Method for acquiring cultivated land planting intensity based on images

Through image acquisition technology, the arable land areas are divided and linear fit is performed, which solves the problem of low manual statistical efficiency in the existing technology, and efficient and accurate acquisition of arable land planting intensity is achieved, distinguishing arable land and non-aerable land areas.

CN118941975APending Publication Date: 2024-11-12BEIJING XIANGTIAN INTELLIGENT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410512410.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-04-26
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the prior art, the use of manual statistics on arable land area is inefficient and prone to problems, making it difficult to efficiently and accurately determine the arable land and non-aerable land areas.

Method used

Using an image acquisition method, by dividing the target area into sub-regions, a vegetation index list is obtained, linear fitting is performed, arable land planting areas are determined, and arable land planting area and intensity are obtained through spatial superposition to generate arable land planting intensity list.

Benefits of technology

It achieves more efficient and accurate acquisition of cultivated land planting intensity, can effectively distinguish cultivated land from non-cultivated land areas, and improves statistical accuracy and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941975A_ABST
    Figure CN118941975A_ABST
Patent Text Reader

Abstract

The invention provides a method for acquiring cultivated land planting intensity based on an image, which relates to the field of cultivated land planting, and comprises the following steps: dividing a target area, acquiring a target sub-area list, acquiring a target vegetation index list set of the target sub-area in a preset time period list, performing linear fitting on target vegetation indexes, and obtaining a target vegetation index list set of the target sub-area in the preset time period list; obtaining a target linear function and a target slope factor corresponding to the target linear function, determining that the target sub-region is a cultivated land planting region in a preset time period based on a preset vegetation index change threshold value and the target slope factor, and carrying out line space superposition on preset grid lists of the cultivated land planting region and the target region to obtain a cultivated land planting region; and obtaining the cultivated land planting area of each preset grid, thereby obtaining the cultivated land planting intensity corresponding to the preset grid, and generating a cultivated land planting intensity list of the target area. According to the method, the cultivated land planting area and the non-cultivated land planting area are determined through the vegetation index, and the planting intensity is obtained more efficiently and accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of cultivated land planting, and in particular to a method for obtaining cultivated land planting intensity based on images. Background Art

[0002] According to the notice, it is clear that the verification of the use of cultivated land should be strengthened. No subsidies shall be given to cultivated land that has been used as livestock farms, forest land, grassland, cultivated land converted to facility agriculture, cultivated land requisitioned (occupied) for non-agricultural purposes, and other cultivated land that has changed its use. No subsidies shall be given to abandoned land. Therefore, it is particularly important to determine cultivated land and non-cultivated land. The existing manual statistical method is too inefficient and prone to problems. It is very important to obtain the cultivated land area efficiently and accurately. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is: a method for obtaining the planting intensity of cultivated land based on images, the method comprising the following steps: S100, divide the target area into sub-areas and obtain a list of target sub-areas A={A1, A2, ..., A i , …, A m}, A i is the i-th target sub-region, i ranges from 1 to m, and m is the number of target sub-regions; S200, obtaining target sub-area A i In the preset time period list J={J1, J2, ..., J x , …, J q}Target vegetation index list set B i ={B i1 , B i2 , …, B ix , …, B iq}, B ix ={B ix1 , B ix2 , …, B ixj , …, B ixn}, B ixj It is B i In the xth preset time period J of the first preset time slice x The target vegetation index at the jth preset time node, J x is the xth preset time period, j ranges from 1 to n, n is the number of preset time nodes; x ranges from 1 to q, q is the number of preset time periods; S300, based on B ix1 , B ix2、 …、B ixj , …, B ixn Do linear fitting to obtain the target linear function Gix and the target linear function G ix The corresponding target slope factor KG ix ; S400, based on a preset vegetation index change threshold Q x and KG ix , determine the target sub-area A i During the preset time period J x The cultivated land area M ix , wherein the preset vegetation index change threshold Q x and J x corresponding; S500, plant the cultivated land in area M ix and a preset grid list C = {C1, C2, ..., C r , …, C s}, perform spatial superposition and obtain each preset grid C r The cultivated land area L r , where L r =∑ q x=1 L xr , L xr It is the grid C r In J x of cultivated land area, C r is the rth preset grid of the target area, r ranges from 1 to s, and s is the number of preset grids in the target area; S600, traverse C, C r , based on C r The cultivated land area L r , get C r The corresponding cultivated land planting intensity P r , thereby generating a list of cultivated land planting intensities in the target area, where P r The value range of is [0, q].

[0004] The present invention has at least the following beneficial effects: In summary, the target area is divided, a list of target sub-areas is obtained, a list of target vegetation indexes of the target sub-areas in a preset time period is obtained, a linear fit is performed on the target vegetation index list, a target linear function and a target slope factor corresponding to the target linear function are obtained, based on a preset vegetation index change threshold and a target slope factor, the target sub-area is determined to be a cultivated land planting area in the preset time period, the preset grid list rows of the cultivated land planting area and the target area are spatially superimposed, the cultivated land planting area of ​​each preset grid is obtained, and thus the cultivated land planting intensity corresponding to the preset grid is obtained, thereby generating a list of cultivated land planting intensities of the target area, the present invention determines the cultivated land planting area and the non-cultivated land planting area through the vegetation index, and obtains the ground planting intensity more efficiently and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0006] Figure 1 A flowchart of a method for obtaining cultivated land planting intensity based on images provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0007] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0008] The embodiment of the present invention provides a method for obtaining the planting intensity of cultivated land based on images, such as Figure 1 As shown, the method comprises the following steps: S100, divide the target area into sub-areas and obtain a list of target sub-areas A={A1, A2, ..., A i , …, A m}, A i is the i-th target sub-region, i ranges from 1 to m, and m is the number of target sub-regions.

[0009] In one embodiment of the present invention, the target area is Jiangdu District, Yangzhou City, Jiangsu Province. The area of ​​Jiangdu District, Yangzhou City, Jiangsu Province is divided according to pixel points to obtain target sub-areas.

[0010] S200, obtaining target sub-area A iIn the preset time period list J={J1, J2, ..., J x , …, J q}Target vegetation index list set B i ={B i1 , B i2 , …, B ix , …, B iq}, B ix ={B ix1 , B ix2 , …, B ixj , …, B ixn}, B ixj It is B i In the xth preset time period J of the first preset time slice x The target vegetation index at the jth preset time node, J x is the x-th preset time period, j ranges from 1 to n, n is the number of preset time nodes; x ranges from 1 to q, q is the number of preset time periods.

[0011] In one embodiment of the present invention, the first time slice is 2023, the preset time period list J={J1}, J1 is July-August, and the jth preset time node is July 19, that is, B ixj A i Target vegetation index on July 19, July-August 2023.

[0012] S300, based on B ix1 , B ix2、 …、B ixj , …, B ixn Do linear fitting to obtain the target linear function G ix and the target linear function G ix The corresponding target slope factor KG ix .

[0013] Specifically, those skilled in the art know that any linear fitting method in the prior art belongs to the protection scope of the present invention and will not be described in detail here.

[0014] S400, based on a preset vegetation index change threshold Q x and KG ix , determine the target sub-area A i During the preset time period J x The cultivated land area M ix , wherein the preset vegetation index change threshold Q x and J x Corresponding.

[0015] S500, plant the cultivated land in area M ixand a preset grid list C = {C1, C2, ..., C r , …, C s}, perform spatial superposition and obtain each preset grid C r The cultivated land area L r , where L r =∑ q x=1 L xr , L xr It is the grid C r In J x of cultivated land area, C r is the rth preset grid in the target area, r ranges from 1 to s, and s is the number of preset grids in the target area.

[0016] Specifically, in one embodiment of the present invention, based on the administrative division characteristics of the assessment area, a preset grid is established according to the average area of ​​the villages. The administrative area of ​​Jiangdu District is 1,332 square kilometers, and it has 13 towns, 268 communities and administrative villages under its jurisdiction. The average area of ​​each village is approximately 4.97 square kilometers (administrative area / number of administrative villages), and the preset grid size is set to 0.74 km×0.74 km.

[0017] S600, traverse C, C r , based on C r The cultivated land area L r , get C r The corresponding cultivated land planting intensity P r , thereby generating a list of cultivated land planting intensities in the target area, where P r The value range of is [0, q].

[0018] Specifically, P r =L r / SC r , among which, SC r It is C r area.

[0019] Specifically, after S600, the method further includes: generating a schematic diagram of the cultivated land planting intensity in the target area based on the cultivated land planting intensity list in the target area. A person skilled in the art knows that any method of generating a schematic diagram based on an intensity value in the prior art belongs to the protection scope of the present invention, for example, generating a schematic diagram of the cultivated land planting intensity based on the brightness change corresponding to the change in the cultivated land planting intensity.

[0020] In summary, the target area is divided, a list of target sub-areas is obtained, a list of target vegetation indexes of the target sub-areas in a preset time period is obtained, a linear fit is performed on the target vegetation index list, a target linear function and a target slope factor corresponding to the target linear function are obtained, based on a preset vegetation index change threshold and a target slope factor, the target sub-area is determined to be a cultivated land planting area in the preset time period, the preset grid list rows of the cultivated land planting area and the target area are spatially superimposed, the cultivated land planting area of ​​each preset grid is obtained, and thus the cultivated land planting intensity corresponding to the preset grid is obtained, thereby generating a list of cultivated land planting intensities of the target area, the present invention determines the cultivated land planting area and the non-cultivated land planting area through the vegetation index, and obtains the ground planting intensity more efficiently and accurately.

[0021] Specifically, the target vegetation index B is obtained by the following steps: ixj : S201, get B i The optical satellite image data (N) at the jth preset time node in the xth preset time period of the first preset time slice ixj , R ixj ), N ixj is the surface reflectivity in the near-infrared band, R ixj is the surface reflectivity in the red light band.

[0022] Specifically, remote sensing technology has the advantages of large coverage and short imaging period, and is suitable for regional surface object surveys. The present invention adopts Sentinel-2 optical satellite image data. Two Sentinel-2 satellites have been launched cumulatively. The specific data source is the atmospheric correction product of Sentinel-2. The data product is atmospherically corrected through Sen2cor, eliminating disturbances caused by the atmosphere and other surface factors. In addition, the present invention selects image data with cloud cover less than 30%.

[0023] S202, obtaining target vegetation index B ixj =(N ixj -R ixj ) / (N ixj +R ixj ).

[0024] Specifically, there are obvious differences in the temporal changes in vegetation index between cultivated land that has been changed in use, such as forest land, grassland, and facility land, and normally cultivated land. Therefore, the present invention distinguishes between cultivated land planting areas and non-cultivated land planting areas based on the target vegetation index, which is more accurate and convenient.

[0025] Furthermore, the preset time period list is obtained by the following steps: S210, obtaining a preset crop list D={D1, D2, ..., D g , …, Dz}, D g is the g-th preset crop in the target area, the value range of g is 1 to z, and z is the number of preset crops in the target area.

[0026] S220, obtaining a list set of vegetation index changes of preset crops in the observation period E = {E1, E2, ..., E g ,…,E z}, E g Yes D g List of vegetation index changes during the observation period.

[0027] Specifically, the vegetation index change list is a list composed of vegetation index values ​​of a list of observation time nodes of preset crops in an observation time period.

[0028] S230, obtaining a vegetation index change list E0 of non-agricultural crops.

[0029] S240 , determining a preset time period list based on the vegetation index change curve list set E and the non-crop vegetation index change list E0 .

[0030] In an exemplary description of the present invention, the preset crops are: wheat is the main crop in the first half of the year, with rapeseed and the like planted sporadically, and rice is the main crop in the second half of the year, with soybeans and the like planted sporadically; Rapeseed: Due to the early planting time, the seedlings emerged in October of the previous year, and the rapeseed began to bloom in mid-March. From March 12 to March 24 to April 6, there was a trend of rapeseed vegetation index decreasing first and then increasing. This is because the vegetation index fluctuates when the rapeseed flowers bloom, especially during the peak flowering period, when the vegetation index is the lowest during the flowering period. In addition, the vegetation index of rapeseed showed an upward trend from January to March, with an increase of 0.3-0.4; after May, the vegetation index of rapeseed showed a downward trend, reaching the lowest value in early June; Wheat: Wheat fields turn green mainly in March. The vegetation index increases rapidly in March and reaches its maximum value in early May. Then, as wheat matures, the vegetation index shows a downward trend and reaches its minimum value in early June. Rice: After rice seedlings emerge and turn green in mid-June, the vegetation index increases. When heading occurs in August, the vegetation index reaches its maximum. As rice matures in October, the vegetation index decreases slightly. Rice is gradually harvested in early November. Other crop plots: Rapeseed is planted in the first half of the year. From June to October, the crop completes a growth cycle, and the growth cycle characteristics meet the growth conditions of soybeans. Rapeseed sowing starts again after October. That is, the plot rotates for rapeseed and soybeans throughout the year; Among the crops in the first half of the year, the vegetation index change trends of rapeseed and wheat showed that the main feature of both crops was a rapid decline in vegetation index in June as the crops matured. Rapeseed and wheat had different growth conditions from January to March, but both showed a rapid decline in vegetation index from May to June, which was significantly different from general non-cultivated plots. Among the crops in the second half of the year, rice and legumes have different maturity times, but the planting time of the crops in the second half of the year is close, and the rapid growth nodes are all from June to August, which is significantly different from the plants grown in other non-arable land plots; Therefore, May to June and June to August are selected as the preset time periods to form a preset time period list.

[0031] Furthermore, the vegetation index change threshold Q is obtained by the following steps: x : S410, obtain D g In the preset time period J of the second preset time slice x Second vegetation index change list within SE xg ={SE xg1 , S.E. xg2 ,…,SE xgj ,…,SE xgn}, thereby obtaining the second vegetation index change list set SE x ={SE x1 , S.E. x2 ,…,SE xg ,…,SE xz}, SE xgj Yes D g In the preset time period J of the second preset time slice x A second vegetation index at the j-th preset time node within the j-th preset time slice, wherein the second preset time slice is not equal to the first preset time slice.

[0032] In an exemplary description of the present invention, the first preset time slice is 2023, the preset time period is July-August, the second preset time slice is 2021, and the preset time period of the second preset time slice is July-August 2021.

[0033] S420, based on SE xg1 , SE xg2 ,…,SE xgj , …, SE xgn Do linear fitting to obtain the second linear function G xg and the second linear function G xg The corresponding second slope KG xg .

[0034] S430, obtaining a preset time period J of E0 in a second preset time slicex The third vegetation index change list within SE x0 ={SE x01 , S.E. x02 ,…,SE x0j ,…,SE x0n}, SE x0j is the preset time period J of E0 in the second preset time slice x The third vegetation index at the j-th preset time node.

[0035] S440, based on SE x01 , SE x02 ,…,SE x0j ,…,SE x0n Do linear fitting to obtain the third linear function G x0 and the third linear function G x0 The corresponding third slope KG x0 .

[0036] S450, based on the second slope list KG x ={KG x1 , KG x2 , …, KG xg , …, KG xz} and the third slope KG x0 , determine the vegetation index change threshold Q x It can be understood that by collecting the historical vegetation index change list set, the second slope list and the third slope are obtained, and the vegetation index change threshold is used to distinguish the second slope and the third slope, thereby obtaining the vegetation index change threshold, which is used to distinguish between cultivated land planting areas and non-cultivated land planting areas.

[0037] In one embodiment of the present invention, the preset crop list D of the target area is {wheat, rapeseed}, the preset time period list J is {J1}, J1 is May-June, and the vegetation index change threshold is Q1=-0.02. i1 <-0.02, determine the target sub-area A i In the preset time period J1, the cultivated land is planted in the area M i1 .

[0038] In another embodiment of the present invention, the preset crop list D of the target area is {rice, beans}, the preset time period list J is {J1}, J1 is June to August, and the vegetation index change threshold is Q1=0.01. i1 >0.01, determine the target sub-area A i In the preset time period J1, the cultivated land is planted in the area M i1 .

[0039] In another embodiment of the present invention, the preset crop list D of the target area is {wheat, rapeseed, rice, beans}, the preset time period list J is {J1, J2}, J1 is May-June, J2 is June-August, and the vegetation index change threshold is Q1=-0.02, Q2=0.01. Further, when x=1, when KG i1 <-0.02, determine the target sub-area A i In the preset time period J1, the cultivated land is planted in the area M i1 ; When x=2, when KG i1 >0.01, determine the target sub-area A i In the preset time period J2, the cultivated land is planted in the area M i2 .

[0040] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0041] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0042] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will also be appreciated by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for obtaining cultivated land planting intensity based on images, It is characterized in that The method comprises the following steps: S100, divide the target area into sub-areas and obtain a list of target sub-areas A={A 1 , A 2 , …, A i , …, A m }, A i is the i-th target sub-region, i ranges from 1 to m, and m is the number of target sub-regions; S200, obtaining target sub-area A i In the preset time period list J={J 1 , J 2 , …, J x , …, J q }Target vegetation index list set B i ={B i1 , B i2 , …, B ix , …, B iq }, B ix ={B ix1 , B ix2 , …, B ixj , …, B ixn }, B ixj It is B i In the xth preset time period J of the first preset time slice x The target vegetation index at the jth preset time node, J x is the xth preset time period, j ranges from 1 to n, n is the number of preset time nodes; x ranges from 1 to q, q is the number of preset time periods; S300, based on B ix1 , B ix2、 …、B ixj , …, B ixn Do linear fitting to obtain the target linear function G ix And the target linear function G ix The corresponding target slope factor KG ix ; S400, based on a preset vegetation index change threshold Q x and KG ix , determine the target sub-area A i During the preset time period J x The cultivated land area M ix , wherein the preset vegetation index change threshold Q x and J x corresponding; S500, plant the cultivated land in area M ix and the preset grid list C of the target area = {C 1 , C 2 , …, C r , …, C s }, perform spatial superposition and obtain each preset grid C r The cultivated land area L r , where L r =∑ q x=1 L xr , L xr It is the grid C r In J x of cultivated land area, C r is the rth preset grid of the target area, r ranges from 1 to s, and s is the number of preset grids in the target area; S600, traverse C, C r , based on C r The cultivated land area L r , get C r The corresponding cultivated land planting intensity P r , thereby generating a list of cultivated land planting intensities in the target area, where P r The value range of is [0, q].

2. The method for obtaining cultivated land planting intensity based on images according to claim 1, It is characterized in that After S600, the method further includes: generating a schematic diagram of the cultivated land planting intensity in the target area based on the cultivated land planting intensity list in the target area.

3. The method for obtaining cultivated land planting intensity based on images according to claim 1, It is characterized in that It also includes obtaining a list of preset time periods by following the steps below: S210, obtaining a preset crop list D of the target area = {D 1 , D 2 , …, D g , …, D z }, D g is the g-th preset crop in the target area, where g ranges from 1 to z, and z is the number of preset crops in the target area; S220, obtaining a list set of vegetation index changes of preset crops in the observation period E = {E 1 , E 2 ,…,E g ,…,E z }, E g Yes D g List of vegetation index changes during the observation period; S230, obtaining a list of changes in vegetation indices for non-agricultural crops E 0 ; S240, based on the vegetation index change curve list set E and the non-crop vegetation index change list E 0 , determine the preset time period.

4. The method for obtaining cultivated land planting intensity based on images according to claim 3, It is characterized in that It also includes obtaining the vegetation index change threshold Q through the following steps x : S410, obtain D g In the preset time period J of the second preset time slice x Second vegetation index change list within SE xg ={SE xg1 , S.E. xg2 ,…,SE xgj ,…,SE xgn }, thereby obtaining the second vegetation index change list set SE x ={SE x1 , S.E. x2 ,…,SE xg ,…,SE xz }, SE xgj Yes D g In the preset time period J of the second preset time slice x A second vegetation index at the j-th preset time node within the range, wherein the second preset time slice is different from the first preset time slice, and the first preset time slice and the second preset time slice are equal in length; S420, based on SE xg1 , SE xg2 ,…,SE xgj , …, SE xgn Do linear fitting to obtain the second linear function G xg and the second linear function G xg The corresponding second slope KG xg ; S430, Get E 0 In the preset time period J of the second preset time slice x The third vegetation index change list within SE x0 ={SE x01 , S.E. x02 ,…,SE x0j ,…,SE x0n }, SE x0j YesE 0 In the preset time period J of the second preset time slice x The third vegetation index at the j-th preset time node; S440, based on SE x01 , SE x02 ,…,SE x0j ,…,SE x0n Do linear fitting to obtain the third linear function G x0 and the third linear function G x0 The corresponding third slope KG x0 ; S450, based on the second slope list KG x ={KG x1 , KG x2 , …, KG xg , …, KG xz } and the third slope KG x0 , determine the vegetation index change threshold Q x .

5. The method for obtaining cultivated land planting intensity based on images according to claim 1, It is characterized in that P r =L r / SC r , among which, SC r It is C r area.

6. The method for obtaining cultivated land planting intensity based on images according to claim 1, It is characterized in that The following steps are also included to obtain the target vegetation index B ixj : S201, get B i The optical satellite image data (N) at the jth preset time node in the xth preset time period of the first preset time slice ixj , R ixj ), N ixj is the surface reflectivity in the near-infrared band, R ixj is the surface reflectivity in the red light band; S202, obtaining target vegetation index B ixj =(N ixj -R ixj ) / (N ixj +R ixj ).

7. The method for obtaining cultivated land planting intensity based on images according to claim 3, It is characterized in that The preset crop list D of the target area = {wheat, rapeseed}, the preset time period list J = {J 1 }, J 1 From May to June, the vegetation index change threshold is Q 1 =-0.

02.

8. The method for obtaining cultivated land planting intensity based on images according to claim 7, It is characterized in that When KG i1 <-0.02, determine the target sub-area A i During the preset time period J 1 M is the cultivated land area i1 .

9. The method for obtaining cultivated land planting intensity based on images according to claim 3, It is characterized in that The preset crop list D of the target area = {rice, beans}, the preset time period list J = {J 1 }, J 1 From June to August, the vegetation index change threshold is Q 1 =0.

01.

10. The method for obtaining cultivated land planting intensity based on images according to claim 3, It is characterized in that The preset crop list D of the target area = {wheat, rapeseed, rice, beans}, and the preset time period list J = {J 1 , J 2 }, J 1 May-June, J 2 From June to August, the vegetation index change threshold is Q 1 =-0.02, Q 2 =0.01.