CN112861766B - Satellite remote sensing extraction method and device for farmland corn stalks - Google Patents
Satellite remote sensing extraction method and device for farmland corn stalks Download PDFInfo
- Publication number
- CN112861766B CN112861766B CN202110220236.6A CN202110220236A CN112861766B CN 112861766 B CN112861766 B CN 112861766B CN 202110220236 A CN202110220236 A CN 202110220236A CN 112861766 B CN112861766 B CN 112861766B
- Authority
- CN
- China
- Prior art keywords
- band
- remote sensing
- straw
- wavelength range
- ndssi
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 235000002017 Zea mays subsp mays Nutrition 0.000 title claims abstract description 120
- 240000008042 Zea mays Species 0.000 title claims abstract description 119
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 title claims abstract description 114
- 235000005822 corn Nutrition 0.000 title claims abstract description 114
- 238000000605 extraction Methods 0.000 title claims abstract description 51
- 239000010902 straw Substances 0.000 claims abstract description 109
- 238000002310 reflectometry Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 31
- 229930002875 chlorophyll Natural products 0.000 claims description 11
- 235000019804 chlorophyll Nutrition 0.000 claims description 11
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000003306 harvesting Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000011160 research Methods 0.000 claims description 6
- 235000016383 Zea mays subsp huehuetenangensis Nutrition 0.000 claims description 5
- 235000009973 maize Nutrition 0.000 claims description 5
- 230000017260 vegetative to reproductive phase transition of meristem Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000011835 investigation Methods 0.000 abstract description 6
- 241000209140 Triticum Species 0.000 description 20
- 235000021307 Triticum Nutrition 0.000 description 20
- 238000001228 spectrum Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 241000196324 Embryophyta Species 0.000 description 3
- 230000006837 decompression Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 241000482268 Zea mays subsp. mays Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Abstract
The invention provides a satellite remote sensing extraction method and device for farmland corn stalks, wherein the method comprises the following steps: determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image; and determining the corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI. According to the method, the farmland corn straw autumn and winter remote sensing monitoring result is determined through three novel straw indexes of normalized short wave infrared straw index, superimposed infrared straw index and superimposed near-infrared straw index, so that the extraction precision and efficiency of the farmland corn straw can be improved, manual investigation is reduced, and data support is provided for straw incineration supervision.
Description
Technical Field
The invention relates to the technical field of agricultural remote sensing, in particular to a satellite remote sensing extraction method and device for farmland corn stalks.
Background
Most of the corn stalks in the farmland are harvested during corn harvesting, but part of the corn stalks are prepared to be planted in spring corn areas and scattered households planting areas in the coming years, and after the corn harvesting season, the stalks are not harvested and are vertically or lodged in the field. The straws are easy to burn in autumn and winter or spring in the coming year, and are high-risk key areas for straw burning supervision in agriculture or environmental protection departments. The farmland straw distribution investigation is the basis of straw burning prevention and control work.
At present, the prevention and control of straw burning mainly depends on the field ground investigation of supervisory personnel, and then statistics report, and is time-consuming, laborious and low in efficiency. At present, the research on remote sensing monitoring of straw plants is less, the related research is remote sensing monitoring of straw coverage after mixing soil and straw stubbles after returning to the field, the focus is on remote sensing monitoring of the field covered with the straw stubbles after crushing and returning to the field after harvesting corn, the monitoring object is the mixture of the crushed straw stubbles and the soil, and the monitoring object of the field upright corn straw monitoring is the complete corn straw plant on the farmland, and the monitoring objects are completely different and different in form, so that the method for monitoring and extracting the field corn straw is also completely different from the straw coverage. In order to meet the requirements of high-precision quick positioning and scientific dispatching of crop corn stalks in actual work of a supervision department, according to the typical characteristics of the crop corn stalks, a novel high-efficiency stalk index suitable for satellite remote sensing images is found, and the technical problem to be solved is urgent to rapidly and efficiently extract the crop corn stalks in autumn and winter.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a farmland corn stalk satellite remote sensing extraction method and device.
The invention provides a satellite remote sensing extraction method for farmland corn stalks, which comprises the following steps: determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image;
according to the value range of any one or more of NDSSI, AIRSI and PNISI, determining the corn stalk area, if adopting various indexes, the monitoring precision can be improved by virtue of complementary advantages;
wherein AIRSI is determined according to the reflectivity weighting values of the B4, B5 and B12 wave bands; PNISI is determined according to the reflectivity of the B4 wave band and the B8 wave band; NDSSI is determined from the B9 and B12 band reflectivities.
According to the remote sensing extraction method of the farmland corn stalk satellite, which is provided by the embodiment of the invention, before determining the corn stalk region according to the value range of any one or more of NDSSI, AIRSI and PNISI, the method further comprises:
acquiring satellite remote sensing images of three time phases in a research area;
determining an artificial ground object area according to the remote sensing image of the first time phase, and determining a woodland area according to the remote sensing image of the second time phase;
removing the artificial land feature area and the woodland area from the remote sensing image in the third time phase to obtain the target remote sensing image;
the first time phase is a flowering period with the highest chlorophyll content of the corn stalks; the second time phase is a time phase with the largest chlorophyll content difference between the woodland and the corn stalks; the third time phase is the harvesting period with the lowest chlorophyll content after the corn stalks are dried.
According to one embodiment of the invention, the remote sensing extraction method for the farmland corn stalk satellite determines an artificial ground object area according to the remote sensing image of a first time phase and determines a forest area according to the remote sensing image of a second time phase, and the remote sensing extraction method comprises the following steps of: according to the remote sensing image of the first time phase, determining an artificial ground object area according to an area with normalized vegetation index NDVI smaller than 0.5 or blue light wave band reflectivity larger than 0.08; and determining the forest area according to the remote sensing image of the second time phase, wherein the NDVI is more than or equal to 0.5.
According to the farmland corn stalk satellite remote sensing extraction method, the determination method of PNISI or NDSSI correspondingly comprises the following steps:
wherein B4, B8, B9 and B12 are the reflectances of the corresponding bands, respectively.
According to the farmland corn stalk satellite remote sensing extraction method of one embodiment of the invention, the value ranges of PNISI, NDSSI and AIRSI are respectively as follows: PNISI is more than 0.05 and less than 0.065, NDSSI is more than 0.07 and less than 0.07,0.6 and AIRSI is more than 0.75.
According to one embodiment of the invention, the remote sensing extraction method of the farmland corn stalk satellite further comprises the following steps after determining the corn stalk area: and converting the grid image of the corn stalk region extraction result into a vector file.
According to an embodiment of the invention, the remote sensing extraction method of the farmland corn stalk satellite determines a corn stalk region according to the value range of any one or more of NDSSI, AIRSI and PNISI, and comprises the following steps: and determining the corn straw area according to the area which simultaneously meets the value ranges of NDSSI, AIRSI and PNISI.
The invention also provides a satellite remote sensing extraction device for farmland corn stalks, which comprises: the acquisition module is used for determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image; the processing module is used for determining a corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI; wherein AIRSI is determined according to the reflectivity weighting values of the B4, B5 and B12 wave bands; PNISI is determined according to the reflectivity of the B4 wave band and the B8 wave band; NDSSI is determined from the B9 and B12 band reflectivities.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the steps of the satellite remote sensing extraction method for farmland corn stalks are realized when the processor executes the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the farmland corn stalk satellite remote sensing extraction method as described in any of the above.
According to the farmland corn stalk satellite remote sensing extraction method and device provided by the invention, the farmland corn stalk autumn and winter remote sensing result is determined through three novel stalk indexes of normalized short wave infrared stalk indexes, superimposed infrared stalk indexes and superimposed near infrared stalk indexes, so that the extraction precision and efficiency of farmland corn stalk can be improved, manual investigation is reduced, and data support is provided for stalk incineration supervision.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a satellite remote sensing extraction method of farmland corn stalks;
FIG. 2 is a second schematic flow chart of the satellite remote sensing extraction method of farmland maize straws;
FIG. 3 is a novel straw index AIRSI-NDSSI scatter diagram of a farmland main ground feature sample point provided by the invention;
fig. 4 is a schematic structural diagram of a satellite remote sensing extraction device for farmland corn stalks;
fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The farmland corn stalk satellite remote sensing extraction method and device of the invention are described below with reference to fig. 1-5. Fig. 1 is a schematic flow chart of a method for remotely sensing and extracting farmland corn stalk satellites, and as shown in fig. 1, the method for remotely sensing and extracting farmland corn stalk satellites provided by the invention comprises the following steps:
101. determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image;
102. determining a corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI;
wherein AIRSI is determined according to the reflectivity weighting values of the B4, B5 and B12 wave bands; PNISI is determined from B4 and B8 band reflectivities e; NDSSI is determined from the B9 and B12 band reflectivities.
B4 is red wave band (650 nm-680 nm), B5 is red edge wave band (698 nm-713 nm), B8 is near infrared wave band (785 nm-900 nm), B9 is water vapor wave band (1360 nm-1390 nm), and B12 is short wave infrared wave band (2100 nm-2280 nm).
As an alternative embodiment, the target remote sensing image is a second satellite remote sensing image of a sentinel, which will be described below as an example. The second sentinel image has 12 wave bands, namely B1 (433 nm-453 nm), B2 (458 nm-523 nm), B3 (543 nm-578 nm), B4 (650 nm-680 nm), B5 (698 nm-713 nm), B6 (733 nm-748 nm), B7 (773 nm-793 nm), B8 (785 nm-900 nm), B8B (935 nm-955 nm), B9 (1360 nm-1390 nm), B11 (1565 nm-1655 nm) and B12 (2100 nm-2280 nm), and the image needs to be preprocessed, including data decompression, data export, wave band combination, radiation correction, geometric correction and image clipping. The decompression and data export of the image data can be completed in SNAP software appointed by European space agency, the wave band combination, radiation correction, geometric correction and image clipping of the image can be completed in ENVI software, the spatial resolution of the image is 10m, and the coordinate system is WGS84_UTM_Zone 50N.
And obtaining the reflectivity of each wave band of the target remote sensing image after acquiring satellite remote sensing image data of the research area in autumn and winter. According to a farmland ground object spectrum graph, 3 novel straw indexes are provided and constructed according to the reflectivity of each wave band by comprehensively analyzing the spectrum differences of upright cornstalk, tiled broken straws, bare land, dense wheat, sparse wheat and fallen leaf forest land, and particularly three novel straw indexes, namely a normalized short-wave infrared straw index NDSSI, a superimposed infrared straw index AIRSI and a superimposed near-infrared straw index PNISI are provided.
1. A novel pile-up near-red straw index PNISI is constructed.
Through detailed analysis of spectrum curves, the spectrum values of the crushed stubble straw, the thinned wheat and the dense wheat in the B8 wave band are obviously larger than those of naked land and corn straw, the spectrum differences of the crushed stubble straw, the thinned wheat and the dense wheat in the B4 wave band and the B8 wave band are also obviously larger than those of other ground objects, and the overlapping near red straw index is constructed according to the characteristics:
in one embodiment, PNISI is:
in the above description, B4 is the reflectivity value of the B4 band (red band) in the second satellite image of the sentinel, and B8 is the reflectivity value of the B8 band (near infrared band) in the second satellite image of the sentinel.
In order to embody details, the reflectivity is enlarged 10000 times later, and then the straw index is calculated. The PNISI can be used for realizing the obvious distinction of dense wheat from sparse wheat, stubble straws, corn straws and bare land, wherein PNISI is more than 1250 and is less than or equal to 1250, and PNISI is less than or equal to 1250 and is mainly distributed in (500, 650). Thus dense wheat can be effectively rejected using PNISI.
2. Construction of novel normalized shortwave infrared straw index NDSSI
Through detailed analysis of the spectrum curve, the spectrum values of the corn straw and the bare land in the B9 wave band are not greatly different, and the spectrum value of the bare land in the B12 wave band is obviously larger than that of the corn straw. According to the characteristics, the normalized short-wave infrared straw index NDSSI is constructed:
in one embodiment, NDSSI is:
in the above description, B9 is the reflectivity value of the B9 wave band in the second satellite image of the sentinel, and B12 is the reflectivity value of the B12 wave band in the second satellite image of the sentinel.
The obvious distinction of the wheat straw and the wheat straw can be realized by using the NDSSI, wherein the NDSSI is less than-0.09, and the wheat straw are mainly distributed in (-0.07,0.07). Therefore, the NDSSI can be used for effectively removing the stubble-breaking straw and the dense wheat.
3. And constructing a novel superimposed infrared straw index AIRSI.
Through detailed analysis of the spectrum curves, the distinguishing degree of the farmland corn stalks and other ground objects (corn stubble, bare land and wheat) is higher in the B4 and B5 wave bands, especially in the B12 wave bands, so that the three wave bands of B4 (red light), B5 (red edge) and B12 (short wave infrared) are sensitive wave bands extracted from the farmland corn stalks, the image value of the B12 wave band is about 3000 (corresponding reflectance is 0.3), the distinguishing degree is maximum, the image values of the B4 and B5 wave bands are about 1500 (corresponding reflectance is 0.15), and the wave bands are distinguished for times. The superimposed infrared straw index AIRSI constructed according to the characteristics is as follows:
AIRSI＝(a×B4+b×B5+B12)/c
in the above description, B4 is the reflectivity value of the B4 wave band in the second satellite image of the sentinel, B5 is the reflectivity value of the B5 wave band in the second satellite image of the sentinel, and B12 is the reflectivity value of the B12 wave band in the second satellite image of the sentinel. a is the B4 band adjustment factor, here 1.8, B is the B5 band adjustment factor, here 1.5, c is the B12 band adjustment factor, here 10000.
According to the sampling point statistics result of the superimposed infrared straw index AIRSI, the obvious distinction between corn straw and close wheat, stubble straw, open wheat and bare land can be realized by utilizing AIRSI, wherein AIRSI is more than 0.6 and less than 0.75, the AIRSI is less than or equal to 0.6 and the close wheat, and AIRSI is more than or equal to 0.76.
According to the farmland corn stalk satellite remote sensing extraction method, the farmland corn stalk autumn and winter remote sensing result is determined through three novel stalk indexes of normalized short wave infrared stalk indexes, superimposed infrared stalk indexes and superimposed near-infrared stalk indexes, so that the extraction precision and efficiency of the farmland corn stalk can be improved, manual investigation is reduced, and data support is provided for stalk incineration supervision.
In one embodiment, before determining the corn stalk region according to the value range of any one or more of NDSSI, AIRSI, and PNISI, the method further comprises: acquiring satellite remote sensing images of three time phases in a research area; determining an artificial ground object area according to the remote sensing image of the first time phase, and determining a woodland area according to the remote sensing image of the second time phase; removing the artificial land feature area and the woodland area from the remote sensing image in the third time phase to obtain the target remote sensing image; the first time phase is a flowering period with the highest chlorophyll content of the corn stalks; the second time phase is a time phase with the largest chlorophyll content difference between the woodland and the corn stalks; the third time phase is the harvesting period with the lowest chlorophyll content after the corn stalks are dried.
In order to improve the accuracy of straw extraction, the invention respectively performs artificial ground object extraction and elimination and woodland extraction and elimination according to three different time phase data in consideration of the influence of the artificial ground object and woodland on the regional result. That is, the target remote sensing image is a remote sensing image from which the woodland and the artificial ground feature are removed.
In the present invention, the three time phases may be selected from the corresponding time periods to be relatively large time periods, and the time periods are not limited to the time periods of the maximum value, but may be time periods within a certain range of the maximum value. For example, in one embodiment, the first, second, and third phases have a period of 9 months 4 days, 10 months 16 days, and 11 months 8 days, respectively, which are close enough to enable relatively accurate corn straw extraction. However, the above date is not limited.
In one embodiment, the determining the artificial ground object area according to the remote sensing image of the first time phase and determining the forest land area according to the remote sensing image of the second time phase respectively includes: according to the remote sensing image of the first time phase, determining an artificial ground object area according to an area with normalized vegetation index NDVI smaller than 0.5 or blue light wave band reflectivity larger than 0.08; and determining the forest area according to the remote sensing image of the second time phase, wherein the NDVI is more than or equal to 0.5.
Firstly, in order to better extract farmland corn stalks, non-target ground objects need to be removed, and artificial ground objects such as house buildings, roads and the like belong to the non-target ground objects and need to be removed.
As most of the artificial buildings are off-white, are mixed with roofs of blue, red and the like, the chlorophyll content of the corn stalks in the farmland is rich in the early 9 months, and the green vegetation signals are strong, and form great contrast with the off-white, blue and red of the artificial buildings, so that the distinguishing degree is high. The normalized vegetation index NDVI calculation can be carried out by selecting 9 months and 4 days of images, and the NDVI value of the artificial building in the period is generally lower than 0.5 through repeated debugging, so that the NDVI is less than 0.5 and is set as an artificial building extraction threshold. As the blue roof mixed in the artificial building is easy to leak, the B2 (blue wave band) reflectivity of the blue ground object is more than 0.08 through repeated debugging. Therefore, binarization processing is carried out on the 9-month 4-day image, the image area with NDVI smaller than 0.5 or B2 larger than 0.08 is assigned as 1, and other image areas are assigned as 0, so that the artificial ground object distribution map is generated. This step may be accomplished in ENVI software.
In the above description, B4 is the reflectivity value of the B4 band (red band) in the second satellite image of the sentinel, and B8 is the reflectivity value of the B8 band (near infrared band) in the second satellite image of the sentinel.
Besides the artificial ground, the woodland and the corn straw belong to the same plant, especially the woodland and the corn straw are withered and yellow in winter, which is easy to be confused, so that the woodland is also required to be removed for better extracting the corn straw in farmland. Lin De is also dense in the early 10 months, the chlorophyll content is rich, the green vegetation signal is strong, and the green vegetation signal is in contrast with the maize straw withered and yellow in the period of time, and the distinguishing degree is high. And (3) selecting the images of 10 months and 16 days to calculate an NDVI vegetation index, and repeatedly debugging to find that the NDVI value of the woodland in the period is generally higher than 0.5, so that the NDVI is more than or equal to 0.5 is set as a woodland extraction threshold value, binarizing the images of 10 months and 16 days, assigning an image area with the NDVI of more than or equal to 0.5 to 1, assigning an image area with the NDVI of less than 0.5 to 0, and generating a woodland distribution map. This step is done in ENVI software.
Setting the artificial ground object distribution map as a mask layer, performing mask processing on the image of 11 months and 8 days (third time phase), and removing the artificial ground object in the image of 11 months and 8 days; then setting the woodland distribution map as a mask layer, performing secondary mask treatment on the 11 month 8 day images from which the artificial ground is removed, and removing woodlands in the 11 month 8 day images. So far, new remote sensing images of 11 months and 8 days are generated, wherein the artificial ground objects and the woodland are removed. This step may be accomplished in ENVI software.
According to the remote sensing extraction method for the farmland corn straw satellite, disclosed by the invention, the influences of the artificial ground and the forest land are removed through three different time phases, so that the accuracy of straw extraction can be improved.
In one embodiment, the determining method of PNISI or NDSSI correspondingly includes:
wherein B4, B8, B9 and B12 are the reflectances of the corresponding bands, respectively. The foregoing embodiments have been illustrated and will not be described in detail herein.
In one embodiment, the PNISI, NDSSI, and AIRSI have values in the ranges: PNISI < 0.05 < 0.065 (500 < PNISI < 650 if 10000 times extended), -NDSSI < 0.07,0.6 < AIRSI < 0.75.
The dense wheat has the largest differentiation degree with other four land features and is easy to extract; the stubble breaking straw can be effectively extracted by utilizing the combination of the AIRSI and the NDSSI indexes; the bare land can be effectively extracted by utilizing the index combination of PNISI-NDSSI; the sparse wheat is easy to be confused with the corn straw.
In one embodiment, the determining the corn stalk region according to the value range of any one or more of NDSSI, AIRSI, and PNISI comprises: and determining the corn straw area according to the area which simultaneously meets the value ranges of NDSSI, AIRSI and PNISI.
The separation and extraction of the sparse wheat and the corn straw are realized by utilizing three index combinations of AIRSI-PNISI-NDSSI, which shows that the corn straw has better separability with other places. The advantages of each index are complemented by extracting a plurality of indexes, so that the monitoring precision is further improved.
Based on the constructed 3 novel straw indexes PNISI, AIRSI and NDSSI, comprehensive analysis is carried out on the ground feature spectral curve and the statistical analysis chart, and then reasonable thresholds for distinguishing different ground features are determined through repeated debugging, so that a comprehensive autumn and winter farmland corn straw classification extraction rule set is formed. This step may be accomplished in ENVI software.
In one embodiment, after the determining the corn stalk region, the method further comprises: and converting the grid image of the corn stalk region extraction result into a vector file.
The farmland corn stalk distribution map generated in the last step is a pair of grid images, and in order to facilitate the later practical application, the farmland corn stalk distribution map (grid image) is converted into a farmland corn stalk distribution map (vector file) in shp format through a grid vector conversion tool. This step may be accomplished in ArcGIS software.
After the step, the generated farmland corn stalk distribution map (shp format) and the sentinel second remote sensing image can be displayed in a superimposed mode and are mapped, and a final farmland corn stalk thematic map is generated. This step may be accomplished in ArcGIS software.
Fig. 2 is a second schematic flow chart of the satellite remote sensing extraction method for farmland corn stalks provided by the invention, which can be seen in the steps of the above embodiment and fig. 2. Fig. 3 is a plot of novel straw index AIRSI-NDSSI scatter of a primary plot of farmland, according to the present invention, and can be referred to in conjunction with the above examples.
The farmland corn stalk satellite remote sensing extraction device provided by the invention is described below, and the farmland corn stalk satellite remote sensing extraction device described below and the farmland corn stalk satellite remote sensing extraction method described above can be correspondingly referred to each other.
Fig. 4 is a schematic structural diagram of a remote sensing and extracting device for farmland corn stalk satellite provided by the invention, as shown in fig. 4, the remote sensing and extracting device for farmland corn stalk satellite includes: an acquisition module 401 and a processing module 402. The obtaining module 401 is configured to determine a normalized short-wave infrared straw index NDSSI, a superimposed infrared straw index AIRSI, and a superimposed near-infrared straw index PNISI according to the reflectivity of each band of the target remote sensing image; the processing module 402 is configured to determine a corn stalk region according to a range of values of any one or more of NDSSI, AIRSI, and PNISI; wherein AIRSI is determined according to the reflectivity weighting values of the B4, B5 and B12 wave bands; PNISI is determined according to the reflectivity of the B4 wave band and the B8 wave band; NDSSI is determined from the B9 and B12 band reflectivities.
The embodiment of the device provided by the embodiment of the present invention is for implementing the above embodiments of the method, and specific flow and details refer to the above embodiments of the method, which are not repeated herein.
According to the farmland corn stalk satellite remote sensing extraction device provided by the embodiment of the invention, the farmland corn stalk autumn and winter remote sensing result is determined through three novel stalk indexes of normalized short wave infrared stalk indexes, superimposed infrared stalk indexes and superimposed near infrared stalk indexes, so that the extraction precision and efficiency of farmland corn stalk can be improved, manual investigation is reduced, and data support is provided for stalk incineration supervision.
Fig. 5 is a schematic structural diagram of an electronic device according to the present invention, and as shown in fig. 5, the electronic device may include: a processor (processor) 501, a communication interface (Communications Interface) 502, a memory (memory) 503 and a communication bus 504, wherein the processor 501, the communication interface 502, and the memory 503 communicate with each other via the communication bus 504. The processor 501 may invoke logic instructions in the memory 503 to perform a method for remote sensing extraction of crop stalks from a satellite in a farm, the method comprising: determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image; and determining the corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI.
Further, the logic instructions in the memory 503 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method for remote sensing extraction of farmland maize straw provided by the above methods, the method comprising: determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image; and determining the corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI.
In still another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the method for remote sensing extraction of farmland corn stalks satellite provided in the above embodiments, the method comprising: determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image; and determining the corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. A satellite remote sensing extraction method for farmland corn stalks is characterized by comprising the following steps:
determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image;
determining a corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI;
wherein AIRSI is determined according to the reflectivity weighting values of the B4, B5 and B12 wave bands; PNISI is determined according to the reflectivity of the B4 wave band and the B8 wave band; NDSSI is determined from B9 and B12 band reflectivities; the target remote sensing image is a sentinel second satellite remote sensing image; the sentry second remote sensing image includes: b1 band, B2 band, B3 band, B4 band, B5 band, B6 band, B7 band, B8B band, B9 band, B11 band, and B12 band; the wavelength range of the B1 band includes 433nm to 4573 nm, the wavelength range of the B2 band includes 458nm to 523nm, the wavelength range of the B3 band includes 543nm to 578nm, the wavelength range of the B4 band includes 650nm to 680nm, the wavelength range of the B5 band includes 698nm to 7193 nm, the wavelength range of the B6 band includes 733nm to 748nm, the wavelength range of the B7 band includes 773nm to 793nm, the wavelength range of the B8 band includes 785nm to 900nm, the wavelength range of the B8B band includes 935nm to 9555 nm, the wavelength range of the B9 band includes 1360nm to 1390nm, the wavelength range of the B11 band includes 1565nm to 1655nm, and the wavelength range of the B12 band includes 2100nm to 2280 nm.
The determining method of PNISI or NDSSI correspondingly comprises the following steps:
wherein B4, B8, B9 and B12 are the reflectivities of the corresponding wave bands respectively;
the AIRSI determination method correspondingly comprises the following steps:
wherein B5 is the reflectivity of the corresponding wave band; a is a B4 band adjusting coefficient, and the value is 1.8; b is a B5 band adjusting coefficient, and the value is 1.5; c is the B12 band adjustment coefficient, and the value is 10000.
2. The method for remotely sensing and extracting corn stalks in farmland according to claim 1, wherein before determining the corn stalk region according to the value range of any one or more of NDSSI, AIRSI and PNISI, further comprising:
acquiring satellite remote sensing images of three time phases in a research area;
determining an artificial ground object area according to the remote sensing image of the first time phase, and determining a woodland area according to the remote sensing image of the second time phase;
removing the artificial land feature area and the woodland area from the remote sensing image in the third time phase to obtain the target remote sensing image;
the first time phase is a flowering period with the highest chlorophyll content of the corn stalks; the second time phase is a time phase with the largest chlorophyll content difference between the woodland and the corn stalks; the third time phase is the harvesting period with the lowest chlorophyll content after the corn stalks are dried.
3. The method for remotely sensing and extracting corn stalks from a satellite in a farmland according to claim 2, wherein the determining the artificial land feature area from the remote sensing image in the first time phase and determining the forest land area from the remote sensing image in the second time phase respectively comprises:
according to the remote sensing image of the first time phase, determining an artificial ground object area according to an area with normalized vegetation index NDVI smaller than 0.5 or blue light wave band reflectivity larger than 0.08;
and determining the forest area according to the remote sensing image of the second time phase, wherein the NDVI is more than or equal to 0.5.
4. The method for remotely sensing and extracting farmland corn stalks by using satellites according to claim 1, wherein the values of PNISI, NDSSI and AIRSI are respectively as follows:
0.05＜PNISI＜0.065，-0.07＜NDSSI＜0.07，0.6＜AIRSI＜0.75。
5. the method for remotely sensing and extracting corn stalks in farmland according to claim 1, further comprising, after determining the corn stalk region:
and converting the grid image of the corn stalk region extraction result into a vector file.
6. The method for remotely sensing and extracting corn stalks in farmland according to claim 1, wherein the determining the corn stalk region according to the value range of any one or more of NDSSI, AIRSI and PNISI comprises:
and determining the corn straw area according to the area which simultaneously meets the value ranges of NDSSI, AIRSI and PNISI.
7. A farmland maize straw satellite remote sensing extraction element, characterized by comprising:
the acquisition module is used for determining normalized short wave infrared straw index NDSSI, superimposed infrared straw index AIRSI and superimposed near-infrared straw index PNISI according to the reflectivity of each wave band of the target remote sensing image;
the processing module is used for determining a corn straw area according to the value range of any one or more of NDSSI, AIRSI and PNISI;
wherein AIRSI is determined according to the reflectivity weighting values of the B4, B5 and B12 wave bands; PNISI is determined according to the reflectivity of the B4 wave band and the B8 wave band; NDSSI is determined from B9 and B12 band reflectivities;
the target remote sensing image is a sentinel second satellite remote sensing image; the sentry second remote sensing image includes: b1 band, B2 band, B3 band, B4 band, B5 band, B6 band, B7 band, B8B band, B9 band, B11 band, and B12 band; the wavelength range of the B1 band includes 433nm to 4573 nm, the wavelength range of the B2 band includes 458nm to 523nm, the wavelength range of the B3 band includes 543nm to 578nm, the wavelength range of the B4 band includes 650nm to 680nm, the wavelength range of the B5 band includes 698nm to 7193 nm, the wavelength range of the B6 band includes 733nm to 748nm, the wavelength range of the B7 band includes 773nm to 793nm, the wavelength range of the B8 band includes 785nm to 900nm, the wavelength range of the B8B band includes 935nm to 9555 nm, the wavelength range of the B9 band includes 1360nm to 1390nm, the wavelength range of the B11 band includes 1565nm to 1655nm, and the wavelength range of the B12 band includes 2100nm to 2280 nm.
The determining method of PNISI or NDSSI correspondingly comprises the following steps:
wherein B4, B8, B9 and B12 are the reflectivities of the corresponding wave bands respectively;
the AIRSI determination method correspondingly comprises the following steps:
wherein B5 is the reflectivity of the corresponding wave band; a is a B4 band adjusting coefficient, and the value is 1.8; b is a B5 band adjusting coefficient, and the value is 1.5; c is the B12 band adjustment coefficient, and the value is 10000.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor performs the steps of the method for remote sensing extraction of farmland maize straw satellite according to any of claims 1 to 6 when the program is executed.
9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor performs the steps of the farmland corn stalk satellite remote sensing extraction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110220236.6A CN112861766B (en) | 2021-02-26 | 2021-02-26 | Satellite remote sensing extraction method and device for farmland corn stalks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110220236.6A CN112861766B (en) | 2021-02-26 | 2021-02-26 | Satellite remote sensing extraction method and device for farmland corn stalks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112861766A CN112861766A (en) | 2021-05-28 |
| CN112861766B true CN112861766B (en) | 2024-02-02 |
Family
ID=75990365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110220236.6A Active CN112861766B (en) | 2021-02-26 | 2021-02-26 | Satellite remote sensing extraction method and device for farmland corn stalks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112861766B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113609910A (en) * | 2021-07-06 | 2021-11-05 | 北京农业信息技术研究中心 | Winter wheat growth early-stage spatial distribution monitoring method and device based on remote sensing image |
| CN113673339B (en) * | 2021-07-16 | 2024-02-23 | 北京农业信息技术研究中心 | Unmanned aerial vehicle image-based on-site straw extraction method and device |
| CN114076955B (en) * | 2021-09-27 | 2022-07-19 | 农业农村部规划设计研究院 | Method for identifying lodging corn based on high-score first satellite data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355143A (en) * | 2016-08-25 | 2017-01-25 | 中国农业大学 | Seed maize field identification method and system based on multi-source and multi-temporal high resolution remote sensing data |
| CN107067334A (en) * | 2017-04-21 | 2017-08-18 | 中国科学院遥感与数字地球研究所 | Farmland fire and crop straw burning monitoring method and system based on multi- source Remote Sensing Data data |
| CN112102312A (en) * | 2020-09-29 | 2020-12-18 | 滁州学院 | Moso bamboo forest remote sensing identification method based on satellite image and phenological difference containing red edge wave band |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020061789A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳市大疆创新科技有限公司 | Image processing method and device, unmanned aerial vehicle, system and storage medium |
-
2021
- 2021-02-26 CN CN202110220236.6A patent/CN112861766B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106355143A (en) * | 2016-08-25 | 2017-01-25 | 中国农业大学 | Seed maize field identification method and system based on multi-source and multi-temporal high resolution remote sensing data |
| CN107067334A (en) * | 2017-04-21 | 2017-08-18 | 中国科学院遥感与数字地球研究所 | Farmland fire and crop straw burning monitoring method and system based on multi- source Remote Sensing Data data |
| CN112102312A (en) * | 2020-09-29 | 2020-12-18 | 滁州学院 | Moso bamboo forest remote sensing identification method based on satellite image and phenological difference containing red edge wave band |
Non-Patent Citations (7)
| Title |
|---|
| Water Bodies’ Mapping from Sentinel-2 Imagery with Modified Normalized Difference Water Index at 10-m Spatial Resolution Produced by Sharpening the SWIR Band;Yun Du 等;《remote sensing》;1-19 * |
| 便携式野外现场近红外地物光谱仪研究与测试;郑志忠;陈春霞;修连存;;《现代科学仪器》(第02期);25-28 * |
| 冬小麦播期遥感监测研究现状与展望;葛艳 等;《麦类作物学报》;58-64 * |
| 基于Landsat 8影像的不同燃烧指数在农田秸秆焚烧区域识别中的应用;马建行 等;《应用生态学报》;第26卷(第11期);3451-3456 * |
| 基于NDVI时间序列影像的张掖市农作物种植结构提取;程良晓 等;《地理信息世界》;第23卷(第04期);37-44 * |
| 基于土壤异质背景的玉米秸秆覆盖度遥感反演;黄晋宇 等;《应用生态学报》;第31卷(第2期);474-482 * |
| 结合Sentinel-2光谱与纹理信息的冬小麦作物茬覆盖度估算;蔡文婷 等;《遥感学报》(第09期);1108-1119 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112861766A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112861766B (en) | Satellite remote sensing extraction method and device for farmland corn stalks | |
| Karlson et al. | Assessing the potential of multi-seasonal WorldView-2 imagery for mapping West African agroforestry tree species | |
| He et al. | Integrating multi-sensor remote sensing and species distribution modeling to map the spread of emerging forest disease and tree mortality | |
| Peña-Barragán et al. | Object-based crop identification using multiple vegetation indices, textural features and crop phenology | |
| de Mattos Scaramuzza et al. | Land-use and land-cover mapping of the Brazilian Cerrado based mainly on Landsat-8 satellite images | |
| Ghulam et al. | Detecting subcanopy invasive plant species in tropical rainforest by integrating optical and microwave (InSAR/PolInSAR) remote sensing data, and a decision tree algorithm | |
| Starks et al. | Measuring eastern redcedar (Juniperus virginiana L.) mass with the use of satellite imagery | |
| Moriya et al. | Detection and mapping of trees infected with citrus gummosis using UAV hyperspectral data | |
| Xiao et al. | Remote sensing detection algorithm for apple fire blight based on UAV multispectral image | |
| Demissie et al. | Geospatial solutions for evaluating the impact of the Tigray conflict on farming | |
| Abdullah et al. | A comparison between day and night land surface temperatures using acquired satellite thermal infrared data in a winter wheat field | |
| Zakaluk et al. | Predicting the leaf water potential of potato plants using RGB reflectance. | |
| Roslin et al. | Mobile Application Development for Spectral Signature of Weed Species in Rice Farming. | |
| Yang et al. | Forest edges near farms enhance wheat productivity measures: a test using high spatial resolution remote sensing of smallholder farms in southern Ethiopia | |
| Kumar et al. | Monitoring of spectral signatures of maize crop using temporal sar and optical remote sensing data | |
| WO2006024686A1 (en) | Method of differentiating and quantifying an olive grove with vegetative covers by means of remote sensing with high-resolution space sensors | |
| Arockiaraj et al. | Identification and quantification of tree species in open mixed forests using high resolution QuickBird satellite imagery | |
| Nigam et al. | Wheat blast detection and assessment combining ground-based hyperspectral and satellite based multispectral data | |
| Lucas et al. | Assessing human impacts on Australian forests through integration of remote sensing data | |
| Daichi et al. | Potential extinction debt due to habitat loss and fragmentation in subalpine moorland ecosystems | |
| Rege et al. | Mapping cashew monocultures in the Western Ghats using optical and radar imagery in Google Earth Engine | |
| Jovanović et al. | Crop yield estimation in 2014 for Vojvodina using methods of remote sensing | |
| Sánchez-Díaz et al. | Use of different spectral vegetation indices to determine the presence of mantled howler monkeys (Alouatta palliata G.) on cocoa agrosystems (Theobroma cacao L.). | |
| Champagne et al. | Exploiting spectral variation from crop phenology for agricultural land-use classification | |
| Manjunath et al. | Machine learning classifiers on Sentinel-2 satellite image for the classification of banana (Musa Sp.) plantations of Theni district, Tamil Nadu, India |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |