CN112129757A - Plant disease and insect pest self-adaptive detection system and method - Google Patents
Plant disease and insect pest self-adaptive detection system and method Download PDFInfo
- Publication number
- CN112129757A CN112129757A CN202011100551.7A CN202011100551A CN112129757A CN 112129757 A CN112129757 A CN 112129757A CN 202011100551 A CN202011100551 A CN 202011100551A CN 112129757 A CN112129757 A CN 112129757A
- Authority
- CN
- China
- Prior art keywords
- mode
- acquisition
- threshold value
- aerial vehicle
- unmanned aerial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 241000607479 Yersinia pestis Species 0.000 title claims abstract description 94
- 201000010099 disease Diseases 0.000 title claims abstract description 68
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 68
- 241000238631 Hexapoda Species 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 title claims description 29
- 238000000034 method Methods 0.000 title abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims abstract description 25
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 238000004891 communication Methods 0.000 claims description 14
- 230000000750 progressive effect Effects 0.000 claims description 10
- 230000007547 defect Effects 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical group C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000005507 spraying Methods 0.000 abstract 1
- 238000012271 agricultural production Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- 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
Abstract
The invention provides a system and a method for acquiring pest and disease monitoring data in precision agriculture, wherein the system mainly comprises a ground monitoring center consisting of a data resolving unit, a high-speed information transceiving unit and a decision control unit and an image acquisition unmanned aerial vehicle data platform for executing conventional/fine operation; the ground monitoring center is communicated with the image acquisition unmanned aerial vehicle data platform through high-speed wireless technologies such as 5G and the like, and data are transmitted and controlled in real time; data acquired by the image acquisition unmanned aerial vehicle platform are monitored, analyzed and resolved, operation of the image acquisition unmanned aerial vehicle in a conventional mode and a fine mode is switched according to a self-adaptive conversion mode threshold, and an effective judgment condition deepening operation mode is further combined; the method greatly reduces the data acquisition amount, ensures the acquisition of key data, and quickly and accurately detects the plant diseases and insect pests. The system and the method are suitable for field operation, particularly for precision agriculture and intelligent agriculture, and provide reliable data support for precision spraying, agricultural decision and management and the like.
Description
Technical Field
The invention relates to the technical field of pest detection in precision agriculture, in particular to a self-adaptive detection system and method for plant pests.
Background
Although China is a big agricultural country, the China is never a strong agricultural country, the agricultural production of China still takes the traditional production mode as the main part, and the fertilizer application, irrigation, disinsection and pest killing are realized by depending on the experience, so that a large amount of manpower and material resources are wasted, the environmental protection and water and soil conservation are seriously threatened, the serious challenge is brought to the sustainable development of agriculture, and the ecological civilized social development requirement is seriously not met. Advanced agricultural production abroad basically carries out fine agricultural production, thereby not only greatly improving the agricultural production benefit, but also enhancing the disaster resistance of crops. In the aspect of precision agriculture, China has a great difference.
Precision agriculture uses big data technology to traditional agriculture, and application sensor and software control agricultural production through mobile platform or computer platform, make traditional agriculture more "accurate". Generally, a plant disease and insect pest detection method is to monitor crop diseases and insect pests by using a plant protection unmanned aerial vehicle, generally, an airborne image acquisition system of the unmanned aerial vehicle is used for acquiring photos to analyze the conditions of the plant diseases and insect pests; unmanned aerial vehicle is at the uniform velocity the collection image that can stabilize in order to expect, is restricted by unmanned aerial vehicle bearing capacity, and bulky backstage analytic system can not carry on unmanned aerial vehicle to image acquisition unmanned aerial vehicle can not directly judge the plant's plant diseases and insect pests situation, need return backstage analytic system with the image information who gathers, returns the plant diseases and insect pests situation that data analysis reachs the crop again by backstage analytic system according to unmanned aerial vehicle. The mode is not focused, so that the data acquisition period is long, no hierarchy exists, the image data volume is huge, the pest and disease analysis efficiency is seriously influenced, and the operation benefit of precision agriculture is also seriously influenced.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the self-adaptive plant disease and insect pest detection method overcomes the defects of the prior art and can detect the plant disease and insect pest timely and accurately.
The invention relates to a system and a method capable of adaptively adjusting a plant information acquisition mode to detect according to the severity of plant diseases and insect pests, wherein FIG. 1 is a schematic diagram of main components of the system, and the system mainly comprises a ground monitoring center and an image acquisition unmanned aerial vehicle; the ground monitoring center consists of a data resolving unit, a high-speed communication unit a, a decision control unit and a carrier platform; the image acquisition unmanned aerial vehicle consists of a flight control unit, a monitoring unit, a high-speed communication unit b and an image acquisition unit; an image acquisition unmanned aerial vehicle for executing conventional/fine operation;
further, the plant disease and insect pest self-adaptive detection system switches a conventional operation mode and a fine operation mode through a self-adaptive conversion mode threshold value;
further, the fine operation mode is divided into a plurality of progressive levels;
furthermore, the ground monitoring center controls the progressive implementation of the fine operation sub-mode hierarchy through effective judgment conditions
Further, the adaptive conversion mode threshold value comprises a color threshold value, a form threshold value and a defect threshold value;
further, the color threshold value is the ratio of the color information of the collected image to the color difference of a color standard value, the color standard value is the average attribute value of three colors of lightness, hue and chroma of the crop without diseases and insect pests, and the color difference threshold value is 15-50%;
further, the form threshold value is a ratio of collected image form information to a form standard value, the form standard value is an average attribute value of three forms, namely the size, height and shape of the crop without diseases and insect pests, and the form threshold value is set to be 15-50%;
further, the incomplete threshold value is the ratio of the collected image leaf information to a leaf standard value, the leaf standard value is the complete leaf state of the crop without diseases and insect pests, and the incomplete threshold value is set to be 15-50%;
further, the ground monitoring center and the image acquisition unmanned aerial vehicle transmit and control data in real time through a 5G high-speed wireless communication device (abbreviated as 5G below);
further, after data acquired by the image acquisition unmanned aerial vehicle platform is analyzed and resolved through ground monitoring, the ground monitoring center controls the image acquisition unmanned aerial vehicle to be converted from a conventional operation mode to a fine operation mode according to a self-adaptive switching strategy rule;
further, the system progressively implements a fine operation sub-mode after effectively judging conditions;
further, the conventional operation mode is constant speed, constant height and constant angle (vertical overlook) image acquisition;
further, the fine operation sub-mode mainly comprises: low-speed acquisition, hovering acquisition, low-position acquisition, repeated acquisition, high-definition acquisition, multi-angle acquisition and dynamic acquisition;
further, the low-speed collecting speed is 1/3-1/2 of the normal operation speed;
further, the hover acquisition is fixed point gaze acquisition;
further, the image acquisition unmanned aerial vehicle is debugged to be 1/50-1/2 of the conventional operation height in the low-position acquisition process;
further, the repeated collection is to collect the same area for multiple times;
further, higher physical pixels are adopted during high-definition acquisition;
further, the multi-angle acquisition is used for multi-angle acquisition of abnormal points;
further, the dynamic acquisition performs continuous image acquisition on outliers.
The invention relates to a self-adaptive detection method for plant diseases and insect pests, which comprises the following steps:
i, planning an operation scheme by a ground monitoring center according to an operation area, plant characteristics, a growth period, pest and disease conditions and the like;
the further operation scheme is transmitted to the unmanned aerial vehicle through 5G, and the image acquisition unmanned aerial vehicle acquires conventional images according to the first area in the operation scheme;
III, further monitoring and analyzing the conventional image and a related disease and insect pest database of the first region conventional image, if the conventional image exceeds a self-adaptive mode conversion threshold value, switching to a fine operation mode, and continuing to collect the lower region conventional image when the conventional image does not exceed the self-adaptive mode conversion threshold value;
IV, further adaptive mode conversion threshold values comprise a color threshold value, a form threshold value, a defect threshold value and the like;
the further color threshold value of V takes three color attributes of lightness, hue and chroma of crops without diseases and insect pests as standard values, the collected image information is compared with the standard values in a color difference way, and the color difference threshold value is 15-50% (the value is in inverse proportion to the definition and is related to factors such as insect pest types and the like;
VI, comparing the collected image information with a standard value by taking three morphological attributes of the size, height and shape of the crop without diseases and insect pests as the standard value, wherein the morphological threshold value is 15-50% (the value is inversely proportional to the definition and is related to factors such as insect pest type and the like;
the further incomplete threshold value is compared with a standard value by taking the integrity of leaves of crops without diseases and insect pests as the standard value, and the incomplete threshold value is 15-50% (the value is inversely proportional to the definition and is related to factors such as insect pest types and the like;
step VIII, the further image acquisition unmanned aerial vehicle enters a fine operation mode through a self-adaptive conversion mode, firstly, the operation is acquired in the area according to a low-speed mode, data are transmitted back to a ground monitoring center in real time, the low-speed mode flight speed is 1/3-1/2 of the conventional mode speed, and the values are taken according to experience and are related to plant attributes and plant diseases and insect pests;
IX, further analyzing data collected by the ground monitoring center according to a low-speed mode, and controlling the image collection unmanned aerial vehicle to carry out conventional image collection operation on a lower area if effective judgment on plant diseases and insect pests can be made; if the effective judgment is not made, entering the next level, namely hovering collection; the effective judgment is that the system can accurately judge the pest condition according to the collected data and by combining with a pest related database;
step X, the ground monitoring center continuously analyzes the data received in real time, and progressively executes corresponding fine operation sub-mode operation according to an effective judgment rule;
when each sub-mode of the XI further fine operation cannot make effective judgment, the area is marked to be abnormal, and manual judgment or special inspection is carried out;
and XII is further compared with the operation scheme, if the operation scheme is not completed, lower region data acquisition is carried out, if the operation scheme is completed, the image acquisition work of the region is finished, and the pest and disease data of the corresponding region are analyzed and completed, so that the application of precision agriculture, intelligent agriculture and the like is rapidly supported.
The beneficial technical effects of the invention are as follows:
1. the invention relates to a plant disease and insect pest self-adaptive detection system and method, which solve the problem of low efficiency caused by large image data quantity due to long data acquisition period and no hierarchy caused by no key point in the prior art; 2. the system and the method transmit data in real time through 5G, and adaptively switch to a fine mode for operation according to the pest and disease conditions, so that key points are realized, the acquisition quality is ensured, and the accuracy of pest and disease detection is ensured; 3. the hierarchical acquisition design of the fine mode effectively judges the reference of the rule, avoids unnecessary acquisition times and data, saves acquisition time and improves analysis efficiency; 4. the two technologies of repeated collection and hierarchical collection not only achieve effective control in collection time, but also greatly reduce the total quantity of collected data, thereby reducing the analysis pressure of a ground monitoring center, reducing the cost of processing equipment of a corresponding control center and correspondingly reducing the comprehensive cost of the whole pest and disease detection system; 5. the adaptive switching strategy can distinguish the application of the conventional acquisition operation and the fine acquisition operation mode, avoids the possibility of fine acquisition operation in the conventional area and reduces waste; 6. the progressive fine operation mode completes acquisition by determining the plant diseases and insect pests, namely the region, so that unnecessary fine acquisition is avoided, and the efficiency is further improved; 7. compared with the conventional collecting operation, the method has higher accuracy, is more beneficial to the accurate judgment of plant diseases and insect pests, and better supports the implementation of accurate agriculture.
The invention relates to a rapid detection system and a rapid detection method for plant diseases and insect pests, which are matched with a data acquisition and analysis system for precision agriculture and intelligent agriculture; the system is used for precise agriculture and intelligent agriculture, and provides reliable data support for agricultural decision, agricultural production, agricultural management and the like so as to continuously improve the agricultural modernization level of China.
Drawings
FIG. 1 is a system configuration diagram of the present invention.
Fig. 2 is a diagram of an image acquisition unmanned aerial vehicle.
Fig. 3 is a ground control center configuration diagram.
FIG. 4 is a flow chart of the method of the present invention.
Fig. 5 is a block diagram of the adaptive mode switching threshold of the present invention.
FIG. 6 is a schematic view of a blade deformity.
Fig. 7 is a schematic of a conventional operation mode.
FIG. 8 is a schematic diagram of multi-angle acquisition in fine job mode.
In the figure: 1-a ground monitoring center, 11-high-speed communication units a, 12-a decision control unit, 13-a data resolving unit and 14-a carrier platform; 2-image acquisition unmanned aerial vehicle, 21-flight control unit, 22-monitoring unit, 23-high-speed communication unit b, 24-carrying platform and 25-image acquisition unit.
Detailed Description
The present invention will be described in detail with reference to specific embodiments. The following examples are presented to assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any manner.
Example one
As shown in the figure, the invention is a system and a method capable of adaptively adjusting a plant information acquisition mode to detect according to the severity of plant diseases and insect pests, and the system mainly comprises a ground monitoring center 1 and an image acquisition unmanned aerial vehicle 1; the ground monitoring center 1 consists of a data resolving unit 13, a high-speed communication unit a11, a decision control unit 12 and a carrier platform 14; the image acquisition unmanned aerial vehicle 2 consists of a flight control unit 21, a monitoring unit 22, a high-speed communication unit b23, a carrying platform 24 and an image acquisition unit 25, and the image acquisition unmanned aerial vehicle 2 can execute a conventional operation mode and a fine operation mode;
further, the plant disease and insect pest self-adaptive detection system switches a conventional operation mode and a fine operation mode through a self-adaptive conversion mode threshold value;
further, the fine operation mode is divided into a plurality of progressive levels;
further, the ground monitoring center 1 controls the progressive implementation of the fine operation sub-mode hierarchy through effective judgment conditions
Further, the adaptive conversion mode threshold value comprises a color threshold value, a form threshold value and a defect threshold value;
further, the color threshold value is the ratio of the color information of the collected image to the color difference of a color standard value, the color standard value is the average attribute value of three colors of lightness, hue and chroma of the crop without diseases and insect pests, and the color difference threshold value is 15-50%;
further, the form threshold value is a ratio of collected image form information to a form standard value, the form standard value is an average attribute value of three forms, namely the size, height and shape of the crop without diseases and insect pests, and the form threshold value is set to be 15-50%;
further, the incomplete threshold value is the ratio of the collected image leaf information to a leaf standard value, the leaf standard value is the complete leaf state of the crop without diseases and insect pests, and the incomplete threshold value is set to be 15-50%;
further, the ground monitoring center 1 and the image acquisition unmanned aerial vehicle 2 transmit and control real-time data through a 5G high-speed wireless communication device (abbreviated as 5G) and the like, the 5G is loaded on the image acquisition unmanned aerial vehicle 2 correspondingly on the basis of the requirement of not obviously increasing the complexity of an onboard system of the image acquisition unmanned aerial vehicle 2, and the data are transmitted back to the ground control center 1 in real time;
further, after the data acquired by the image acquisition unmanned aerial vehicle 2 is analyzed and resolved through ground monitoring, the ground monitoring center 1 controls the image acquisition unmanned aerial vehicle 2 to be converted from a conventional operation mode to a fine operation mode according to a self-adaptive switching strategy rule;
further, after the system effectively judges the condition, a fine operation sub-mode is progressively implemented through a conventional operation mode, and fine image data acquisition is carried out on a hotspot area;
further, the conventional operation mode is constant speed, constant height and constant angle (vertical overlook) image acquisition, and image acquisition is carried out on a common area;
further, the fine operation sub-mode mainly comprises: the unmanned image acquisition system comprises an unmanned image acquisition machine 2, a low-speed acquisition unit, a hovering acquisition unit, a low-position acquisition unit, a repeated acquisition unit, a high-definition acquisition unit, a multi-angle acquisition unit and a dynamic acquisition unit, wherein the unmanned image acquisition machine is used for further refining and pertinently acquiring images of key areas;
further, the low-speed acquisition speed is 1/3-1/2 of the conventional operation speed, and the image acquisition unmanned aerial vehicle 2 reduces the flight speed and performs image acquisition more carefully;
further, the hovering acquisition is fixed-point staring acquisition, and the image acquisition unmanned aerial vehicle 2 performs uninterrupted image acquisition at the same position;
further, the image acquisition unmanned aerial vehicle 2 is debugged to be 1/50-1/2 of the conventional operation height during low-position acquisition, so that the functions of reducing the high-low tensioning distance and improving the definition are achieved;
further, the repeated acquisition is to acquire the same region for multiple times, and acquire images for multiple times;
furthermore, higher physical pixels are adopted during high-definition acquisition, so that the definition of the image is improved, and the image identification is facilitated;
furthermore, the multi-angle acquisition acquires abnormal points in multiple angles, so that the condition of the abnormal points is reflected in an all-dimensional manner;
further, the dynamic acquisition performs continuous image acquisition on outliers.
The invention relates to a self-adaptive detection method for plant diseases and insect pests, which comprises the following steps:
i, planning an operation scheme by a ground monitoring center 1 according to an operation area, plant characteristics, a growth period, pest and disease conditions and the like;
the further operation scheme is transmitted to the image acquisition unmanned aerial vehicle 2 through 5G, and the image acquisition unmanned aerial vehicle 2 performs conventional image acquisition according to the first area in the operation scheme;
III, further monitoring and analyzing the conventional image and a related disease and insect pest database of the first region conventional image, if the conventional image exceeds a self-adaptive mode conversion threshold value, switching to a fine operation mode, and continuing to collect the lower region conventional image when the conventional image does not exceed the self-adaptive mode conversion threshold value;
IV, further adaptive mode conversion threshold values comprise a color threshold value, a form threshold value, a defect threshold value and the like;
the further color threshold value of V takes three color attributes of lightness, hue and chroma of crops without diseases and insect pests as standard values, the collected image information is compared with the standard values in a color difference way, and the color difference threshold value is 15-50% (the value is in inverse proportion to the definition and is related to factors such as insect pest types and the like);
VI, comparing the collected image information with a standard value by taking three morphological attributes of the size, height and shape of the crop without diseases and insect pests as the standard value, wherein the morphological threshold value is 15-50% (the value is inversely proportional to the definition and is related to factors such as insect pest type and the like;
the further incomplete threshold value is compared with a standard value by taking the integrity of leaves of crops without diseases and insect pests as the standard value, and the incomplete threshold value is 15-50% (the value is inversely proportional to the definition and is related to factors such as insect pest types and the like;
VIII, the further image acquisition unmanned aerial vehicle 2 enters a fine operation mode through a self-adaptive conversion mode, firstly, the operation is acquired in the area according to a low-speed mode, data are transmitted back to the ground monitoring center 1 in real time, the low-speed mode flight speed is 1/3-1/2 of the conventional mode speed, and the values are taken according to experience and are related to plant attributes and plant diseases and insect pests;
IX further ground monitoring center 1 collects data analysis according to low speed mode, can make effective judgement to pest and disease damage, control image acquisition unmanned aerial vehicle 2 to carry on the routine operation of image acquisition of the inferior region; if the effective judgment is not made, entering the next level, namely hovering collection; the effective judgment is that the system can accurately judge the pest condition according to the collected data and by combining with a pest related database;
the ground monitoring center 1 further analyzes the data received in real time continuously, and executes corresponding fine operation sub-mode operation according to effective judgment rules, and the progressive level of the fine operation sub-mode can be adjusted according to factors such as plant conditions, operation areas, operation real-time environment and the like, so that the data acquisition is facilitated;
when each sub-mode of the XI further fine operation cannot make effective judgment, the area is marked to be abnormal, and manual judgment or special inspection is carried out;
and XII is further compared with the operation scheme, if the operation scheme is not completed, lower region data acquisition is carried out, if the operation scheme is completed, the image acquisition work of the region is finished, and the pest and disease data of the corresponding region are analyzed and completed, so that the application of precision agriculture, intelligent agriculture and the like is rapidly supported.
Example two
The invention relates to a self-adaptive detection method for plant diseases and insect pests, which comprises the following steps:
i, planning an operation scheme by a ground monitoring center 1 according to an operation area, plant characteristics, a growth period, pest and disease conditions and the like;
II, transmitting the planned operation scheme to the multi-rotor unmanned aerial vehicle through 5G, and carrying out conventional image acquisition on the multi-rotor unmanned aerial vehicle according to a first area in the operation scheme;
III, transmitting the conventional image acquisition of the first area to a ground monitoring center 1 by a multi-rotor unmanned aerial vehicle through 5G in real time;
analyzing the conventional image and the pest and disease database by the ground monitoring center 1, if the conventional image exceeds the self-adaptive mode conversion threshold value, switching to a fine operation mode, and if the conventional image does not exceed the self-adaptive mode conversion threshold value, continuing to collect the lower-region conventional image;
v, the multi-rotor unmanned aerial vehicle enters a fine operation mode, operation is collected in the area according to a low-speed mode, and data are transmitted back to a ground monitoring center in real time; the ground monitoring center 1 collects data according to a low-speed mode, analyzes the data, can effectively judge plant diseases and insect pests, and controls the unmanned aerial vehicle to carry out conventional image collection operation on a lower area;
VI, if the effective judgment is not made, entering the next level, namely hovering collection; if each sub-mode of the fine operation cannot make effective judgment, marking the area with abnormity, and manually judging; many rotor unmanned aerial vehicle then compares with the operation scheme, if do not accomplish the operation scheme, gets into lower region data acquisition, accomplishes the operation scheme, then this regional image acquisition work finishes, and corresponding regional plant diseases and insect pests data also analyzes and accomplishes.
When image acquisition unmanned aerial vehicle 2 adopted fixed wing or single rotor unmanned aerial vehicle, but the preliminary analytic system of airborne, directly carry out the self-adaptation threshold value by image acquisition unmanned aerial vehicle 2 real-time and judge, reduce data transmission, improve the operating efficiency.
The image acquisition unit of the image acquisition unmanned aerial vehicle 2 can carry multispectral, infrared or hyperspectral cameras and the like so as to widen the detection means and improve the detection precision and efficiency.
The ground monitoring center 1 and the high-speed communication unit a11 of the image acquisition unmanned aerial vehicle 2 adopt a wireless frequency domain multi-channel technology, the pressure of large image data volume on transmission is reduced, and the operation efficiency is improved.
The above-described embodiments of the present invention should not be construed as limiting the scope of the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. The utility model provides a plant diseases and insect pests self-adaptation detecting system, includes ground surveillance center (1) and image acquisition unmanned aerial vehicle (2), its characterized in that: the ground monitoring center (1) consists of a data resolving unit (13), a high-speed communication unit a (11), a decision control unit (12) and a carrier platform (14); the image acquisition unmanned aerial vehicle (2) consists of a flight control unit (21), a monitoring unit (22), a high-speed communication unit b (23), a carrying platform (24) and an image acquisition unit (25), and is used for performing a conventional operation mode and a fine operation mode; the plant disease and insect pest self-adaptive detection system switches a conventional operation mode and a fine operation mode through a self-adaptive conversion mode threshold; the fine operation mode is divided into a plurality of progressive levels; the ground monitoring center (1) controls the progressive implementation of the fine operation sub-mode hierarchy through effective judgment conditions.
2. A plant pest adaptive detection system according to claim 1, characterised in that: the adaptive conversion mode threshold value comprises a color threshold value, a form threshold value and a defect threshold value;
the color threshold is the ratio of collected image color information to a color standard value color difference, the color standard value is an average attribute value of three colors of lightness, hue and chroma of crops without diseases and insect pests, and the color difference threshold is 15-50%;
the form threshold value is the ratio of the collected image form information to a form standard value, the form standard value is an average attribute value of three forms of the size, height and shape of the crop without diseases and insect pests, and the form threshold value is set to be 15-50%;
the incomplete threshold value is the ratio of collected image leaf information to a leaf standard value, the leaf standard value is the complete leaf state of the crop without diseases and insect pests, and the incomplete threshold value is set to be 15-50%.
3. A plant pest adaptive detection system according to claim 1, characterised in that: the fine operation mode comprises sub-modes of low-speed acquisition, hovering acquisition, low-order acquisition, repeated acquisition, high-definition acquisition, multi-angle acquisition and dynamic acquisition, and the sub-modes of the fine operation are sequentially adopted in a progressive mode.
4. A plant pest adaptive detection system according to claim 1, characterised in that: the effective judgment condition is that the system can accurately judge the pest condition according to the collected data and by combining with the pest related database.
5. A plant pest and disease adaptive detection system according to any one of claims 1 to 4, wherein: the self-adaptive conversion is carried out by the ground monitoring center (1) according to comparison and analysis of real-time acquisition data and a self-adaptive conversion mode threshold value, and the ground monitoring center sends a message to control the image acquisition unmanned aerial vehicle (2) to carry out conventional acquisition operation and switch the conventional acquisition operation into a fine acquisition operation mode.
6. A plant pest and disease adaptive detection system according to any one of claims 1 to 4, wherein: the self-adaptive conversion is realized by analyzing and comparing the real-time data and the threshold value of the self-adaptive conversion mode of the image acquisition unmanned aerial vehicle (2) and controlling the image acquisition unmanned aerial vehicle (2) to carry out conventional acquisition operation and switch the conventional acquisition operation into a fine acquisition operation mode.
7. A plant pest adaptive detection system according to claim 1, characterised in that: the high-speed communication unit a (11) and the high-speed communication unit b (23) adopt a wireless frequency domain multi-channel mode or a 5G high-speed communication mode.
8. A plant pest adaptive detection system according to claim 1, characterised in that: the image acquisition unmanned aerial vehicle (2) is a multi-rotor unmanned aerial vehicle, a single-rotor unmanned aerial vehicle or a fixed-wing unmanned aerial vehicle.
9. A self-adaptive detection method for plant diseases and insect pests is characterized by comprising the following steps: the self-adaptive detection method is carried out according to the following steps:
i, planning an operation scheme by a ground monitoring center (1) according to an operation area, plant characteristics, a growth period, pest and disease damage conditions and the like;
the further operation scheme is transmitted to the image acquisition unmanned aerial vehicle (2) through 5G, and the image acquisition unmanned aerial vehicle (2) performs conventional image acquisition according to the first area in the operation scheme;
III, further monitoring and analyzing the conventional image and a related disease and insect pest database of the first region conventional image, if the conventional image exceeds a self-adaptive mode conversion threshold value, switching to a fine operation mode, and continuing to collect the lower region conventional image when the conventional image does not exceed the self-adaptive mode conversion threshold value;
IV, further adaptive mode conversion threshold values comprise a color threshold value, a form threshold value, a defect threshold value and the like;
the further color threshold value of V takes three color attributes of lightness, hue and chroma of crops without diseases and insect pests as standard values, the collected image information is compared with the standard values in a color difference way, and the color difference threshold value is 15-50% (the value is in inverse proportion to the definition and is related to factors such as insect pest types and the like);
VI, comparing the collected image information with a standard value by taking three morphological attributes of the size, height and shape of the crop without diseases and insect pests as the standard value, wherein the morphological threshold value is 15-50% (the value is inversely proportional to the definition and is related to factors such as insect pest type and the like);
VII, taking the integrity of leaves of crops without diseases and insect pests as a standard value, acquiring image information and comparing the image information with the standard value, wherein the defect threshold value is 15-50% (the value is inversely proportional to the definition and is related to factors such as insect pest types);
VIII, a further image acquisition unmanned aerial vehicle (2) enters a fine operation mode through a self-adaptive conversion mode, firstly, acquisition operation is carried out on the area according to a low-speed mode, data are transmitted back to the ground monitoring center (2) in real time, and the low-speed mode flight speed is 1/3-1/2 of the conventional mode speed, (relevant to plant attributes and plant diseases and insect pests, and values are taken according to experience);
IX further ground monitoring center 1 collects data analysis according to low speed mode, can make effective judgement to pest and disease damage, control image acquisition unmanned aerial vehicle (2) to carry on the routine operation of image acquisition of the inferior region; if the effective judgment is not made, entering the next level, namely hovering collection; the effective judgment is that the system can accurately judge the pest condition according to the collected data and by combining with a pest related database;
the ground monitoring center (1) further analyzes the data received in real time continuously, and executes corresponding fine operation sub-mode operation according to effective judgment rules;
when each sub-mode of the XI further fine operation cannot make effective judgment, the area is marked to be abnormal, and manual judgment or special inspection is carried out;
and XII is further compared with the operation scheme, if the operation scheme is not completed, lower region data acquisition is carried out, if the operation scheme is completed, the image acquisition work of the region is finished, and the pest and disease damage data of the corresponding region are analyzed and completed.
10. A plant pest adaptive detection method according to claim 9, characterised in that: the progressive hierarchical sequence of the fine operation sub-mode can be adjusted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011100551.7A CN112129757A (en) | 2020-10-15 | 2020-10-15 | Plant disease and insect pest self-adaptive detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011100551.7A CN112129757A (en) | 2020-10-15 | 2020-10-15 | Plant disease and insect pest self-adaptive detection system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112129757A true CN112129757A (en) | 2020-12-25 |
Family
ID=73854107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011100551.7A Pending CN112129757A (en) | 2020-10-15 | 2020-10-15 | Plant disease and insect pest self-adaptive detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112129757A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113325872A (en) * | 2021-06-10 | 2021-08-31 | 广州极飞科技股份有限公司 | Plant inspection method, device and system and aircraft |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202042825U (en) * | 2011-03-09 | 2011-11-16 | 南京航空航天大学 | Power transmission line routing inspection system based on multi-rotor unmanned aerial vehicle |
| CN105510242A (en) * | 2015-12-28 | 2016-04-20 | 南京农业大学 | Crop growth monitoring method and device based on multi-rotor wing unmanned aerial vehicle platform |
| CN106200683A (en) * | 2016-07-04 | 2016-12-07 | 广东天米教育科技有限公司 | Unmanned plane plant protection system and plant protection method |
| CN107315381A (en) * | 2017-08-02 | 2017-11-03 | 宿松县玖索科技信息有限公司 | A kind of monitoring method of diseases and pests of agronomic crop |
| US20170374323A1 (en) * | 2015-01-11 | 2017-12-28 | A.A.A Taranis Visual Ltd | Systems and methods for agricultural monitoring |
| CN107783522A (en) * | 2017-10-18 | 2018-03-09 | 来安县威光绿园生态农业专业合作社 | A kind of diseases and pests of agronomic crop Intelligent prevention and cure system based on Internet of Things |
| CN109901624A (en) * | 2019-04-11 | 2019-06-18 | 株洲时代电子技术有限公司 | A kind of bridge method for inspecting |
| CN110050619A (en) * | 2019-05-10 | 2019-07-26 | 广西润桂科技有限公司 | Unmanned plane sugarcane prevention and control of plant diseases, pest control spray method based on accurate meteorological support technology |
| CN110286091A (en) * | 2019-06-11 | 2019-09-27 | 华南农业大学 | A kind of near-earth remote sensing images acquisition method based on unmanned plane |
| WO2020040063A1 (en) * | 2018-08-20 | 2020-02-27 | 株式会社ナイルワークス | Field crop photographing method and photographing drone |
| CN111543413A (en) * | 2020-05-28 | 2020-08-18 | 中国农业大学 | Method and system for accurately applying pesticide by agricultural robot in air-ground cooperation |
-
2020
- 2020-10-15 CN CN202011100551.7A patent/CN112129757A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202042825U (en) * | 2011-03-09 | 2011-11-16 | 南京航空航天大学 | Power transmission line routing inspection system based on multi-rotor unmanned aerial vehicle |
| US20170374323A1 (en) * | 2015-01-11 | 2017-12-28 | A.A.A Taranis Visual Ltd | Systems and methods for agricultural monitoring |
| CN105510242A (en) * | 2015-12-28 | 2016-04-20 | 南京农业大学 | Crop growth monitoring method and device based on multi-rotor wing unmanned aerial vehicle platform |
| CN106200683A (en) * | 2016-07-04 | 2016-12-07 | 广东天米教育科技有限公司 | Unmanned plane plant protection system and plant protection method |
| CN107315381A (en) * | 2017-08-02 | 2017-11-03 | 宿松县玖索科技信息有限公司 | A kind of monitoring method of diseases and pests of agronomic crop |
| CN107783522A (en) * | 2017-10-18 | 2018-03-09 | 来安县威光绿园生态农业专业合作社 | A kind of diseases and pests of agronomic crop Intelligent prevention and cure system based on Internet of Things |
| WO2020040063A1 (en) * | 2018-08-20 | 2020-02-27 | 株式会社ナイルワークス | Field crop photographing method and photographing drone |
| CN109901624A (en) * | 2019-04-11 | 2019-06-18 | 株洲时代电子技术有限公司 | A kind of bridge method for inspecting |
| CN110050619A (en) * | 2019-05-10 | 2019-07-26 | 广西润桂科技有限公司 | Unmanned plane sugarcane prevention and control of plant diseases, pest control spray method based on accurate meteorological support technology |
| CN110286091A (en) * | 2019-06-11 | 2019-09-27 | 华南农业大学 | A kind of near-earth remote sensing images acquisition method based on unmanned plane |
| CN111543413A (en) * | 2020-05-28 | 2020-08-18 | 中国农业大学 | Method and system for accurately applying pesticide by agricultural robot in air-ground cooperation |
Non-Patent Citations (1)
| Title |
|---|
| 顾军林: "大数据在农业无人机上的应用研究", pages 213 - 217 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113325872A (en) * | 2021-06-10 | 2021-08-31 | 广州极飞科技股份有限公司 | Plant inspection method, device and system and aircraft |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111339921A (en) | Insect disease detection unmanned aerial vehicle based on lightweight convolutional neural network and detection method | |
| CN108845536A (en) | A kind of stockyard fugitive dust real-time detection and intelligent water sprinkling device for reducing dust and method based on video technique | |
| CN109220226A (en) | Fruit automatic recognition classification and the orchard intellectualizing system of picking | |
| CN102131101A (en) | Intelligent video image quality automatic analysis system and method | |
| CN112166911B (en) | Rapid accurate pest and disease damage detection pesticide application system and method | |
| CN109991911A (en) | A kind of orchard comprehensive monitoring system based on Internet of Things | |
| CN104202560B (en) | A kind of video monitoring system and method based on image recognition | |
| CN104680524A (en) | Disease diagnosis method for leaf vegetables | |
| CN112069985B (en) | High-resolution field image rice spike detection and counting method based on deep learning | |
| CN103090946B (en) | Method and system for measuring single fruit tree yield | |
| CN102208099A (en) | Illumination-change-resistant crop color image segmentation method | |
| CN112129757A (en) | Plant disease and insect pest self-adaptive detection system and method | |
| CN113408087A (en) | Substation inspection method based on cloud side system and video intelligent analysis | |
| CN110187653A (en) | A kind of diseases and pests of agronomic crop monitoring system and operating method based on LoRa Delamination Transmission | |
| CN115660288A (en) | Analysis management system based on internet big data | |
| CN103226709B (en) | A kind of network curtain image recognition method of fall webworm larvae | |
| CN106909898A (en) | Image intelligent analysing terminal and method in straw-returning monitoring | |
| CN102608349B (en) | Intelligent greenhouse nectarine fruit growth rate wireless monitoring system based on embedded dual-camera platform | |
| CN113349188B (en) | Lawn and forage precise weeding method based on cloud weeding spectrum | |
| CN205179252U (en) | Look screen and gather processing system based on thing networking | |
| Hong et al. | Adaptive target spray system based on machine vision for plant protection UAV | |
| CN114627505A (en) | Automatic milk cow cleanliness scoring method and system, storage medium and equipment | |
| CN202004914U (en) | Intelligent video image quality automatic analysis system | |
| Lina et al. | Design of intelligent pest monitoring system based on image classification algorithm | |
| Bai et al. | An algorithm of leaf image segmentation based on color features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |
|
| RJ01 | Rejection of invention patent application after publication |