CN116309625A - Data processing method suitable for intelligent agriculture - Google Patents

Data processing method suitable for intelligent agriculture Download PDF

Info

Publication number
CN116309625A
CN116309625A CN202211409305.9A CN202211409305A CN116309625A CN 116309625 A CN116309625 A CN 116309625A CN 202211409305 A CN202211409305 A CN 202211409305A CN 116309625 A CN116309625 A CN 116309625A
Authority
CN
China
Prior art keywords
abnormal
area
acquisition
value
pixel
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.)
Granted
Application number
CN202211409305.9A
Other languages
Chinese (zh)
Other versions
CN116309625B (en
Inventor
周鹏
邹红强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
JURONG INDIGENOUS TREE SPECIES RESEARCH INSTITUTE
Original Assignee
JURONG INDIGENOUS TREE SPECIES RESEARCH INSTITUTE
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by JURONG INDIGENOUS TREE SPECIES RESEARCH INSTITUTE filed Critical JURONG INDIGENOUS TREE SPECIES RESEARCH INSTITUTE
Priority to CN202211409305.9A priority Critical patent/CN116309625B/en
Publication of CN116309625A publication Critical patent/CN116309625A/en
Application granted granted Critical
Publication of CN116309625B publication Critical patent/CN116309625B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0631Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06312Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02Agriculture; Fishing; Forestry; Mining
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/52Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Multimedia (AREA)
  • Agronomy & Crop Science (AREA)
  • Databases & Information Systems (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Primary Health Care (AREA)
  • Animal Husbandry (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Geometry (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a data processing method suitable for intelligent agriculture, which is characterized in that a cultivated area of Tian Changduan is collected in a partitioning mode according to attribute data and quantity information to obtain a current cultivated area top view; decomposing a top view of a current cultivated land to generate a current pixel point set, comparing a pixel value of each pixel point in the current pixel point set with a standard pixel value to determine abnormal pixel points, counting the abnormal pixel points to generate a first abnormal total set, and splitting the first abnormal total set into a plurality of independent first abnormal subsets according to the position relation of each abnormal pixel point; if the number of the pixel points in the abnormal subset is larger than a preset number value, determining a shooting path according to the abnormal subset, controlling the acquisition device to acquire according to the shooting path, generating a verification image, and sending the verification image to the field long end for verification, so that an abnormal area can be automatically identified and shooting verification can be performed.

Description

Data processing method suitable for intelligent agriculture
Technical Field
The invention relates to a data processing technology, in particular to a data processing method suitable for intelligent agriculture.
Background
The intelligent agriculture can build novel facilities in rural areas through informatization and intelligent methods, and after good network facilities are built, unique core resource advantages such as video monitoring and artificial intelligent identification methods can be fully exerted to manage rural cultivated lands, so that comprehensive supervision of the cultivated lands is achieved.
However, at present, a field length or unmanned aerial vehicle is still required to carry out fixed inspection at fixed time, and a great deal of manpower is consumed for carrying out farmland protection and supervision on each inspection path and inspection of cultivated lands, and meanwhile, in the prior art, the inspection through the unmanned aerial vehicle still requires a user to carry out real-time operation, so that the user needs to spend a great deal of energy and has low image efficiency for viewing corresponding cultivated land areas in real time.
Therefore, how to automatically identify abnormal areas in a cultivated area is a problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a data processing method suitable for intelligent agriculture, which can automatically identify abnormal areas in cultivated areas, saves a great deal of manpower, automatically and comprehensively collects the abnormal areas and sends the abnormal areas to Tian Changduan for secondary verification, and ensures the accuracy of results.
In a first aspect of the embodiments of the present invention, a data processing method suitable for smart agriculture is provided, including:
Acquiring attribute data and corresponding quantity information of the idle acquisition device, and carrying out regional acquisition on the cultivated area of Tian Changduan according to the attribute data and the quantity information to obtain a current cultivated land top view;
acquiring preset crop type information corresponding to the cultivated land area and a standard pixel value corresponding to the preset crop type information;
decomposing the current cultivated land top view to generate a current pixel point set, comparing the pixel value of each pixel point in the current pixel point set with a standard pixel value to determine an abnormal pixel point, counting the abnormal pixel points to generate a first abnormal total set, and splitting the first abnormal total set into a plurality of independent first abnormal subsets according to the position relation of each abnormal pixel point;
if the number of the pixel points in the abnormal subset is larger than a preset number value, determining a shooting path according to the abnormal subset, controlling an acquisition device to acquire according to the shooting path, generating a verification image, and sending the verification image to a field long end for verification.
Optionally, in one possible implementation manner of the first aspect, the acquiring attribute data and corresponding quantity information of the idle collection device, and performing partition collection on a cultivated area of Tian Changduan according to the attribute data and the quantity information, to obtain a current cultivated area top view, includes:
Acquiring a first acquisition area and corresponding quantity information of idle acquisition devices of each model in a preset time period, and distributing the corresponding cultivated land area of the cultivated land area according to the first acquisition area and the quantity information to acquire a second acquisition area corresponding to each idle acquisition device;
the second acquisition area is obtained by the following formula,
Figure SMS_1
wherein M is R A first collecting area, l, of the idle collecting device of the R type r For the number of the r-th idle acquisition devices, p r For the first acquisition area of the r-th idle acquisition device in a preset time period, u is the upper limit value of the number of idle acquisition device models, and c i For the number information of the ith idle acquisition device, m i For the device first acquisition area, M, of each idle acquisition device of the ith type α For the cultivated land area M r A second acquisition area of each idle acquisition device for the r-th model;
acquiring device numbers of a plurality of idle acquisition devices, distributing the second acquisition areas to the idle acquisition devices of the corresponding device numbers, and controlling the idle acquisition devices of the device numbers to carry out regional acquisition on a cultivated area with the corresponding second acquisition areas to obtain a top view of the current cultivated area.
Optionally, in one possible implementation manner of the first aspect, the acquiring device numbers of the plurality of idle collecting devices, allocating the second collecting areas to the idle collecting devices of the corresponding device numbers, and controlling the idle collecting devices of the device numbers to collect the cultivated area in a partition manner with the corresponding second collecting areas, so as to obtain a current cultivated area top view, where the method includes:
acquiring device numbers of a plurality of idle acquisition devices, distributing the second acquisition areas to the corresponding device numbers, and carrying out ascending order sequencing on the device numbers according to the second acquisition areas to obtain an ascending order acquisition sequence;
dividing the second acquisition area in the ascending acquisition sequence of the cultivated land area based on a preset division sequence to obtain at least one acquisition area, and sequentially controlling each idle acquisition device in the ascending acquisition sequence to acquire images of the acquisition area according to the preset division sequence;
and splicing the images acquired by each idle acquisition device based on the shooting time to generate an area image corresponding to each idle acquisition device, and splicing the area images in turn based on the sequence of device numbers in the ascending acquisition sequence to generate a top view of the current cultivated land.
Optionally, in one possible implementation manner of the first aspect, the acquiring device numbers of the plurality of idle collecting devices, allocating the second collecting areas to the idle collecting devices of the corresponding device numbers, and controlling the idle collecting devices of the device numbers to collect the cultivated area in a partition manner with the corresponding second collecting areas, so as to obtain a current cultivated area top view, where the method includes:
acquiring the total pixel number of the cultivated land area, determining the number of sub-pixel points corresponding to each second acquisition area according to the total pixel number, counting the number of the sub-pixel points, sequencing in an ascending order to obtain an acquisition area set, acquiring the device numbers of a plurality of idle acquisition devices, and binding the device numbers with the corresponding number of the sub-pixel points one by one;
displaying the collection area set, and determining the number of one sub-pixel point in the collection area set as the area to be allocated and the device number corresponding to the area to be allocated according to the selected information of the user;
a transparent layer is overlapped on an image of a cultivated land area, the cultivated land area is divided into areas in response to the triggering of a worker on the transparent layer, a first subarea corresponding to the area to be allocated is obtained, and the first subarea is associated with the device number;
Repeating the steps until the number of the sub-pixel points in the collection area set is the last, stopping dividing, taking an unallocated area in the cultivated area as an unallocated first sub-area, and establishing association between the unallocated first sub-area and an unallocated device number;
and carrying out regional acquisition on the corresponding first subarea by utilizing each idle acquisition device to obtain the top view of the current cultivated land.
Optionally, in one possible implementation manner of the first aspect, the superimposing a transparent layer on a cultivated land area, and performing area division on the cultivated land area in response to triggering of the transparent layer by a worker to obtain a first sub-area corresponding to the area to be allocated, and associating the first sub-area with the device number includes:
generating a first trigger signal based on the transparent layer, responding to the first trigger signal, recording that a worker generates a dividing line for a first trigger trace of the transparent layer in real time, and recording that the current position of the dividing line is a first position;
responding to a second trigger signal, recording the dragging trace of a worker on the dividing line in real time to generate a dragging track, synchronously moving the dividing line based on the dragging track, and recording the position of the dividing line as a second position when the number of pixel points traversed by the dividing line is equal to or larger than the area to be distributed;
And taking the cultivated land area between the first position and the second position as a first subarea corresponding to the area to be allocated, determining a device number corresponding to the area to be allocated, and establishing association between the first subarea and the device number.
Optionally, in one possible implementation manner of the first aspect, the decomposing the current cultivated land top view to generate a current pixel point set, comparing a pixel value of each pixel point in the current pixel point set with a standard pixel value to determine an abnormal pixel point, counting the abnormal pixel points to generate a first abnormal total set, and splitting the first abnormal total set into a plurality of independent first abnormal subsets according to a positional relationship of each abnormal pixel point, where the splitting includes:
establishing a coordinate system based on preset pixel points in the current cultivated land top view to decompose to obtain a current pixel point set;
if the pixel value of the pixel point in the current pixel point set is equal to the standard pixel value, the pixel point is used as a normal pixel point;
if the pixel value of the pixel point in the current pixel point set is not equal to the standard pixel value, taking the pixel point as an abnormal pixel point, and counting the abnormal pixel point to generate a first abnormal total set;
Sequentially selecting abnormal pixel points in the first abnormal total set as first abnormal pixel points, and counting the abnormal pixel points which are directly connected and indirectly connected with the first abnormal pixel points to obtain a first abnormal subset;
deleting the abnormal pixel points in the first abnormal subset from the first abnormal total set, and repeating the step of obtaining the first abnormal subset until the first abnormal total set is an empty set, so as to generate a plurality of independent first abnormal subsets.
Optionally, in one possible implementation manner of the first aspect, if the number of pixels in the abnormal subset is greater than a preset number value, determining a shooting path according to the abnormal subset, controlling an acquisition device to acquire according to the shooting path, generating a verification image, and sending the verification image to a field length end for verification, where the method includes:
if the number of the pixel points in the first abnormal subset is larger than or equal to a preset number value, the first abnormal subset is used as a second abnormal subset, the adjacent pixel points in the second abnormal subset are extracted to be abnormal pixel points of normal pixel points, and an abnormal contour set is generated;
respectively obtaining minimum values and maximum values corresponding to the abscissa and the ordinate of the abnormal pixel points in the abnormal contour set to obtain a minimum abscissa value, a maximum abscissa value, a minimum ordinate value and a maximum ordinate value;
Constructing longitudinal parallel lines according to the minimum abscissa value and the maximum abscissa value, constructing transverse parallel lines according to the minimum ordinate value and the maximum ordinate value, and generating an abnormal rectangular area according to the longitudinal parallel lines and the transverse parallel lines;
the abnormal rectangular areas are subjected to descending order based on the areas of the abnormal rectangular areas, a rectangular area sequence is generated, the acquisition devices are subjected to descending order based on the acquisition areas of the devices, and a device sequence is generated;
if the number of the abnormal rectangular areas is larger than that of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas in the rectangular area sequence, the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas, and after the acquisition is finished, the acquisition devices in the device sequence are in one-to-one correspondence with the rest abnormal rectangular areas in the rectangular area sequence and are acquired;
if the number of the abnormal rectangular areas is smaller than or equal to the number of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas, and the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas;
and determining center point coordinates and first shooting times according to the abnormal rectangular areas, generating acquisition paths according to the distance relation between the center point coordinates and starting point coordinates of the acquisition devices, controlling the acquisition devices to acquire side images according to the corresponding first shooting times for each second abnormal subset based on the acquisition paths, generating verification images according to the side images and overlooking images corresponding to the corresponding abnormal rectangular areas, and sending the verification images to the long ends of the fields for verification.
Optionally, in a possible implementation manner of the first aspect, the calculating the preset number value includes:
acquiring the cultivated land grade and the cultivated land area of each cultivated land in the cultivated land area corresponding to Tian Changduan, and calculating according to the cultivated land grade, the cultivated land area and the cultivated land quantity to obtain a preset quantity value;
the preset quantity value is calculated by the following formula,
Figure SMS_2
wherein S is a preset quantity value, n is an upper limit value of the cultivated land quantity, h o For the corresponding cultivated land grade of the o th cultivated land, m o For the corresponding cultivated area of the o th cultivated land, M α In order to cultivate the area of the land,
Figure SMS_3
to preset the cultivated land grade omega 1 Level normalization value->
Figure SMS_4
For reference cultivated land area omega 2 Area normalization value->
Figure SMS_5
Is a reference number value.
Optionally, in one possible implementation manner of the first aspect, the determining the center point coordinate and the first shooting number according to the abnormal rectangular area, and generating the acquisition path according to a distance relationship between the center coordinate and a start point coordinate of the acquisition device, includes:
obtaining a first ordinate and a second ordinate according to the ordinate values of two vertexes with the same abscissa in the abnormal rectangular area, and obtaining the ordinate value of the center point according to the average value of the first ordinate and the second ordinate;
Acquiring abscissa values of two vertexes with the same ordinate in the abnormal rectangular area to obtain a first abscissa and a second abscissa, and obtaining an abscissa value of a center point according to an average value of the first abscissa and the second abscissa;
generating a central point coordinate of an abnormal rectangular area according to the longitudinal coordinate value of the central point and the transverse coordinate value of the central point, acquiring a starting point coordinate of an acquisition device, generating a linear distance according to the central point coordinates and the starting point coordinates of all the abnormal rectangular areas, and sequencing the central point coordinates in ascending order based on the linear distance to obtain a distance sequence;
sequentially connecting the starting point coordinates with the central point coordinates in the distance sequence to generate an acquisition path;
the center point coordinates are used as circle center coordinates, a radius is generated according to the circle center coordinates and vertex coordinates of the abnormal rectangular area, and an abnormal circumference is generated according to the circle center coordinates and the radius;
calculating according to the abnormal circumference and a preset arc length to obtain a first shooting frequency;
the first photographing times are calculated by the following formula,
Figure SMS_6
wherein n is 1 For the first shooting times, x 1 X is the first abscissa, x 2 In the second abscissa of the graph, the first abscissa,
Figure SMS_7
is the abscissa value of the center point, y 1 As the first ordinate, y 2 For the second ordinate, +.>
Figure SMS_8
Is the ordinate value of the center point, L For the preset arc length, k of the epsilon-type acquisition device 2 The first shooting frequency weight value;
and determining any vertex in the abnormal rectangular area as a shooting starting point based on the center point coordinates of the acquisition path, controlling an acquisition device to acquire side images of each second abnormal subset according to corresponding first shooting times based on the shooting starting point, and generating a verification image according to the side images and top images corresponding to the corresponding abnormal rectangular area.
Optionally, in one possible implementation manner of the first aspect, the method further includes:
displaying the first shooting times, receiving second shooting times actively input by a user, and changing the first shooting times into the second shooting times;
if the second shooting times are larger than the first shooting times, determining an increase adjustment value, and increasing and adjusting the weight value of the first shooting times according to the increase adjustment value and the difference value between the second shooting times and the first shooting times to obtain a first shooting times weight value after increasing and adjusting;
If the second shooting times are smaller than the first shooting times, determining a reduction adjustment value, and reducing and adjusting the weight value of the first shooting times according to the reduction adjustment value and the difference value of the first shooting times and the second shooting times to obtain a first shooting times weight value after reduction adjustment;
the adjusted first photographing time weight value is increased and the adjusted first photographing time weight value is decreased by the following formula,
Figure SMS_9
wherein n is 2 For the second shooting times, n 1 For the first shooting times, k 3 To increase the adjusted first shooting times weight value k 2 For the first shooting times weight value, tau is an increasing adjustment value, k 4 To reduce the adjusted first shot count weight value,
Figure SMS_10
to reduceThe adjustment value is small.
In a second aspect of an embodiment of the present invention, there is provided an electronic device, including: a memory, a processor and a computer program stored in the memory, the processor running the computer program to perform the first aspect of the invention and the methods that the first aspect may relate to.
In a third aspect of the embodiments of the present invention, there is provided a readable storage medium having stored therein a computer program for implementing the method of the first aspect and the various possible aspects of the first aspect when executed by a processor.
According to the data processing method suitable for intelligent agriculture, the areas of the cultivated areas are collected in a partitioning mode according to the number of the current idle collecting devices and the corresponding attribute data, processing efficiency is improved, pixel values of crops in the cultivated areas are obtained and are automatically compared to judge abnormal pixel point areas, after the abnormal areas are detected in a comparison mode, different surrounding shooting paths are correspondingly arranged according to different abnormal areas, corresponding top views are collected to obtain verification images, and the reasons for the abnormal areas are conveniently and accurately identified according to the top views and the surrounding images.
According to the technical scheme provided by the invention, the total pixel point number of the cultivated area can be obtained, the total pixel point number can be understood as the total area, the sub-pixel point number corresponding to each second acquisition area is determined according to the total pixel point number, a user can select any one sub-pixel point number in the acquisition area set, namely, the user can freely select the current idle acquisition device, the transparent layer is utilized to realize the free division of the cultivated area, the free division of the cultivated area is realized through the first trigger signal and the second trigger signal of the transparent layer, and the distribution flexibility of the idle acquisition device and the division flexibility of the cultivated area are better promoted through the interaction form with the user.
According to the technical scheme provided by the invention, different preset numbers are correspondingly set according to different cultivated land grades and cultivated land areas, and it can be understood that the larger the cultivated land area is and the larger the cultivated land grade is, the larger the allowed preset number is, namely the larger the cultivated land area is, the larger the cultivated land grade is (the worse the cultivated land quality is), the larger the allowed abnormal area is, and the area which is smaller than the preset number is temporarily not treated as the abnormal area for the first time, so that the treatment capacity is reduced, and the larger the cultivated land area is, the larger the corresponding possibility of foreign matters exists is, for example: the paper sheets, the movable sundries affecting the cultivated land, such as the convenience bags, are used as the sub-collection to be processed, and when the collection processing is performed again next time, if the sub-collection to be processed is found to still exist and is even larger than the original area, the area is used as the abnormal area to be detected, so that the workload is reduced, and meanwhile, omission is not generated in the abnormal area.
According to the technical scheme provided by the invention, the current pixel value is automatically compared with the standard pixel value, so that the corresponding abnormal region is automatically identified, real-time observation by a user is not needed, human resources are saved, after the abnormal region is found by comparison, different peripheral shooting times are generated according to the shape and the size of the abnormal region, the corresponding shooting times are combined with the corresponding top view and sent to the field long end for verification, and the user can conveniently and accurately judge the abnormal region.
Drawings
FIG. 1 is a flow chart of a data processing method suitable for intelligent agriculture;
FIG. 2 is a schematic diagram of dividing a cultivated area based on a predetermined division sequence according to the present invention;
FIG. 3 is a schematic diagram of a parting line formed in accordance with the present invention;
FIG. 4 is a schematic diagram of area division based on dividing lines according to the present invention;
FIG. 5 is a schematic diagram of another area division based on dividing lines according to the present invention;
fig. 6 is a schematic diagram of a hardware structure of an electronic device according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein.
It should be understood that, in various embodiments of the present invention, the sequence number of each process does not mean that the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present invention, "plurality" means two or more. "and/or" is merely an association relationship describing an association object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "comprising A, B and C", "comprising A, B, C" means that all three of A, B, C comprise, "comprising A, B or C" means that one of the three comprises A, B, C, and "comprising A, B and/or C" means that any 1 or any 2 or 3 of the three comprises A, B, C.
It should be understood that in the present invention, "B corresponding to a", "a corresponding to B", or "B corresponding to a" means that B is associated with a, from which B can be determined. Determining B from a does not mean determining B from a alone, but may also determine B from a and/or other information. The matching of A and B is that the similarity of A and B is larger than or equal to a preset threshold value.
As used herein, "if" may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to detection" depending on the context.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
The invention provides a data processing method suitable for intelligent agriculture, as shown in figure 1, comprising the following steps:
and S110, acquiring attribute data and corresponding quantity information of the idle acquisition device, and carrying out regional acquisition on the cultivated area of Tian Changduan according to the attribute data and the quantity information to obtain a current cultivated area top view.
According to the technical scheme provided by the invention, the system can acquire the attribute data and the corresponding quantity information of the idle acquisition devices, wherein the attribute data of the idle acquisition devices are first acquisition areas of the idle acquisition devices in a preset time period, and the current cultivated land top view is obtained by carrying out regional acquisition on the cultivated area of Tian Changduan according to the first acquisition areas and the quantity information of each idle acquisition device in each model.
In one possible implementation manner, the step S110 specifically includes:
acquiring a first acquisition area and corresponding quantity information of idle acquisition devices of each model in a preset time period, and distributing the corresponding cultivated land area of the cultivated land area according to the first acquisition area and the quantity information to obtain a second acquisition area corresponding to each idle acquisition device.
According to the technical scheme provided by the invention, the system can automatically acquire the first acquisition area and the corresponding quantity information of each type of idle acquisition device in the preset time period, and allocate the corresponding arable area of the arable area according to the first acquisition area and the quantity information, so as to acquire the second acquisition area corresponding to each idle acquisition device, and it can be understood that the system can automatically acquire the first acquisition area and the corresponding quantity information of each type of unmanned aerial vehicle in the preset time period, for example: the collection area of A model unmanned aerial vehicle every minute is 100 square meters, the quantity of A model unmanned aerial vehicle every minute is 2, the collection area of B model unmanned aerial vehicle every minute is 200 square meters, the quantity of B model unmanned aerial vehicle is 1, the arable land area in arable land region is 800 square meters, then can let 2A model unmanned aerial vehicle gather 400 square meters, 1B model gather 400 square meters, wherein, first collection area is the collection area in the preset time quantum that each model unmanned aerial vehicle corresponds, namely 100 square meters/min of A model unmanned aerial vehicle, the area after the area is allocated to arable land area that arable land area corresponds according to first collection area and quantity information, it is understood that the more corresponding second collection area of each model unmanned aerial vehicle is big, the second collection area of each model unmanned aerial vehicle is just obtained to the convenience, namely be the second collection area of each model unmanned aerial vehicle that does not distribute.
The second acquisition area is obtained by the following formula,
Figure SMS_11
wherein M is R A first collecting area, l, of the idle collecting device of the R type r For the number of the r-th idle acquisition devices, p r For the first acquisition area of the r-th idle acquisition device in a preset time period, u is the upper limit value of the number of idle acquisition device models, and c i For the number information of the ith idle acquisition device, m i For the device first acquisition area, M, of each idle acquisition device of the ith type α For the cultivated land area M r A second collection area for each idle collection device of the r type, wherein the number of the idle collection devices of the r type is l r First acquisition area M of idle acquisition device of R type R In proportion, the first acquisition area p of the r-th idle acquisition device in a preset time period r First acquisition area M of idle acquisition device of R type R Proportional to the cultivated area M α First acquisition area M of idle acquisition device of R type R Proportional, it will be appreciated that the tilling area M α The larger the corresponding second acquisition area M r The larger the first acquisition area p of the r-th idle acquisition device in a preset time period r The larger the corresponding second acquisition area M r The larger.
Acquiring device numbers of a plurality of idle acquisition devices, distributing the second acquisition areas to the idle acquisition devices of the corresponding device numbers, and controlling the idle acquisition devices of the device numbers to carry out regional acquisition on a cultivated area with the corresponding second acquisition areas to obtain a top view of the current cultivated area.
According to the technical scheme provided by the invention, the system can acquire the device numbers corresponding to the plurality of idle acquisition devices, and it can be understood that each idle acquisition device has the corresponding number, wherein the device numbers can be 1, 2, 3 and 4, or 111, 112 and 113, and are not limited herein, for example: the collection area of A model unmanned aerial vehicle every minute is 100 square meters, the quantity of A model unmanned aerial vehicle is 2, the device serial number is 01 respectively, 02, the collection area of B model unmanned aerial vehicle every minute is 200 square meters, the quantity of B model unmanned aerial vehicle is 1, the device serial number is 03, thereby allocate the idle collection device of corresponding device serial number with second collection area, the arable land area of arable land region is 800 square meters, will distribute 200 square meters (second collection area) to the A model unmanned aerial vehicle of device serial number 01, will distribute 200 square meters (second collection area) to the A model unmanned aerial vehicle of device serial number 02, distribute 400 square meters (second collection area) to the B model unmanned aerial vehicle of device serial number 03, then control 01, 02, 03's unmanned aerial vehicle carries out subregion collection with corresponding second collection area, splice the area after the collection, obtain current arable land top view, thereby make things convenient for follow-up to carry out pixel value and correspond and find abnormal region, automatic comparison has saved the manpower.
In one possible implementation manner, the method for obtaining the device numbers of the plurality of idle collection devices, allocating the second collection areas to the corresponding device numbers, and controlling each idle collection device in each device number to conduct regional collection on a cultivated area with the corresponding second collection area to obtain a current cultivated area top view includes:
acquiring device numbers of a plurality of idle acquisition devices, distributing the second acquisition areas to the corresponding device numbers, and carrying out ascending order sequencing on the device numbers according to the second acquisition areas to obtain an ascending order acquisition sequence.
According to the technical scheme provided by the invention, the system can acquire the device numbers of the plurality of idle acquisition devices, and it can be understood that each unmanned aerial vehicle is provided with the corresponding number, and the device numbers are sequenced in an ascending order according to the second acquisition area, so that a corresponding ascending acquisition sequence is obtained, for example: the acquisition area of the A-type unmanned aerial vehicle per minute is 100 square meters, the number of the A-type unmanned aerial vehicle is 2, and the device numbers are 01 and 02 respectively; the collection area of the type B unmanned aerial vehicle per minute is 200 square meters, the number of the type B unmanned aerial vehicles is 1, the device number is 03, thereby the second collection area is allocated to an idle collection device corresponding to the device number, the cultivated area of a cultivated area is 800 square meters, 200 square meters (second collection area) are allocated to the type A unmanned aerial vehicle with the device number of 01, 200 square meters (second collection area) are allocated to the type A unmanned aerial vehicle with the device number of 02, 400 square meters (second collection area) are allocated to the type B unmanned aerial vehicle with the device number of 03, and the device numbers are sorted according to the second collection area in an ascending order, so that ascending collection sequences of 01, 02, 03 or 02, 01 and 03 are obtained, and it can be understood that the corresponding second collection areas of 01 and 02 are all 200 square meters, the subsequent division of the collection areas according to the ascending collection sequences is convenient, and accordingly, the corresponding current cultivated area top view is formed by splicing.
Dividing the second acquisition area in the ascending acquisition sequence of the cultivated land area based on a preset division sequence to obtain at least one acquisition area, and sequentially controlling each idle acquisition device in the ascending acquisition sequence to acquire images of the acquisition area according to the preset division sequence.
According to the technical scheme provided by the invention, the system divides the second acquisition area in the ascending acquisition sequence of the cultivated land area based on the preset division sequence, as shown in fig. 2, wherein the preset division sequence can be manually preset, for example: the second collection areas in the ascending collection sequence may be sequentially divided by the system based on a preset division sequence, for example: the area is divided from top to bottom, the ascending acquisition sequence is 01 (second acquisition area: 200 square meters), 02 (second acquisition area: 200 square meters) and 03 (second acquisition area: 400 square meters), so that 3 acquisition areas are obtained, each idle acquisition device in the ascending acquisition sequence is sequentially controlled to acquire images of the acquisition areas according to a preset division sequence, it can be understood that the unmanned aerial vehicle with the number 01 is divided into 200 square meters for the first time, the unmanned aerial vehicle with the number 02 is divided into 200 square meters for the second time, the unmanned aerial vehicle with the number 03 is divided into 400 square meters for the third time, and the subsequent combination of the photographed images of the unmanned aerial vehicles with the numbers in sequence is facilitated, so that the current cultivated land top view is generated.
And splicing the images acquired by each idle acquisition device based on the shooting time to generate an area image corresponding to each idle acquisition device, and splicing the area images in turn based on the sequence of device numbers in the ascending acquisition sequence to generate a top view of the current cultivated land.
According to the technical scheme provided by the invention, the system splices the images acquired by each idle acquisition device based on the shooting time, so as to generate the area image corresponding to each idle acquisition device, and it can be understood that the system splices the images acquired by each unmanned aerial vehicle according to the shooting time of the unmanned aerial vehicle, for example: the method comprises the steps of carrying out image stitching according to the sequence of the shooting time of the unmanned aerial vehicle with the device number of 01 so as to generate an area image acquired with the device number of 01, stitching the area images in sequence based on the sequence of the device numbers in the ascending acquisition sequence so as to generate a current cultivated land top view, and stitching the area images acquired respectively according to the sequence of the device numbers of 01, 02 and 03 in the ascending acquisition sequence so as to obtain the current cultivated land top view, so that the comparison of pixel values is convenient to carry out subsequently, the abnormal pixel values are found, and the abnormal area is positioned.
In one possible implementation manner, the method for obtaining the device numbers of the plurality of idle collection devices, allocating the second collection area to the idle collection device with the corresponding device number, and controlling the idle collection device with the device number to conduct partition collection on the cultivated area with the corresponding second collection area to obtain the current cultivated area top view includes:
the method comprises the steps of obtaining the total pixel number of a cultivated land area, determining the number of sub-pixel points corresponding to each second acquisition area according to the total pixel number, counting the number of the sub-pixel points, sequencing in an ascending order to obtain an acquisition area set, obtaining device numbers of a plurality of idle acquisition devices, and binding the device numbers with the corresponding number of the sub-pixel points one by one.
According to the technical scheme provided by the invention, the system acquires the total pixel number of the cultivated land area, the corresponding sub-pixel number corresponding to the second acquisition area is obtained according to the ratio of the second acquisition area to the total cultivated land area of the cultivated land area, the sub-pixel number is counted and ordered in ascending order to obtain an acquisition area set, the device numbers of a plurality of idle acquisition devices are acquired, the device numbers are bound with the corresponding sub-pixel number one by one, and it can be understood that the acquisition area set is ordered by the pixel number and the unmanned aerial vehicle numbers are bound with the corresponding pixel number one by one, for example: the total cultivated area of the cultivated area is 800 square meters, the corresponding total pixel number is 800, the second collecting area is 200 square meters (01), 200 square meters (02) and 400 square meters (03), so that 200 (01), 200 (02) and 400 (03) corresponding pixel points are obtained, the sub-pixel number of 200 (01), 200 (02) and 400 (03) is sequenced in ascending order to obtain collecting area sets {200, 200 and 400 }, the device number is obtained, the device number and the corresponding sub-pixel number are bound one by one, and accordingly the obtained collecting area sets {200 (01), 200 (02) and 400 (03) }, and the cultivated area can be conveniently and flexibly divided by interaction with a user.
And displaying the collection area set, determining the number of one sub-pixel point in the collection area set as the area to be allocated according to the selected information of the user, and the device number corresponding to the area to be allocated.
According to the technical scheme provided by the invention, the system can display the collection area set, and determine that the number of one sub-pixel point in the collection area set is the area to be allocated and the device number corresponding to the area to be allocated according to the selected information of the user, it can be understood that the system can display the collection area sets {200 (01), 200 (02) and 400 (03) } to the user, and the user can actively select any one sub-pixel point number in the collection area set and the unmanned aerial vehicle with the corresponding number as the area to be allocated, for example: the user can preferentially select the unmanned aerial vehicle with the 03 serial numbers of 400 pixel points to be preferentially allocated, the cultivated area is collected, the method is not limited herein, the flexibility of allocation is improved, and the user can select according to the requirements.
And superposing a transparent layer on the cultivated land area image, responding to the triggering of a worker on the transparent layer to carry out area division on the cultivated land area to obtain a first subarea corresponding to the area to be allocated, and associating the first subarea with the device number.
According to the technical scheme provided by the invention, the transparent layer corresponding to the cultivated area is constructed, and the corresponding transparent layer is superimposed on the image of the cultivated area, wherein the transparent layer is used for recording the triggering behavior of a user, responding to the triggering of the transparent layer by a worker, so that the cultivated area is divided into areas, a first subarea corresponding to the area to be allocated is obtained, the first subarea is associated with the device number of the area to be allocated, the triggering operation of the transparent layer by the user is free, the user can realize the division of the area by using any angle of straight line or curve, the degree of freedom of division is improved, and especially, the integrity of the area collected each time can be ensured for the irregular cultivated area.
In one possible implementation manner, the overlapping of the transparent layer on the cultivated land area, the area division of the cultivated land area in response to the triggering of the transparent layer by the staff member, to obtain a first sub-area corresponding to the area to be allocated, and the association of the first sub-area and the device number includes:
generating a first trigger signal based on the transparent layer, responding to the first trigger signal, recording that a worker generates a dividing line for a first trigger trace of the transparent layer in real time, and recording that the current position of the dividing line is a first position.
According to the technical scheme provided by the invention, as shown in fig. 3, a system generates a corresponding first trigger signal based on the triggering of a user on the transparent layer, and responds to the first trigger signal to record the first trigger trace of the transparent layer in real time to generate a dividing line, wherein the user can draw a transverse line, a vertical line, oblique lines and the like on the transparent layer at will, the user does not limit the drawing, generates the corresponding first trigger trace, generates the corresponding dividing line according to the first trigger trace, and records the current position of the dividing line as the first position, and the user can slide the transparent layer according to the requirement to generate the corresponding dividing line, wherein the dividing line can be a straight line, can be a curve, can be a transverse line or an oblique line, the degree of freedom of the dividing line is improved, and the dividing line can be divided freely according to different images.
And responding to a second trigger signal, recording that a worker generates a dragging track for the dragging trace of the dividing line in real time, synchronously moving the dividing line based on the dragging track, and recording that the position of the dividing line is a second position when the number of pixel points traversed by the dividing line is equal to or larger than the area to be distributed.
According to the technical scheme provided by the invention, as shown in fig. 4, a system responds to a second trigger signal for a user to drag a dividing line, a dragging track is generated by a worker on the dragging trace of the dividing line in real time, the dividing line is synchronously moved based on the dragging track, when the number of pixel points traversed by the dividing line is equal to or larger than the area to be distributed, the position of the dividing line is recorded as a second position, wherein the second trigger signal is a dragging track signal generated by the user on the dragging trace of the dividing line, and it can be understood that when the system records the number of pixel points traversed by the user in the dragging process of the dividing line, when the number of pixel points traversed is equal to or larger than the number of sub-pixel points corresponding to the area to be distributed, the dragging of the user is stopped, the position of the dividing line is recorded as the second position, and the first sub-area imaged by the unmanned plane is conveniently generated according to the first position and the second position.
And taking the cultivated land area between the first position and the second position as a first subarea corresponding to the area to be allocated, determining a device number corresponding to the area to be allocated, and establishing association between the first subarea and the device number.
According to the technical scheme provided by the invention, the system takes the cultivated land area between the first position and the second position as a first subarea corresponding to the area to be allocated, determines the device number corresponding to the area to be allocated, and establishes association between the first subarea and the device number, and it can be understood that the area between the first position and the second position is taken as an acquisition area corresponding to the unmanned aerial vehicle device number of the area to be allocated, for example: the collection area set {200 (01), 200 (02), 400 (03) }, the user actively selects 200 (01), the user actively selects 200 unmanned aerial vehicle with the pixel device number of 01, and the cultivated land area between the first position and the second position is used as the collection area of the 01 unmanned aerial vehicle, so that different divisions can be carried out on different cultivated land areas, the flexibility of division of the cultivated land areas is improved, and the integrity of the collection area of the unmanned aerial vehicle is ensured.
Repeating the steps until the number of the sub-pixel points in the collection area set is the last, stopping dividing, taking an unallocated area in the cultivated area as an unallocated first sub-area, and establishing association between the unallocated first sub-area and an unallocated device number.
According to the technical scheme provided by the invention, as shown in fig. 5, the allocated first sub-area is deleted on the cultivated land area, the steps are continuously repeated until the number of sub-pixel points in the collection area is the last, it can be understood that the idle unmanned aerial vehicle is allocated to the last, the division is stopped, the unallocated area in the cultivated area is taken as the unallocated first sub-area, the unallocated first sub-area is associated with the unallocated device number, it can be understood that when other unmanned aerial vehicles are allocated, only the last unmanned aerial vehicle is left, only the last corresponding area to be allocated is left, the two are directly associated with each other, the last unmanned aerial vehicle is dispatched to collect the images of the residual areas, and the current cultivated land top view is conveniently generated by splicing according to the corresponding device number of the collection area.
And carrying out regional acquisition on the corresponding first subarea by utilizing each idle acquisition device to obtain the top view of the current cultivated land.
After the farmland area is allocated, the system uses each idle acquisition device to acquire the corresponding first subarea in a partitioning way, so as to obtain a corresponding current farmland top view.
Step S120, obtaining preset crop type information corresponding to the cultivated land area and a standard pixel value corresponding to the preset crop type information.
According to the technical scheme provided by the invention, the system can acquire the information of the preset crop types corresponding to the cultivated land, and it can be understood that the crop types planted in the cultivated land all the year round are relatively fixed, and the standard pixel values corresponding to the preset crop types are directly acquired.
Step S130, decomposing the current cultivated land top view to generate a current pixel point set, comparing the pixel value of each pixel point in the current pixel point set with a standard pixel value to determine an abnormal pixel point, counting the abnormal pixel points to generate a first abnormal total set, and splitting the first abnormal total set into a plurality of independent first abnormal subsets according to the position relation of each abnormal pixel point.
According to the technical scheme provided by the invention, the system can select the preset pixel points as the coordinate origin to decompose the top view of the current cultivated land after the collection is completed, the current pixel point set is obtained, the pixel value of each pixel point in the current pixel point set is compared with the standard pixel value to determine the abnormal pixel point, it can be understood that when the standard pixel value is green but the pixel points in the current pixel point sets are not green, the pixel points are taken as the abnormal pixel points, all the abnormal pixel points are counted to generate a first abnormal total set, the first abnormal total set is split into a plurality of independent first abnormal subsets according to the position relation of each abnormal pixel point, and it can be understood that the first abnormal total set is all the abnormal pixel points, but the abnormal area can be a plurality of abnormal areas, so that the first abnormal total set needs to be split, a plurality of abnormal areas are obtained, and the follow-up shooting verification according to the abnormal areas is convenient.
In one possible implementation manner, the step S130 specifically includes:
and establishing a coordinate system based on the preset pixel points in the top view of the current cultivated land to decompose to obtain a current pixel point set.
According to the technical scheme provided by the invention, the system can build a coordinate system based on the preset pixel points in the top view of the current cultivated land to decompose, so that a current pixel point set is obtained, wherein the current pixel point set can be any pixel point selected by a user in advance.
And if the pixel value of the pixel point in the current pixel point set is equal to the standard pixel value, taking the pixel point as a normal pixel point.
According to the technical scheme provided by the invention, if the pixel value of the pixel point in the current pixel point set is equal to the standard pixel value, it can be understood that if the pixel value of the pixel point in the current pixel point set is the same as the standard pixel value, the pixel point is green, and the pixel point is normal and no subsequent processing is needed.
If the pixel value of the pixel point in the current pixel point set is not equal to the standard pixel value, taking the pixel point as an abnormal pixel point, and counting the abnormal pixel point to generate a first abnormal total set.
According to the technical scheme provided by the invention, if the pixel value of the pixel point in the current pixel point set is different from the standard pixel value, the pixel point is taken as an abnormal pixel point, all abnormal pixel strip points are counted to obtain the first abnormal total set, and it can be understood that when the pixel values are different, the pixel point is defaulted to be the abnormal pixel point, and at the moment, all the abnormal pixel points are counted.
And sequentially selecting the abnormal pixel points in the first abnormal total set as first abnormal pixel points, and counting the abnormal pixel points which are directly connected and indirectly connected with the first abnormal pixel points to obtain a first abnormal subset.
According to the technical scheme provided by the invention, the system sequentially selects the abnormal pixel points in the first abnormal total set as the first abnormal pixel points and counts the abnormal pixel points which are directly connected with the first abnormal pixel points and indirectly connected with the first abnormal pixel points, so as to obtain a first abnormal sub-set, and it can be understood that the system sequentially selects the abnormal pixel points in the set in the first abnormal total set and counts the abnormal pixel points which are directly or indirectly connected with the abnormal pixel points, and the abnormal pixel points are selected through coordinates, wherein the step of determining the abnormal pixel points which are directly connected with or indirectly connected with the first abnormal pixel points is as follows: determining abnormal pixel points adjacent to the first abnormal pixel point to obtain a plurality of second abnormal pixel points, determining the abnormal pixel points adjacent to the second abnormal pixel point to obtain a plurality of third abnormal pixel points, taking the third abnormal pixel points as the second abnormal pixel points, determining the third abnormal pixel points connected with the second abnormal pixel points again until all the second abnormal pixel points are selected, obtaining a first abnormal subset, conveniently deleting the first abnormal subset from the first abnormal total set, sequentially selecting the abnormal pixel points, splitting the first abnormal total set into a plurality of independent first abnormal subsets, and understandably, the plurality of independent first abnormal subsets are a plurality of independent abnormal areas.
Deleting the abnormal pixel points in the first abnormal subset from the first abnormal total set, and repeating the step of obtaining the first abnormal subset until the first abnormal total set is an empty set, so as to generate a plurality of independent first abnormal subsets.
According to the technical scheme provided by the invention, the system can delete the abnormal pixel points in the first abnormal subset from the first abnormal total set and repeatedly generate the first abnormal subset until the first abnormal total set is an empty set, and it can be understood that the first abnormal total set is split into a plurality of independent first abnormal subsets, namely a plurality of independent abnormal areas, so that the subsequent screening and verification processing of the size of the areas are facilitated, and the processing efficiency is improved.
And step 140, if the number of the pixel points in the abnormal subset is larger than a preset number value, determining a shooting path according to the abnormal subset, controlling an acquisition device to acquire according to the shooting path, generating a verification image, and transmitting the verification image to a field long end for verification.
According to the technical scheme provided by the invention, if the number of the pixel points in the abnormal subset is larger than the preset number value, the abnormal subset determines a shooting path, and the larger the number of the pixel points in the abnormal subset is, the larger the corresponding abnormal area is, the larger the corresponding number of times of four-circle shooting is needed, so that the acquisition device is controlled according to the shooting path to acquire the four-circle images of the abnormal area and combine the top view of the abnormal area to generate a verification image, and the verification image is sent to the field long end for verification, and the Tian Changduan can receive the top view of the abnormal area and the four-circle images for better verification, and when the verification is sent, the top view image is placed in the middle, and the four-circle images are sequentially arranged around the top view according to the shooting sequence, so that the field length can better judge the abnormal area.
In one possible implementation manner, the step S140 specifically includes:
and if the number of the pixel points in the first abnormal subset is larger than or equal to a preset number value, the first abnormal subset is used as a second abnormal subset, the adjacent pixel points in the second abnormal subset are extracted to be abnormal pixel points of normal pixel points, and an abnormal contour set is generated.
According to the technical scheme provided by the invention, if the number of the pixels in the first abnormal subset is larger than or equal to the preset number value, the first abnormal subset is taken as the second abnormal subset, the abnormal pixels with the adjacent pixels in the second abnormal subset as the normal pixels are extracted, the abnormal contour set is generated, and if the number of the pixels in the first abnormal subset is smaller than the preset number value, the first abnormal subset is taken as the sub-set to be processed without processing for the first time, and it is understood that if the number of the pixels in the first abnormal subset is smaller than the preset number value, the abnormal area is smaller at the moment, and it is difficult to understand that the cultivated area is too large and no sundries fall into cultivated land, for example: plastic bags, paper, etc., and thus an abnormal region of a small area, the first scanning finds that no processing is performed, reducing the throughput, for example: the plastic bag is strong in mobility, the area is easy to change, the large influence on cultivated land crops is avoided, the data volume to be verified is reduced, the working efficiency is improved, however, if the number of the pixel points in the first abnormal subset is larger than or equal to a preset number value, the fact that the abnormal area is larger at the moment is indicated, the follow-up shooting verification is needed, the first abnormal subset is used as a second abnormal subset, the abnormal pixel points, of which the adjacent pixel points are normal pixel points, in the second abnormal subset are extracted, the abnormal outline set is obtained, the abnormal pixel points connected with the normal pixel points are selected from the second abnormal subset by the system, statistics is carried out, the outline of the abnormal area is obtained, the corresponding abnormal outline set is obtained, the follow-up shooting four-circle image is conveniently obtained according to the abnormal outline set, and the follow-up Tian Changjin line verification is convenient.
And respectively obtaining the minimum value and the maximum value corresponding to the abscissa and the ordinate of the abnormal pixel point in the abnormal contour set, and obtaining the minimum abscissa value, the maximum abscissa value, the minimum ordinate value and the maximum ordinate value.
According to the technical scheme provided by the invention, the system can acquire the minimum value and the maximum value corresponding to the abscissa and the ordinate of the abnormal pixel point in the abnormal contour set respectively to acquire the minimum abscissa value, the maximum abscissa value, the minimum ordinate value and the maximum ordinate value, and can acquire the maximum value and the minimum value of the abscissa and the ordinate of the abnormal pixel point in the abnormal contour set, so that the corresponding abnormal rectangular area can be conveniently acquired according to the maximum value and the minimum value of the abscissa and the ordinate.
And constructing longitudinal parallel lines according to the minimum abscissa value and the maximum abscissa value, constructing transverse parallel lines according to the minimum ordinate value and the maximum ordinate value, and generating an abnormal rectangular area according to the longitudinal parallel lines and the transverse parallel lines.
According to the technical scheme provided by the invention, the system can construct longitudinal parallel lines according to the minimum abscissa value and the maximum abscissa value, and construct transverse parallel lines according to the minimum ordinate value and the maximum ordinate value, and it can be understood that the longitudinal lines are constructed according to the maximum and minimum abscissa values, and the transverse lines are constructed according to the maximum and minimum ordinate values, so that an abnormal rectangular area is obtained, the subsequent generation of shooting times corresponding to each area according to the size of the abnormal rectangular area is facilitated, and the verification of the field length is facilitated after shooting is completed.
And ordering the abnormal rectangular areas in a descending order based on the areas of the abnormal rectangular areas to generate a rectangular area sequence, and ordering the acquisition devices in a descending order based on the acquisition areas of the devices to generate a device sequence.
According to the technical scheme provided by the invention, the system can sort the abnormal rectangular areas in a descending order based on the areas of the abnormal rectangular areas to generate the corresponding rectangular area sequences, sort the acquisition devices in a descending order based on the acquisition areas of the devices to generate the corresponding device sequences, and the abnormal rectangular areas in the rectangular area sequences can be conveniently acquired from large to small according to the acquisition areas of the device sequences, so that the unmanned aerial vehicle with good performance can acquire relatively large abnormal areas, and the working efficiency is improved.
And if the number of the abnormal rectangular areas is greater than that of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas in the rectangular area sequence, the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas, and after the acquisition is finished, the acquisition devices in the device sequence are in one-to-one correspondence with the rest abnormal rectangular areas in the rectangular area sequence and are acquired.
According to the technical scheme provided by the invention, if the number of the abnormal rectangular areas is larger than that of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas in the rectangular area sequence, the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas, after the acquisition is finished, the acquisition devices in the device sequence are in one-to-one correspondence with the rest abnormal rectangular areas in the rectangular area sequence and are acquired, and it is understood that if the abnormal areas to be acquired are too many, the unmanned aerial vehicle is controlled to acquire the abnormal areas with larger area first, the serious problem is found preferentially, after all the acquisition is finished, the rest abnormal rectangular areas are again in one-to-one correspondence and are acquired, the abnormal areas with larger abnormal areas are processed preferentially, and the abnormal areas with serious corresponding problems are acquired and verified.
And if the number of the abnormal rectangular areas is smaller than or equal to the number of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas, and the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas.
According to the technical scheme provided by the invention, if the number of the abnormal rectangular areas is smaller than or equal to the number of the idle acquisition devices, the acquisition devices in the device sequence are directly in one-to-one correspondence with the abnormal rectangular areas, image data acquisition is carried out, the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas, and it can be understood that when the abnormal areas are fewer, the unmanned aerial vehicle is directly controlled to shoot.
And determining center point coordinates and first shooting times according to the abnormal rectangular areas, generating acquisition paths according to the distance relation between the center point coordinates and starting point coordinates of the acquisition devices, controlling the acquisition devices to acquire side images according to the corresponding first shooting times for each second abnormal subset based on the acquisition paths, generating verification images according to the side images and overlooking images corresponding to the corresponding abnormal rectangular areas, and sending the verification images to the long ends of the fields for verification.
According to the technical scheme provided by the invention, the system can determine the center point coordinates and the first shooting times according to the abnormal rectangular area, and can understand that the abnormal rectangular area is a regular graph, so that the center point coordinates of the abnormal rectangular area can be directly determined, the larger the area of the abnormal rectangular area is, the corresponding first shooting times are more, a corresponding acquisition path is generated according to the distance relation between the center coordinates and the starting point coordinates of the acquisition device, the acquisition device is controlled to acquire side images of each second abnormal subset according to the corresponding first shooting times based on the acquisition path, the acquired side images and top images corresponding to the corresponding abnormal rectangular area are generated to verify images, and the verify images are sent to the long end of the field for verification.
In one possible implementation manner, the technical scheme provided by the invention calculates the preset quantity value through the following steps:
and acquiring the cultivated land grade and the cultivated land area of each cultivated land in the cultivated land areas corresponding to Tian Changduan, and calculating according to the cultivated land grade, the cultivated land area and the cultivated land quantity to obtain a preset quantity value.
According to the technical scheme provided by the invention, the system can acquire the cultivated land grade and the cultivated land area of each cultivated land in the cultivated land area corresponding to the long end of the field, and the cultivated lands are basically divided into the superior lands, the higher lands, the middle lands and the lower lands according to 1-4, 5-8, 9-12, 13-15 and the like, the corresponding soil quality is poorer when the grade number is higher, the preset quantity value is obtained by calculating according to the cultivated land grade, the cultivated land area and the cultivated land quantity, and the corresponding allowable abnormal area of the cultivated land with larger cultivated land area and lower land is smaller than the abnormal area of the cultivated land and larger than the abnormal area of the superior land.
The preset quantity value is calculated by the following formula,
Figure SMS_12
wherein S is a preset quantity value, n is an upper limit value of the cultivated land quantity, h o For the corresponding cultivated land grade of the o th cultivated land, m o For the corresponding cultivated area of the o th cultivated land, M α For the cultivated area of the cultivated area,
Figure SMS_13
to preset the cultivated land grade omega 1 Level normalization value->
Figure SMS_14
For reference cultivated land area omega 2 Area normalization value->
Figure SMS_15
As the reference quantity value, it is understood that the preset quantity value S and the cultivated area M of the cultivated area α Proportional to->
Figure SMS_16
For the average cultivated land level of the cultivated land area, a preset number value S and the average cultivated land level +.>
Figure SMS_17
Proportional to the ratio.
According to the technical scheme provided by the invention, the system can count the total area of the current cultivated land and the corresponding average cultivated land grade to obtain the preset quantity value, namely the abnormal area, when the area of the abnormal area is larger than or equal to the area corresponding to the preset quantity, the system can carry out shooting verification on the abnormal area, and it can be understood that the better the cultivated land quality is, the smaller the cultivated land area is, the corresponding range of the allowable abnormal area is smaller, the worse the cultivated land quality is, the larger the cultivated land area is, the corresponding range of the allowable abnormal area is larger, the preset quantity values with different area sizes can be generated according to actual conditions, and statistics on sundries such as convenience bags, paper sheets and the like are reduced.
In one possible implementation manner, the method for determining the center point coordinate and the first shooting times according to the abnormal rectangular region and generating the acquisition path according to the distance relation between the center coordinate and the starting point coordinate of the acquisition device includes:
And obtaining a first ordinate and a second ordinate according to the ordinate values of the two vertexes with the same abscissa in the abnormal rectangular region, and obtaining the ordinate value of the central point according to the average value of the first ordinate and the second ordinate.
According to the technical scheme provided by the invention, the system can obtain the first ordinate and the second ordinate according to the ordinate values of the two vertexes with the same abscissa in the abnormal rectangular area, and obtain the ordinate value of the center point according to the average value of the first ordinate and the second ordinate.
And acquiring abscissa values of two vertexes with the same ordinate in the abnormal rectangular region to obtain a first abscissa and a second abscissa, and obtaining the abscissa value of the center point according to the average value of the first abscissa and the second abscissa.
According to the technical scheme provided by the invention, the system can obtain the first abscissa and the second abscissa according to the abscissa values of the two vertexes with the same ordinate in the abnormal rectangular area, and obtain the abscissa value of the center point according to the average value of the first abscissa and the second abscissa, and it can be understood that the abscissa value and the ordinate value of the center point can be determined according to the abscissa and the ordinate of the vertexes because the rectangular area is a regular image.
Generating a central point coordinate of the abnormal rectangular region according to the longitudinal coordinate value of the central point and the transverse coordinate value of the central point, acquiring a starting point coordinate of the acquisition device, generating a linear distance according to the central point coordinates and the starting point coordinates of all the abnormal rectangular regions, and sequencing the central point coordinates in ascending order based on the linear distance to obtain a distance sequence.
According to the technical scheme provided by the invention, the system can determine the center point coordinates of the abnormal rectangular area according to the ordinate values of the center points and the abscissa values of the center points, the coordinates formed by the ordinate values of the center points and the abscissa values of the center points are the center point coordinates of the abnormal rectangular area, the starting point coordinates of the unmanned aerial vehicle are obtained, the unmanned aerial vehicle is placed in a fixed area, the starting point coordinates can be set manually in advance, the straight line distance is generated according to the center point coordinates and the starting point coordinates of all the abnormal rectangular areas, the straight line distance between the two points can be obtained by knowing the 2 point coordinate values, the ascending order of the center point coordinates is performed according to the straight line distance, the distance sequence is obtained, the distances between the abnormal areas and the starting point of the unmanned aerial vehicle are arranged in a near-far mode, and the acquisition path is conveniently generated by connecting the starting point coordinates with the follow-up time.
And sequentially connecting the starting point coordinates with the central point coordinates in the distance sequence to generate an acquisition path.
According to the technical scheme provided by the invention, the system sequentially connects the starting point coordinates with the central point coordinates in the distance sequence to generate the acquisition path, and the shortest linear distance between the system and the abnormal area can be calculated as the flight acquisition path.
And taking the center point coordinate as a circle center coordinate, generating a radius according to the circle center coordinate and the vertex coordinate of the abnormal rectangular area, and generating an abnormal circumference according to the circle center coordinate and the radius.
According to the technical scheme provided by the invention, the system takes the center point coordinate as the center coordinate, generates the radius according to the center coordinate and the vertex coordinate of the abnormal rectangular area, and generates the abnormal circumference according to the center coordinate and the radius.
And calculating according to the abnormal circumference and the preset arc length to obtain a first shooting frequency.
According to the technical scheme provided by the invention, the system can calculate the corresponding first shooting times according to the abnormal circumference and the preset arc length corresponding to each unmanned aerial vehicle, and it can be understood that each unmanned aerial vehicle shoots at the preset distance, the corresponding shooting range of each unmanned aerial vehicle is fixed to be the preset arc length under the preset distance, and the corresponding first shooting times are obtained by calculating the abnormal circumference and the preset arc length, so that the follow-up unmanned aerial vehicle can conveniently acquire the surrounding images, and a verification image is generated.
The first photographing times are calculated by the following formula,
Figure SMS_18
wherein n is 1 For the first shooting times, x 1 X is the first abscissa, x 2 In the second abscissa of the graph, the first abscissa,
Figure SMS_19
is the abscissa value of the center point, y 1 As the first ordinate, y 2 For the second ordinate, +.>
Figure SMS_20
Is the ordinate value of the center point, L For the preset arc length, k of the epsilon-type acquisition device 2 The first shooting time weight value.
And determining any vertex in the abnormal rectangular area as a shooting starting point based on the center point coordinates of the acquisition path, controlling an acquisition device to acquire side images of each second abnormal subset according to corresponding first shooting times based on the shooting starting point, and generating a verification image according to the side images and top images corresponding to the corresponding abnormal rectangular area.
According to the technical scheme provided by the invention, any vertex in the abnormal rectangular area is determined as a shooting starting point based on the central point coordinates of the acquisition path, the unmanned aerial vehicle performs first shooting at a preset distance from the shooting starting point, and performs shooting in a clockwise or anticlockwise manner according to the calculated first shooting times, so that all images around the abnormal area are obtained, top views are combined with top view images corresponding to the abnormal rectangular area, the top views are arranged on the middle peripheral side images according to the shooting sequence, corresponding verification images are obtained, and the field length can better judge the abnormal area.
In one possible implementation manner, the technical scheme provided by the invention further comprises:
and displaying the first shooting times, receiving the second shooting times actively input by the user, and changing the first shooting times into the second shooting times.
According to the technical scheme provided by the invention, the system can display the first shooting times, and the user can correspondingly adjust when the current shooting times of Tian Changfa are too high or too low, and actively input the second shooting times, so that the system can change the first shooting times into the second shooting times, and the follow-up system can conveniently perform self-adaptive learning adjustment according to the data input by the field length.
If the second shooting times are larger than the first shooting times, determining an increase adjustment value, and increasing and adjusting the weight value of the first shooting times according to the increase adjustment value and the difference value between the second shooting times and the first shooting times to obtain a first shooting times weight value after increasing and adjusting.
According to the technical scheme provided by the invention, if the second shooting times are larger than the first shooting times, the first shooting times are too small, and the shot surrounding images are not comprehensive enough, so that the shooting times are more adjusted by a user, an increase adjustment value is determined, the weight value of the first shooting times is increased and adjusted according to the increase adjustment value and the difference value between the second shooting times and the first shooting times, and the adjusted weight value of the first shooting times is obtained.
If the second shooting times are smaller than the first shooting times, determining a reduction adjustment value, and reducing and adjusting the weight value of the first shooting times according to the reduction adjustment value and the difference value of the first shooting times and the second shooting times to obtain a first shooting times weight value after reduction adjustment.
According to the technical scheme provided by the invention, if the second shooting times are smaller than the first shooting times, the first shooting times are too large, and the shot surrounding images are too many, so that the shooting times are adjusted to be small by a user, the reduction adjustment value is determined, the weight value of the first shooting times is reduced and adjusted according to the reduction adjustment value and the difference value of the first shooting times and the second shooting times, and the reduced and adjusted weight value of the first shooting times is obtained.
The adjusted first photographing times weight value is calculated by the following formula,
Figure SMS_21
wherein n is 2 For the second shooting times, n 1 For the first shooting times, k 3 To increase the adjusted first shooting times weight value k 2 For the first shooting times weight value, tau is an increasing adjustment value, k 4 To reduce the adjusted first shot count weight value,
Figure SMS_22
to reduce the adjustment value, where n 2 -n 1 N is the difference between the second shooting times and the first shooting times 1 -n 2 For the difference between the first shooting times and the second shooting times, it can be understood that the adjusted weight value k of the first shooting times is increased 3 Difference n from the second shooting times and the first shooting times 2 -n 1 In proportion to the reduction of the adjusted first shooting frequency weight value k 4 Difference n from the first shooting times and the second shooting times 1 -n 2 Inversely proportional.
According to the technical scheme provided by the invention, the system can perform autonomous learning according to the shooting times actively input by the user, and continuously train the weight value of the shooting times, so that the output shooting times more meet the actual requirements of the field length when the calculation is performed subsequently.
In one possible implementation manner, the technical scheme provided by the invention further comprises:
and if the number of the pixel points in the first abnormal subset is smaller than a preset number value, the first abnormal subset is used as a subset to be processed, and the pixel value of the corresponding coordinate of the subset to be processed is adjusted to be a standard pixel value.
According to the technical scheme provided by the invention, if the number of the pixel points in the first abnormal subset is smaller than the preset number value, it can be understood that the number of the pixel points in the first abnormal subset is smaller than the preset number value, namely the area of the abnormal region is smaller than the area of the preset region, the first abnormal subset is taken as the subset to be processed, the pixel values of the coordinates corresponding to the subset to be processed are adjusted to be standard pixel values, and when the area corresponding to the abnormal region is too small, it can be understood that plastic bags, paper and the like are likely to fall in cultivated land, at the moment, subsequent shooting verification is not needed, the pixel values of the pixel points of the coordinates corresponding to the subset to be processed are adjusted to be standard pixel values, subsequent processing is not needed, but the system records all the coordinates in the subset to be processed, and can be compared and determine whether the plastic bags, the paper and the like are movable foreign matters conveniently when the image acquisition is carried out again.
After a preset acquisition time period, the idle acquisition device acquires and generates a first abnormal subset again, wherein the first abnormal subset comprises a to-be-processed subset, the number of the pixels in the first abnormal subset is greater than or equal to the number of the pixels in the to-be-processed subset, and the first abnormal subset is used as a second abnormal subset.
The technical proposal provided by the invention, after a preset acquisition time period which is set by people, wherein the preset acquisition time period can be 1 day or 10 days, and is not limited again, the idle acquisition device acquires and generates a first abnormal subset which comprises a subset to be processed again, and the number of the pixel points in the first abnormal subset is more than or equal to the number of the pixel points in the subset to be processed, the first abnormal subset is taken as a second abnormal subset, and it can be understood that the first abnormal subset obtained when the unmanned aerial vehicle acquires again comprises the coordinates of all the pixel points in the subset to be processed, namely, the coordinates of all the pixel points in the subset to be processed exist in the first abnormal subset and the coordinates of other abnormal pixel points possibly exist in the first abnormal subset at the moment, and the number of the pixel points in the first abnormal subset is larger than or equal to the number of the pixel points in the to-be-processed subset, and it can be understood that the last neglected abnormal area still exists in the re-collected abnormal area, even the abnormal area is larger than that in the last scanning, which means that the abnormal area still exists and even the area of the abnormal area expands at the moment, the first abnormal subset at the moment is used as the second abnormal subset for subsequent shooting verification.
As shown in fig. 6, a schematic hardware structure of an electronic device according to an embodiment of the present invention is shown, where the electronic device 60 includes: a processor 61, a memory 62 and a computer program; wherein the method comprises the steps of
A memory 62 for storing the computer program, which memory may also be a flash memory (flash). Such as application programs, functional modules, etc. implementing the methods described above.
A processor 61 for executing the computer program stored in the memory to implement the steps executed by the apparatus in the above method. Reference may be made in particular to the description of the embodiments of the method described above.
Alternatively, the memory 62 may be separate or integrated with the processor 61.
When the memory 62 is a device separate from the processor 61, the apparatus may further include:
a bus 63 for connecting the memory 62 and the processor 61.
The present invention also provides a readable storage medium having stored therein a computer program for implementing the methods provided by the various embodiments described above when executed by a processor.
The readable storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium. In the alternative, the readable storage medium may be integral to the processor. The processor and the readable storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the readable storage medium may reside as discrete components in a communication device. The readable storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.
The present invention also provides a program product comprising execution instructions stored in a readable storage medium. The at least one processor of the device may read the execution instructions from the readable storage medium, the execution instructions being executed by the at least one processor to cause the device to implement the methods provided by the various embodiments described above.
In the above embodiment of the apparatus, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims (10)

1. A data processing method suitable for intelligent agriculture, comprising:
acquiring attribute data and corresponding quantity information of the idle acquisition device, and carrying out regional acquisition on the cultivated area of Tian Changduan according to the attribute data and the quantity information to obtain a current cultivated land top view;
acquiring preset crop type information corresponding to the cultivated land area and a standard pixel value corresponding to the preset crop type information;
decomposing the current cultivated land top view to generate a current pixel point set, comparing the pixel value of each pixel point in the current pixel point set with a standard pixel value to determine an abnormal pixel point, counting the abnormal pixel points to generate a first abnormal total set, and splitting the first abnormal total set into a plurality of independent first abnormal subsets according to the position relation of each abnormal pixel point;
if the number of the pixel points in the abnormal subset is larger than a preset number value, determining a shooting path according to the abnormal subset, controlling an acquisition device to acquire according to the shooting path, generating a verification image, and sending the verification image to a field long end for verification.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
The obtaining the attribute data and the corresponding quantity information of the idle collecting device, and carrying out regional collection on the cultivated area of Tian Changduan according to the attribute data and the quantity information to obtain the top view of the current cultivated area, comprising:
acquiring a first acquisition area and corresponding quantity information of idle acquisition devices of each model in a preset time period, and distributing the corresponding cultivated land area of the cultivated land area according to the first acquisition area and the quantity information to acquire a second acquisition area corresponding to each idle acquisition device;
the second acquisition area is obtained by the following formula,
Figure FDA0003937917190000011
wherein M is R Idle for type RFirst collection area of collection device, l r For the number of the r-th idle acquisition devices, p r For the first acquisition area of the r-th idle acquisition device in a preset time period, u is the upper limit value of the number of idle acquisition device models, and c i For the number information of the ith idle acquisition device, m i For the device first acquisition area, M, of each idle acquisition device of the ith type α For the cultivated land area M r A second acquisition area of each idle acquisition device for the r-th model;
acquiring device numbers of a plurality of idle acquisition devices, distributing the second acquisition areas to the idle acquisition devices of the corresponding device numbers, and controlling the idle acquisition devices of the device numbers to carry out regional acquisition on a cultivated area with the corresponding second acquisition areas to obtain a top view of the current cultivated area.
3. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the acquiring the device numbers of the plurality of idle acquisition devices, distributing the second acquisition areas to the idle acquisition devices of the corresponding device numbers, and controlling the idle acquisition devices of the device numbers to acquire the cultivated area in a partitioning manner by the corresponding second acquisition areas to obtain a top view of the current cultivated area, wherein the method comprises the following steps:
acquiring device numbers of a plurality of idle acquisition devices, distributing the second acquisition areas to the corresponding device numbers, and carrying out ascending order sequencing on the device numbers according to the second acquisition areas to obtain an ascending order acquisition sequence;
dividing the second acquisition area in the ascending acquisition sequence of the cultivated land area based on a preset division sequence to obtain at least one acquisition area, and sequentially controlling each idle acquisition device in the ascending acquisition sequence to acquire images of the acquisition area according to the preset division sequence;
and splicing the images acquired by each idle acquisition device based on the shooting time to generate an area image corresponding to each idle acquisition device, and splicing the area images in turn based on the sequence of device numbers in the ascending acquisition sequence to generate a top view of the current cultivated land.
4. The method of claim 2, wherein the step of determining the position of the substrate comprises,
the acquiring the device numbers of the plurality of idle acquisition devices, distributing the second acquisition areas to the idle acquisition devices of the corresponding device numbers, and controlling the idle acquisition devices of the device numbers to acquire the cultivated area in a partitioning manner by the corresponding second acquisition areas to obtain a top view of the current cultivated area, wherein the method comprises the following steps:
acquiring the total pixel number of the cultivated land area, determining the number of sub-pixel points corresponding to each second acquisition area according to the total pixel number, counting the number of the sub-pixel points, sequencing in an ascending order to obtain an acquisition area set, acquiring the device numbers of a plurality of idle acquisition devices, and binding the device numbers with the corresponding number of the sub-pixel points one by one;
displaying the collection area set, and determining the number of one sub-pixel point in the collection area set as the area to be allocated and the device number corresponding to the area to be allocated according to the selected information of the user;
a transparent layer is overlapped on an image of a cultivated land area, the cultivated land area is divided into areas in response to the triggering of a worker on the transparent layer, a first subarea corresponding to the area to be allocated is obtained, and the first subarea is associated with the device number;
Repeating the steps until the number of the sub-pixel points in the collection area set is the last, stopping dividing, taking an unallocated area in the cultivated area as an unallocated first sub-area, and establishing association between the unallocated first sub-area and an unallocated device number;
and carrying out regional acquisition on the corresponding first subarea by utilizing each idle acquisition device to obtain the top view of the current cultivated land.
5. The method of claim 4, wherein the step of determining the position of the first electrode is performed,
the step of superposing a transparent layer on a cultivated land area, responding to the triggering of a worker on the transparent layer to divide the cultivated land area into areas, obtaining a first subarea corresponding to the area to be allocated, and associating the first subarea with the device number, comprising the following steps:
generating a first trigger signal based on the transparent layer, responding to the first trigger signal, recording that a worker generates a dividing line for a first trigger trace of the transparent layer in real time, and recording that the current position of the dividing line is a first position;
responding to a second trigger signal, recording the dragging trace of a worker on the dividing line in real time to generate a dragging track, synchronously moving the dividing line based on the dragging track, and recording the position of the dividing line as a second position when the number of pixel points traversed by the dividing line is equal to or larger than the area to be distributed;
And taking the cultivated land area between the first position and the second position as a first subarea corresponding to the area to be allocated, determining a device number corresponding to the area to be allocated, and establishing association between the first subarea and the device number.
6. The method according to claim 3 or 5, wherein,
decomposing the current cultivated land top view to generate a current pixel point set, comparing a pixel value of each pixel point in the current pixel point set with a standard pixel value to determine an abnormal pixel point, counting the abnormal pixel points to generate a first abnormal total set, and splitting the first abnormal total set into a plurality of independent first abnormal subsets according to the position relation of each abnormal pixel point, wherein the method comprises the following steps of:
establishing a coordinate system based on preset pixel points in the current cultivated land top view to decompose to obtain a current pixel point set;
if the pixel value of the pixel point in the current pixel point set is equal to the standard pixel value, the pixel point is used as a normal pixel point;
if the pixel value of the pixel point in the current pixel point set is not equal to the standard pixel value, taking the pixel point as an abnormal pixel point, and counting the abnormal pixel point to generate a first abnormal total set;
Sequentially selecting abnormal pixel points in the first abnormal total set as first abnormal pixel points, and counting the abnormal pixel points which are directly connected and indirectly connected with the first abnormal pixel points to obtain a first abnormal subset;
deleting the abnormal pixel points in the first abnormal subset from the first abnormal total set, and repeating the step of obtaining the first abnormal subset until the first abnormal total set is an empty set, so as to generate a plurality of independent first abnormal subsets.
7. The method of claim 6, wherein the step of providing the first layer comprises,
if the number of the pixel points in the abnormal subset is greater than a preset number value, determining a shooting path according to the abnormal subset, controlling an acquisition device to acquire according to the shooting path, generating a verification image, and sending the verification image to a field long end for verification, wherein the method comprises the following steps:
if the number of the pixel points in the first abnormal subset is larger than or equal to a preset number value, the first abnormal subset is used as a second abnormal subset, the adjacent pixel points in the second abnormal subset are extracted to be abnormal pixel points of normal pixel points, and an abnormal contour set is generated;
respectively obtaining minimum values and maximum values corresponding to the abscissa and the ordinate of the abnormal pixel points in the abnormal contour set to obtain a minimum abscissa value, a maximum abscissa value, a minimum ordinate value and a maximum ordinate value;
Constructing longitudinal parallel lines according to the minimum abscissa value and the maximum abscissa value, constructing transverse parallel lines according to the minimum ordinate value and the maximum ordinate value, and generating an abnormal rectangular area according to the longitudinal parallel lines and the transverse parallel lines;
the abnormal rectangular areas are subjected to descending order based on the areas of the abnormal rectangular areas, a rectangular area sequence is generated, the acquisition devices are subjected to descending order based on the acquisition areas of the devices, and a device sequence is generated;
if the number of the abnormal rectangular areas is larger than that of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas in the rectangular area sequence, the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas, and after the acquisition is finished, the acquisition devices in the device sequence are in one-to-one correspondence with the rest abnormal rectangular areas in the rectangular area sequence and are acquired;
if the number of the abnormal rectangular areas is smaller than or equal to the number of the idle acquisition devices, the acquisition devices in the device sequence are in one-to-one correspondence with the abnormal rectangular areas, and the acquisition devices are controlled to acquire the corresponding abnormal rectangular areas;
and determining center point coordinates and first shooting times according to the abnormal rectangular areas, generating acquisition paths according to the distance relation between the center point coordinates and starting point coordinates of the acquisition devices, controlling the acquisition devices to acquire side images according to the corresponding first shooting times for each second abnormal subset based on the acquisition paths, generating verification images according to the side images and overlooking images corresponding to the corresponding abnormal rectangular areas, and sending the verification images to the long ends of the fields for verification.
8. The method of claim 7, wherein the step of determining the position of the probe is performed,
the method comprises the following steps of calculating a preset quantity value, wherein the method specifically comprises the following steps of:
acquiring the cultivated land grade and the cultivated land area of each cultivated land in the cultivated land area corresponding to Tian Changduan, and calculating according to the cultivated land grade, the cultivated land area and the cultivated land quantity to obtain a preset quantity value;
the preset quantity value is calculated by the following formula,
Figure FDA0003937917190000051
wherein S is a preset quantity value, n is an upper limit value of the cultivated land quantity, h o For the corresponding cultivated land grade of the o th cultivated land, m o Corresponding cultivated land for the o th cultivated landArea, M α In order to cultivate the area of the land,
Figure FDA0003937917190000053
to preset the cultivated land grade omega 1 Level normalization value->
Figure FDA0003937917190000052
For reference cultivated land area omega 2 Area normalization value->
Figure FDA0003937917190000054
Is a reference number value.
9. The method of claim 8, wherein the step of determining the position of the first electrode is performed,
the step of determining the center point coordinate and the first shooting times according to the abnormal rectangular region and generating an acquisition path according to the distance relation between the center point coordinate and the starting point coordinate of the acquisition device comprises the following steps:
obtaining a first ordinate and a second ordinate according to the ordinate values of two vertexes with the same abscissa in the abnormal rectangular area, and obtaining the ordinate value of the center point according to the average value of the first ordinate and the second ordinate;
Acquiring abscissa values of two vertexes with the same ordinate in the abnormal rectangular area to obtain a first abscissa and a second abscissa, and obtaining an abscissa value of a center point according to an average value of the first abscissa and the second abscissa;
generating a central point coordinate of an abnormal rectangular area according to the longitudinal coordinate value of the central point and the transverse coordinate value of the central point, acquiring a starting point coordinate of an acquisition device, generating a linear distance according to the central point coordinates and the starting point coordinates of all the abnormal rectangular areas, and sequencing the central point coordinates in ascending order based on the linear distance to obtain a distance sequence;
sequentially connecting the starting point coordinates with the central point coordinates in the distance sequence to generate an acquisition path;
the center point coordinates are used as circle center coordinates, a radius is generated according to the circle center coordinates and vertex coordinates of the abnormal rectangular area, and an abnormal circumference is generated according to the circle center coordinates and the radius;
calculating according to the abnormal circumference and a preset arc length to obtain a first shooting frequency;
the first photographing times are calculated by the following formula,
Figure FDA0003937917190000061
wherein n is 1 For the first shooting times, x 1 X is the first abscissa, x 2 In the second abscissa of the graph, the first abscissa,
Figure FDA0003937917190000062
is the abscissa value of the center point, y 1 As the first ordinate, y 2 For the second ordinate, +.>
Figure FDA0003937917190000063
Is the ordinate value of the center point, L For the preset arc length, k of the epsilon-type acquisition device 2 The first shooting frequency weight value;
and determining any vertex in the abnormal rectangular area as a shooting starting point based on the center point coordinates of the acquisition path, controlling an acquisition device to acquire side images of each second abnormal subset according to corresponding first shooting times based on the shooting starting point, and generating a verification image according to the side images and top images corresponding to the corresponding abnormal rectangular area.
10. The method as recited in claim 9, further comprising:
displaying the first shooting times, receiving second shooting times actively input by a user, and changing the first shooting times into the second shooting times;
if the second shooting times are larger than the first shooting times, determining an increase adjustment value, and increasing and adjusting the weight value of the first shooting times according to the increase adjustment value and the difference value between the second shooting times and the first shooting times to obtain a first shooting times weight value after increasing and adjusting;
If the second shooting times are smaller than the first shooting times, determining a reduction adjustment value, and reducing and adjusting the weight value of the first shooting times according to the reduction adjustment value and the difference value of the first shooting times and the second shooting times to obtain a first shooting times weight value after reduction adjustment;
the adjusted first photographing time weight value is increased and the adjusted first photographing time weight value is decreased by the following formula,
Figure FDA0003937917190000064
wherein n is 2 For the second shooting times, n 1 For the first shooting times, k 3 To increase the adjusted first shooting times weight value k 2 For the first shooting times weight value, tau is an increasing adjustment value, k 4 To reduce the adjusted first shot count weight value,
Figure FDA0003937917190000065
to reduce the adjustment value.
CN202211409305.9A 2022-11-11 2022-11-11 Data processing method suitable for intelligent agriculture Active CN116309625B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211409305.9A CN116309625B (en) 2022-11-11 2022-11-11 Data processing method suitable for intelligent agriculture

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211409305.9A CN116309625B (en) 2022-11-11 2022-11-11 Data processing method suitable for intelligent agriculture

Publications (2)

Publication Number Publication Date
CN116309625A true CN116309625A (en) 2023-06-23
CN116309625B CN116309625B (en) 2024-01-30

Family

ID=86819153

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211409305.9A Active CN116309625B (en) 2022-11-11 2022-11-11 Data processing method suitable for intelligent agriculture

Country Status (1)

Country Link
CN (1) CN116309625B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116543309A (en) * 2023-06-28 2023-08-04 华南农业大学 Crop abnormal information acquisition method, system, electronic equipment and medium
CN117172962A (en) * 2023-07-17 2023-12-05 南京工业职业技术大学 Power system-based electricity utilization energy saving method and system
CN117315508A (en) * 2023-08-24 2023-12-29 北京智盟信通科技有限公司 Power grid equipment monitoring method and system based on data processing
CN118114957A (en) * 2024-04-30 2024-05-31 四川众瓴数字科技有限公司 Farmland construction quality supervision method based on digital technology

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110320163A (en) * 2019-06-26 2019-10-11 深圳市宇驰检测技术股份有限公司 Online water quality monitoring method, system and the storage medium of unmanned plane
WO2020216091A1 (en) * 2019-04-22 2020-10-29 Oppo广东移动通信有限公司 Image processing method and related apparatus
WO2021092815A1 (en) * 2019-11-13 2021-05-20 深圳市大疆创新科技有限公司 Identification method, temperature measurement method, device and storage medium
CN114743117A (en) * 2022-04-18 2022-07-12 宋敬洁 Remote sensing image acquisition prevention and control method and system suitable for pest and disease damage monitoring
CN115225870A (en) * 2022-09-21 2022-10-21 北京瞭望神州科技有限公司 Data processing-based intelligent protection remote monitoring method and system for cultivated land
CN115271435A (en) * 2022-07-27 2022-11-01 北京瞭望神州科技有限公司 Data processing method and device suitable for intelligent protection of cultivated land

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020216091A1 (en) * 2019-04-22 2020-10-29 Oppo广东移动通信有限公司 Image processing method and related apparatus
CN110320163A (en) * 2019-06-26 2019-10-11 深圳市宇驰检测技术股份有限公司 Online water quality monitoring method, system and the storage medium of unmanned plane
WO2021092815A1 (en) * 2019-11-13 2021-05-20 深圳市大疆创新科技有限公司 Identification method, temperature measurement method, device and storage medium
CN114743117A (en) * 2022-04-18 2022-07-12 宋敬洁 Remote sensing image acquisition prevention and control method and system suitable for pest and disease damage monitoring
CN115271435A (en) * 2022-07-27 2022-11-01 北京瞭望神州科技有限公司 Data processing method and device suitable for intelligent protection of cultivated land
CN115225870A (en) * 2022-09-21 2022-10-21 北京瞭望神州科技有限公司 Data processing-based intelligent protection remote monitoring method and system for cultivated land

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
ZHONG JIE ET AL.: "Fuzzy Gain Scheduler Based Path Tracking on Image Plane for XY/Z Partitioned IBVS System", 《 PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON MODELLING, IDENTIFICATION AND CONTROL (ICMIC2019)》, vol. 582, pages 727 - 735 *
孔百川: "无人机数据采集的路径规划算法研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 02, pages 002 - 789 *
曲鹏等: "田间异物识别算法研究", 《农机化研究》, vol. 40, no. 07, pages 42 - 47 *
赵颖等: "基于机器视觉的耕作机器人行走目标直线检测", 《农业机械学报》, no. 04, pages 83 - 86 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116543309A (en) * 2023-06-28 2023-08-04 华南农业大学 Crop abnormal information acquisition method, system, electronic equipment and medium
CN116543309B (en) * 2023-06-28 2023-10-27 华南农业大学 Crop abnormal information acquisition method, system, electronic equipment and medium
CN117172962A (en) * 2023-07-17 2023-12-05 南京工业职业技术大学 Power system-based electricity utilization energy saving method and system
CN117172962B (en) * 2023-07-17 2024-04-16 南京工业职业技术大学 Power system-based electricity utilization energy saving method and system
CN117315508A (en) * 2023-08-24 2023-12-29 北京智盟信通科技有限公司 Power grid equipment monitoring method and system based on data processing
CN117315508B (en) * 2023-08-24 2024-05-14 北京智盟信通科技有限公司 Power grid equipment monitoring method and system based on data processing
CN118114957A (en) * 2024-04-30 2024-05-31 四川众瓴数字科技有限公司 Farmland construction quality supervision method based on digital technology

Also Published As

Publication number Publication date
CN116309625B (en) 2024-01-30

Similar Documents

Publication Publication Date Title
CN116309625B (en) Data processing method suitable for intelligent agriculture
CN106403904A (en) Landscape-scale vegetation coverage calculation method and system based on unmanned aerial vehicle
CN111985724B (en) Crop yield estimation method, device, equipment and storage medium
CN110176024A (en) Method, apparatus, equipment and the storage medium that target is detected in video
CN105869175A (en) Image segmentation method and system
CN113822198B (en) Peanut growth monitoring method, system and medium based on UAV-RGB image and deep learning
CN108876903B (en) Corn variety distinguishing method and system based on corn tassel three-dimensional phenotype
CN115311587B (en) Intelligent generation method for photovoltaic power station inspection waypoints
CN114638292A (en) Artificial intelligence pathology auxiliary diagnosis system based on multi-scale analysis
CN115049925A (en) Method for extracting field ridge, electronic device and storage medium
CN113095441A (en) Pig herd bundling detection method, device, equipment and readable storage medium
CN108229289A (en) Target retrieval method, apparatus and electronic equipment
CN110555371A (en) Wild animal information acquisition method and device based on unmanned aerial vehicle
CN110689022B (en) Method for extracting images of crops of each plant based on blade matching
CN114022771B (en) Deep learning-based corn seedling stage field distribution information statistical method
CN111340889A (en) Method for automatically acquiring matched image block and point cloud ball based on vehicle-mounted laser scanning
CN112597995B (en) License plate detection model training method, device, equipment and medium
CN116739739A (en) Loan amount evaluation method and device, electronic equipment and storage medium
CN111950773A (en) System and method for predicting tea yield
CN113807128A (en) Seedling shortage marking method and device, computer equipment and storage medium
CN116486312A (en) Video image processing method and device, electronic equipment and storage medium
CN113011220A (en) Spike number identification method and device, storage medium and processor
CN106339683A (en) Road test traffic light identification method and device
CN115240091A (en) Method and device for quickly detecting rice panicle grains
CN112287787B (en) Crop lodging grading method based on gradient histogram characteristics

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: Building 2, Beihuan Road, Jurong Economic Development Zone, Zhenjiang City, Jiangsu Province (Jinliyuan Hotel)

Applicant after: Jurong Native Tree Species Research Institute Co.,Ltd.

Address before: Building 2, Beihuan Road, Jurong Economic Development Zone, Zhenjiang City, Jiangsu Province (Jinliyuan Hotel)

Applicant before: JURONG INDIGENOUS TREE SPECIES Research Institute

CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Zhou Peng

Inventor after: Zou Hongqiang

Inventor after: Shu Chang

Inventor after: Guo Wenjing

Inventor before: Zhou Peng

Inventor before: Zou Hongqiang

GR01 Patent grant
GR01 Patent grant