video data based on the matching degree output by each data layer, and screening matched target results from the collected video data based on the label data mapping relation of the data labels;
searching the target result to determine the data change rate between two adjacent result shooting data;
Counting possible factors influencing the change of video data, carrying out correlation analysis, and screening main factors;
determining the association relation between each result shooting data and the main factor, determining the change rule, and further determining the change trend in the acquisition process;
According to the change trend and the data change rate, determining an abnormal shooting result and a normal shooting result in the acquisition process;
And confirming and rejecting abnormal shooting results as shooting data which are not used for acquiring shooting conditions, and confirming and retaining normal shooting results as shooting data which are used for acquiring shooting conditions.
The reserved shooting data is the preprocessed video data.
In this embodiment, the photographing setting parameters refer to some setting parameters such as aperture, shutter speed, ISO, white balance, focal length at the time of photographing.
In this embodiment, the photographed data sample refers to a previously photographed video data sample as the current photographing parameter.
In this embodiment, the self-organizing feature mapping neural network is a deep learning model that is capable of segmenting an input image into different regions and extracting features in each region.
In this embodiment, the first attribute feature value refers to a feature value of a captured data sample, such as frame rate, resolution.
In this embodiment, the second attribute feature value refers to a feature value of video data photographed under the current setting parameter.
In this embodiment, the attribute feature database is a database system for storing and managing a large number of attribute features, and the database is constructed based on different data layers for storing and managing data of matching features.
In this embodiment, principal component analysis is a commonly used data dimension reduction technique for reducing dimensions of a high-dimensional dataset into a low-dimensional dataset while retaining main information of the dataset, and acquiring attribute features of the data according to the main information.
In this embodiment, the matching degree refers to the similarity between the feature value of the actual shooting data and the feature value corresponding to the attribute feature database, and the closer the feature value is, the higher the matching degree is.
In this embodiment, a data tag refers to a tag or label used in video data to identify and distinguish different categories, such as frame number, length, encoding.
In this embodiment, the rate of change of the data is used to measure the degree of change of the video data over time.
In this embodiment, possible factors are, for example: media, network conditions, hardware devices.
In this embodiment, the main factor is, for example, a media medium, and the quality of the video data gradually increases due to the lifting of the media medium, so that the media medium in the acquisition process is determined according to the relationship, and the quality change trend of the video data is determined.
In this embodiment, the abnormal photographing result generally refers to photographing results that should not normally occur, such as a black screen, where the data change rate is infinite and the change trend is different from the original classification and a mutation occurs.
The beneficial effects of the technical scheme are as follows: the method comprises the steps of determining shooting setting of a camera, extracting a data sample from a video database to classify, extracting classification results and characteristic values in the process, inputting the characteristic values into the database to obtain matching degree, determining data labels according to the matching degree, screening the matching results, counting possible influencing factors and screening main factors if the data change rate of a target result is large, analyzing the association relation between shooting data and the main factors of the result, determining the change trend, determining abnormal and normal shooting results, retaining useful data, improving the acquisition of the useful data, and avoiding the need to watch a large amount of video data.
Example 8:
The invention provides a monitoring self-adaptive adjustment method based on the technology of agricultural Internet of things, which comprises the following steps of:
acquiring a shooting area of a camera, and decomposing the shooting area of the camera into a plurality of subareas;
determining definition of each sub-area and shooting degree of the camera, drawing an expected shooting area of the camera according to the shooting degree and the definition of each sub-area, and calculating deviation degree of the expected shooting area and a target area:
; where k is represented as a degree of deviation of the desired photographing region from the target region, N is represented as the number of decomposed sub-regions,/> Definition expressed as the ith decomposition sub-region,/>Expressed as spatial frequency of camera vision, F (u) is expressed as a spatial frequency function of preset camera vision recognition definition,/>Expressed as the included angle between the straight line of sight of the camera looking directly at the target farmland and the vertical direction of the target farmland, and the angle is/isThe cosine value expressed as the included angle between the straight line of sight of the camera looking directly at the target farmland and the vertical direction of the screen of the target farmland is the value of the angle of the straight line of sight of the camera looking directly at the target farmlandExpressed as the degree of shooting by the camera,/>The value of the influence factor caused by the reflection coefficient of the target farmland is [0.15,0.2],/>Region characteristic factor expressed as target region,/>Region feature factors expressed as desired photographing regions;
Comparing the deviation degree of the expected shooting area and the target area with a preset threshold value to obtain a comparison result;
; wherein A is represented as a comparison result, and B is represented as a preset threshold;
and when the comparison result is 1, the expected shooting area and the target area are simultaneously presented and watched by the camera for the camera to select a final shooting area, and when the comparison result is 0, the target area is confirmed to be the final shooting area.
In this embodiment, the photographing area refers to a range in which the camera can photograph plants when photographing a farmland. In this embodiment, sub-areas refer to the areas in the shot area where, due to the special needs of the camera,
The shooting needs to be divided into a plurality of sub-areas, for example, in shooting, different sub-areas need to be selected according to factors such as focal length, picture size, shooting angle and the like of a lens so as to obtain the best effect.
In this embodiment, the shooting degree of the camera refers to the number of actual light rays or digital signals that can be captured by the camera during shooting.
In this embodiment, the region feature factor of the photographed region refers to an index for measuring certain region features of the photographed scene, such as overall color, brightness, contrast, and edge ambiguity of the scene, in photographing.
In this embodiment of the present invention, the process is performed,The value of (2) is in the range of 0 DEG to 90 deg.
The beneficial effects of the technical scheme are as follows: the shooting area of the camera is divided into a plurality of subareas, the definition of each subarea and the shooting degree of the camera are determined, the expected shooting area of the camera is drawn, the deviation degree of the expected shooting area and the target area is calculated, the deviation degree is compared with a preset threshold value, and a comparison result is obtained, so that the final shooting area is determined, the shooting to the greatest extent is ensured to be the expected shooting area, and the shooting efficiency is improved.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (6)
1. A monitoring self-adaptive adjusting method based on the technology of the agricultural Internet of things is characterized by comprising the following steps:
step 1: acquiring the type of a target farmland, and installing corresponding multiple types of cameras based on the type of the target farmland;
Step 2: acquiring a plurality of video data in an agricultural production environment in real time based on the plurality of types of cameras;
Step 3: determining the growth trend of plants in a target farmland according to the plurality of video data, and determining abnormal information;
Step 4: determining an abnormal area of plants in the target farmland according to the abnormal information;
Step 5: according to the abnormal coverage and the abnormal coverage type of the abnormal area, monitoring and self-adaptive adjustment are carried out on the abnormal area based on the agricultural Internet of things technology so as to realize effective monitoring of the abnormal area;
wherein, step1 includes:
Acquiring a remote sensing image of a target farmland, and extracting structural features of the farmland;
Determining the type of a camera to be installed in a farmland according to the structural characteristics of the farmland, wherein the type of the camera to be installed comprises: wide angle, ultra wide angle, long focal length, ultra long focal length;
Determining a camera mounting point position in the farmland according to the type of the camera to be mounted in the farmland and the structural characteristics of the farmland;
installing corresponding multiple types of cameras at camera installation points in a farmland;
Wherein, step5 includes:
confirming the distribution condition of cameras around the abnormal area;
determining available cameras in an abnormal area according to the distribution condition of the cameras;
Generating a camera array according to the dominable cameras of the abnormal area, and determining initial adjustment parameters of each dominable camera and the relative position relation between each dominable camera and the abnormal area according to the arrangement mode of the camera array;
determining final adjusting parameters of each dominable camera according to the abnormal coverage surface, the abnormal coverage type and the relative position relation of the abnormal region to adaptively adjust the dominable cameras so as to realize the important monitoring of the abnormal region;
the abnormal coverage refers to the size of an area with abnormal conditions in the target farmland;
The abnormal coverage type includes: physical abnormalities, biological abnormalities, chemical abnormalities, and bio-chemical abnormalities;
structural features of farmlands include shape, size, position, orientation, obstructions, and topography of the farmlands.
2. The method for monitoring and adaptively adjusting based on the technology of the internet of things of agriculture according to claim 1, wherein the step of collecting a plurality of video data in an agricultural production environment in real time based on the plurality of types of cameras comprises the steps of:
acquiring the shooting purpose of a target farmland;
And setting different parameters for the multiple types of cameras based on the shooting purpose, and acquiring multiple video data by using the multiple types of cameras with the parameters set.
3. The monitoring self-adaptive adjusting method based on the technology of the agricultural Internet of things according to claim 1,
The method is characterized in that the growth trend of plants in a target farmland is determined according to a plurality of video data, and abnormal information is determined, and the method comprises the following steps:
Preprocessing the collected video data, analyzing the video data based on a computer vision technology, and extracting important information;
acquiring actual growth forms of plants in the corresponding unit area in the target farmland in different time periods based on the important information, and acquiring actual growth trend of the plants in the target farmland;
And extracting a standard growth trend matched with the plants in the corresponding unit area in the target farmland from a farmland database, analyzing the actual growth trend, and determining abnormal information in the corresponding unit area.
4. The method for monitoring and adaptively adjusting based on the technology of the internet of things according to claim 1, wherein determining an abnormal area of plants in a target farmland according to the abnormality information comprises:
acquiring a farmland deployment diagram of the target farmland to establish a farmland health monitoring structure;
And synchronously inputting the first position of the unit area to which the abnormal information belongs and the abnormal information into a farmland health monitoring structure for position communication to obtain an abnormal area.
5. The method for monitoring and adaptively adjusting based on the technology of the internet of things according to claim 3, wherein preprocessing the collected video data comprises the following steps:
determining current shooting setting parameters of a camera, and extracting shooting data samples consistent with the current shooting setting parameters from a video database;
classifying the shot data samples by using a self-organizing feature mapping neural network to obtain classification results;
extracting a first attribute characteristic value of each category in the classification result, and respectively storing the first attribute characteristic value into a corresponding data layer of an attribute characteristic database;
Extracting attribute parameters of the video data acquired based on the current shooting setting parameters according to a principal component analysis method to obtain a second attribute characteristic value;
Inputting the second attribute characteristic value into each data layer of an attribute characteristic database, and obtaining the matching degree output by each data layer;
Determining a plurality of data labels of the collected video data based on the matching degree output by each data layer, and screening matched target results from the collected video data based on the label data mapping relation of the data labels;
searching the target result to determine the data change rate between two adjacent result shooting data;
Counting possible factors influencing the change of video data, carrying out correlation analysis, and screening main factors;
determining the association relation between each result shooting data and the main factor, determining the change rule, and further determining the change trend in the acquisition process;
According to the change trend and the data change rate, determining an abnormal shooting result and a normal shooting result in the acquisition process;
confirming and rejecting abnormal shooting results as shooting data which are not used for acquiring shooting conditions, and confirming and retaining normal shooting results as shooting data which are used for acquiring shooting conditions;
The reserved shooting data is the preprocessed video data.
6. The method for monitoring and self-adaptive adjustment based on the technology of the agricultural internet of things according to claim 1, wherein after installing the corresponding multiple types of cameras at the camera installation points in the farmland, the method comprises the following steps:
acquiring a shooting area of a camera, and decomposing the shooting area of the camera into a plurality of subareas;
determining definition of each sub-area and shooting degree of the camera, drawing an expected shooting area of the camera according to the shooting degree and the definition of each sub-area, and calculating deviation degree of the expected shooting area and a target area:
; where k is represented as a degree of deviation of the desired photographing region from the target region, N is represented as the number of decomposed sub-regions,/> Definition expressed as the ith decomposition sub-region,/>Expressed as spatial frequency of camera vision, F (u) is expressed as a spatial frequency function of preset camera vision recognition definition,/>Expressed as the included angle between the straight line of sight of the camera looking directly at the target farmland and the vertical direction of the target farmland, and the angle is/isThe cosine value expressed as the included angle between the straight line of sight of the camera looking directly at the target farmland and the vertical direction of the screen of the target farmland is the value of the angle of the straight line of sight of the camera looking directly at the target farmlandExpressed as the degree of shooting by the camera,/>The value of the influence factor caused by the reflection coefficient of the target farmland is [0.15,0.2],/>Region characteristic factor expressed as target region,/>Region feature factors expressed as desired photographing regions;
Comparing the deviation degree of the expected shooting area and the target area with a preset threshold value to obtain a comparison result;
; wherein A is represented as a comparison result, and B is represented as a preset threshold;
and when the comparison result is 1, the expected shooting area and the target area are simultaneously presented and watched by the camera for the camera to select a final shooting area, and when the comparison result is 0, the target area is confirmed to be the final shooting area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311785284.5A CN117640898B (en) | 2023-12-22 | 2023-12-22 | Monitoring self-adaptive adjusting method based on agricultural Internet of things technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311785284.5A CN117640898B (en) | 2023-12-22 | 2023-12-22 | Monitoring self-adaptive adjusting method based on agricultural Internet of things technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117640898A CN117640898A (en) | 2024-03-01 |
| CN117640898B true CN117640898B (en) | 2024-06-07 |
Family
ID=90032248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311785284.5A Active CN117640898B (en) | 2023-12-22 | 2023-12-22 | Monitoring self-adaptive adjusting method based on agricultural Internet of things technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117640898B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016062131A (en) * | 2014-09-16 | 2016-04-25 | 日本電気株式会社 | Video monitoring device |
| CN105791767A (en) * | 2016-03-11 | 2016-07-20 | 柳州好顺科技有限公司 | Straw burning monitoring system having self-regulating function |
| JP2020178617A (en) * | 2019-04-25 | 2020-11-05 | 株式会社クボタ | Harvester |
| CN112714410A (en) * | 2021-01-25 | 2021-04-27 | 中北大学 | Agricultural monitoring method with movable nodes |
| CN214670211U (en) * | 2021-04-08 | 2021-11-09 | 南通七和互联网络科技有限公司 | Intelligent control device based on internet of things |
| KR20210147705A (en) * | 2020-05-29 | 2021-12-07 | 농업회사법인 한국도시농업 주식회사 | 3D conversion technology of volume evaluation method for harvesting from 2D images of agricultural products and harvesting of target crops by robots operating based on this and pest management system, and method thereof |
| CN114900671A (en) * | 2022-07-12 | 2022-08-12 | 深圳市盈润科技有限公司 | Comprehensive management service system and method based on agricultural Internet of things |
| CN114998335A (en) * | 2022-08-02 | 2022-09-02 | 江苏三棱智慧物联发展股份有限公司 | Internet of things video monitoring system and monitoring method thereof |
| CN117008505A (en) * | 2023-07-05 | 2023-11-07 | 浪潮云洲(山东)工业互联网有限公司 | Crop state monitoring method, device and medium based on identification analysis |
-
2023
- 2023-12-22 CN CN202311785284.5A patent/CN117640898B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016062131A (en) * | 2014-09-16 | 2016-04-25 | 日本電気株式会社 | Video monitoring device |
| CN105791767A (en) * | 2016-03-11 | 2016-07-20 | 柳州好顺科技有限公司 | Straw burning monitoring system having self-regulating function |
| JP2020178617A (en) * | 2019-04-25 | 2020-11-05 | 株式会社クボタ | Harvester |
| KR20210147705A (en) * | 2020-05-29 | 2021-12-07 | 농업회사법인 한국도시농업 주식회사 | 3D conversion technology of volume evaluation method for harvesting from 2D images of agricultural products and harvesting of target crops by robots operating based on this and pest management system, and method thereof |
| CN112714410A (en) * | 2021-01-25 | 2021-04-27 | 中北大学 | Agricultural monitoring method with movable nodes |
| CN214670211U (en) * | 2021-04-08 | 2021-11-09 | 南通七和互联网络科技有限公司 | Intelligent control device based on internet of things |
| CN114900671A (en) * | 2022-07-12 | 2022-08-12 | 深圳市盈润科技有限公司 | Comprehensive management service system and method based on agricultural Internet of things |
| CN114998335A (en) * | 2022-08-02 | 2022-09-02 | 江苏三棱智慧物联发展股份有限公司 | Internet of things video monitoring system and monitoring method thereof |
| CN117008505A (en) * | 2023-07-05 | 2023-11-07 | 浪潮云洲(山东)工业互联网有限公司 | Crop state monitoring method, device and medium based on identification analysis |
Non-Patent Citations (2)
| Title |
|---|
| "智慧农业远程监控***开发与研究";李梦迪;中国优秀硕士学位论文全文数据库;20210215;全文 * |
| 段丽英等."颗粒图像识别及计数在良种品质测定中的应用".石家庄学院学报.2011,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117640898A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Identification of grape diseases using image analysis and BP neural networks | |
| RU2735151C2 (en) | Weeds identification in natural environment | |
| US10796161B2 (en) | System and method for identifying a number of insects in a horticultural area | |
| Qureshi et al. | Machine vision for counting fruit on mango tree canopies | |
| Zhu et al. | In-field automatic observation of wheat heading stage using computer vision | |
| CN110455340B (en) | Agricultural product planting environment detection system based on big data | |
| Ruiz-Ruiz et al. | Testing different color spaces based on hue for the environmentally adaptive segmentation algorithm (EASA) | |
| Lu et al. | A novel image measurement algorithm for common mushroom caps based on convolutional neural network | |
| Bhujel et al. | Detection of gray mold disease and its severity on strawberry using deep learning networks | |
| Ji et al. | In-field automatic detection of maize tassels using computer vision | |
| WO2020000043A1 (en) | Plant growth feature monitoring | |
| CN113033279A (en) | Crop fine classification method and system based on multi-source remote sensing image | |
| CN115861721B (en) | Livestock and poultry breeding spraying equipment state identification method based on image data | |
| CN114818909A (en) | Weed detection method and device based on crop growth characteristics | |
| CN114998335A (en) | Internet of things video monitoring system and monitoring method thereof | |
| Fiona et al. | Automated detection of plant diseases and crop analysis in agriculture using image processing techniques: A survey | |
| Zhou et al. | Research on cucumber downy mildew detection system based on SVM classification algorithm | |
| Loresco et al. | Segmentation of lettuce plants using super pixels and thresholding methods in smart farm hydroponics setup | |
| Steward et al. | Real-time machine vision weed-sensing | |
| Xu et al. | Research and application on corn crop identification and positioning method based on Machine vision | |
| Steward et al. | Real-time weed detection in outdoor field conditions | |
| CN117640898B (en) | Monitoring self-adaptive adjusting method based on agricultural Internet of things technology | |
| Ashok Kumar et al. | A review on crop and weed segmentation based on digital images | |
| WO2020172546A1 (en) | Machine vision sensor system for optimal growing conditions | |
| CN117036926A (en) | Weed identification method integrating deep learning and image processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |