CN114332461B - Intelligent agricultural insect pest remote detection system and method - Google Patents
Intelligent agricultural insect pest remote detection system and method Download PDFInfo
- Publication number
- CN114332461B CN114332461B CN202111634701.7A CN202111634701A CN114332461B CN 114332461 B CN114332461 B CN 114332461B CN 202111634701 A CN202111634701 A CN 202111634701A CN 114332461 B CN114332461 B CN 114332461B
- Authority
- CN
- China
- Prior art keywords
- area
- farmland
- areas
- pest
- rectangular
- 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
Images
Landscapes
- Catching Or Destruction (AREA)
Abstract
The invention discloses an intelligent agricultural insect pest remote detection system, which comprises a data extraction module, a data acquisition module and a data processing module, wherein the data extraction module is used for distinguishing the type of crops in a farmland to be detected from big data, extracting the planting information of the type of crops, and extracting the accompanying insect pest type data of the type of crops based on the big data; the region division module is used for performing region division on the farmland to be detected; the image segmentation and identification module is used for segmenting the crop leaf surface representation image and identifying the characteristic insect spots accompanying the insect pest species in each region obtained after segmentation; the spot spread area identification module is used for calculating the area of the spot and the permeability of the farmland area and carrying out marking processing according to the calculation result; a pest grade detection and judgment module; the system is used for detecting and judging the insect pest level of the farmland to be detected; the intelligent agricultural insect pest remote detection method is further provided for better realizing the system function.
Description
Technical Field
The invention relates to the technical field of intelligent agricultural data processing, in particular to a system and a method for remotely detecting insect pests for intelligent agriculture.
Background
The problem of agricultural insect damage is one of the causes of blocking agricultural output and causing major loss of agricultural production, and pests are often characterized by multiple species, fast propagation, small volume, difficult investigation and frequent outbreak and disaster; the range and severity of occurrence often has a direct impact on economics; detection of insect pests in the prior art often depends on manual investigation, and misjudgment on actual insect conditions often occurs due to small size of the insect pests and egg laying stage of the insect pests when the insect pests are directly obtained by utilizing an image acquisition and processing technology for pest information, so that a conclusion close to actual insect pest results cannot be obtained.
Disclosure of Invention
The invention aims to provide an intelligent agricultural insect pest remote detection system and method to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: an intelligent agricultural insect pest remote detection method comprises the following steps:
step S100: confirming the types of crops in a farmland to be detected, extracting the planting information of the types of crops, and locking the accompanying insect pest types of the types of crops based on big data; the planting information comprises crop rhizome planting distribution density and crop leaf distribution density;
step S200: dividing a farmland working area to be detected into n parts of rectangular farmland areas, and dividing the n parts of rectangular farmland areas into a plurality of first areas, second areas and spreading areas of the second areas on the basis of planting information;
step S300: acquiring a crop leaf surface characterization image in the farmland to be detected, and correspondingly dividing the crop leaf surface characterization image into n parts of region characterization images on the basis of the region division in the step S200 to obtain n parts of rectangular farmland regions;
step S400: identifying characteristic insect spots accompanied with insect pest species for each region characterization image, calculating the insect spot area of each region characterization image, and marking the corresponding n rectangular farmland regions according to the insect spot area condition of each region characterization image; meanwhile, respectively calculating the permeability of each rectangular farmland area;
step S500: identifying a spot spread area based on the permeability;
step S600: carrying out insect pest grade detection judgment on a farmland to be detected; the insect pest grades comprise severe, prevention and mild.
Further, step S100 is to screen the condition based on the detected climate characteristic when the accompanying insect pest species are locked; and extracting the accompanying insect pest type information of which the occurrence probability of the crop type is greater than a probability threshold value under the climate characteristic condition during detection.
Further, step S200 includes:
step S201: based on big data, respectively taking the optimum distribution density of the rhizome planting and the optimum distribution density of the leaves of the unit space crop as reference threshold values, namely the reference threshold values comprise the rhizome planting density W and the leaf distribution density S; the distribution density of the crop leaves refers to the ratio of the total area of the overlapping or covering of the leaves between the crop leaves to the total visible area formed by all the crop leaves in the area; i.e. the available formula S = S 1 /s 2 Is shown in which s 1 Represents the total area of the crop leaves between which the leaf overlap or coverage occurs; s is 2 Representing the total visible area formed by all the crop leaves in the area;
step S202: setting a unit rectangular area according to the actual area of the farmland to be detected, and selecting one side edge of the farmland to be detected to begin to divide by the unit rectangular area to obtain n rectangular farmland areas; calculating the rhizome planting distribution density of n rectangular farmland regions, and dividing a region smaller than the rhizome planting density W into a first region; dividing the area which is larger than the rhizome planting density W into a second area;
step S203: searching the adjacent edge information of all the first areas respectively, taking the first areas with three or more than three adjacent edges with the second areas as the spreadable areas of the second areas, calculating the distribution density of the crop leaves in each spreadable area, and taking the spreadable areas with the distribution density of the crop leaves being greater than the distribution density S of the leaves as the spreading areas of the second areas;
according to the method, different areas are divided based on the actual planting condition of crops on a farmland to be detected, the probability that pests propagate and finally cause pests is different according to different planting densities of the crops, and the higher the planting density of the crops is, the higher the probability that the pests propagate and finally cause the pests is; the smaller the planting density of crops is, the smaller the probability of pest reproduction and eventual pest damage is; the plant area with low planting density which is closely connected with the plant distribution area with high planting density is taken as the spreading area of the plant area with high planting density, and the probability of pest propagation and the probability of pest damage caused by the distribution of the surrounding plants are increased.
Further, step S400 includes:
step S401: setting a first area threshold value a and a second area threshold value b, wherein a > b; when the area of the insect spots on one part of the area representation image is larger than a first area threshold value a, making a first mark on the rectangular farmland area corresponding to the part of the area representation image; when the area of the insect spots on one part of the area representation image is larger than a second area threshold value b and smaller than a first area threshold value a, making a second mark on the rectangular farmland area corresponding to the part of the area representation image;
step S402: capturing all blade gap images of each rectangular farmland area, and taking the farmland area corresponding to the blade gap as a penetration area when a pest spot appears on one blade gap image;
step S403: according to the formula
Calculating the permeability P of each rectangular farmland area; wherein h is 1 Represents the average plant height of the crop in the area where the infiltration occurs; h is 2 Representing the average plant height of the crop at the contour edge of the infiltration area; h represents the average plant height of the crop in the rectangular farmland area; s represents the area of a rectangular farmland region; s is 1 Represents the area of the penetration region;
in the invention, the calculation of the permeability is introduced, namely, the blade clearance area with high dislocation can be formed due to the fact that the actual planting height of crops is different, the blade clearance area can often have an overlapping area or a hidden area with other crop blades, and the condition of a certain number of hidden pests can be reflected on a data level by extracting the distribution information of the insect spots on the blade clearance area.
Further, the step S500 of identifying the lesion spreading area includes:
step S501: setting a penetration threshold, screening out rectangular farmland areas with the permeability P greater than the penetration threshold, and performing line segment connection between all rectangular farmland areas with the permeability P greater than the penetration threshold by taking the area central point of each rectangular farmland area as a starting end;
step S502: and when the length of the line segment meets the length threshold, taking the rectangular farmland areas through which the line segment passes as the insect spot spreading areas of the two rectangular farmland areas.
Further, the process of judging the pest level in step S600 includes:
when the detection system detects that two or more rectangular farmland areas marked with the first marks exist, the detection system identifies the pest spot spreading areas of the two or more rectangular farmland areas marked with the first marks, and when the pest spot spreading areas exist and areas which belong to the second areas or spreading areas of the second areas exist in the pest spot spreading areas, the pest grade judgment result is serious;
when the detection system detects that two or more rectangular farmland areas marked with the second marks exist, the detection system identifies the pest spot spreading area of the two or more rectangular farmland areas marked with the second marks, and when the pest spot spreading area exists and the pest spot spreading area has an area which belongs to the second area or a spreading area of the second area, the pest grade judgment result is that prevention is needed;
when the detection system detects that two or more rectangular farmland areas marked with the second marks exist, the detection system identifies the pest spot spreading areas of the two or more rectangular farmland areas marked with the second marks, and when the pest spot spreading areas exist and areas of the pest spot spreading areas which belong to spreading areas of the first area or the second area exist, the pest grade judgment result is slight; when no spot spread area exists, the insect pest grade judgment result is slight.
Furthermore, when insect pest grades are judged, the number of rectangular farmland areas marked with the first marks is detected in priority to the number of rectangular farmland areas marked with the second marks, namely, when the detection system cannot detect that two or more rectangular farmland areas marked with the first marks exist, the number of rectangular farmland areas marked with the second marks is detected in a downward sequential delay mode.
The intelligent agricultural insect pest remote detection system comprises a data extraction module, a region division module, an image segmentation and identification module, an insect spot spreading region identification module and an insect pest grade detection and judgment module;
the data extraction module is used for distinguishing the types of crops in the farmland to be detected from the big data, extracting the planting information of the crops of the types and extracting the accompanying insect pest type data of the crops of the types based on the big data;
the region division module is used for performing region division on the farmland to be detected and further performing region division on the farmland to be detected after the region division based on the data extracted from the data extraction module to obtain unequal first regions, second regions and spreading regions of the second regions;
the image segmentation and identification module is used for acquiring a crop leaf surface characterization image in a farmland to be detected and segmenting the crop leaf surface characterization image based on a region segmentation method in the region segmentation module; meanwhile, each region obtained after the segmentation processing is subjected to characteristic insect spot identification accompanied with insect pest species;
the spot spread area identification module is used for receiving the data in the image segmentation identification module, calculating the area of the spot and marking according to the calculation result; calculating the permeability of the farmland area, and identifying and judging the spot spreading area based on the permeability;
and the pest grade detection and judgment module is used for detecting and judging pest grades of the farmland to be detected, wherein the pest grades comprise serious, prevention and slight.
Further, the insect plaque spreading area identification module comprises a blade gap capturing unit, a penetration area identification unit, a penetration rate calculation unit and an insect plaque spreading area judgment unit;
the blade gap capturing unit is used for capturing all blade gap images of each rectangular farmland area;
the infiltration area recognition unit is used for recognizing the insect spots of the images in the blade gap capturing unit and taking the blade gap areas captured with the insect spots as infiltration areas;
the permeability calculation unit is used for receiving the data in the permeability area identification unit and calculating the permeability of each rectangular farmland area;
and the spot spread area judgment unit is used for receiving the data in the permeability calculation unit and finishing the judgment of the spot spread area.
Further, the insect pest grade detection and judgment module comprises a rectangular farmland area number detection unit and a grade judgment unit;
the rectangular farmland area number detection unit is used for setting priority levels for detecting the number of rectangular farmland areas with different marks; and the grade judgment unit is used for correspondingly judging different grades of the farmland to be detected according to the priority setting in the rectangular farmland area number detection unit, and the insect pest grade judgment result comprises severity, prevention and slight.
Compared with the prior art, the invention has the following beneficial effects: the invention can obtain the insect pest detection result without carrying out detailed investigation aiming at the insect pest situation on the whole farmland for detecting the farmland insect pests; performing different predictions on insect pest degrees based on the actual planting condition of crops on a farmland to be detected; judging the pest spreading area based on the distribution of pest spots on crops; the invention can realize the judgment of the spreading trend of the insect pest by collecting a few samples in the insect pest detection; and the obtained pest registration judgment result is predictive in the data processing category, so that the effect of being informed is achieved, the pest detection efficiency is improved, and the labor force is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of the intelligent agricultural pest remote detection method of the present invention;
fig. 2 is a schematic structural diagram of the intelligent agricultural insect pest remote detection system.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: an intelligent agricultural insect pest remote detection method comprises the following steps:
step S100: confirming the types of crops in a farmland to be detected, extracting the planting information of the types of crops, and locking the types of accompanying insect pests of the types of crops based on big data; the planting information comprises crop rhizome planting distribution density and crop leaf distribution density; when the accompanying insect pest species are locked, screening conditions are screened by taking the climate characteristics in detection as a reference; extracting accompanying insect pest type information of which the occurrence probability is greater than a probability threshold value under the climate characteristic condition of the type crop during detection;
step S200: dividing a farmland region to be detected into n parts of rectangular farmland regions, and dividing the n parts of rectangular farmland regions into a plurality of first regions, second regions and spreading regions of the second regions based on planting information; wherein, step S200 includes:
step S201: based on big data, respectively taking the optimum distribution density of the rhizome planting and the optimum distribution density of the leaves of the unit space crop as reference threshold values, namely the reference threshold values comprise the rhizome planting density W and the leaf distribution density S;
step S202: setting a unit rectangular area according to the actual area of the farmland to be detected, and selecting one side edge of the farmland to be detected to begin to divide by the unit rectangular area to obtain n rectangular farmland areas; calculating the rhizome planting distribution density of n rectangular farmland regions, and dividing a region smaller than the rhizome planting density W into a first region; dividing the area which is larger than the rhizome planting density W into a second area;
step S203: searching the adjacent edge information of all the first areas respectively, taking the first areas with three or more than three adjacent edges with the second areas as the spreadable areas of the second areas, calculating the distribution density of the crop leaves in each spreadable area, and taking the spreadable areas with the distribution density of the crop leaves being greater than the distribution density S of the leaves as the spreading areas of the second areas;
the distribution density of the crop leaves refers to the ratio of the total area of the overlapping or covering of the crop leaves to the total visible area formed by all the crop leaves in the area; i.e. the available formula S = S 1 /s 2 Is shown in which s 1 Represents the total area of the crop leaves between which the leaf overlap or coverage occurs; s 2 Representing the total visible area formed by all the crop leaves in the area;
step S300: acquiring a crop leaf surface characterization image in the farmland to be detected, and correspondingly dividing the crop leaf surface characterization image into n parts of region characterization images on the basis of the region division in the step S200 to obtain n parts of rectangular farmland regions;
step S400: identifying characteristic insect spots accompanying insect pest types for each region characterization image, calculating the insect spot area of each region characterization image, and marking n corresponding rectangular farmland regions according to the insect spot area condition of each region characterization image; simultaneously, respectively calculating the permeability of each rectangular farmland area;
wherein, step S400 includes:
step S401: setting a first area threshold value a and a second area threshold value b, wherein a > b; when the area of the insect spots on one part of the area representation image is larger than a first area threshold value a, making a first mark on the rectangular farmland area corresponding to the part of the area representation image; when the area of the insect spots on one part of the area representation image is larger than a second area threshold value b and smaller than a first area threshold value a, making a second mark on the rectangular farmland area corresponding to the part of the area representation image;
step S402: capturing all blade gap images of each rectangular farmland area, and taking the farmland area corresponding to the blade gap as a penetration area when a pest spot appears on one blade gap image;
step S403: according to the formula
Calculating the permeability P of each rectangular farmland area; wherein h is 1 Indicating the average plant height of the crop in the area where the infiltration occurs; h is 2 Representing the average plant height of the crop at the contour edge of the infiltration area; h represents the average plant height of the crop in the rectangular farmland area; s represents the area of a rectangular farmland region; s 1 Represents the area of the penetration region;
step S500: identifying a spot spread area based on the permeability;
wherein the identification of the plaque-spreading area comprises:
step S501: setting a penetration threshold, screening out rectangular farmland areas with the permeability P greater than the penetration threshold, and performing line segment connection between all rectangular farmland areas with the permeability P greater than the penetration threshold by taking the area central point of each rectangular farmland area as a starting end;
step S502: when the length of the line segment meets the length threshold, taking the rectangular farmland areas through which the line segment passes as the insect spot spreading areas of the two rectangular farmland areas;
step S600: carrying out insect pest grade detection judgment on a farmland to be detected; insect pest grades include severe, to be prevented, mild;
wherein, the process of insect pest grade judgement includes:
when the detection system detects that two or more rectangular farmland areas marked with the first marks exist, the detection system identifies the pest spot spreading area of the two or more rectangular farmland areas marked with the first marks, and when the pest spot spreading area exists and the pest spot spreading area has an area which belongs to the second area or a spreading area of the second area, the pest grade judgment result is serious;
when the detection system detects that two or more rectangular farmland areas marked with the second marks exist, the detection system identifies the pest spot spreading areas of the two or more rectangular farmland areas marked with the second marks, and when the pest spot spreading areas exist and areas which belong to the second areas or spreading areas of the second areas exist in the pest spot spreading areas, the pest grade judgment result is that prevention is needed;
when the detection system detects that two or more rectangular farmland areas marked with the second marks exist, the detection system identifies the pest spot spreading area of the two or more rectangular farmland areas marked with the second marks, and when the pest spot spreading area exists and the pest spot spreading area has an area which belongs to the spreading area of the first area or the second area, the pest grade judgment result is slight; when no spot spread area exists, the insect pest grade judgment result is slight.
When the pest level is judged, the number of the rectangular farmland areas marked with the first marks is detected in priority to the number of the rectangular farmland areas marked with the second marks, namely, when the detection system cannot detect that two or more rectangular farmland areas marked with the first marks exist, the number of the rectangular farmland areas marked with the second marks is detected in a downward forward delay mode.
The intelligent agricultural insect pest remote detection system comprises a data extraction module, a region division module, an image segmentation and identification module, an insect spot spreading region identification module and an insect pest grade detection and judgment module;
the data extraction module is used for distinguishing the types of crops in the farmland to be detected from the big data, extracting the planting information of the types of crops, and extracting the accompanying insect pest type data of the types of crops based on the big data;
the region division module is used for performing region division on the farmland to be detected and further performing region division on the farmland to be detected after the region division based on the data extracted from the data extraction module to obtain unequal first regions, second regions and spreading regions of the second regions;
the image segmentation and identification module is used for acquiring a crop leaf surface characterization image in a farmland to be detected and segmenting the crop leaf surface characterization image based on a region segmentation method in the region segmentation module; meanwhile, each region obtained after the segmentation processing is subjected to characteristic insect spot identification accompanied with insect pest species;
the spot spread area identification module is used for receiving the data in the image segmentation identification module, calculating the area of the spot and marking according to the calculation result; calculating the permeability of the farmland area, and identifying and judging the spot spreading area based on the permeability;
the insect spot spreading area identification module comprises a blade gap capture unit, a penetration area identification unit, a penetration rate calculation unit and an insect spot spreading area judgment unit;
the blade gap capturing unit is used for capturing all blade gap images of each rectangular farmland area; the infiltration area recognition unit is used for recognizing the insect spots of the images in the blade gap capturing unit and taking the blade gap areas captured with the insect spots as infiltration areas; the permeability calculation unit is used for receiving the data in the permeability area identification unit and calculating the permeability of each rectangular farmland area; the spot spread area judgment unit is used for receiving the data in the permeability calculation unit and finishing the judgment of the spot spread area;
and the pest grade detection and judgment module is used for detecting and judging pest grades of the farmland to be detected, wherein the pest grades comprise serious, prevention and slight.
The pest grade detection and judgment module comprises a rectangular farmland area number detection unit and a grade judgment unit;
the rectangular farmland area number detection unit is used for setting priority levels for detecting the number of rectangular farmland areas with different marks; and the grade judgment unit is used for correspondingly judging different grades of the farmland to be detected according to the priority setting in the rectangular farmland area number detection unit, and the insect pest grade judgment result comprises severity, prevention and slight.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. Intelligent agricultural insect pest remote detection method is characterized by comprising the following steps:
step S100: confirming the types of crops in a farmland to be detected, extracting the planting information of the types of crops, and locking the types of accompanying insect pests of the types of crops based on big data; the planting information comprises crop rhizome planting distribution density and crop leaf distribution density;
step S200: dividing the region of the farmland to be detected into n rectangular farmland regions, and dividing the n rectangular farmland regions into a plurality of first regions, second regions and spreading regions of the second regions based on the planting information;
step S300: acquiring a crop leaf surface characterization image in a farmland to be detected, and correspondingly segmenting the crop leaf surface characterization image into n parts of area characterization images as n parts of rectangular farmland areas are obtained by carrying out area segmentation on the crop leaf surface characterization image in the step S200;
step S400: identifying characteristic insect spots accompanied with insect pest species for each region characterization image, calculating the insect spot area of each region characterization image, and marking the corresponding n rectangular farmland regions according to the insect spot area condition of each region characterization image; simultaneously, respectively calculating the permeability of each rectangular farmland area;
the step S400 includes:
step S401: setting a first area threshold value a and a second area threshold value b, wherein a > b; when the area of the insect spots on one part of the area representation image is larger than the first area threshold value a, making a first mark on the rectangular farmland area corresponding to the part of the area representation image; when the area of the insect spots on one region representation image is larger than the second area threshold value b and smaller than the first area threshold value a, making a second mark on the rectangular farmland region corresponding to the region representation image;
step S402: capturing all blade gap images of each rectangular farmland area, and taking the farmland area corresponding to the blade gap as a penetration area when a pest spot appears on one blade gap image;
step S403: according to the formula
Calculating the permeability P of each rectangular farmland area; wherein h is 1 Indicating the average plant height of the crop in the area where the infiltration occurs; h is 2 Representing the average plant height of the crop at the contour edge of the infiltration area; h represents the average plant height of the crop in the rectangular farmland area; s represents the area of a rectangular farmland region; s 1 Represents the area of the penetration region;
step S500: identifying a plaque propagation region based on the permeability;
step S600: carrying out insect pest grade detection judgment on a farmland to be detected; the insect pest grades comprise severe, prevention and mild.
2. The intelligent agricultural insect pest remote detection method according to claim 1, wherein in step S100, when the accompanying insect pest species are locked, the climate characteristics at the time of detection are used as reference screening conditions; and extracting the accompanying insect pest type information of which the occurrence probability of the crop type is greater than a probability threshold value under the climate characteristic condition during detection.
3. The intelligent agricultural pest remote detection method according to claim 1, wherein the step S200 includes:
step S201: respectively taking the optimum distribution density of the rootstock planting and the optimum distribution density of the leaves of the unit space crop as reference thresholds based on big data, wherein the reference thresholds comprise the rootstock planting density W and the leaf distribution density S; the distribution density of the crop leaves refers to the ratio of the total area of the overlapping or covering of the crop leaves to the total visible area formed by all the crop leaves in the area; i.e. the available formula S = S 1 /s 2 Is shown in which s 1 Represents the total area of the crop leaves between which the leaf overlap or coverage occurs; s 2 Representing the total visible area formed by all the crop leaves in the area;
step S202: setting a unit rectangular area according to the actual area of the farmland to be detected, and selecting one side edge of the farmland to be detected to begin to divide by the unit rectangular area to obtain n rectangular farmland areas; calculating the rhizome planting distribution density of the n rectangular farmland regions, and dividing a region smaller than the rhizome planting density W into a first region; dividing a region larger than the rhizome planting density W into a second region;
step S203: searching the adjacent edge information of all the first areas respectively, taking the first areas with three or more adjacent edges with the second areas as the spreadable areas of the second areas, calculating the distribution density of the crop leaves in each spreadable area, and taking the spreadable areas with the distribution density of the crop leaves being greater than the distribution density S of the leaves as the spreadable areas of the second areas.
4. The intelligent remote pest detection method for agriculture according to claim 3, wherein the step S500 of identifying the region where the pest plague spread comprises:
step S501: setting a penetration threshold, screening out rectangular farmland areas with the permeability P greater than the penetration threshold, and performing line segment connection between all rectangular farmland areas with the permeability P greater than the penetration threshold by taking the area central point of each rectangular farmland area as a starting end;
step S502: and when the length of the line segment meets the length threshold, taking the rectangular farmland areas through which the line segment passes as the insect spot spreading areas of the two rectangular farmland areas.
5. The intelligent agricultural insect pest remote detection method according to claim 1, wherein the insect pest grade judgment process in the step S600 comprises:
when a detection system detects that two or more rectangular farmland areas marked with first marks exist, the detection system identifies the pest spot spreading areas of the two or more rectangular farmland areas marked with the first marks, and when the pest spot spreading areas exist and the pest spot spreading areas have areas which belong to the second areas or spreading areas of the second areas, the pest grade judgment result is serious;
when the detection system detects that two or more rectangular farmland areas marked with second marks exist, the detection system identifies the pest spot spreading areas of the two or more rectangular farmland areas marked with the second marks, and when the pest spot spreading areas exist and the pest spot spreading areas have areas which belong to the second areas or spreading areas of the second areas, the pest grade judgment result is that prevention is needed;
when the detection system detects that two or more rectangular farmland areas marked with second marks exist, the detection system identifies the pest spot spreading areas of the two or more rectangular farmland areas marked with the second marks, and when the pest spot spreading areas exist and areas which belong to the spreading areas of the first area or the second area exist, the pest grade judgment result is slight; and when the spot spread area does not exist, the pest grade judgment result is slight.
6. The intelligent agricultural pest remote detection method according to claim 5, wherein the detection of the number of rectangular farmland areas marked with the first mark is prioritized over the detection of the number of rectangular farmland areas marked with the second mark when the pest level is judged, that is, the detection of the number of rectangular farmland areas marked with the second mark is started in a downward direction when the detection system does not detect the existence of two or more rectangular farmland areas marked with the first mark.
7. The intelligent agricultural insect pest remote detection system applied to the intelligent agricultural insect pest remote detection method according to any one of claims 1 to 6, wherein the system comprises a data extraction module, a region division module, an image segmentation identification module, an insect pest spreading region identification module and an insect pest grade detection judgment module;
the data extraction module is used for distinguishing the types of crops in the farmland to be detected from the big data, extracting the planting information of the types of crops, and extracting the accompanying insect pest type data of the types of crops based on the big data;
the region division module is used for performing region division on the farmland to be detected, and further performing region division on the farmland to be detected after the region division based on the data extracted from the data extraction module to obtain different first regions, second regions and spreading regions of the second regions;
the image segmentation and identification module is used for acquiring a crop leaf surface characterization image in a farmland to be detected and segmenting the crop leaf surface characterization image based on a region segmentation method in the region segmentation module; meanwhile, each region obtained after the segmentation processing is subjected to characteristic insect spot identification accompanied with insect pest species;
the spot spread area identification module is used for receiving the data in the image segmentation identification module, calculating the area of the spot and marking according to the calculation result; calculating the permeability of the farmland area, and identifying and judging the spot spread area based on the permeability;
the insect pest grade detection and judgment module is used for detecting and judging insect pest grades of farmlands to be detected, wherein the insect pest grades comprise serious, prevention and slight insect pest grades.
8. The intelligent remote agricultural pest detection system according to claim 7, wherein the pest spot spreading area identifying module comprises a blade gap capturing unit, a penetration area identifying unit, a penetration rate calculating unit, and a pest spot spreading area determining unit;
the blade gap capturing unit is used for capturing all blade gap images of each rectangular farmland area;
the penetration area recognition unit is used for recognizing the insect spots of the images in the blade gap capturing unit and taking the blade gap areas captured with the insect spots as penetration areas;
the permeability calculation unit is used for receiving the data in the permeability area identification unit and calculating the permeability of each rectangular farmland area;
and the spot spread area judging unit is used for receiving the data in the permeability calculating unit and finishing the judgment of the spot spread area.
9. The intelligent agricultural insect pest remote detection system according to claim 7, wherein the insect pest grade detection and judgment module comprises a rectangular farmland area number detection unit and a grade judgment unit;
the rectangular farmland area number detection unit is used for setting priority levels for detecting the number of rectangular farmland areas with different marks; and the grade judgment unit is used for correspondingly judging different grades of the farmland to be detected according to the priority setting in the rectangular farmland area number detection unit, and the insect pest grade judgment result comprises severity, prevention and slight degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111634701.7A CN114332461B (en) | 2021-12-29 | 2021-12-29 | Intelligent agricultural insect pest remote detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111634701.7A CN114332461B (en) | 2021-12-29 | 2021-12-29 | Intelligent agricultural insect pest remote detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114332461A CN114332461A (en) | 2022-04-12 |
| CN114332461B true CN114332461B (en) | 2023-03-24 |
Family
ID=81016800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111634701.7A Active CN114332461B (en) | 2021-12-29 | 2021-12-29 | Intelligent agricultural insect pest remote detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114332461B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116267445A (en) * | 2023-03-23 | 2023-06-23 | 上海华维可控农业科技集团股份有限公司 | Controllable agricultural cultivation method for preventing and controlling plant virus diseases |
| CN116630815B (en) * | 2023-07-25 | 2023-09-22 | 济南玖通志恒信息技术有限公司 | Intelligent agricultural pest detection method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113050473A (en) * | 2021-02-22 | 2021-06-29 | 上海有间建筑科技有限公司 | Wisdom is insect pest situation remote monitering system for agricultural |
| CN113289341A (en) * | 2020-12-07 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data processing method, aid decision method, skill training method and device |
| CN113344524A (en) * | 2021-06-02 | 2021-09-03 | 武汉飞渡星空科技有限公司 | Intelligent agricultural crop planting management method and system based on remote data acquisition and analysis technology and storage medium |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3091297A1 (en) * | 2018-02-20 | 2019-08-29 | Osram Gmbh | Controlled agricultural system and method for agriculture |
| CA3121647A1 (en) * | 2018-12-24 | 2020-07-02 | The Climate Corporation | Predictive seed scripting for soybeans |
| CN114730437A (en) * | 2019-11-18 | 2022-07-08 | 索尼集团公司 | Information processing apparatus, information processing method, and program |
| CA3151673C (en) * | 2019-11-22 | 2024-01-16 | Farmers Edge Inc. | Dynamic area thresholding for automatic crop health change detection and alerting system |
| CN112106747A (en) * | 2020-08-11 | 2020-12-22 | 上海有间建筑科技有限公司 | Intelligent agricultural insect pest remote automatic monitoring system |
| CN112055079B (en) * | 2020-09-03 | 2022-08-23 | 华艺生态园林股份有限公司 | Disease and pest monitoring and early warning system based on cloud computing platform |
| CN112818982B (en) * | 2021-01-19 | 2022-09-09 | 中国科学院合肥物质科学研究院 | Agricultural pest image detection method based on depth feature autocorrelation activation |
| AU2021100930A4 (en) * | 2021-02-19 | 2021-04-29 | Daniel, D. Arul Pon DR | The controlling irrigation and pesticides in agricultural using method of artificial intelligence |
| CN113313374A (en) * | 2021-05-26 | 2021-08-27 | 郭继光 | Insect density and harmfulness analysis method |
| CN113837076A (en) * | 2021-09-24 | 2021-12-24 | 金陵科技学院 | Agricultural pest intelligent terminal analysis system |
-
2021
- 2021-12-29 CN CN202111634701.7A patent/CN114332461B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113289341A (en) * | 2020-12-07 | 2021-08-24 | 阿里巴巴集团控股有限公司 | Data processing method, aid decision method, skill training method and device |
| CN113050473A (en) * | 2021-02-22 | 2021-06-29 | 上海有间建筑科技有限公司 | Wisdom is insect pest situation remote monitering system for agricultural |
| CN113344524A (en) * | 2021-06-02 | 2021-09-03 | 武汉飞渡星空科技有限公司 | Intelligent agricultural crop planting management method and system based on remote data acquisition and analysis technology and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114332461A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114332461B (en) | Intelligent agricultural insect pest remote detection system and method | |
| US7983446B2 (en) | Method and apparatus for automatic object identification | |
| Gougeon | Automatic individual tree crown delineation using a valley-following algorithm and rule-based system | |
| Gougeon et al. | The individual tree crown approach applied to Ikonos images of a coniferous plantation area | |
| CN109214439B (en) | Infrared image frozen river detection method based on multi-feature fusion | |
| Sanyal et al. | Remote sensing and GIS‐based flood vulnerability assessment of human settlements: a case study of Gangetic West Bengal, India | |
| US20180137612A1 (en) | A stepwise refinement detection method for pavement cracks | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| US11721019B2 (en) | Anomaly detection system | |
| CN112913436A (en) | Water and fertilizer integrated water-saving irrigation control system, method, medium, equipment and terminal | |
| CN114821268A (en) | Weed and crop identification method based on machine learning | |
| CN116911500A (en) | Grassland mouse condition intelligent supervision system and method based on big data monitoring | |
| Ghods et al. | A novel automated image analysis method for counting the population of whiteflies on leaves of crops | |
| CN117095015A (en) | Image segmentation method, device, computer equipment and readable storage medium | |
| CN117237617B (en) | Overhead transmission line image identification method, device, equipment and storage medium | |
| Susaki et al. | Crop field extraction method based on texture analysis and automatic threshold determination | |
| CN108734093B (en) | Method for eliminating pseudo change of fixed-point land video monitoring | |
| CN114972520A (en) | Online detection method for rice lodging direction information | |
| JP2012203582A (en) | Determination method, determination device, determination system and determination program of vegetation region in color image | |
| Noonan | Classification of fallow and yields using Landsat TM data in the sugarcane lands of the Herbert River Catchment | |
| CN117612102A (en) | Agricultural insect pest monitoring system | |
| JP3824922B2 (en) | Image processing apparatus and method | |
| McAlpine et al. | Mapping glider habitat in dry eucalypt forests for Montreal Process indicator 1.1 e: fragmentation of forest types | |
| CN116824403A (en) | Tobacco field Yi Jishui area extraction method and system | |
| Freeman et al. | Mapping inundation of the Amazon Basin |
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 | ||
| GR01 | Patent grant |