CN116310489A - Agricultural pest monitoring system and method based on big data - Google Patents
Agricultural pest monitoring system and method based on big data Download PDFInfo
- Publication number
- CN116310489A CN116310489A CN202211706884.3A CN202211706884A CN116310489A CN 116310489 A CN116310489 A CN 116310489A CN 202211706884 A CN202211706884 A CN 202211706884A CN 116310489 A CN116310489 A CN 116310489A
- Authority
- CN
- China
- Prior art keywords
- image
- branch
- leaf
- pest
- plant
- 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.)
- Withdrawn
Links
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 122
- 238000012544 monitoring process Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 title claims abstract description 11
- 201000010099 disease Diseases 0.000 claims abstract description 59
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 59
- 241000238631 Hexapoda Species 0.000 claims abstract description 47
- 239000013598 vector Substances 0.000 claims description 21
- 238000007726 management method Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 9
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 7
- 230000000295 complement effect Effects 0.000 claims description 6
- 230000000153 supplemental effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 4
- 241000196324 Embryophyta Species 0.000 description 87
- 230000009286 beneficial effect Effects 0.000 description 7
- 239000011800 void material Substances 0.000 description 7
- 240000004050 Pentaglottis sempervirens Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
Abstract
The invention provides an agricultural pest monitoring system and method based on big data, wherein the system comprises: the branch and leaf image acquisition module is used for acquiring branch and leaf images of crops in the agricultural garden through the camera trolley; the plant disease and insect pest image acquisition module is used for acquiring plant disease and insect pest images of the crops from the big data platform; the plant disease and insect pest crop determining module is used for determining plant disease and insect pest crops based on the branch and leaf images and the plant disease and insect pest images; and the early warning module is used for early warning the pest and disease crops to management personnel in the agricultural garden. According to the agricultural pest monitoring system and method based on big data, a plurality of personnel with pest judgment experience of crops do not need to be arranged for checking the pests of the crops regularly, and labor cost is reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an agricultural pest monitoring system and method based on big data.
Background
At present, a large number of crops are planted in an agricultural garden, a plurality of personnel with crop pest judgment experience are required to be arranged for checking the crop pest at regular intervals, and labor cost is high.
Thus, a solution is needed.
Disclosure of Invention
The invention aims to provide an agricultural pest monitoring system based on big data, which does not need to arrange a plurality of personnel with pest judgment experience to regularly check the pests of crops one by one, and reduces the labor cost.
The embodiment of the invention provides an agricultural pest monitoring system based on big data, which comprises the following components:
the branch and leaf image acquisition module is used for acquiring branch and leaf images of crops in the agricultural garden through the camera trolley;
the plant disease and insect pest image acquisition module is used for acquiring plant disease and insect pest images of the crops from the big data platform;
the plant disease and insect pest crop determining module is used for determining plant disease and insect pest crops based on the branch and leaf images and the plant disease and insect pest images;
and the early warning module is used for early warning the pest and disease crops to management personnel in the agricultural garden.
Preferably, the branch and leaf image acquisition module acquires the branch and leaf image of crops in the agricultural garden through the camera trolley, and performs the following operations:
acquiring a bird's eye view image of the crop;
planning a tour route of the camera trolley based on the aerial view image;
controlling the camera trolley to move in the agricultural garden based on the inspection route;
when the camera dolly reaches to the side of any target plant in the crops, controlling the camera dolly to shoot an external image of the target plant;
determining a supplementary shooting position of the target plant, which needs to be subjected to supplementary shooting, based on the external image;
controlling the camera trolley to shoot the internal image of the supplementary shooting position;
and taking the external image and the internal image as branch and leaf images.
Preferably, the branch and leaf image acquisition module plans a route for shooting the dolly based on the aerial view image, and performs the following operations:
extracting a park road from the aerial view image and a plant gap connected with the park road;
dividing the plant space into a plurality of space segments based on a preset segmentation template;
traversing the gap sections from near to far according to the position relation between the gap sections and the park roads;
performing feature extraction on the traversed gap segments based on a preset first feature extraction template every time, and obtaining a gap feature set;
matching the gap characteristic set with a preset standard gap characteristic set corresponding to the crops to obtain a first matching degree;
if the first matching degree is smaller than a preset first matching degree threshold value, splicing the previously traversed gap segments to be used as the longest moving gap;
extracting plant distribution from the aerial view image;
planning a route of inspection of the camera trolley based on the park road, the longest moving gap and the plant distribution.
Preferably, the branch and leaf image acquisition module determines a repair shooting position of the target plant, where repair shooting is required, based on the external image, and performs the following operations:
determining whether image acquisition is necessary for the back of the leaf of the target plant based on the external image;
if yes, taking the position of the target plant corresponding to the back of the leaf as a supplementary shooting position;
and/or the number of the groups of groups,
determining whether image acquisition is necessary on the back of the branches and stems of the target plant based on the external image;
if yes, taking the position of the target plant corresponding to the back of the branch and stem as a supplementary shooting position;
and/or the number of the groups of groups,
and determining a branch and leaf shooting blind area of the target plant based on the external image, and taking the position of the branch and leaf shooting blind area as a supplementary shooting position.
Preferably, the branch and leaf image acquisition module determines whether the image acquisition is necessary for the back of the leaf of the target plant based on the external image, and performs the following operations:
extracting a leaf contour from the external image;
extracting the leaf profile based on a preset second feature extraction template to obtain a first profile feature set;
matching the first contour feature set with a preset first standard contour feature set corresponding to the crops to obtain a second matching degree;
if the second matching degree is smaller than or equal to a preset second matching degree threshold value, determining that the back surface of the leaf of the target plant is necessary to acquire an image.
Preferably, the branch and leaf image acquisition module determines whether image acquisition is necessary for the back of the branch and stem of the target plant based on the external image, including:
extracting a branch and stem contour from the external image;
extracting the branch and stem outline based on a preset third feature extraction template to obtain a second outline feature set;
matching the second contour feature set with a preset second standard contour feature set corresponding to the crops to obtain a third matching degree;
if the third matching degree is smaller than or equal to a preset third matching degree threshold value, determining that the back of the branch and stem of the target plant is necessary to acquire an image.
Preferably, the branch and leaf image acquisition module controls the camera trolley to shoot the internal image of the supplementary shooting position, and performs the following operations:
extracting branch and leaf gaps from the external image;
determining the supplementary shooting position beside the branch and leaf gap, and taking the supplementary shooting position as a target supplementary shooting position;
constructing a direction vector based on the target supplemental photographing position and a straight line direction from the target supplemental photographing position to the gap center of the branch and leaf gap;
when the vector included angles between every two continuous N direction vectors fall in a preset vector included angle interval, determining a relative centering position from the target complement shooting positions corresponding to the continuous N direction vectors;
taking a straight line direction from the center of the gap to the relatively central position as a lens shooting direction;
and controlling a camera on the camera trolley to go to the center of the gap and shooting the internal image of the complement shooting position in the shooting direction of the lens.
Preferably, the pest image acquisition module acquires pest images of the crops from a big data platform, and performs the following operations:
acquiring a preset disease and pest image retrieval template corresponding to the crops;
and searching the pest image of the crop from a big data platform based on the pest image searching template.
Preferably, the pest crop determining module determines a pest crop based on the branch and leaf image and the pest image, including:
inputting the plant disease and insect pest image as a training sample into a neural network model for training to obtain a plant disease and insect pest identification model;
inputting the branch and leaf images into the plant disease and insect pest identification model to determine plant disease and insect pest crops.
The method for supervising the agricultural plant diseases and insect pests based on big data provided by the embodiment of the invention comprises the following steps:
step S1: acquiring branch and leaf images of crops in an agricultural garden through a camera trolley;
step S2: acquiring a disease and pest image of the crop from a big data platform;
step S3: determining a pest crop based on the branch and leaf image and the pest image;
step S4: and early warning the pest and disease crops to management personnel of the agricultural garden.
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 will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended 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 schematic diagram of an agricultural pest management system based on big data in an embodiment of the present invention;
fig. 2 is a schematic diagram of an agricultural pest monitoring method based on big data in an embodiment of the 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.
The embodiment of the invention provides an agricultural pest monitoring system based on big data, as shown in fig. 1, comprising:
the branch and leaf image acquisition module 1 is used for acquiring branch and leaf images of crops in an agricultural garden through a camera trolley;
the plant disease and insect pest image acquisition module 2 is used for acquiring plant disease and insect pest images of the crops from a big data platform;
a pest crop determining module 3 for determining a pest crop based on the branch and leaf image and the pest image;
and the early warning module 4 is used for early warning the pest crops to management personnel of the agricultural garden.
The working principle and the beneficial effects of the technical scheme are as follows:
the camera trolley is a mobile trolley with a camera. The big data platform collects pest images of crops based on big data technology. When the method is specifically applied, the camera trolley moves in the agricultural garden, the images of branches and leaves of crops are shot, the crops with diseases and insect pests are determined based on the images of the branches and leaves and the images of the diseases and insect pests acquired from the data platform, for example, the crops with the diseases and insect pests are determined in a mode of comparing the images of the two, and early warning of the crops with the diseases and insect pests is carried out for management staff, for example, the management staff is informed in a mode of mobile phone information notification. A plurality of personnel with crop pest judgment experience do not need to be arranged to regularly carry out one-to-one pest inspection on crops, and labor cost is reduced.
In one embodiment, the branch and leaf image acquisition module 1 acquires a branch and leaf image of crops in an agricultural garden through a camera dolly, and performs the following operations:
acquiring a bird's eye view image of the crop;
planning a tour route of the camera trolley based on the aerial view image;
controlling the camera trolley to move in the agricultural garden based on the inspection route;
when the camera dolly reaches to the side of any target plant in the crops, controlling the camera dolly to shoot an external image of the target plant;
determining a supplementary shooting position of the target plant, which needs to be subjected to supplementary shooting, based on the external image;
controlling the camera trolley to shoot the internal image of the supplementary shooting position;
and taking the external image and the internal image as branch and leaf images.
The working principle and the beneficial effects of the technical scheme are as follows:
the bird's-eye view image can be obtained by shooting downward with a bird's-eye view camera provided at a high position in the agricultural garden. The route and crop distribution for the camera trolley to move in the agricultural garden can be determined based on the aerial view image, so that the camera trolley can be used for planning a route for inspection. Based on the route of patrolling, control the dolly of making a video recording and remove in the agriculture garden. Normally, the branches and leaves of the plants are overlapped and staggered, and the plant diseases and insect pests can not only occur on the front sides of the branches and leaves, but also occur on the back sides of the branches and leaves, so that the external image of the target plant is shot singly, and the plant diseases and insect pests are determined, so that the internal shooting position of the target plant, which is required to be subjected to the shooting, is determined based on the external image, for example, the back sides of the branches and leaves, the internal shooting blind area and the like, the internal image of the shooting position of the shooting trolley is controlled, the external image and the internal image are used as the branch and leaf image, and the comprehensiveness and rationality of the branch and leaf image acquisition for monitoring the plant diseases and insect pests are improved.
In one embodiment, the branch and leaf image acquisition module 1 plans a route for inspection of the camera dolly based on the bird's eye view image, and performs the following operations:
extracting a park road from the aerial view image and a plant gap connected with the park road;
dividing the plant space into a plurality of space segments based on a preset segmentation template;
traversing the gap sections from near to far according to the position relation between the gap sections and the park roads;
performing feature extraction on the traversed gap segments based on a preset first feature extraction template every time, and obtaining a gap feature set;
matching the gap characteristic set with a preset standard gap characteristic set corresponding to the crops to obtain a first matching degree;
if the first matching degree is smaller than a preset first matching degree threshold value, splicing the previously traversed gap segments to be used as the longest moving gap;
extracting plant distribution from the aerial view image;
planning a route of inspection of the camera trolley based on the park road, the longest moving gap and the plant distribution.
The working principle and the beneficial effects of the technical scheme are as follows:
there is garden road in the agricultural garden, and many sets up in plant planting area periphery, can supply the dolly of making a video recording to travel. Secondly, normally, the plant can arrange with many rows when planting, consequently, can leave the space between two rows of plants, and this space can supply the dolly of making a video recording to go, but, along with the growth plant of plant can become flourishing, the space area can become little, if hard will make a video recording the dolly control and go in the space, can destroy the plant. Therefore, the camera dolly can only shoot the branch and leaf images on the garden road and the plant gap which can be driven by the garden road. Extracting plant gaps connected with the park roads, and dividing the plant gaps into a plurality of gap ends based on a preset segmentation template; the preset segmentation template specifically comprises the following steps: and (3) making perpendicular bisectors in the longer direction of the plant gaps in the plant gaps, making perpendicular lines perpendicular to the perpendicular bisectors on the perpendicular bisectors every 0.5 meter, and withdrawing the perpendicular bisectors, wherein each perpendicular line divides the plant gaps into a plurality of sections. Extracting a void feature set of the void segment, the void feature set comprising: minimum void width and average void width, etc. When the preset standard gap feature set that crops correspond specifically is that this crops are planted and are two rows, when the space region between two rows can hold the dolly of making a video recording and travel, the image feature that the space region outside presented includes: the minimum void width is 0.35 meters and the average void width is 0.42 meters. And matching the gap feature set with the standard gap feature set, if the first matching degree is smaller than or equal to a preset first matching degree threshold value, indicating that the gap section cannot accommodate the running of the camera trolley, and splicing the previously traversed gap section as the longest moving gap. And extracting plant distribution from the aerial view image, and planning a shooting route of the shooting trolley based on the park road, the longest moving gap and the plant distribution. According to the embodiment of the invention, the longest movement gap in the plant gap, which can be used for the shooting trolley to travel, is adaptively determined, so that the applicability of planning the shooting trolley inspection route in the plant planting area is improved, and meanwhile, the intelligent shooting trolley inspection route is realized.
In one embodiment, the branch and leaf image acquisition module 1 determines, based on the external image, a supplementary shooting position where the inside of the target plant needs to be subjected to supplementary shooting, and performs the following operations:
determining whether image acquisition is necessary for the back of the leaf of the target plant based on the external image;
if yes, taking the position of the target plant corresponding to the back of the leaf as a supplementary shooting position;
and/or the number of the groups of groups,
determining whether image acquisition is necessary on the back of the branches and stems of the target plant based on the external image;
if yes, taking the position of the target plant corresponding to the back of the branch and stem as a supplementary shooting position;
and/or the number of the groups of groups,
and determining a branch and leaf shooting blind area of the target plant based on the external image, and taking the position of the branch and leaf shooting blind area as a supplementary shooting position.
The working principle and the beneficial effects of the technical scheme are as follows:
most of the external images of the plants are presented on the front surfaces of the branches and leaves of the plants, however, as the growth angles of the branches and leaves are different from the angles of the external images shot by the shooting trolley, part of the back surfaces of some branches and leaves can be exposed, and most of plant diseases and insect pests occur in a regional mode, if the exposed part is not abnormal, the back surfaces are not required to be collected. Therefore, the first and second methods first determine whether or not image acquisition is necessary for the back of the leaf/branch of the target plant, and if so, take the corresponding position as the dead position. The back of each leaf and each branch does not need to be subjected to supplementary shooting, so that shooting resources are reduced, and the shooting efficiency of the branch and leaf images is improved. Thirdly, taking the position of the branch and leaf shooting blind area as the supplementary shooting position.
In one embodiment, the branch and leaf image acquisition module 1 determines, based on the external image, whether or not image acquisition is necessary for the leaf back surface of the target plant, and performs the following operations:
extracting a leaf contour from the external image;
extracting the leaf profile based on a preset second feature extraction template to obtain a first profile feature set;
matching the first contour feature set with a preset first standard contour feature set corresponding to the crops to obtain a second matching degree;
if the second matching degree is smaller than or equal to a preset second matching degree threshold value, determining that the back surface of the leaf of the target plant is necessary to acquire an image.
The working principle and the beneficial effects of the technical scheme are as follows:
in general, when a portion of the back surface of a leaf appears on an external image, the more the contour of the leaf does not conform to the contour of the leaf when the front surface of the leaf is spread. Thus, a first set of contour features of the leaf contour is extracted, the first set of contour features comprising: profile area, profile maximum length, and profile minimum length. The first preset standard profile feature set corresponding to the crop is specifically a feature of a profile of the crop when the front surface of the leaves is spread, for example, including: the profile area is 3.2 square centimeters, the maximum profile length is 3 centimeters and the minimum profile length is 1.5 centimeters. And matching the first contour feature set with the first standard contour feature set, and if the second matching degree is smaller than or equal to a preset second matching degree threshold value, indicating that the back surface of the leaf has fewer parts presented on the external image, and acquiring the leaf. The determination efficiency and the determination accuracy of whether the back of the leaf of the target plant is necessary to perform image acquisition are improved.
In one embodiment, the shoot and leaf image acquisition module 1 determines whether image acquisition is necessary on the back of the shoot of the target plant based on the external image, including:
extracting a branch and stem contour from the external image;
extracting the branch and stem outline based on a preset third feature extraction template to obtain a second outline feature set;
matching the second contour feature set with a preset second standard contour feature set corresponding to the crops to obtain a third matching degree;
if the third matching degree is smaller than or equal to a preset third matching degree threshold value, determining that the back of the branch and stem of the target plant is necessary to acquire an image.
The working principle and the beneficial effects of the technical scheme are as follows:
in general, when a portion of the back of the branch is presented on the external image, the more the outline of the branch is inconsistent with the outline of the branch when the front of the branch is spread. Thus, a second set of profile features of the shoot profile is extracted, the second set of profile features comprising: profile area, profile maximum length, and profile minimum length. The second preset standard profile feature set corresponding to the crop is specifically a feature of a profile of the crop when the front of the branch and the stem of the crop is spread, for example, including: the contour area is 5.1 square centimeters, the contour maximum length is 4 centimeters and the contour minimum length is 1.1 centimeters. And matching the second contour feature set with the second standard contour feature set, wherein if the third matching degree is smaller than or equal to a preset third matching degree threshold value, the condition that the back surface of the branch and the stem presents fewer parts on the external image is indicated, and acquisition is required. The determination efficiency and the determination accuracy of whether the back of the branch and the stem of the target plant is necessary to carry out image acquisition are improved.
In one embodiment, the branch and leaf image acquisition module 1 controls the camera dolly to shoot an internal image of the supplementary shooting position, and performs the following operations:
extracting branch and leaf gaps from the external image;
determining the supplementary shooting position beside the branch and leaf gap, and taking the supplementary shooting position as a target supplementary shooting position;
constructing a direction vector based on the target supplemental photographing position and a straight line direction from the target supplemental photographing position to the gap center of the branch and leaf gap;
when the vector included angles between every two continuous N direction vectors fall in a preset vector included angle interval, determining a relative centering position from the target complement shooting positions corresponding to the continuous N direction vectors;
taking a straight line direction from the center of the gap to the relatively central position as a lens shooting direction;
and controlling a camera on the camera trolley to go to the center of the gap and shooting the internal image of the complement shooting position in the shooting direction of the lens.
The working principle and the beneficial effects of the technical scheme are as follows:
gaps exist between branches and leaves, and cameras can enter the gaps to perform supplementary shooting. N is a positive integer. The preset vector angle interval is 0 to 120 degrees. When the vector included angles between every two continuous N direction vectors fall in a preset vector included angle interval, the fact that the camera can perform one-time supplementary shooting on target supplementary shooting positions corresponding to the continuous N direction vectors at the target supplementary shooting positions is explained, the relative centering position is determined from the target supplementary shooting positions corresponding to the continuous N direction vectors, the straight line direction from the gap center to the relative centering position can be used as a lens shooting direction, and the camera on the camera trolley is controlled to move to the gap center to shoot an internal image of the supplementary shooting position in the lens shooting direction. The rationality of the shooting control of the shooting trolley is improved, the supplementary shooting resources are reduced, and the supplementary shooting efficiency is improved.
In one embodiment, the pest image acquiring module 2 acquires a pest image of the crop from a big data platform, and performs the following operations:
acquiring a preset disease and pest image retrieval template corresponding to the crops;
and searching the pest image of the crop from a big data platform based on the pest image searching template.
The preset plant diseases and insect pests image retrieval template corresponding to the crops specifically comprises the following steps: and searching the searching conditions of the plant disease and insect pest images of the plant disease and insect pest types possibly generated by the farming. And retrieving the pest image of the crop from the big data platform based on the pest image retrieval template.
In one embodiment, the pest crop determination module 3 determines a pest crop based on the branch and leaf image and the pest image, comprising:
inputting the plant disease and insect pest image as a training sample into a neural network model for training to obtain a plant disease and insect pest identification model;
inputting the branch and leaf images into the plant disease and insect pest identification model to determine plant disease and insect pest crops.
The plant disease and insect pest image is input into the neural network model as a training sample for training, the plant disease and insect pest identification model is obtained after the training is converged, the plant disease and insect pest identification model can replace manual plant disease and insect pest judgment based on the branch and leaf image, the branch and leaf image is input into the plant disease and insect pest identification model, and the plant disease and insect pest crops are determined.
The embodiment of the invention provides an agricultural pest monitoring method based on big data, which is shown in fig. 2 and comprises the following steps:
step S1: acquiring branch and leaf images of crops in an agricultural garden through a camera trolley;
step S2: acquiring a disease and pest image of the crop from a big data platform;
step S3: determining a pest crop based on the branch and leaf image and the pest image;
step S4: and early warning the pest and disease crops to management personnel of the agricultural garden.
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 (10)
1. An agricultural pest management system based on big data, characterized by comprising:
the branch and leaf image acquisition module is used for acquiring branch and leaf images of crops in the agricultural garden through the camera trolley;
the plant disease and insect pest image acquisition module is used for acquiring plant disease and insect pest images of the crops from the big data platform;
the plant disease and insect pest crop determining module is used for determining plant disease and insect pest crops based on the branch and leaf images and the plant disease and insect pest images;
and the early warning module is used for early warning the pest and disease crops to management personnel in the agricultural garden.
2. The agricultural pest management system based on big data according to claim 1, wherein the branch and leaf image acquisition module acquires a branch and leaf image of a crop in an agricultural garden through a camera dolly, performs the following operations:
acquiring a bird's eye view image of the crop;
planning a tour route of the camera trolley based on the aerial view image;
controlling the camera trolley to move in the agricultural garden based on the inspection route;
when the camera dolly reaches to the side of any target plant in the crops, controlling the camera dolly to shoot an external image of the target plant;
determining a supplementary shooting position of the target plant, which needs to be subjected to supplementary shooting, based on the external image;
controlling the camera trolley to shoot the internal image of the supplementary shooting position;
and taking the external image and the internal image as branch and leaf images.
3. The agricultural pest management system based on big data according to claim 2, wherein the branch and leaf image acquisition module plans a route for inspection of the camera dolly based on the bird's eye view image, and performs the following operations:
extracting a park road from the aerial view image and a plant gap connected with the park road;
dividing the plant space into a plurality of space segments based on a preset segmentation template;
traversing the gap sections from near to far according to the position relation between the gap sections and the park roads;
performing feature extraction on the traversed gap segments based on a preset first feature extraction template every time, and obtaining a gap feature set;
matching the gap characteristic set with a preset standard gap characteristic set corresponding to the crops to obtain a first matching degree;
if the first matching degree is smaller than a preset first matching degree threshold value, splicing the previously traversed gap segments to be used as the longest moving gap;
extracting plant distribution from the aerial view image;
planning a route of inspection of the camera trolley based on the park road, the longest moving gap and the plant distribution.
4. The agricultural pest management system according to claim 2, wherein the branch and leaf image acquisition module determines a supplementary shooting position where the inside of the target plant needs to be subjected to supplementary shooting based on the external image, and performs the following operations:
determining whether image acquisition is necessary for the back of the leaf of the target plant based on the external image;
if yes, taking the position of the target plant corresponding to the back of the leaf as a supplementary shooting position;
and/or the number of the groups of groups,
determining whether image acquisition is necessary on the back of the branches and stems of the target plant based on the external image;
if yes, taking the position of the target plant corresponding to the back of the branch and stem as a supplementary shooting position;
and/or the number of the groups of groups,
and determining a branch and leaf shooting blind area of the target plant based on the external image, and taking the position of the branch and leaf shooting blind area as a supplementary shooting position.
5. The big data based agricultural pest management system according to claim 4, wherein said branch and leaf image acquisition module determines whether or not image acquisition is necessary for a leaf back surface of said target plant based on said external image, and performs the following operations:
extracting a leaf contour from the external image;
extracting the leaf profile based on a preset second feature extraction template to obtain a first profile feature set;
matching the first contour feature set with a preset first standard contour feature set corresponding to the crops to obtain a second matching degree;
if the second matching degree is smaller than or equal to a preset second matching degree threshold value, determining that the back surface of the leaf of the target plant is necessary to acquire an image.
6. The big data based agricultural pest management system according to claim 4, wherein said branch and leaf image acquisition module determining whether image acquisition is necessary on a back side of a branch and a stem of said target plant based on said external image, comprising:
extracting a branch and stem contour from the external image;
extracting the branch and stem outline based on a preset third feature extraction template to obtain a second outline feature set;
matching the second contour feature set with a preset second standard contour feature set corresponding to the crops to obtain a third matching degree;
if the third matching degree is smaller than or equal to a preset third matching degree threshold value, determining that the back of the branch and stem of the target plant is necessary to acquire an image.
7. The big data based agricultural pest management system according to claim 2, wherein said branch and leaf image acquisition module controls said camera dolly to take an internal image of said supplementary shooting position, and performs the following operations:
extracting branch and leaf gaps from the external image;
determining the supplementary shooting position beside the branch and leaf gap, and taking the supplementary shooting position as a target supplementary shooting position;
constructing a direction vector based on the target supplemental photographing position and a straight line direction from the target supplemental photographing position to the gap center of the branch and leaf gap;
when the vector included angles between every two continuous N direction vectors fall in a preset vector included angle interval, determining a relative centering position from the target complement shooting positions corresponding to the continuous N direction vectors;
taking a straight line direction from the center of the gap to the relatively central position as a lens shooting direction;
and controlling a camera on the camera trolley to go to the center of the gap and shooting the internal image of the complement shooting position in the shooting direction of the lens.
8. The agricultural pest management system based on big data according to claim 1, wherein the pest image acquisition module acquires pest images of the crop from a big data platform, performs the following operations:
acquiring a preset disease and pest image retrieval template corresponding to the crops;
and searching the pest image of the crop from a big data platform based on the pest image searching template.
9. The big data based agricultural pest management system of claim 1, wherein the pest crop determination module determines a pest crop based on the branch and leaf image and the pest image, comprising:
inputting the plant disease and insect pest image as a training sample into a neural network model for training to obtain a plant disease and insect pest identification model;
inputting the branch and leaf images into the plant disease and insect pest identification model to determine plant disease and insect pest crops.
10. The agricultural pest monitoring method based on big data is characterized by comprising the following steps:
step S1: acquiring branch and leaf images of crops in an agricultural garden through a camera trolley;
step S2: acquiring a disease and pest image of the crop from a big data platform;
step S3: determining a pest crop based on the branch and leaf image and the pest image;
step S4: and early warning the pest and disease crops to management personnel of the agricultural garden.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211706884.3A CN116310489A (en) | 2022-12-29 | 2022-12-29 | Agricultural pest monitoring system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211706884.3A CN116310489A (en) | 2022-12-29 | 2022-12-29 | Agricultural pest monitoring system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116310489A true CN116310489A (en) | 2023-06-23 |
Family
ID=86834843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211706884.3A Withdrawn CN116310489A (en) | 2022-12-29 | 2022-12-29 | Agricultural pest monitoring system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116310489A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541177A (en) * | 2023-11-09 | 2024-02-09 | 南京邮电大学 | Intelligent agriculture monitoring management method and system based on big data |
-
2022
- 2022-12-29 CN CN202211706884.3A patent/CN116310489A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541177A (en) * | 2023-11-09 | 2024-02-09 | 南京邮电大学 | Intelligent agriculture monitoring management method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418188B (en) | Crop growth whole-course digital evaluation method based on unmanned aerial vehicle vision | |
| CN111372444B (en) | Information processing device, information processing method, and vegetation management system | |
| US20220272907A1 (en) | Automated plant monitoring systems and methods | |
| CN110849264A (en) | Multi-row track based field crop phenotype monitoring system and method | |
| CN105547360B (en) | Crop canopies image-pickup method based on context aware | |
| CN116310489A (en) | Agricultural pest monitoring system and method based on big data | |
| CN112163639B (en) | Crop lodging grading method based on height distribution feature vector | |
| JP2020054289A (en) | Harvest prediction system for facility cultivated fruits | |
| CN113011221A (en) | Crop distribution information acquisition method and device and measurement system | |
| CN115526521A (en) | Plant growth state monitoring and alarming system for plant factory | |
| CN107464232B (en) | Image detection method for planting quality of unmanned rice transplanter | |
| CN116300608A (en) | Intelligent agriculture remote monitoring system based on big data | |
| CN116109268A (en) | Intelligent agriculture supervision system and method based on Internet of things | |
| CN109598215A (en) | Orchard modeling analysis system and method based on positioning shooting of unmanned aerial vehicle | |
| CN110689022B (en) | Method for extracting images of crops of each plant based on blade matching | |
| CN115756037A (en) | Greenhouse vegetable management and control method and system | |
| CN117575835A (en) | Tea garden growth monitoring system and method based on unmanned aerial vehicle aerial photography | |
| CN118247073A (en) | Intelligent greenhouse crop growth recording method and system | |
| EP3559864B1 (en) | Method of selecting an ordered image subset for structure assessment | |
| CN117197595A (en) | Fruit tree growth period identification method, device and management platform based on edge calculation | |
| CN112580513A (en) | Intelligent identification method for crop diseases and insect pests | |
| CN116993059A (en) | Internet of things intelligent agricultural plant protection system based on big data | |
| CN117218534A (en) | Crop leaf disease identification method | |
| CN116740378A (en) | Garden plant diseases and insect pests evaluation system based on image processing | |
| CN109598767A (en) | Orchard monitoring system and method based on positioning shooting of unmanned aerial vehicle |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230623 |