Method and device for monitoring the progress of straw harvesting in the field

Abstract

The application provides a kind of field site straw harvesting progress monitoring method and device, the method comprises: based on the target straw index of first target remote sensing image, first target vegetation index and first target texture feature, obtain the first region of target area in first time target region straw, target straw index includes near infrared adjustment straw index NIASI And / or superimposed straw index ASI;The NIASI of first target remote sensing image is determined based on the reflectivity of first target remote sensing image B6 band, B7 band and B8 band;The ASI of first target remote sensing image is determined based on the reflectivity of first target remote sensing image B5 band, B6 band, B7 band, B8 band, B8A band and B9 band.The application can improve the accuracy of large-scale field site straw monitoring, can improve the monitoring efficiency of field site straw monitoring, can provide data support for straw burning supervision while improving the efficiency of straw supervision.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a method and device for monitoring the harvesting progress of standing straw in a field. BACKGROUND

[0002] Straw is the general term for the stem and leaf (ear) parts of mature crops, usually referring to the remaining parts of wheat, rice, corn, potatoes, rapeseed, cotton, sugarcane and other crops (usually coarse grains) after the seeds are harvested. Since straw can be burned, monitoring the harvesting progress of standing straw in a field is of great significance for the prevention and control of straw burning.

[0003] With the rapid development of remote sensing technology, remote sensing images are widely used in the fields of environmental protection, land resource investigation, disaster monitoring, etc. due to their high imaging clarity, objective and rich information, timeliness and strong practicability. In the prior art, remote sensing technology can be used to monitor the standing straw in a field. However, in the case of a large crop planting area, the accuracy and efficiency of large-scale monitoring of standing straw in a field based on the above prior art are not high. Therefore, how to improve the accuracy and efficiency of large-scale monitoring of standing straw in a field is a technical problem to be solved in the field. SUMMARY

[0004] The present application provides a method and device for monitoring the harvesting progress of standing straw in a field, which solves the problem of low accuracy and efficiency of large-scale monitoring of standing straw in a field in the prior art, and improves the accuracy and efficiency of large-scale monitoring of standing straw in a field.

[0005] The present application provides a method for monitoring the harvesting progress of standing straw in a field, comprising:

[0006] obtaining a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target area at a first time, the first time being within a first period, the first period being from the harvesting of seeds of crops planted in the target area to the next sowing in the target area; obtaining a first target vegetation index, a first target texture feature and a target straw index of the first target remote sensing image;

[0007] based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, obtaining a first area in which the standing straw in the target area at the first time is located;

[0008] The number of the first time is multiple; the target straw index includes a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on reflectivity of B6, B7 and B8 bands of the first target remote sensing image; and the ASI of the first target remote sensing image is determined based on reflectivity of B5, B6, B7, B8, B8A and B9 bands of the first target remote sensing image.

[0009] According to the method for monitoring the field site straw harvesting progress provided by the application, before the first region where the field site straw in the target region is located at the first time is acquired based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the method further comprises the following steps of:

[0010] acquiring a second target remote sensing image, the second target remote sensing image being a remote sensing image of the target region at a second time, the second time being in a second period, the second period being from sowing of the crop to harvesting of the seeds of the crop;

[0011] acquiring a second target vegetation index and a second texture feature of the second target remote sensing image;

[0012] acquiring a second region where the crop in the target region is located at the second time based on the second target vegetation index and the second target texture feature of the second target remote sensing image;

[0013] Correspondingly, the first region where the field site straw in the target region is located at the first time is acquired based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, and the method comprises the following steps of:

[0014] determining the first region in the second region based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image.

[0015] According to the method for monitoring the field site straw harvesting progress provided by the application, the number of the first time is multiple, and after the first region where the field site straw in the target region is located at the first time is acquired based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the method further comprises the following steps of:

[0016] obtaining field site straw harvesting progress monitoring data sets based on the first region corresponding to the adjacent first time.

[0017] According to the method for monitoring the field site straw harvesting progress provided by the application, after the first region is determined in the second region, the method further comprises the following steps of:

[0018] respectively, to obtain the standing straw harvest progress at the first time and the standing straw harvest progress at the second time;

[0019] Based on the standing straw harvest progress at the first time and the standing straw harvest progress at the second time, a field crop and standing straw harvest progress monitoring data set is obtained.

[0020] According to the present application, a kind of field standing straw harvest progress monitoring method is provided, and the NIASI is obtained based on the following formula:

[0021]

[0022] Wherein, B8, B7 and B6 respectively indicate the reflectivity of B8 band, B7 band and B6 band of the first target remote sensing image.

[0023] According to the present application, a kind of field standing straw harvest progress monitoring method is provided, and the ASI is obtained based on the following formula:

[0024] ASI=B5+B6+B7+B8+B8A+B9;

[0025] Wherein, B5, B6, B7, B8, B8A and B9 respectively indicate the reflectivity of B5 band, B6 band, B7 band, B8 band, B8A band and B9 band of the first target remote sensing image.

[0026] According to the present application, a kind of field standing straw harvest progress monitoring method is provided, and the target straw index further includes: short-wave infrared normalized straw index INDSI;The INDSI is obtained based on the following formula:

[0027]

[0028] Wherein, B9 is the reflectivity of B9 band of Sentinel 2, and B12 is the reflectivity of B12 band of Sentinel 2.

[0029] The present application also provides a kind of field standing straw harvest progress monitoring device, comprising:

[0030] Image acquisition module is used to obtain the first target remote sensing image, and the first target remote sensing image is the remote sensing image of target area at the first time, the first time is in the first period, the first period is from the harvest of seed of crop planted in the target area, to the next sowing of the target area stops;

[0031] Feature extraction module is used to obtain the first target vegetation index, the first target texture feature and the target straw index of the first target remote sensing image.

[0032] a straw harvesting progress monitoring module configured to acquire a first region in which standing straw is located in the target region at the first time based on a target straw index, a first target vegetation index and a first target texture feature of the first target remote sensing image;

[0033] The number of the first time is multiple; the target straw index comprises a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on reflectivity of a B6 band, a B7 band and a B8 band of the first target remote sensing image; and the ASI of the first target remote sensing image is determined based on reflectivity of a B5 band, a B6 band, a B7 band, a B8 band, a B8A band and a B9 band of the first target remote sensing image.

[0034] The application further provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method for monitoring the straw harvesting progress in a field according to any one of the above.

[0035] The application further provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the method for monitoring the straw harvesting progress in a field according to any one of the above.

[0036] The method and device for monitoring the straw harvesting progress in a field provided by the application can improve the accuracy of large-scale field straw monitoring, improve the monitoring efficiency of field straw monitoring, provide data support for straw burning supervision while improving the efficiency of straw supervision, determine the region with low straw harvesting progress for strengthened supervision, and prevent straw burning. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0038] Figure 1 is one of the flowcharts of the method for monitoring the straw harvesting progress in a field provided by the application;

[0039] Figure 2 is a spectral curve of a main ground object in a farmland in a sample remote sensing image;

[0040] Figure 3 A NIASI contrast chart of main farmland features in a sample remote sensing image;

[0041] Figure 4 An ASI contrast chart of main farmland features in a sample remote sensing image

[0042] Figure 5 It is the second flowchart of the monitoring method for the field site straw harvesting progress provided by the application;

[0043] Figure 6 A INDSI contrast chart of main farmland features in a sample remote sensing image;

[0044] Figure 7 It is the structural schematic diagram of the field site straw monitoring device provided by the application;

[0045] Figure 8 It is the structural schematic diagram of the electronic device provided by the application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme in the present application will be described clearly and completely below in combination with the drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0047] In the description of the application, it should be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connection" and "connection" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0048] It should be noted that corn is an important crop, which has the advantages of wide planting range, high yield, etc. The field site straw after corn harvesting can be recycled as fertilizer, or can be crushed and returned to the field to increase soil fertility. Therefore, the monitoring of corn planting range and the monitoring of field site straw harvesting progress in autumn and winter can help the agricultural department to grasp the dynamic changes of corn planting in time, and is also the basis for the environmental protection department to prevent and control straw burning.

[0049] With the gradual popularization of agricultural remote sensing technology, the use of remote sensing technology to monitor the field site straw harvesting progress can save a lot of manpower and time cost, thereby improving the monitoring efficiency of the field site straw.

[0050] Generally, the planting area of corn appears in patches, and in the case of large corn planting area, large-scale corn planting monitoring and field site straw harvesting progress monitoring often have the problem of low monitoring accuracy.

[0051] To this end, the present application provides a field site straw harvesting progress monitoring method and device. The field site straw harvesting progress monitoring method provided by the present application can improve the field site straw monitoring accuracy and efficiency by obtaining remote sensing images of farmland based on remote sensing satellites, obtaining at least one new straw index based on the remote sensing images, and combining the spectral characteristics and texture characteristics of the field site straw to obtain the planting area of the field crop and the distribution area of the field site straw. It can provide data support for straw burning supervision while improving the efficiency of straw supervision, determine the area with slow straw harvesting progress for strengthened supervision, and prevent straw burning.

[0052] Figure 1 is one of the flowcharts of the field site straw harvesting progress monitoring method provided by the present application. The field site straw harvesting progress monitoring method provided by the present application will be described below with reference to Figure 1 The field site straw harvesting progress monitoring method provided by the present application will be described below with reference to Figure 1 As shown in the figure, the method comprises the following steps: step 101, obtaining a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target area at a first time, the first time being within a first period, the first period being from the harvesting of seeds of crops planted in the target area to the next planting in the target area; the number of first times is multiple.

[0053] It should be noted that the execution subject of the embodiment of the present application is a field site straw harvesting progress monitoring device.

[0054] It should be noted that the field site straw in the embodiment of the present application is the remaining part of mature crops after harvesting seeds, and the above-mentioned crops can include but are not limited to wheat, rice, corn, potatoes, rapeseed, cotton and sugarcane, etc. The specific type of field site straw in the embodiment of the present application is not limited. The field site straw harvesting progress monitoring method provided by the present application will be described below with the field site straw being the remaining part of mature corn after harvesting seeds as an example.

[0055] In the embodiment of the present application, the GEE (Google Earth Engine) platform can be used to obtain a remote sensing image of a target region at a first time as a first target remote sensing image. The remote sensing image is taken by a remote sensing satellite. The target region is a monitoring object of the method for monitoring the harvesting progress of field standing straw provided by the present application. The harvesting progress of field standing straw in the target region can be monitored based on the method for monitoring the harvesting progress of field standing straw provided by the present application.

[0056] Optionally, the GEE platform is a remote sensing cloud computing platform. The GEE platform integrates massive geographic spatial data, image data, climate and weather data, and geophysical data, has corresponding visualization and analysis calculation capabilities, and an application program interface (API) that can be used to exchange information and commands with a computer operating system. The image data includes Landsat series, Sentinel series, MODIS, and high-resolution image data of local regions. The weather and climate data includes surface temperature and emissivity, long-term climate prediction and historical difference of ground variables, satellite observation inversion of atmospheric data, and short-time prediction and observation of weather data. The geophysical data includes topographic data, land cover data, farmland distribution data, and night light data.

[0057] It should be noted that in the embodiment of the present application, the period from the harvesting of seeds of corn planted in the target region to the next sowing in the target region can be determined as the first period, for example, the first period can be from October of the current year to March of the next year.

[0058] In the embodiment of the present application, any time in the first period can be determined as the first time. According to actual conditions and / or prior knowledge, a specific time in the first period can also be determined as the first time. The first period and the first time are not specifically limited in the embodiment of the present application.

[0059] It should be noted that the number of the first time is multiple. The multiple first times in the first period can be used to monitor the harvesting progress.

[0060] Optionally, the remote sensing satellite can be a Sentinel-2 remote sensing satellite. Correspondingly, the first target remote sensing image is a Sentinel-2 remote sensing image.

[0061] The Sentinel-2 remote sensing image has 13 bands, which are B1 band (center wavelength 443 nm), B2 band (center wavelength 490 nm), B3 band (center wavelength 560 nm), B4 band (center wavelength 665 nm), B5 band (center wavelength 705 nm), B6 band (center wavelength 740 nm), B7 band (center wavelength 783 nm), B8 band (center wavelength 842 nm), B8A band (center wavelength 865 nm), B9 band (center wavelength 940 nm), B10 band (center wavelength 1375 nm), B11 band (center wavelength 1610 nm), and B12 band (center wavelength 2190 nm).

[0062] It should be noted that the Sentinel-2 remote sensing image is a Sentinel-2 Level-2A remote sensing image, which has been orthorectified and sub-pixel geometrically corrected, and contains atmospheric bottom reflectance data after atmospheric correction, so no additional preprocessing is required.

[0063] Step 102, obtaining a first target vegetation index, a first target texture feature, and a target straw index of the first target remote sensing image.

[0064] The target straw index includes a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on the reflectance of the B6 band, the B7 band, and the B8 band of the first target remote sensing image; and the ASI of the first target remote sensing image is determined based on the reflectance of the B5 band, the B6 band, the B7 band, the B8 band, the B8A band, and the B9 band of the first target remote sensing image.

[0065] Specifically, since the field standing straw has a unique texture feature relative to bare land, field road, etc., and the vegetation index can be used to distinguish corn and field standing straw, the vegetation index and the texture feature of the first target remote sensing image are helpful for monitoring the target area field standing straw. After obtaining the first target remote sensing image, the first target vegetation index and the first target texture feature of the first target remote sensing image can be obtained by numerical calculation.

[0066] Optionally, in the embodiment of the present application, the mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation of the first target remote sensing image can be obtained by a gray level co-occurrence matrix (GLCM) as the original texture features of the first target remote sensing image. The GLCM takes 7*7 as the texture calculation window and is calculated based on the near-infrared band of the first target remote sensing image.

[0067] In order to avoid the feature redundancy affecting the classification efficiency, after the original texture features of the first target remote sensing image are obtained, the importance of the original texture features can be evaluated, and the mean, variance and contrast with the highest importance score are taken as the first target texture features of the first target remote sensing image.

[0068] In the embodiment of the present application, the normalized difference vegetation index (NDVI) and the enhanced vegetation index (EVI) of the first target remote sensing image can also be obtained by numerical calculation as the first target vegetation index of the first target remote sensing image.

[0069] The normalized difference vegetation index NDVI can be calculated based on the following formula:

[0070]

[0071] The enhanced vegetation index EVI can be calculated based on the following formula:

[0072]

[0073] wherein, ρ r represents the reflectivity of the red band of the remote sensing image; ρ b represents the reflectivity of the blue band of the remote sensing image; and ρ nir represents the reflectivity of the near-infrared band of the remote sensing image.

[0074] Figure 2The spectral curve of the main ground objects of the farmland in the sample remote sensing image is obtained. In the embodiment of the present application, 500 sample points are selected, including 90 sample points of corn stalks, 63 sample points of bare land, 166 sample points of sparse wheat, 62 sample points of dense wheat, and 119 sample points of stubble. The remote sensing image of each sample point is obtained as a sample remote sensing image. The spectral curves of corn stalks, stubble, bare land, dense wheat and sparse wheat in the above sample remote sensing image are as shown in Figure 2 .

[0075] It should be noted that based on Figure 2 spectral analysis, it can be found that the rising trend of corn stalks and stubble in the sample remote sensing image in the B7 and B8 bands is obviously higher than that of other ground objects, and the spectral value of corn stalks and stubble in the sample remote sensing image is the lowest among all ground objects. The above characteristics can be amplified through the B6 band, so as to construct the near-infrared adjusted straw index NIASI.

[0076] After obtaining the first target remote sensing image, the near-infrared adjusted straw index NIASI of the first target remote sensing image can also be obtained based on the reflectivity of the B6, B7 and B8 bands of the first target remote sensing image through numerical calculation.

[0077] Based on the content of the above embodiments, NIASI is obtained based on the following formula:

[0078]

[0079] Wherein, B8, B7 and B6 respectively represent the reflectivity of the B8, B7 and B6 bands of the first target remote sensing image.

[0080] It should be noted that the near-infrared adjusted straw index NIASI of the first target remote sensing image includes the near-infrared adjusted straw index NIASI of each pixel point in the first target remote sensing image.

[0081] Figure 3 The NIASI comparison chart of the main ground objects of the farmland in the sample remote sensing image. Based on the reflectivity of the B8, B7 and B6 bands of the sample remote sensing image, the near-infrared adjusted straw index NIASI of the bare land, dense wheat, sparse wheat, stubble and corn stalks in the sample remote sensing image can be calculated according to formula (3), and the average value of the near-infrared adjusted straw index NIASI of each ground object is plotted, so as to obtain Figure 3 .

[0082] As shown in Figure 3 , the near-infrared adjusted straw index NIASI of the corn stalks in the sample remote sensing image is the largest, and has good distinction from other ground objects.

[0083] It should be noted that, based on Figure 2 It can be found by performing spectral analysis that the spectral values of corn stalks in the sample remote sensing image in the B5 band, the B6 band, the B7 band, the B8 band, the B8A band and the B9 band are the lowest compared with other ground objects, and combined with the spectral values of the superimposed band, the low spectral reflectivity of the stalks is amplified, so that the superimposed stalk index ASI can be constructed.

[0084] After obtaining the first target remote sensing image, the superimposed stalk index ASI of the first target remote sensing image can be obtained by numerical calculation based on the reflectivity of the B5 band, the B6 band, the B7 band, the B8 band, the B8A band and the B9 band of the first target remote sensing image.

[0085] Based on the content of each of the above embodiments, the ASI is obtained based on the following formula:

[0086] ASI=B5+B6+B7+B8+B8A+B9 (4)

[0087] Wherein, B5, B6, B7, B8, B8A and B9 respectively represent the reflectivity of the B5 band, the B6 band, the B7 band, the B8 band, the B8A band and the B9 band of the first target remote sensing image.

[0088] It should be noted that the superimposed stalk index ASI of the first target remote sensing image includes the superimposed stalk index ASI of each pixel point in the first target remote sensing image.

[0089] Figure 4 The ASI comparison chart of the main ground objects in the sample remote sensing image. Based on the reflectivity of the B5 band, the B6 band, the B7 band, the B8 band, the B8A band and the B9 band of the sample remote sensing image, the superimposed stalk index ASI of bare land, dense wheat, sparse wheat, stubble stalk and corn stalk in the sample remote sensing image can be calculated according to formula (4), and the average value of the superimposed stalk index ASI of each ground object is taken to draw a graph, so that Figure 4 .

[0090] As Figure 4 shown, the superimposed stalk index ASI of the corn stalks in the sample remote sensing image is the smallest, and has good distinction from other ground objects.

[0091] Step 103, based on the target stalk index, the first target vegetation index and the first target texture feature of the first target remote sensing image, obtaining the first region where the standing stalks in the target region at the first time are located.

[0092] Specifically, after obtaining the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image can be input into the trained field site straw monitoring model, and then the first region where the site straw in the target region at the first time is obtained, and then the site straw harvesting progress at different first times can be monitored.

[0093] Optionally, the field site straw monitoring model can be constructed based on a random forest algorithm, and can be trained based on the target straw index, the first target vegetation index and the first target texture feature of the first sample remote sensing image as a sample, and the region where the site straw in the sample region at the first sample time as a sample label.

[0094] The first sample remote sensing image is a remote sensing image of the sample region at the first sample time, the first sample time is within the first sample period, and the first sample period is from the harvesting of seeds of the crops planted in the sample region to the next sowing of the sample region.

[0095] The region where the site straw in the sample region at the first sample time can be obtained based on ground investigation, mobile phone recording and reporting, etc.

[0096] The embodiment of the present application can improve the accuracy of large-scale field site straw monitoring, improve the monitoring efficiency of field site straw harvesting progress, provide data support for straw burning supervision and improve the efficiency of straw supervision, determine the area with low straw harvesting progress for strengthened supervision, and prevent straw burning.

[0097] Based on the content of each embodiment, based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the first region where the site straw in the target region at the first time is obtained, and the method further comprises: obtaining a second target remote sensing image, the second target remote sensing image is a remote sensing image of the target region at the second time, and the second time is within the second period, and the second period is from the sowing of the crops to the harvesting of the seeds of the crops.

[0098] Figure 5 is a flowchart of the monitoring method of the field site straw harvesting progress provided by the present application. As shown in Figure 5 Sentinel-2 remote sensing image can be obtained as the original remote sensing image.

[0099] After the above original remote sensing image is cropped, inlaid and classified, the first target remote sensing image and the second target remote sensing image can be obtained respectively.

[0100] It should be noted that the period from sowing corn in the target area to harvesting corn seeds in the embodiment of the application can be determined as the second period, for example, the first period can be from April to September of the same year.

[0101] In the embodiment of the application, any time in the second period can be determined as the second time; and according to actual conditions and / or prior knowledge, a specific time in the second period can be determined as the second time. The second period and the second time are not specifically limited in the embodiment of the application.

[0102] It should be noted that the number of the second time can be one or more.

[0103] In the embodiment of the application, the remote sensing satellite can be used to obtain the remote sensing image of the target area at the second time as the second target remote sensing image.

[0104] Optionally, the above-mentioned remote sensing satellite can be a Sentinel-2 remote sensing satellite. Correspondingly, the second target remote sensing image is a Sentinel-2 remote sensing image.

[0105] The second target vegetation index and the second texture feature of the second target remote sensing image are obtained.

[0106] Specifically, since corn has certain differences in texture distribution compared with grassland, woodland, bare land and other ground objects, the texture feature can increase its resolution and thus improve the classification accuracy, and the vegetation index can be used to distinguish corn and field standing straw, so the vegetation index and the texture feature of the second target remote sensing image are helpful for monitoring corn in the target area. After the second target remote sensing image is obtained, the second target vegetation index and the second target texture feature of the second target remote sensing image can be obtained by numerical calculation.

[0107] Optionally, in the embodiment of the application, the mean value, variance, synergy, contrast, dissimilarity, information entropy, second moment and correlation of the second target remote sensing image can be obtained by a gray level co-occurrence matrix as the original texture feature of the second target remote sensing image. The gray level co-occurrence matrix takes 7*7 as the texture calculation window and is calculated based on the near-infrared band of the first target remote sensing image.

[0108] In order to avoid the influence of feature redundancy on classification efficiency, after the original texture feature of the second target remote sensing image is obtained, the importance of the above-mentioned original texture feature can be evaluated, and the mean value, variance and contrast with the highest importance score are taken as the second target texture feature of the second target remote sensing image.

[0109] In the embodiments of the present application, the normalized vegetation index, the difference vegetation index (DVI), the radar vegetation index (RVI), the green chlorophyll index (CIgreen), the NAVI, the structure insensitive pigment index (SIPI) and the normalized water index (NDWI) of the first target remote sensing image can be obtained by numerical calculation, and used as the second target vegetation index of the second target remote sensing image.

[0110] The difference vegetation index DVI can be calculated based on the following formula:

[0111] DVI = p nir -p r (5)

[0112] The radar vegetation index RVI can be calculated based on the following formula:

[0113]

[0114] The green chlorophyll index CIgreen can be calculated based on the following formula:

[0115]

[0116] The NAVI can be calculated based on the following formula:

[0117]

[0118] The structure insensitive pigment index SIPI can be calculated based on the following formula:

[0119]

[0120] The normalized water index NDWI can be calculated based on the following formula:

[0121]

[0122] wherein p r represents the red band reflectivity of the remote sensing image; p b represents the blue band reflectivity of the remote sensing image; p g represents the green band reflectivity of the remote sensing image; p nir represents the near-infrared band reflectivity of the remote sensing image.

[0123] Based on the second target vegetation index and the second target texture feature of the second target remote sensing image, a second region in which crops are located in the target region at the second time is acquired.

[0124] Specifically, after the second target vegetation index and the second target texture feature of the second target remote sensing image are acquired, the second target vegetation index and the second target texture feature of the second target remote sensing image can be input into the trained crop monitoring model, and then the second region in which corn is located in the target region at the second time output by the crop monitoring model can be acquired.

[0125] Optionally, the crop monitoring model can be constructed based on a maximum likelihood method, and can be trained by taking the target straw index, the second target vegetation index and the second target texture feature of the second sample remote sensing image as samples, and taking the region in which corn is located in the sample region at the second sample time as a sample label.

[0126] The second sample remote sensing image is a remote sensing image of a sample region at a second sample time, the second sample time is within a second sample period, and the second sample period is from sowing of corn planted in the sample region to harvesting of seeds of the corn.

[0127] The region in which corn is located in the sample region at the second sample time can be acquired based on ground investigation, mobile phone recording and reporting and the like.

[0128] Correspondingly, based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, a region in which standing straw is located in the target region at the first time is acquired, including: based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, determining the first region in the second region.

[0129] Specifically, as shown in Figure 5 After the second region in which crops are located in the target region at the second time is acquired, the first region in which standing straw is located in the target region at the first time can be determined in the second region based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, so that the calculation amount in the process of monitoring standing straw in the field can be reduced, and the monitoring efficiency can be improved.

[0130] After the first region and the second region are acquired, mapping can be performed based on the first region and the second region, and the obtained image can be output as a result of crop monitoring and a result of monitoring of harvesting progress of standing straw in the field.

[0131] The embodiment of the present application can improve the accuracy of large-scale crop monitoring, improve the monitoring efficiency of crop monitoring, provide data support for crop planting management, reduce the calculation amount in the process of monitoring the harvesting progress of the field stand straw, and improve the monitoring efficiency.

[0132] Based on the content of each of the above embodiments, after obtaining the first region in which the stand straw in the target region at the first time is located based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the method further comprises: obtaining a field stand straw harvesting progress monitoring data set based on the adjacent first region corresponding to the first time.

[0133] Specifically, in the embodiment of the present application, a plurality of first times can be determined in a first period, and each first region corresponding to each first time can be obtained based on the content of each of the above embodiments.

[0134] It should be noted that any two first times are different times.

[0135] After obtaining the first region corresponding to each first time, a field stand straw harvesting progress monitoring data set can be obtained based on the first region corresponding to each first time, which is used to reflect the change of the region in which the straw in the target region is located in the first period, and to determine the key region for strengthening supervision.

[0136] The embodiment of the present application can monitor the harvesting progress of the field stand straw by combining multiple features and multiple time sequences, and form a field stand straw harvesting progress monitoring data set based on the monitoring result, so as to more intuitively understand the distribution and change trend of the field stand straw in different periods, and provide data support for the harvesting of the field stand straw and the monitoring of straw burning.

[0137] Based on the content of each of the above embodiments, after determining the first region in the second region, the method further comprises: respectively estimating the crop planting area of the second region and the first region to obtain the harvesting progress of the stand straw at the first time and the harvesting progress of the stand straw at the second time.

[0138] Based on the harvesting progress of the stand straw at the first time and the harvesting progress of the stand straw at the second time, a field crop and stand straw harvesting progress monitoring data set is obtained.

[0139] Specifically, the straw harvesting ratio of the second area can be obtained based on the content in each of the above embodiments.

[0140] After the second area corresponding to the second time and the first area corresponding to the first time are obtained, the crop planting area of the second area and the first area can be estimated respectively to obtain the straw harvesting progress of the field at the first time and the straw harvesting progress of the field at the second time, and then based on the straw harvesting progress of the field at the first time and the straw harvesting progress of the field at the second time, the field crop and field straw harvesting progress monitoring data set is obtained, which reflects the straw harvesting situation in the target area in the second period and the first period.

[0141] Optionally, after the second area corresponding to the second time is obtained, a field crop monitoring data set can also be generated to reflect the change of the area where the crops are located in the target area in the second period.

[0142] The embodiment of the present application can monitor the field straw harvesting progress by combining multiple features and multiple time sequences, and form a field crop and field straw harvesting progress monitoring data set based on the monitoring results, which can more intuitively understand the distribution and change trend of the field crops and the field straw in different periods, and can provide data support for field crop harvesting, field straw harvesting and straw burning monitoring.

[0143] Based on the content of each of the above embodiments, the target straw index further includes: an infrared normalized straw index INDSI.

[0144] INDSI is determined based on the reflectivity of the B12 band and the B9 band of the first target remote sensing image.

[0145] It should be noted that, based on the above Figure 2 Spectral analysis shows that the reflectivity of corn straw in the sample remote sensing image in the short-wave infrared B9 band and the short-wave infrared B12 band is not much different, the spectral value of bare land in the sample remote sensing image in the B12 band is higher than that in the B9 band, and the spectral value of the remaining ground objects in the sample remote sensing image in the B12 band is less than that in the B9 band. Based on the above characteristics, an infrared normalized straw index (Infrared normalized difference straw index, INDSI) can be constructed.

[0146] The infrared normalized straw index INDSI of the first target remote sensing image can be obtained based on the following formula:

[0147]

[0148] Wherein, B12 and B9 represent the reflectivity of the B12 band and the B9 band of the first target remote sensing image respectively.

[0149] It should be noted that the short-wave infrared normalized straw index INDSI of the first target remote sensing image includes the short-wave infrared normalized straw index INDSI of each pixel point in the first target remote sensing image.

[0150] Figure 6 The sample remote sensing image is a sample remote sensing image, and the short-wave infrared normalized straw index INDSI of the main ground objects in the sample remote sensing image is shown in a contrast chart. The short-wave infrared normalized straw index INDSI of bare land, dense wheat, sparse wheat, stubble and corn straw in the sample remote sensing image can be calculated according to formula (1) based on the reflectivity of the B9 band and the B12 band of the sample remote sensing image.

[0151] As shown in Figure 6 , the short-wave infrared normalized straw index INDSI of the dense wheat, sparse wheat and stubble in the sample remote sensing image is negative, the short-wave infrared normalized straw index INDSI of the bare land and corn straw in the sample remote sensing image is positive, and the short-wave infrared normalized straw index INDSI of the corn straw in the sample remote sensing image is lower than that of the bare land, so the short-wave infrared normalized straw index INDSI has a good distinguishing effect on corn straw and other ground objects.

[0152] The target straw index in the embodiment of the application further includes a short-wave infrared normalized straw index INDSI, which can further improve the accuracy of monitoring the standing straw in the field.

[0153] Figure 7 is a structural schematic diagram of the monitoring device for the harvesting progress of the standing straw in the field provided by the application. The monitoring device for the harvesting progress of the standing straw in the field provided by the application will be described below in combination with Figure 7 The monitoring device for the harvesting progress of the standing straw in the field provided by the application will be described below, and the monitoring device for the harvesting progress of the standing straw in the field described below can be correspondingly referred to the monitoring method for the harvesting progress of the standing straw in the field provided by the application described above. As shown in Figure 7 , the device comprises an image acquisition module 701, a feature extraction module 702 and a straw harvesting progress monitoring module 703.

[0154] The image acquisition module 701 is configured to acquire a first target remote sensing image, wherein the first target remote sensing image is a remote sensing image of a target region at a first time, and the first time is within a first period, and the first period is from the harvesting of seeds of crops planted in the target region to the next sowing in the target region.

[0155] The feature extraction module 702 is configured to acquire a first target vegetation index, a first target texture feature and a target straw index of the first target remote sensing image.

[0156] The straw harvesting progress monitoring module 703 is configured to acquire a first region in which standing straw in the target region at the first time point is located based on the target straw index, the first target vegetation index, and the first target texture feature of the first target remote sensing image.

[0157] The first time point is a plurality of time points; the target straw index includes a near-infrared adjusted straw index NIASI and / or a stacked straw index ASI; the NIASI of the first target remote sensing image is determined based on reflectivity of a B6 band, a B7 band, and a B8 band of the first target remote sensing image; and the ASI of the first target remote sensing image is determined based on reflectivity of a B5 band, the B6 band, the B7 band, the B8 band, a B8A band, and a B9 band of the first target remote sensing image.

[0158] Specifically, the image acquisition module 701, the feature extraction module 702, and the straw monitoring module 703 are electrically connected.

[0159] The image acquisition module 701 can be configured to acquire, by a remote sensing satellite, a remote sensing image of a target region at a first time point as a first target remote sensing image.

[0160] The feature extraction module 702 can be configured to acquire, by a numerical calculation, a first target vegetation index and a first target texture feature of the first target remote sensing image.

[0161] The feature extraction module 702 can also be configured to acquire, by a numerical calculation, a near-infrared adjusted straw index NIASI of the first target remote sensing image based on reflectivity of a B6 band, a B7 band, and a B8 band of the first target remote sensing image.

[0162] The feature extraction module 702 can also be configured to acquire, by a numerical calculation, a stacked straw index ASI of the first target remote sensing image based on reflectivity of a B5 band, the B6 band, the B7 band, the B8 band, a B8A band, and a B9 band of the first target remote sensing image.

[0163] The straw harvesting progress monitoring module 703 can be configured to input the target straw index, the first target vegetation index, and the first target texture feature of the first target remote sensing image into a trained field standing straw monitoring model, and thus can acquire a first region in which standing straw in the target region at the first time point is located, which is output by the field standing straw monitoring model.

[0164] Optionally, the field standing straw harvesting progress monitoring device can further include a crop monitoring module.

[0165] The crop monitoring module can be configured to acquire a second target remote sensing image, the second target remote sensing image being a remote sensing image of the target region at a second time, the second time being within a second period, the second period being from crop planting to crop harvesting of seeds and fruits; acquire a second target vegetation index and a second texture feature of the second target remote sensing image; and acquire a second region in which the crops in the target region at the second time are located based on the second target vegetation index and the second texture feature of the second target remote sensing image.

[0166] Correspondingly, the straw harvesting progress monitoring module 703 can also be configured to determine the first region in the second region based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image.

[0167] Optionally, the field site straw harvesting progress monitoring device can further include a straw harvesting progress dataset generation module.

[0168] The straw harvesting progress dataset generation module can be configured to obtain the field site straw harvesting progress monitoring dataset based on the first region corresponding to the adjacent first time.

[0169] The straw harvesting progress dataset generation module can also be configured to respectively estimate the crop planting area of the second region and the first region, acquire the site straw harvesting progress at each first time and the site straw harvesting progress at the second time, and obtain the field crop and site straw harvesting progress monitoring dataset based on the site straw harvesting progress at the first time and the site straw harvesting progress at the second time.

[0170] The field site straw harvesting progress monitoring device in the embodiment of the present application can improve the accuracy of large-scale field site straw monitoring, improve the monitoring efficiency of field site straw monitoring, provide data support for straw burning supervision while improving the efficiency of straw supervision, determine the area with low straw harvesting progress for strengthened supervision, and prevent straw burning.

[0171] Figure 8 An example of an entity structure diagram of an electronic device is shown in FIG. Figure 8As shown, the electronic device can include a processor 810, a communications interface 820, a memory 830, and a communications bus 840, wherein the processor 810, the communications interface 820, and the memory 830 complete mutual communication through the communications bus 840. The processor 810 can invoke the logical instructions in the memory 830 to execute the field site straw harvesting progress monitoring method, which includes: acquiring a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target region at a first time, the first time being within a first period and the first time including multiple time points, the first period being from the harvesting of seeds of crops planted in the target region to the next sowing in the target region; acquiring a first target vegetation index, a first target texture feature, and a target straw index of the first target remote sensing image; based on the target straw index, the first target vegetation index, and the first target texture feature of the first target remote sensing image, acquiring a first region in which a field straw in the target region at the first time is located; wherein the number of the first time is multiple; the target straw index includes a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on the reflectivity of the B6, B7, and B8 bands of the first target remote sensing image; the INDSI of the first target remote sensing image is determined based on the reflectivity of the B9 and B12 bands of the remote sensing image; and the ASI of the first target remote sensing image is determined based on the reflectivity of the B5, B6, B7, B8, B8A, and B9 bands of the first target remote sensing image.

[0172] In addition, the logical instructions in the memory 830 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0173] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program being stored in a non-transitory computer-readable storage medium, and the computer program being executable by a processor to enable a computer to perform the method for monitoring the field site straw harvesting progress as described above, the method comprising: obtaining a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target region at a first time, the first time being within a first period, and the first time comprising a plurality of time points, the first period being from when a crop planted in the target region is harvested for seeds to when the target region is next sowed; obtaining a first target vegetation index, a first target texture feature, and a target straw index of the first target remote sensing image; and obtaining a first region in which a field site straw is located in the target region at the first time based on the target straw index, the first target vegetation index, and the first target texture feature of the first target remote sensing image; wherein the number of the first time is a plurality; the target straw index comprises a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on reflectivity of a B6 band, a B7 band, and a B8 band of the first target remote sensing image; the INDSI of the first target remote sensing image is determined based on reflectivity of a B9 band and a B12 band of the remote sensing image; and the ASI of the first target remote sensing image is determined based on reflectivity of a B5 band, a B6 band, a B7 band, a B8 band, a B8A band, and a B9 band of the first target remote sensing image.

[0174] In yet another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method for monitoring the field site straw harvesting progress as described above, the method comprising: obtaining a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target region at a first time, the first time being within a first period, and the first time comprising a plurality of time points, the first period being from when a crop planted in the target region is harvested for seeds to when the target region is next sowed; obtaining a first target vegetation index, a first target texture feature, and a target straw index of the first target remote sensing image; and obtaining a first region in which a field site straw is located in the target region at the first time based on the target straw index, the first target vegetation index, and the first target texture feature of the first target remote sensing image; wherein the number of the first time is a plurality; the target straw index comprises a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on reflectivity of a B6 band, a B7 band, and a B8 band of the first target remote sensing image; the INDSI of the first target remote sensing image is determined based on reflectivity of a B9 band and a B12 band of the remote sensing image; and the ASI of the first target remote sensing image is determined based on reflectivity of a B5 band, a B6 band, a B7 band, a B8 band, a B8A band, and a B9 band of the first target remote sensing image.

[0175] The apparatus embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0176] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary universal hardware platforms, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of software products, and the computer software products can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and include a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0177] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of monitoring the progress of a standing crop of straw in a field, characterised by, The method comprises the following steps: obtaining a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target region at a first time, the first time being within a first period, the first period being from the harvesting of seeds of crops planted in the target region to the next sowing in the target region; obtaining a first target vegetation index, a first target texture feature and a target straw index of the first target remote sensing image; based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, obtaining a first region in which standing straw in the target region at the first time is located; wherein the number of the first time is multiple; the target straw index comprises a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on the reflectivity of B6, B7 and B8 bands of the first target remote sensing image; the ASI of the first target remote sensing image is determined based on the reflectivity of B5, B6, B7, B8, B8A and B9 bands of the first target remote sensing image; before the step of obtaining the first region in which the standing straw in the target region at the first time is located based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the method further comprises the following steps: obtaining a second target remote sensing image, the second target remote sensing image being a remote sensing image of the target region at a second time, the second time being within a second period, the second period being from the sowing of the crops to the harvesting of the seeds of the crops; obtaining a second target vegetation index and a second texture feature of the second target remote sensing image; based on the second target vegetation index and the second target texture feature of the second target remote sensing image, obtaining a second region in which the crops in the target region at the second time are located; correspondingly, the step of obtaining the first region in which the standing straw in the target region at the first time is located based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image comprises the following steps: based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, determining the first region in the second region; after the step of determining the first region in the second region, the method further comprises the following steps: respectively estimating the crop planting area of the second region and the first region, and obtaining the standing straw harvesting progress at the first time and the standing straw harvesting progress at the second time; based on the standing straw harvesting progress at the first time and the standing straw harvesting progress at the second time, obtaining a field crop and standing straw harvesting progress monitoring data set.

2. The method of claim 1, wherein the method further comprises: after the step of obtaining the first region in which the standing straw in the target region at the first time is located based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image, the method further comprises the following steps: based on the first region corresponding to the adjacent first time, obtaining a field standing straw harvesting progress monitoring data set.

3. The method of claim 1, wherein the method further comprises: the NIASI is obtained based on the following formula: B8, B7 and B6 represent reflectivity of the first target remote sensing image B8 band, B7 band and B6 band respectively.

4. The method of claim 1, wherein the method further comprises: The ASI is obtained based on the following formula: ASI = B5 + B6 + B7 + B8 + B8A + B9 B5, B6, B7, B8, B8A and B9 represent reflectivity of the first target remote sensing image B5 band, B6 band, B7 band, B8 band, B8A band and B9 band respectively.

5. The method of claim 1, wherein the method further comprises: The target straw index further comprises a short-wave infrared normalized straw index INDSI, and the INDSI is obtained based on the following formula: B9 is a Sentinel-2 B9 band reflectivity, and B12 is a Sentinel-2 B12 band reflectivity.

6. A monitoring device for monitoring the progress of harvesting of standing crops in a field, which is applied to the monitoring method for monitoring the progress of harvesting of standing crops in a field according to any one of claims 1 to 5, characterized by Comprise: An image acquisition module is configured to acquire a first target remote sensing image, the first target remote sensing image being a remote sensing image of a target region at a first time, the first time being within a first period, the first period being from harvesting seeds of crops planted in the target region to the next sowing in the target region; A feature extraction module is configured to acquire a first target vegetation index, a first target texture feature and a target straw index of the first target remote sensing image; A straw harvesting progress monitoring module is configured to acquire a first area where standing straw in the target region is located at the first time based on the target straw index, the first target vegetation index and the first target texture feature of the first target remote sensing image. The number of the first time is multiple; the target straw index comprises a near-infrared adjusted straw index NIASI and / or a superimposed straw index ASI; the NIASI of the first target remote sensing image is determined based on reflectivity of B6 band, B7 band and B8 band of the first target remote sensing image; and the ASI of the first target remote sensing image is determined based on reflectivity of B5 band, B6 band, B7 band, B8 band, B8A band and B9 band of the first target remote sensing image.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the field standing straw harvesting progress monitoring method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the field standing straw harvesting progress monitoring method according to any one of claims 1 to 5.

Images