Remote sensing identification method and device for abnormal state of regional vegetation

Abstract

The invention provides a remote sensing recognition method and device for an abnormal state of regional vegetation, and the method comprises the steps: obtaining a remote sensing image of a time sequence of a target region, and recognizing a forest and grass region in the remote sensing image; in the forest and grass area, establishing a grid which covers the forest and grass area and has a certain specification; identifying abnormal grids suspected to have withered and yellow vegetation in the area; according to the vegetation withering and yellowing change index and the vegetation withering and yellowing collaborative change index, identifying vegetation abnormal withering and yellowing pixels in the suspected abnormal grid; and according to the vegetation degradation early-warning index, identifying an early-warning unit with a vegetation abnormal state. Through adoption of the method, the problem that the vegetation abnormal state information in the region obtained through a remote sensing method is not accurate enough in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing and vegetation monitoring, and in particular to a remote sensing identification method and device for abnormal status of regional vegetation. Background Art

[0002] Abnormal changes in vegetation yellowing refer to the phenomenon that leaves of forests and grasses turn yellow prematurely or suddenly due to external factors such as drought, pests and diseases during the growing period. The yellowing of natural vegetation such as forests and grasses will affect the normal growth of vegetation, and may cause local or large-scale damage to forests and grasses. Timely and effective acquisition of abnormal vegetation conditions such as yellowing of vegetation in the region will help promote the scientific restoration and management of vegetation ecosystems.

[0003] Currently, remote sensing methods are widely used to obtain information on the withering and yellowing of vegetation in a region during its growth period, such as vegetation index analysis methods, remote sensing image classification methods, and canopy moisture observation methods. However, when these traditional remote sensing methods are used in practice, the information on abnormal vegetation status in the region is not accurate enough. Summary of the invention

[0004] The present invention provides a remote sensing identification method and device for abnormal vegetation status in a region, which are used to solve the problem that the abnormal vegetation status information in a region obtained by remote sensing method in the related art is not accurate enough.

[0005] The present invention provides a remote sensing identification method for abnormal vegetation status in a region, comprising the following steps: Obtain time series remote sensing images of the target area and identify forest and grass areas in the remote sensing images; The grid establishes a plurality of grids or a plurality of early warning units in the forest and grassland area; Identify suspected abnormal grids among the plurality of grids, and identify abnormal pixels in each of the suspected abnormal grids; Identifying abnormally yellowed vegetation pixels among the abnormal pixels according to the vegetation yellowing change index and the vegetation yellowing coordinated change index; According to the vegetation degradation warning index, the warning unit where the vegetation is abnormal is identified.

[0006] According to the remote sensing identification method of regional vegetation abnormal state provided by the present invention, the early warning unit for identifying the presence of vegetation abnormal state according to the vegetation degradation early warning index comprises: Obtaining the vegetation degradation index of each pixel in each of the early warning units, and obtaining the average vegetation degradation index of each pixel in each of the early warning units; According to the vegetation degradation index and the average vegetation degradation index, the vegetation degradation warning index of each warning unit is obtained to identify the warning unit with abnormal vegetation status.

[0007] According to the remote sensing identification method for abnormal state of regional vegetation provided by the present invention, the step of obtaining the vegetation degradation index of each pixel in each early warning unit includes: According to the normalized vegetation index at the first time point and the normalized vegetation index at the second time point, the vegetation degradation index of each early warning unit is obtained; the first time point is the time point corresponding to the maximum value of the vegetation degradation index of the pixel in each early warning unit, and the second time point is the next time point of the first time point in the time series.

[0008] According to the remote sensing identification method of regional vegetation abnormality state provided by the present invention, the identification of forest and grass areas in remote sensing images includes: Obtaining the average normalized vegetation index of each sub-image in the forest and grassland area in time series; Obtaining a crop recognition index of the remote sensing image according to an average normalized vegetation index of each sub-image in a time series and a normalized vegetation index of each sub-image; The forest and grass area in the remote sensing image is identified according to the crop identification index and the mean normalized difference vegetation index.

[0009] According to the remote sensing identification method for abnormal state of regional vegetation provided by the present invention, the step of identifying suspected abnormal grids among the plurality of grids comprises: The suspected abnormal grid is identified from a plurality of grids according to a grid-level vegetation change rate index of each grid, wherein the grid-level vegetation change rate index is obtained according to a normalized vegetation index of each grid pixel in the grid.

[0010] According to the remote sensing identification method of regional vegetation abnormality state provided by the present invention, identifying abnormal pixels in each of the suspected abnormal grids includes: According to the pixel-level vegetation change rate index of each grid pixel in the suspected abnormal grid, the abnormal pixels in the suspected abnormal grid are identified.

[0011] According to the remote sensing identification method of regional vegetation abnormality provided by the present invention, the pixel-level vegetation change rate index is obtained based on the vegetation index of each grid pixel in the suspected abnormal grid, and the vegetation index includes any one or more of the normalized vegetation index, the enhanced vegetation index and the difference vegetation index.

[0012] The present invention also provides a remote sensing identification device for abnormal state of regional vegetation, comprising: The region recognition module is used to obtain the time series remote sensing images of the target area and identify the forest and grass areas in the remote sensing images; A region segmentation module is used to establish multiple grids or multiple early warning units in the forest and grassland area; A grid recognition module, used to identify suspected abnormal grids among the plurality of grids, and to identify abnormal pixels in each of the suspected abnormal grids; A pixel identification module, used for identifying abnormally yellowed vegetation pixels among the abnormal pixels according to the vegetation yellowing change index and the vegetation yellowing coordinated change index; The unit identification module is used to identify the warning unit with abnormal vegetation status according to the vegetation degradation warning index.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described methods when executing the program.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, any of the methods described above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, any of the above-described methods is implemented.

[0016] The present invention provides a remote sensing identification method and device for abnormal vegetation status in a region. The method identifies the forest and grass areas in the remote sensing image and divides the forest and grass areas into multiple grids or warning units constructed based on time series. The method considers the change of the normalized vegetation index of each grid or warning unit in the time series to comprehensively judge whether each grid or warning unit has abnormal vegetation status, thereby improving the accuracy of the acquired information on abnormal vegetation status in the region. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is one of the flow charts of a remote sensing identification method for abnormal state of regional vegetation provided by the present invention.

[0019] Figure 2 This is the second flow chart of a remote sensing identification method for abnormal state of regional vegetation provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of a remote sensing identification device for abnormal status of regional vegetation provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the descriptions used in this way can be interchanged where appropriate, so that the embodiments can be implemented in a sequence other than that illustrated or described in the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or modules is not necessarily limited to those steps or modules that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of the steps that appear in the present application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The process steps that have been named or numbered can change the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of modules in this application is a logical division. There may be other division methods when it is implemented in actual applications. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between units can be electrical or other similar forms, which are not limited in this application. In addition, the modules or submodules described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed in multiple circuit units, and some or all of the units may be selected according to actual needs to achieve the purpose of the present application.

[0024] Because the forests and grasslands in forestry-related areas are affected by factors such as drought, pests and diseases, the vegetation may turn yellow or experience other abnormal phenomena prematurely or suddenly. Therefore, in order to better serve regional ecosystem restoration, drought management, etc., the present invention provides a remote sensing identification method and device for abnormal vegetation status in a region.

[0025] Combine the following Figure 1-Figure 4 The specific contents of the present invention are described.

[0026] Figure 1 It is a flow chart of a remote sensing identification method for abnormal vegetation status in a region provided by the present invention, which is applied to a server, such as Figure 1 As shown, the method includes the following steps S101-S105.

[0027] Step S101, obtaining a time series of remote sensing images of a target area, and identifying forest and grass areas in the remote sensing images.

[0028] Specifically, in an embodiment of the present invention, a target area is determined, such as a forestry area in a drought region, and a suitable time series is selected. The time series can be selected monthly, weekly or daily, and the embodiment of the present application does not specifically limit this. Based on the selected time series, a remote sensing image of the target area is obtained.

[0029] In an embodiment of the present invention, the vegetation status of the farmland area is affected by human factors. The present invention needs to identify the vegetation status of the non-agricultural area in the target area under natural conditions. Therefore, the agricultural area in the target area needs to be excluded to avoid interfering with the identification results.

[0030] In a possible implementation, Figure 2 As shown, identifying forest and grass areas in remote sensing images specifically includes steps S201-S203.

[0031] Step S201, obtaining the average normalized vegetation index of each sub-image in the remote sensing image in the time series.

[0032] In the embodiment of the present application, the remote sensing image is composed of multiple sub-images. The average value of the normalized vegetation index of the sub-images is , For the The average value of the normalized vegetation index of the sub-image at each time point in the time series.

[0033] In the embodiment of the present invention, NDVI is the Normalized Difference Vegetation Index, which is a value between -1 and 1 and is used to quantitatively evaluate vegetation coverage and its growth vitality. NDVI quantifies vegetation by measuring the difference between the reflectance of the near-infrared band and the reflectance of the red band. The specific calculation formula is:

[0034] in represents the reflectivity in the near-infrared band, Represents the reflectance of the red band. The Normalized Difference Vegetation Index can not only reflect the status of land cover vegetation, but also evaluate vegetation coverage, monitor crop growth, predict crop yields, and warn of pests and diseases.

[0035] Step S202, obtaining the crop recognition index of the remote sensing image according to the average normalized vegetation index of each sub-image in the time series and the normalized vegetation index of each sub-image.

[0036]

[0037] Through the above formula, we can get the crop recognition index of remote sensing images: ; Different sub-images correspond to different crop recognition indexes. is the total number of sub-images in the remote sensing image, For the Normalized vegetation index of sub-images when performing region recognition.

[0038] Step S203, identifying the forest and grass areas in the remote sensing image according to the crop identification index and the mean normalized difference vegetation index.

[0039] In one embodiment of the present invention, for the i-th sub-image in the remote sensing image, its average normalized vegetation index and crop identification index are respectively

[0040] when is greater than or equal to a first preset normalized difference vegetation index threshold, and When it is greater than or equal to the preset crop recognition index threshold, the area corresponding to the i-th sub-image is determined to be a farmland area; otherwise, the area corresponding to the i-th sub-image is a forest and grass area.

[0041] By traversing all sub-images, the forest and grass areas in the remote sensing images can be identified.

[0042] Step S102, the grid establishes multiple grids or multiple early warning units in the forest and grassland area; Regarding segmenting the forest and grass area to obtain multiple early warning units. In the embodiment of the present application, the forest and grass area can be segmented according to the image texture and spectral characteristics of the forest and grass area to obtain multiple early warning units. In the embodiment of the present invention, the specific method of segmenting the forest and grass area is not specifically limited. Segmenting the forest and grass area to obtain multiple grids can refer to the subsequent embodiments.

[0043] In the embodiment of the present application, in the recognition process of the non-agricultural remote sensing area image, in addition to segmenting the non-agricultural remote sensing area image into multiple early warning units to further identify whether there is an abnormal vegetation state, the non-agricultural remote sensing area image can also be segmented into multiple grids, each grid is constructed based on a time series.

[0044] It should be noted that in the embodiment of the present application, unlike dividing the forest and grassland area into multiple early warning units, dividing the forest and grassland area into multiple grids has a higher degree of division, that is, for the same forest and grassland area, its single early warning unit has a larger range than a single grid.

[0045] Step S103, identifying suspected abnormal grids among the multiple grids, and identifying abnormal pixels in each suspected abnormal grid.

[0046] The step S103 in the present invention is described in detail below.

[0047] In a possible implementation, in step S103, identifying a suspected abnormal grid among the multiple grids includes: identifying a suspected abnormal grid from the multiple grids according to a grid-level vegetation change rate index of each grid, wherein the grid-level vegetation change rate index is obtained according to a normalized vegetation index of each grid pixel in the grid. The suspected abnormal grid is an abnormal grid among the multiple grids that is suspected to have withered and yellowed vegetation.

[0048] Specifically, the grid-level vegetation change rate index of a single grid , determined according to the following formula:

[0049] in, The time nodes of the natural vegetation growth period and the withering period can be determined by those skilled in the art according to the types of vegetation in the grid. For the grid Pixels at time point The normalized difference vegetation index, , is the first Pixels at time point The normalized difference vegetation index, is the total number of pixels in the grid.

[0050] When the grid-level vegetation change rate index of a grid When it is greater than or equal to the preset grid-level vegetation change rate index threshold, the grid is confirmed as a suspected abnormal grid, and all grids are traversed to screen out suspected abnormal grids from multiple grids.

[0051] In a possible implementation, in step S103, identifying abnormal pixels in each suspected abnormal grid includes: identifying abnormal pixels in the suspected abnormal grid according to a pixel-level vegetation change rate index of each grid pixel in the suspected abnormal grid.

[0052] Specifically, the pixel-level vegetation change rate of each grid pixel in the suspected abnormal grid Determined according to the following formula:

[0053] in, The first Grid pixels at time nodes The vegetation index, The first Grid pixels at time nodes The vegetation index.

[0054] For example, for a grid pixel in a certain grid, when the pixel-level vegetation change rate of the grid pixel is When it is greater than or equal to the preset pixel-level vegetation change rate threshold, the grid pixel is confirmed as an abnormal pixel.

[0055] On the contrary, when the pixel-level vegetation change rate of the grid pixel When it is less than the preset pixel-level vegetation change rate threshold, the grid pixel is confirmed not to be an abnormal pixel.

[0056] In a possible implementation, the pixel-level vegetation change rate index is obtained according to the vegetation index of each grid pixel in the abnormal grid, and the vegetation index includes any one or more of the normalized vegetation index, the enhanced vegetation index and the difference vegetation index.

[0057] In an embodiment of the present invention, the vegetation index includes any one or more of a normalized vegetation index, an enhanced vegetation index and a difference vegetation index.

[0058] Among them, for the suspected abnormal grid Grid pixels at time nodes Normalized Difference Vegetation Index Come on.

[0059] when When the vegetation index is greater than or equal to a second preset normalized vegetation index threshold, the vegetation index is determined to be an enhanced vegetation index EVI; when When the vegetation index is less than or equal to a third preset normalized vegetation index threshold, the vegetation index is determined as a difference vegetation index DVI; Dangdang When the vegetation index is less than the second preset normalized vegetation index threshold and greater than the third preset normalized vegetation index threshold, the vegetation index is determined as the normalized vegetation index DNVI.

[0060] In an embodiment of the present invention, , ; Among them, G=2.5; L=1; C1=6; C2=7.5, is the reflectance of the blue band.

[0061] In the embodiment of the present invention, when the vegetation index is different, the corresponding preset pixel-level vegetation change rate threshold will also change.

[0062] Step S104, identifying abnormally yellowed vegetation pixels among the abnormal pixels according to the vegetation yellowing change index and the vegetation yellowing coordinated change index.

[0063] In the embodiment of the present invention, for the Vegetation yellowing index of abnormal pixels Determined according to the following formula:

[0064] in, For the The abnormal pixels are at time The vegetation yellowing index, For the The abnormal pixels are at time Vegetation yellowing index; in, Determined according to the following formula:

[0065] in, is the green band reflectance.

[0066] In the embodiment of the present invention, for the The vegetation yellowing coordinated change index of abnormal pixels Determined according to the following formula:

[0067] For the The maximum value of the normalized vegetation index of the abnormal pixel at each time node in the time series, for The corresponding time node, for The next time point, For the The abnormal pixels are The normalized difference vegetation index.

[0068] In one embodiment of the present invention, when Vegetation yellowing index of abnormal pixels is greater than or equal to the preset vegetation yellowing change index threshold, and the The vegetation yellowing coordinated change index of abnormal pixels If the value is greater than or equal to the preset vegetation yellowing coordinated change index threshold, the abnormal pixel is confirmed to be a grid pixel with abnormal vegetation yellowing, that is, an abnormal vegetation yellowing pixel.

[0069] Step S105: identifying the warning unit with abnormal vegetation status according to the vegetation degradation warning index.

[0070] In a possible implementation, step S105, identifying the warning unit with abnormal vegetation status according to the vegetation degradation warning index, specifically includes: Step S105A, obtaining the vegetation degradation index of each pixel in each warning unit, and obtaining the average vegetation degradation index warning unit of each pixel in each warning unit.

[0071] In a possible implementation manner, obtaining the vegetation degradation index of each pixel in each early warning unit includes: According to the normalized vegetation index at the first time point and the normalized vegetation index at the second time point, the vegetation degradation index of each warning unit is obtained; the first time point is the time point corresponding to when the vegetation degradation index of the pixel in each warning unit is maximum, and the second time point is the next time point of the first time point in the time series.

[0072] Specifically, the normalized vegetation index of each pixel in each warning unit at each time point in the time series is sorted from large to small, and the first time point ranked first is obtained. Normalized Difference Vegetation Index .

[0073] In the embodiment of the present application, in each pixel of each early warning unit, there is a first time point Normalized Difference Vegetation Index , and the second time point Normalized Difference Vegetation Index , the second time point is the next time point of the first time point in the time series.

[0074] In an embodiment of the present invention, the vegetation degradation index of each pixel in each early warning unit is obtained according to the normalized vegetation index at the first time point and the normalized vegetation index at the second time point. .

[0075]

[0076] The vegetation degradation index is used to characterize the degree of decline of the vegetation index of the corresponding early warning unit after the normalized vegetation index reaches its maximum value, reflecting the degree of vegetation degradation of the pixels in the early warning unit.

[0077] Step S105B: obtaining the vegetation degradation warning index of each warning unit according to the vegetation degradation index and the average vegetation degradation index, so as to identify the warning unit with abnormal vegetation status.

[0078] Vegetation degradation early warning index in forest and grassland areas Determined by the following formula:

[0079] is the average value of vegetation degradation index of each pixel in a single early warning unit, is the total number of pixels in a single warning unit, For a single early warning unit Vegetation degradation index of pixels.

[0080] For example, when the vegetation degradation warning index of an early warning unit If the vegetation degradation warning index is greater than or equal to the preset one, There are abnormal vegetation conditions in the early warning units.

[0081] On the contrary, when the vegetation degradation warning index of an early warning unit If the value is less than the preset vegetation degradation warning index, it means that there is no abnormal vegetation state in the warning unit at this time.

[0082] In an embodiment of the present application, when an early warning unit with abnormal vegetation status is identified, or a grid pixel with abnormal vegetation status is identified in a suspected abnormal grid, it indicates that the vegetation in the area has changed from a green growth period to a yellowing period. If the current time period is not the yellowing and falling leaf period of the vegetation in the area, it indicates that the vegetation in the area is abnormally yellow and an early warning needs to be initiated.

[0083] By adopting the above invention, the present invention can achieve at least one of the following beneficial effects: 1. By acquiring remote sensing images of the target area based on time series and focusing specifically on forest and grass areas, this method can accurately capture the long-term dynamic changes of vegetation. By sorting the normalized vegetation index of the early warning unit and comparing adjacent time points, the abnormal state of vegetation can be more effectively identified, providing timely and accurate information for environmental protection and resource management.

[0084] 2. By calculating the vegetation degradation index and vegetation degradation early warning index, this method can quantify the degree and trend of vegetation degradation, providing a scientific basis for the formulation of targeted protection measures. At the same time, according to these indices, early warning units with abnormal vegetation status can be identified, which helps to timely discover and deal with vegetation degradation problems.

[0085] 3. By further dividing the forest and grassland area into multiple grids and screening and identifying vegetation change rate indices at the grid and pixel levels, this method can monitor vegetation changes more carefully and facilitate the discovery of abnormal vegetation conditions in local areas.

[0086] 4. By calculating the grid-level vegetation change rate index based on the normalized vegetation index of each grid pixel in each grid, this method can comprehensively reflect the changing trend of vegetation in the region, help to timely discover the abnormal status of vegetation in the entire region, and provide guidance for regional ecological protection and resource management.

[0087] like Figure 3 FIG. 1 is a schematic diagram of a remote sensing identification device for abnormal vegetation status in a region provided by the present invention, comprising: The region identification module 310 is used to obtain time series remote sensing images of the target area and identify the forest and grass areas in the remote sensing images.

[0088] The area segmentation module 320 is used to segment the forest and grassland area to obtain multiple grids or multiple early warning units.

[0089] The grid identification module 330 is used to identify suspected abnormal grids among the multiple grids, and to identify abnormal pixels in each suspected abnormal grid.

[0090] The pixel identification module 340 is used to identify abnormally yellowed vegetation pixels among the abnormal pixels according to the vegetation yellowing change index and the vegetation yellowing coordinated change index.

[0091] The unit identification module 350 is used to identify the warning units with abnormal vegetation status according to the vegetation degradation warning index.

[0092] In a possible implementation, the unit identification module 350 is specifically used to obtain the vegetation degradation index of each pixel in each warning unit, and obtain the average vegetation degradation index of each pixel in each warning unit; based on the vegetation degradation index and the average vegetation degradation index, the vegetation degradation warning index of each warning unit is obtained to identify the warning units with abnormal vegetation conditions.

[0093] In a possible implementation, the unit identification module 350 is specifically configured to: According to the normalized vegetation index at the first time point and the normalized vegetation index at the second time point, the vegetation degradation index of each early warning unit is obtained; the first time point is the time point corresponding to the maximum value of the vegetation degradation index of the pixel in each early warning unit, and the second time point is the next time point of the first time point in the time series.

[0094] In a possible implementation, the region identification module 310 is specifically configured to: The average normalized vegetation index of each sub-image in the forest and grassland area in the time series is obtained; the crop recognition index of the remote sensing image is obtained according to the average normalized vegetation index of each sub-image in the time series and the normalized vegetation index of each sub-image; the forest and grassland area in the remote sensing image is identified according to the crop recognition index and the average normalized vegetation index.

[0095] In a possible implementation, the grid identification module 330 is specifically configured to: According to the grid-level vegetation change rate index of each grid, suspected abnormal grids are identified from multiple grids. The grid-level vegetation change rate index is obtained according to the normalized vegetation index of each grid pixel in the grid.

[0096] In a possible implementation, the grid identification module 330 is specifically configured to: According to the pixel-level vegetation change rate index of each grid pixel in the suspected abnormal grid, the abnormal pixels in the suspected abnormal grid are identified.

[0097] In a possible implementation, the pixel-level vegetation change rate index is obtained according to the vegetation index of each grid pixel in the suspected abnormal grid, and the vegetation index includes any one or more of the normalized vegetation index, the enhanced vegetation index and the difference vegetation index.

[0098] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communications interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute a remote sensing identification method for abnormal vegetation status in a region, the method comprising: Obtain time series remote sensing images of the target area and identify forest and grass areas in the remote sensing images; Grids establish multiple grids or multiple early warning units in forest and grassland areas; Identify suspected abnormal grids among multiple grids, and identify abnormal pixels in each suspected abnormal grid; According to the vegetation yellowing change index and the vegetation yellowing coordinated change index, the abnormal vegetation yellowing pixels among the abnormal pixels are identified; According to the vegetation degradation warning index, the warning units with abnormal vegetation status are identified.

[0099] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0100] On the other hand, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute a remote sensing identification method for abnormal vegetation status in a region provided by the above methods, the method includes

[0101] Obtain time series remote sensing images of the target area and identify forest and grass areas in the remote sensing images; Grids establish multiple grids or multiple early warning units in forest and grassland areas; Identify suspected abnormal grids among multiple grids, and identify abnormal pixels in each suspected abnormal grid; According to the vegetation yellowing change index and the vegetation yellowing coordinated change index, the abnormal vegetation yellowing pixels among the abnormal pixels are identified; According to the vegetation degradation warning index, the warning units with abnormal vegetation status are identified.

[0102] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform a remote sensing identification method for abnormal vegetation status in a region provided by the above methods, the method comprising: Obtain time series remote sensing images of the target area and identify forest and grass areas in the remote sensing images; Grids establish multiple grids or multiple early warning units in forest and grassland areas; Identify suspected abnormal grids among multiple grids, and identify abnormal pixels in each suspected abnormal grid; According to the vegetation yellowing change index and the vegetation yellowing coordinated change index, the abnormal vegetation yellowing pixels among the abnormal pixels are identified; According to the vegetation degradation warning index, the warning units with abnormal vegetation status are identified.

[0103] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0104] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote sensing identification method for abnormal vegetation status in a region, characterized in that: include: Obtain time series remote sensing images of the target area and identify forest and grass areas in the remote sensing images; The grid establishes a plurality of grids or a plurality of early warning units in the forest and grassland area; Identify suspected abnormal grids among the plurality of grids, and identify abnormal pixels in each of the suspected abnormal grids; Identifying abnormally yellowed vegetation pixels among the abnormal pixels according to the vegetation yellowing change index and the vegetation yellowing coordinated change index; According to the vegetation degradation warning index, the warning unit where the vegetation is abnormal is identified.

2. The remote sensing identification method of regional vegetation abnormality according to claim 1 is characterized in that: The early warning unit for identifying the abnormal state of vegetation according to the vegetation degradation early warning index includes: Obtaining the vegetation degradation index of each pixel in each of the early warning units, and obtaining the average vegetation degradation index of each pixel in each of the early warning units; According to the vegetation degradation index and the average vegetation degradation index, the vegetation degradation warning index of each warning unit is obtained to identify the warning unit with abnormal vegetation status.

3. The remote sensing identification method of regional vegetation abnormality state according to claim 2 is characterized in that: The obtaining of the vegetation degradation index of each pixel in each early warning unit includes: According to the normalized vegetation index at the first time point and the normalized vegetation index at the second time point, the vegetation degradation index of each early warning unit is obtained; the first time point is the time point corresponding to the maximum value of the vegetation degradation index of the pixel in each early warning unit, and the second time point is the next time point of the first time point in the time series.

4. The remote sensing identification method of regional vegetation abnormality state according to claim 1 is characterized in that: The identifying of forest and grass areas in remote sensing images includes: Obtaining the average normalized vegetation index of each sub-image in the forest and grassland area in time series; Obtaining a crop recognition index of the remote sensing image according to an average normalized vegetation index of each sub-image in a time series and a normalized vegetation index of each sub-image; The forest and grass area in the remote sensing image is identified according to the crop identification index and the mean normalized difference vegetation index.

5. The remote sensing identification method of regional vegetation abnormality state according to claim 1 is characterized in that: The step of identifying a suspected abnormal grid among the plurality of grids comprises: The suspected abnormal grid is identified from a plurality of grids according to a grid-level vegetation change rate index of each grid, wherein the grid-level vegetation change rate index is obtained according to a normalized vegetation index of each grid pixel in the grid.

6. The remote sensing identification method of regional vegetation abnormality state according to claim 1 is characterized in that: Identifying abnormal pixels in each of the suspected abnormal grids, including: According to the pixel-level vegetation change rate index of each grid pixel in the suspected abnormal grid, the abnormal pixels in the suspected abnormal grid are identified.

7. The remote sensing identification method of regional vegetation abnormality state according to claim 6 is characterized in that: The pixel-level vegetation change rate index is obtained according to the vegetation index of each grid pixel in the suspected abnormal grid, and the vegetation index includes any one or more of the normalized vegetation index, the enhanced vegetation index and the difference vegetation index.

8. A remote sensing identification device for abnormal vegetation status in a region, characterized in that: include: The region recognition module is used to obtain the time series remote sensing images of the target area and identify the forest and grass areas in the remote sensing images; A region segmentation module is used to establish multiple grids or multiple early warning units in the forest and grassland area; A grid recognition module, used to identify suspected abnormal grids among the plurality of grids, and to identify abnormal pixels in each of the suspected abnormal grids; A pixel identification module, used for identifying abnormally yellowed vegetation pixels among the abnormal pixels according to the vegetation yellowing change index and the vegetation yellowing coordinated change index; The unit identification module is used to identify the warning unit with abnormal vegetation status according to the vegetation degradation warning index.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the remote sensing identification method for abnormal vegetation status in a region as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the remote sensing identification method for abnormal vegetation status in a region as described in any one of claims 1 to 7 is implemented.

Images