NL2032240B1 - Red dates maturity and picking analysis method and system considering environmental factors - Google Patents

Red dates maturity and picking analysis method and system considering environmental factors Download PDF

Info

Publication number
NL2032240B1
NL2032240B1 NL2032240A NL2032240A NL2032240B1 NL 2032240 B1 NL2032240 B1 NL 2032240B1 NL 2032240 A NL2032240 A NL 2032240A NL 2032240 A NL2032240 A NL 2032240A NL 2032240 B1 NL2032240 B1 NL 2032240B1
Authority
NL
Netherlands
Prior art keywords
historical
data
gray
red dates
maturity
Prior art date
Application number
NL2032240A
Other languages
Dutch (nl)
Inventor
Li Xu
Zhang Yuyang
Wu Cuiyun
Lv Xifeng
Original Assignee
Univ Tarim
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 Univ Tarim filed Critical Univ Tarim
Priority to NL2032240A priority Critical patent/NL2032240B1/en
Application granted granted Critical
Publication of NL2032240B1 publication Critical patent/NL2032240B1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Animal Husbandry (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Agronomy & Crop Science (AREA)
  • Development Economics (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention discloses a red dates maturity and picking analysis method, system and a terminal considering environmental factors, and relates to the technical field of maturity analysis for agricultural products. The technical solution has a key point 5 as follows: performing curve fitting on historical canopy light radiation data, historical temperature data and historical humidity data; extracting total gray information of all red dates in a target image, and dividing, according to a gray level range, the total gray information. into a plurality of levels of gray 10 information; solving and obtaining maturity time nodes of different levels of hierarchical gray information according to the light radiation fitting function, the temperature fitting function and, the humidity fitting function. as well as a gray evolution model; and determining, an optimal time node for picking red dates 15 in the target region according to all the maturity time nodes. (+ Fig.)

Description

P1409/NLpd
RED DATES MATURITY AND PICKING ANALYSIS METHOD AND SYSTEM
CONSIDERING ENVIRONMENTAL FACTORS
TECHNICAL FIELD
The present invention relates to the technical field of anal- ysis of maturity of agricultural products, specifically to a red dates maturity and picking analysis method and system considering environmental factors.
BACKGROUND ART
The picking time of an agricultural product is affected by its maturity. Due to a high growth density of red dates, the mor- phological changes during the growth are not particularly obvious, and are affected by environmental factors such as temperature, hu- midity and light. The maturities of red dates in the same plant easily have great differences. Therefore, it is difficult to ana- lyze the maturity of red dates accurately and in a large area.
SUMMARY
The present invention aims to provide a red dates maturity and picking analysis method and system considering environmental factors. Maturity time nodes corresponding to different levels can be obtained, and an optimal time node for picking which can bal- ance the quality of red dates and the economical benefit is ob- tained.
The above-mentioned technical aim of the present invention is achieved by the following technical solution.
In a first aspect, a red dates maturity and picking analysis method considering environmental factors includes the following steps: acquiring historical canopy light radiation data, histori- cal temperature data and historical humidity data; respectively performing curve fitting on the historical cano- py light radiation data, the historical temperature data and the historical humidity data by using the least square method to ob- tain a corresponding light radiation fitting function, temperature fitting function and humidity fitting function; acquiring a target image containing red dates in a target re- gion, extracting total gray information of all the red dates in the target image, and dividing, according to a gray level range, the total gray information into a plurality of levels of gray in- formation; solving and obtaining maturity time nodes of different levels of hierarchical gray information according to the light radiation fitting function, the temperature fitting function and the humidi- ty fitting function as well as a gray evolution model; and determining an optimal time node for picking red dates in the target region according to all the maturity time nodes, and ob- taining a picking strategy.
Further, a calculation formula of the gray evolution model is specifically: [os Tek
Mo +) =log sp f(r £xk(1) a>] 4 “+ ce e+ EN j + D = 50 where y(t;+t) represents a maturity corresponding to a red dates growth duration of t;+f£; a is a constant, which is determined according to growth characteristics of a red date variety in the
Jy target region; HGF represents a maturity mapped from a gray val- ue corresponding to a current time node of t,; t represents a time interval from the current time node; KI) presents a mean of environmental factor influence factors within the time interval £; yo represents a maturity reference value; and ft, represents a ma- turity time node.
Further, a calculation formula of the mean of the environmen- tal factor influence factors is specifically: 1 Je
D= DAB) . f= where A(i) represents an influence factor of a light radia- tion at time i; B(i) represents an influence factor of a tempera- ture at time i; and C{i) represents an influence factor of a hu- midity at time 1.
Further, a calculation formula of the influence factor of the light radiation at time i is specifically:
A=" where RH(i) represents the light radiation fitting function;
RH; represents a light radiation reference value; a calculation formula of the influence factor of the tempera- ture at time i is specifically: oo LE)
B i) eg, where T(i) represents the temperature fitting function, and
T, represents a temperature reference value; a calculation formula of the influence factor of the humidity at time i is specifically:
SS
Cf) =—— where S5(i) represents the humidity fitting function, and 3; represents a humidity reference value.
Further, if the calculated influence factor of the light ra- diation at time i is greater than a first threshold, the first threshold is used as an actual influence factor of the light radi- ation at time i; if the calculated influence factor of the temperature at time i is greater than a second threshold, the second threshold is used as an actual influence factor of the temperature at time 1; if the calculated influence factor of the humidity at time i is greater than a third threshold, the third threshold is used as an actual influence factor of the humidity at time 1.
Further, a calculation formula of the optimal time node is specifically: # >, (7) —t, Pp =0
As where n represents the number of levels of the total gray in- formation; £;{(j) represents a maturity time node corresponding to a 3% layer of gray information; t, represents the optimal time node; and &; represents a weight coefficient of the j°’ layer of gray information.
Further, a weight coefficient of the maturity time node is allocated according to ratios of red dates in different levels of gray information. In a second aspect, a red dates maturity and picking analysis system considering environmental factors is pro- vided, including: a data acquisition module configured for acquiring historical canopy light radiation data, historical temperature data and his- torical humidity data of a target region; a curve fitting module configured for respectively performing curve fitting on the historical canopy light radiation data, the historical temperature data and the historical humidity data by using the least square method to obtain a corresponding light ra- diation fitting function, temperature fitting function and humidi- ty fitting function; a gray stratification module configured for acquiring a tar- get image containing red dates in the target region, extracting total gray information of all the red dates in the target image, and dividing, according to a gray level range, the total gray in- formation into a plurality of levels of gray information; an evolution analysis module configured for solving and ob- taining maturity time nodes of different levels of hierarchical gray information according to the light radiation fitting func- tion, the temperature fitting function and the humidity fitting function; and a strategy generation module configured for determining an optimal time node for picking red dates in the target region ac- cording to all the maturity time nodes, and obtaining a picking strategy.
The present invention has the following beneficial effects: 1. According to the red dates maturity and picking analysis method considering the environmental factors, environmental factor data corresponding to time nodes is selected from the historical 5 canopy light radiation data, the historical temperature data and the historical humidity data, and the red dates in the target im- age are subjected to stratification analysis according to the gray information, thus obtaining the maturity time nodes corresponding to different levels; finally, the optimal time node for picking that can balance the quality of red dates and the economical bene- fit can be obtained by considering the density distributions of the red dates at different levels and a specific difference be- tween the levels; and reference data is provided for the picking of the red dates. 2. In the present invention, the gray evolution model consid- ers different influences of the environmental factors on the ma- turities of the red dates at different growth time points, so that it can adapt to prediction and analysis of maturities of the red dates at different growth time nodes, and the application range is large. 3. By fusing and accumulating the influence factors of vari- ous environmental factors, the present invention effectively re- duces the complexity of the maturity analysis process and is suit- able for batch analysis of a large number of red dates.
BRIEF DESCRIPTION OF THE DRAWINGS
FIG. 1 is a flow chart of an embodiment of the present inven- tion.
FIG. 2 is a system block diagram of an embodiment of the pre- sent invention.
DETAILED DESCRIPTION OF THE EMBODIMENTS
Embodiment 1: A red dates maturity and picking analysis meth- od considering the environmental factors, as shown in FIG. 1, in- cludes the following steps:
Sl: historical canopy light radiation data, historical tem- perature data and historical humidity data of a target region are acquired;
Sl: curve fitting is performed respectively on the historical canopy light radiation data, the historical temperature data and the historical humidity data by using the least square method to obtain a corresponding light radiation fitting function, tempera- ture fitting function and humidity fitting function;
Sl: a target image containing red dates in the target region is acquired; total gray information of all the red dates in the target image is extracted; and the total gray information is di- vided, according to a gray level range, into a plurality of levels of gray information;
Sl: maturity time nodes of different levels of hierarchical gray information are solved and obtained according to the light radiation fitting function, the temperature fitting function and the humidity fitting function as well as a gray evolution model; and
Sl: an optimal time node for picking red dates in the target region is determined according to all the maturity time nodes, and a picking strategy is obtained.
The historical canopy light radiation data, the historical temperature data and the historical humidity data are mainly se- lected from historical year or season data in the same target re- gion. In order to avoid obvious difference points in the light ra- diation fitting function, the temperature fitting function and the humidity fitting function, interpolation correction processing can be performed on the light radiation fitting function, the tempera- ture fitting function and the humidity fitting function according to a correlation among light radiation, temperature and humidity.
In the present invention, environmental factor data corre- sponding to time nodes is selected from the historical canopy light radiation data, the historical temperature data and the his- torical humidity data, and the red dates in the target image are subjected to stratification analysis according to the gray infor- mation, thus obtaining the maturity time nodes corresponding to different levels; finally, the optimal time node for picking that can balance the quality of red dates and the economical benefit can be obtained by considering the density distributions of the red dates at different levels and a specific difference between the levels; and reference data is provided for the picking of the red. dates.
A calculation formula of the gray evolution model is specifi- cally: - [os os _ FE
L(t, +0 =log ob flr) tk) | a> 1s 4 “> | ReBoy = r+ D=y We =t+ 2 { + f= oF = where y(ts+t)} represents a maturity corresponding to a red dates growth duration of ts+t; a is a constant, which is determined according to growth characteristics of a red date variety in the ft) target region; RGB represents a maturity mapped from a gray value corresponding to a current time node of ts; t represents a time interval from the current time node; key represents a mean of environmental factor influence factors within the time interval t; yo represents a maturity reference value; and t, represents a maturity time node.
A calculation formula of the mean of the environmental factor influence factors is specifically: _ k(fy=—3 A(x Bi) x Ci) where A(i) represents an influence factor of a light radia- tion at time i; B(i) represents an influence factor of a tempera- ture at time i; and C(i) represents an influence factor of a hu- midity at time i.
A calculation formula of the influence factor of the light radiation at time i is specifically:
A) => where RH{i) represents the light radiation fitting function;
RH, represents a light radiation reference value; a calculation formula of the influence factor of the tempera- ture at time i is specifically:
TG)
B)= "ke
T; where T({i) represents the temperature fitting function, and
Ts represents a temperature reference value; a calculation formula of the influence factor of the humidity at time i is specifically:
Cliy=—— where S{i) represents the humidity fitting function, and S; represents a humidity reference value.
In order to consider the reasonability of the values of the influence factors, thresholds can be set for limitation. Specifi- cally, if the calculated influence factor of the light radiation at time i is greater than a first threshold, the first threshold is used as an actual influence factor of the light radiation at time i; if the calculated influence factor of the temperature at time i is greater than a second threshold, the second threshold is used as an actual influence factor of the temperature at time i; and if the calculated influence factor of the humidity at time i is greater than a third threshold, the third threshold is used as an actual influence factor of the humidity at time 1.
A calculation formula of the optimal time node is specifical- ly:
H
Sele where n represents the number of levels of the total gray in- formation; t(j) represents a maturity time node corresponding to a 7 layer of gray information; t4 represents the optimal time node; and /J7 represents a weight coefficient of the 7 layer of gray information.
A weight coefficient of the maturity time node is allocated according to ratios of red dates in different levels of gray in- formation.
Embodiment 2: A red dates maturity and picking analysis sys- tem considering the environmental factors, as shown in FIG. 2, in- cludes a data acquisition module, a curve fitting module, a gray stratification module, an evolution analysis module and a strategy generation module.
The data acquisition module is configured for acquiring his- torical canopy light radiation data, historical temperature data and historical humidity data of a target region; the curve fitting module is configured for respectively performing curve fitting on the historical canopy light radiation data, the historical temper- ature data and the historical humidity data by using the least square method to obtain a corresponding light radiation fitting function, temperature fitting function and humidity fitting func- tion; the gray stratification module is configured for acquiring a target image containing red dates in the target region, extracting total gray information of all the red dates in the target image, and dividing, according to a gray level range, the total gray in- formation into a plurality of levels of gray information; the evo- lution analysis module is configured for solving and obtaining ma- turity time nodes of different levels of hierarchical gray infor- mation according to the light radiation fitting function, the tem- perature fitting function and the humidity fitting function; and the strategy generation module is configured for determining an optimal time node for picking red dates in the target region ac- cording to all the maturity time nodes, and obtaining a picking strategy.

Claims (2)

CONCLUSIESCONCLUSIONS 1. Rijpings- en plukanalysemethode voor rode dadels die rekening houdt met omgevingsfactoren, met het kenmerk, dat deze omvat: het verwerven van historische gegevens over de lichtstraling van het bladerdak, historische temperatuurgegevens en historische vochtigheidsgegevens van een doelregio; respectievelijk het uitvoeren van curve-aanpassing op de histor- ische lichtstralingsgegevens van het bladerdak, de historische temperatuurgegevens en de historische vochtigheidsgegevens door gebruik te maken van de kleinste-kwadratenmethode om een overeenkomstige lichtstralingsaanpassingsfunctie, tempera- tuuraanpassingsfunctie en vochtigheidsaanpassingsfunctie te verkrijgen; het verwerven van een doelbeeld dat rode dadels in het doelgebied bevat, het extraheren van totale grijsinformatie van alle rode dadels in het doelbeeld, en het verdelen, in overeenstemming met een grijsniveaubereik, van de totale grijsinformatie in meerdere niveaus van grijsinformatie; het oplossen en verkrijgen van rijpheidstijdknooppunten van verschillende niveaus van hiërarchische grijsinformatie in overeenstemming met de lichtstralingsaanpassingsfunctie, de tem- peratuuraanpassingsfunctie en de vochtigheidsaanpassingsfunctie, evenals een grijs evolutiemodel; en het bepalen van een optimaal tijdknooppunt voor het plukken van rode dadels in de doelregio op basis van alle rijpheidstijdknoop- punten, en het verkrijgen van een plukstrategie.1. Ripening and picking analysis method for red dates that takes into account environmental factors, characterized in that it includes: acquiring historical canopy light radiation data, historical temperature data and historical humidity data of a target region; respectively, performing curve fitting on the historical canopy light irradiance data, the historical temperature data and the historical humidity data by using the least square method to obtain a corresponding light radiance adjustment function, temperature adjustment function and humidity adjustment function; acquiring a target image containing red dates in the target area, extracting total gray information of all red dates in the target image, and dividing, in accordance with a gray level range, the total gray information into multiple levels of gray information; solving and obtaining maturity time nodes of different levels of hierarchical gray information according to the light irradiance adjustment function, the temperature adjustment function and the humidity adjustment function, as well as a gray evolution model; and determining an optimal time node for picking red dates in the target region based on all ripeness time nodes, and obtaining a picking strategy. 2. Rijpings- en plukanalysesysteem voor rode dadels die rekening houdt met omgevingsfactoren, gekenmerkt door: een data-acquisitiemodule die is geconfigureerd voor het verwerven van historische lichtstralingsgegevens van het bladerdak, histor- ische temperatuurgegevens en historische vochtigheidsgegevens van een doelregio; een curve-aanpassingsmodule die is geconfigureerd voor het re- spectievelijk uitvoeren van curve-aanpassing op de historische lichtstralingsgegevens van het bladerdak, de historische tempera- tuurgegevens en de historische vochtigheidsgegevens door gebruik te maken van de kleinste-kwadratenmethode om een corresponderende lichtstralingsaanpassingsfunctie, temperatuuraanpassingsfunctie en vochtigheidsaanpassingsfunctie te verkrijgen; een grijsstratificatiemodule die is geconfigureerd voor het ver- werven van een doelafbeelding met rode dadels in de doelregio, het extraheren van totale grijsinformatie van alle rode dadels in het doelbeeld en het verdelen, volgens een grijsniveaubereik, van de totale grijsinformatie in een veelvoud van niveaus van grijsin- formatie; een evolutieanalysemodule die is geconfigureerd voor het oplossen en verkrijgen van rijpheidstijdknooppunten van verschillende niveaus van hiërarchische grijsinformatie volgens de lichtstralingsaanpassingsfunctie, de temperatuuraanpassingsfunctie en de vochtigheidsaanpassingsfunctie, evenals een grijs evolutie- model; en een module voor het genereren van strategieën die is geconfig- ureerd voor het bepalen van een optimaal tijdknooppunt voor het plukken van rode dadels in de doelregio op basis van alle rijpheidstijdknooppunten, en het verkrijgen van een plukstrategie.2. A ripening and picking analysis system for red dates that takes environmental factors into account, characterized by: a data acquisition module configured to acquire historical canopy light radiation data, historical temperature data and historical humidity data of a target region; a curve adjustment module configured to respectively perform curve adjustment on the historical canopy light irradiance data, the historical temperature data and the historical humidity data by using the least squares method to obtain a corresponding light irradiance adjustment function, temperature adjustment function and obtain humidity adjustment function; a gray stratification module configured to acquire a target image with red dates in the target region, extract total gray information of all red dates in the target image and divide, according to a gray level range, the total gray information into a plurality of levels of gray information; an evolution analysis module configured to solve and obtain maturity time nodes of different levels of hierarchical gray information according to the light irradiance adjustment function, the temperature adjustment function and the humidity adjustment function, as well as a gray evolution model; and a strategy generation module configured to determine an optimal time node for picking red dates in the target region based on all ripeness time nodes, and obtain a picking strategy.
NL2032240A 2022-06-22 2022-06-22 Red dates maturity and picking analysis method and system considering environmental factors NL2032240B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
NL2032240A NL2032240B1 (en) 2022-06-22 2022-06-22 Red dates maturity and picking analysis method and system considering environmental factors

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
NL2032240A NL2032240B1 (en) 2022-06-22 2022-06-22 Red dates maturity and picking analysis method and system considering environmental factors

Publications (1)

Publication Number Publication Date
NL2032240B1 true NL2032240B1 (en) 2024-01-08

Family

ID=83506391

Family Applications (1)

Application Number Title Priority Date Filing Date
NL2032240A NL2032240B1 (en) 2022-06-22 2022-06-22 Red dates maturity and picking analysis method and system considering environmental factors

Country Status (1)

Country Link
NL (1) NL2032240B1 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170161560A1 (en) * 2014-11-24 2017-06-08 Prospera Technologies, Ltd. System and method for harvest yield prediction
WO2021140941A1 (en) * 2020-01-10 2021-07-15 株式会社大林組 Harvest prediction device and harvest prediction method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170161560A1 (en) * 2014-11-24 2017-06-08 Prospera Technologies, Ltd. System and method for harvest yield prediction
WO2021140941A1 (en) * 2020-01-10 2021-07-15 株式会社大林組 Harvest prediction device and harvest prediction method

Similar Documents

Publication Publication Date Title
US11317562B2 (en) Generating a yield map for an agricultural field using classification and regression methods
Nipen et al. Adopting citizen observations in operational weather prediction
Gao et al. Rice clock model—a computer model to simulate rice development
Masazhar et al. Digital image processing technique for palm oil leaf disease detection using multiclass SVM classifier
Kaur et al. Data mining in agriculture on crop price prediction: techniques and applications
CN107622322B (en) Forecasting factor identification method of medium-long term runoff and forecasting method of medium-long term runoff
JP7176980B2 (en) Crop management system and crop management method
CN110633841B (en) Provincial range plot scale data assimilation yield prediction method based on set sampling
CN115345076B (en) Wind speed correction processing method and device
CN106897998B (en) Method and system for predicting information of direct solar radiation intensity
CN108427862B (en) Nondestructive measurement method for biomass of multi-variety cotton in whole growth period based on image analysis
NL2032240B1 (en) Red dates maturity and picking analysis method and system considering environmental factors
JPH04372046A (en) Method and device for predicting demand amount
Stillitano et al. Technical efficiency assessment of intensive and traditional olive farms in southern Italy
Waidyarathne et al. Application of artificial neural network to predict copra conversion factor
CN111275246A (en) Price prediction method for single-variety agricultural products based on big data technology
Rahman et al. Application of data mining tools for rice yield prediction on clustered regions of Bangladesh
Priya et al. Stochastic models for sugarcane yield forecasting
CN106096780A (en) The dissolved oxygen prediction method of ant group algorithm Optimized Least Square Support Vector
Bhimani et al. Forecasting of groundnut yield using meteorological variables
CN117196659A (en) Product tracing method and system based on block chain technology
Dahal et al. Assessment of ‘hen and chicken’disorder for marketable yield estimates of table grape using the ‘Berry Analysis Tool’
CN113988351A (en) Numerical mode air temperature forecast product release method based on space-time local model
Brini et al. A machine learning approach to forecasting honey production with tree-based methods
Santhosh Kumar et al. Review on disease detection of plants using image processing and machine learning techniques