Method and device for processing trace remote sensing image under crop cover, and electronic equipment

Abstract

The application provides a crop-covered relic remote sensing image processing method and device and electronic equipment, and belongs to the technical field of computers.The method comprises the following steps: acquiring time series remote sensing images of a target area; calculating the separation degree between a relic site area and a non-relic site area sample based on a vegetation index set and the time series remote sensing images of the target area, and determining a plurality of first vegetation indexes in the vegetation index set; and acquiring integral images corresponding to the plurality of first vegetation indexes based on the plurality of first vegetation indexes and the time series remote sensing images of the target area. The separation degree between the relic site area and the non-relic site area sample is calculated, the plurality of first vegetation indexes suitable for the target area are screened out, and then the integral value difference between the relic site area and the non-relic site area is expanded through integral calculation. The integral images corresponding to the plurality of first vegetation indexes can assist an archaeological staff in efficiently and accurately finding crop marks, and can adapt to relic detection work in crop-covered areas in different environments.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and in particular to a crop-covered site remote sensing image processing method and device and electronic equipment. BACKGROUND

[0002] Ancient sites have been buried under the ground for a long time due to natural and human factors. Especially in the agricultural developed areas, which have been the gathering place of civilization since ancient times, there are a large number of sites, but many of them have been turned into farmland, and a large number of relics are covered under crops, forming extremely weak archaeological features on the ground, which is difficult to identify directly through traditional field archaeological investigation means, and it is difficult to carry out cultural relic survey and protection. When ancient sites are buried under the crop planting area, they will affect the physical characteristics such as the structure or water content of the surrounding soil, thereby interfering with the normal growth of crops. The vegetation index can use the spectral characteristics of vegetation in the visible and near-infrared parts to find crop marks on remote sensing images, that is, vegetation anomaly information corresponding to buried sites, which provides a possibility for using vegetation index to detect sites under crops.

[0003] In related technologies, a single vegetation index is used for site detection, but each type of vegetation index has certain applicability, which makes it difficult to adapt to site detection and archaeological investigation work in different environments through a single vegetation index, and the weak information of sites under crops obtained is relatively limited. SUMMARY

[0004] In view of the problems in the prior art, the embodiments of the present application provide a crop-covered site remote sensing image processing method, device and electronic equipment.

[0005] In a first aspect, the present application provides a crop-covered site remote sensing image processing method, comprising:

[0006] Obtaining time series remote sensing images of a target area, the target area comprising a site area and a plurality of non-site area samples, the non-site area samples being areas around the site area;

[0007] Based on a vegetation index set and the time series remote sensing images of the target area, the separation degree between the site area and the non-site area samples is calculated to determine a plurality of first vegetation indexes suitable for crop mark extraction in the vegetation index set.

[0008] Based on the plurality of first vegetation indexes and the time series remote sensing images of the target area, the integral images corresponding to various first vegetation indexes are obtained through vegetation index time series integral calculation.

[0009] Optionally, the present application further provides a method for processing remote sensing images of ruins under crop cover, which comprises the following steps:

[0010] Based on the preset condition and the time series remote sensing images of the target region, a plurality of second vegetation indexes satisfying the preset condition are screened out from the set of vegetation indexes.

[0011] For each second vegetation index, based on the time series remote sensing images of the target region, the separation degree between the ruin site and each non-ruin site sample is statistically analyzed to determine the separation degree statistical index of each second vegetation index.

[0012] Based on the separation degree statistical index of each second vegetation index, a plurality of first vegetation indexes are determined from the plurality of second vegetation indexes.

[0013] The preset condition comprises that the vegetation index value is greater than 0 and the vegetation index value of the same position in the ruin site is less than the vegetation index value of the non-ruin site sample.

[0014] Optionally, the present application further provides a method for processing remote sensing images of ruins under crop cover, which comprises the following steps:

[0015] Based on the third vegetation index and the time series remote sensing images of the target region, the separation degree between the ruin site and each non-ruin site sample is analyzed to determine a plurality of separation degree values, and the third vegetation index is any one of the plurality of second vegetation indexes.

[0016] Based on the plurality of separation degree values, the separation degree statistical index of the third vegetation index is determined by calculating the average value; or, based on the plurality of separation degree values, the separation degree statistical index of the third vegetation index is determined by screening the minimum value.

[0017] Optionally, the present application further provides a method for processing remote sensing images of ruins under crop cover, which comprises the following steps:

[0018] Based on the separation degree statistical index of each second vegetation index, the separation degree statistical index is sorted in descending order according to the separation degree statistical index.

[0019] Determine the plurality of first vegetation indexes based on the top N second vegetation indexes in the sorting of the separation statistical indicators, where N is an integer and N is greater than 1.

[0020] Optionally, the present application further provides a crop-covered trace remote sensing image processing method, which comprises the following steps of:

[0021] Processing the time-series remote sensing images of the target area based on the first vegetation index to obtain the vegetation index time-series image corresponding to the first vegetation index for each first vegetation index;

[0022] Integrating the vegetation index based on the vegetation index time-series image corresponding to the first vegetation index to obtain the integral image corresponding to the first vegetation index.

[0023] Optionally, the present application further provides a crop-covered trace remote sensing image processing method, which comprises the following steps of:

[0024] Normalizing the integral image corresponding to each first vegetation index to obtain the normalized integral image corresponding to each first vegetation index;

[0025] Determining the integral image weight coefficient corresponding to each first vegetation index by calculating the separation average value of the image based on the normalized integral image corresponding to each first vegetation index;

[0026] Performing weighted calculation based on the normalized integral image corresponding to each first vegetation index and the integral image weight coefficient to obtain the crop mark distribution map of the target area.

[0027] Optionally, the present application further provides a crop-covered trace remote sensing image processing method, which comprises the following steps of:

[0028] Performing grid color segmentation processing on the integral image corresponding to each first vegetation index according to the vegetation index time-series integral value based on a plurality of integral intervals to obtain the color-enhanced integral image corresponding to each first vegetation index, and the color configuration corresponding to each integral interval is different from each other.

[0029] Optionally, the present application also provides a method for processing a remote sensing image of a site under crop cover, before determining a plurality of first vegetation indices suitable for crop mark extraction from a set of vegetation indices based on a time series of remote sensing images of a target area, the method further comprises:

[0030] generating a plurality of first random points in the target area by randomly generating points;

[0031] determining a target buffer zone based on the site and a buffer distance;

[0032] selecting the plurality of first random points based on the target buffer zone to determine a plurality of second random points;

[0033] determining the plurality of non-site area samples based on the plurality of second random points.

[0034] In a second aspect, the present application also provides a device for processing a remote sensing image of a site under crop cover, comprising:

[0035] a first obtaining module configured to obtain a time series of remote sensing images of a target area, the target area comprising a site and a plurality of non-site area samples, the non-site area samples being areas around the site;

[0036] a determining module configured to determine a plurality of first vegetation indices suitable for crop mark extraction from a set of vegetation indices based on the time series of remote sensing images of the target area and the set of vegetation indices by calculating a separation degree between the site and the non-site area samples;

[0037] a second obtaining module configured to obtain integral images corresponding to the plurality of first vegetation indices by vegetation index time series integral calculation based on the plurality of first vegetation indices and the time series of remote sensing images of the target area.

[0038] In a third aspect, the present application 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 executes the program to implement any of the above-mentioned methods for processing a remote sensing image of a site under crop cover.

[0039] The application provides a crop-covered site remote sensing image processing method and device and electronic equipment, which can filter out a plurality of first vegetation indexes suitable for a target region from a vegetation index set by analyzing the separation degree between a site area and a non-site area sample based on time sequence remote sensing images of the target region for various vegetation indexes in the vegetation index set, and then can expand the vegetation index integral value difference between the site area and the non-site area by vegetation index time sequence integral calculation based on the plurality of first vegetation indexes and the time sequence remote sensing images of the target region, so that the plurality of first vegetation indexes respectively corresponding to integral images can assist an archaeologist in efficiently and accurately finding crop marks, analyzing the distribution direction of potential sites in an unexcavated site area, and reducing the detection range of underground sites, and the method can adapt to site detection and archaeological investigation work in crop-covered areas in different environments. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0041] Figure 1 is one of the flowcharts of the crop-covered site remote sensing image processing method provided by the application;

[0042] Figure 2 is another flowchart of the crop-covered site remote sensing image processing method provided by the application;

[0043] Figure 3 is a third flowchart of the crop-covered site remote sensing image processing method provided by the application;

[0044] Figure 4 is a fourth flowchart of the crop-covered site remote sensing image processing method provided by the application;

[0045] Figure 5 is a fifth flowchart of the crop-covered site remote sensing image processing method provided by the application;

[0046] Figure 6 is a sixth flowchart of the crop-covered site remote sensing image processing method provided by the application;

[0047] Figure 7 is a seventh flowchart of the crop-covered site remote sensing image processing method provided by the application;

[0048] Figure 8Fig. 8 is a flowchart of a method for processing a remote sensing image of a site under crop cover according to the present application;

[0049] Figure 9 Fig. 1 is a schematic diagram of a structure of a device for processing a remote sensing image of a site under crop cover according to the present application;

[0050] Figure 10 Fig. 1 is a schematic diagram of a structure of a device for processing a remote sensing image of a site under crop cover according to the present application; DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below with reference to the drawings of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0052] Figure 1 Fig. 1 is a schematic diagram of a structure of a device for processing a remote sensing image of a site under crop cover according to the present application; Figure 1 As shown in Fig. 1, the execution subject of the method for processing a remote sensing image of a site under crop cover can be an electronic device, such as a server, etc. The method comprises the following steps.

[0053] In step 101, time series remote sensing images of a target region are acquired, the target region comprising a site region and a plurality of non-site region samples, the non-site region samples being regions around the site region.

[0054] Specifically, the target region can comprise a known site region, a plurality of non-site region samples can be selected in the target region, the non-site region samples being regions around the site region, and time series remote sensing images of the target region can be acquired by collecting remote sensing images at a plurality of time instants within a target time period (e.g., one year, two years, or three years, etc.) for the target region, i.e., the time series remote sensing images comprise remote sensing images at a plurality of time instants.

[0055] It can be understood that, by analyzing and processing the time series remote sensing images of the target region, the advantages of long-period earth observation of remote sensing images can be fully utilized (avoiding the use of a single or a small number of time-phase vegetation indices), the influences of different phenological periods on the formation of crop vegetation marks can be reflected, key crop growth anomaly information can be extracted, and the accuracy of site detection can be improved.

[0056] In step 102, a plurality of first vegetation indices suitable for crop mark extraction are determined in a set of vegetation indices by calculating the separation degree between the site region and the non-site region samples based on the set of vegetation indices and the time series remote sensing images of the target region.

[0057] Specifically, the vegetation index set includes a plurality of vegetation indexes. After obtaining the time-series remote sensing images of the target region, the separation between the site area and the non-site area samples is analyzed based on the time-series remote sensing images of the target region for various vegetation indexes in the vegetation index set, and a plurality of first vegetation indexes suitable for crop marker extraction of the target region can be screened out from the vegetation index set.

[0058] Optionally, the separation between the site area and the non-site area can be analyzed by the following separation formula to quantify the ability evaluation of the vegetation index for site detection:

[0059] VI contrast = [(VI n.a.a. / max VI n.a.a.p.c. )-(VI a.a. / max VI a.a.p.c. )]x100.

[0060] Where VI contrast is the separation value, VI n.a.a. is the average vegetation index of the non-site area sample, max VI n.a.a.p.c. is the maximum vegetation index of the non-site area sample, VI a.a. is the average vegetation index of the site area, and max VI a.a.p.c. is the maximum vegetation index of the site area.

[0061] Step 103, based on the plurality of first vegetation indexes and the time-series remote sensing images of the target region, the integral images corresponding to the various first vegetation indexes are obtained by vegetation index time-series integral calculation.

[0062] Specifically, after determining the plurality of first vegetation indexes, the vegetation index time-series integral calculation can be used based on the plurality of first vegetation indexes and the time-series remote sensing images of the target region to expand the vegetation index integral value difference between the site area and the non-site area. The integral images corresponding to the plurality of first vegetation indexes can assist the archaeologists to efficiently and accurately find the abnormal vegetation markers.

[0063] Optionally, the time-series integral of the vegetation index can reflect the growth of the crops in different time periods, and the combination of the crop phenological information can highlight the biomass difference between the vegetation, expand the vegetation index integral value difference between the site area and the non-site area, and thus highlight the vegetation markers, making them more easily identifiable on the integral images. The time-series integral formula of the vegetation index is:

[0064]

[0065] Wherein, the TVI is an integral value corresponding to VI, VI is a vegetation index, t1 is a starting time of a time series, and t2 is a termination time of the time series.

[0066] It can be understood that the vegetation index is more applied in agriculture and environment, but the application in the field of archaeology is still relatively less. Various vegetation indexes commonly used in various fields can be collected into a vegetation index set, and then the vegetation indexes in the vegetation index set can be systematically analyzed for a specific target area, so as to screen out effective vegetation indexes in a typical environment. Through the calculation mode of image integration, the archaeological information on the long time series image can be integrated, so as to realize effective enhancement of the information of the relics covered by vegetation, improve the accuracy of weak information detection, and provide an effective technical means for cultural relic survey and field archaeological investigation in crop coverage area.

[0067] The crop-covered relic remote sensing image processing method provided by the application can screen out a plurality of first vegetation indexes suitable for the target area in the vegetation index set by analyzing the separation degree between the site area and the non-site area sample based on the time series remote sensing image of the target area for various vegetation indexes in the vegetation index set, and then the time series integral calculation of the vegetation index can be performed based on the plurality of first vegetation indexes and the time series remote sensing image of the target area to enlarge the difference in the integral value of the vegetation index between the site area and the non-site area. The plurality of first vegetation indexes respectively corresponding to the integral image can assist the archaeologists to efficiently and accurately find the crop marks, analyze the distribution direction of the potential relics in the unexcavated site area, reduce the detection range of the underground site, and adapt to the relic detection and archaeological investigation work in the crop coverage area in different environments.

[0068] Optionally, according to the crop-covered relic remote sensing image processing method provided by the application, the plurality of first vegetation indexes suitable for crop mark extraction are determined in the vegetation index set based on the vegetation index set and the time series remote sensing image of the target area by calculating the separation degree between the site area and the non-site area sample, and the method comprises the following steps:

[0069] Based on the preset condition and the time series remote sensing image of the target area, a plurality of second vegetation indexes satisfying the preset condition are screened out in the vegetation index set;

[0070] For various second vegetation indexes, based on the time series remote sensing image of the target area, the separation degree between the site area and each non-site area sample is statistically analyzed, and the separation degree statistical index of each second vegetation index is determined;

[0071] Based on the separation degree statistical index of various second vegetation indexes, a plurality of first vegetation indexes are determined in the plurality of second vegetation indexes;

[0072] The preset condition comprises: a vegetation index value is greater than 0 and a vegetation index value of the same position in the site area is less than a vegetation index value of the non-site area sample.

[0073] Specifically, Figure 2 is a flowchart of a method for processing a remote sensing image of a site under crop coverage provided by the present application, as shown in Figure 2 The method for processing a remote sensing image of a site under crop coverage comprises steps 201 to 205.

[0074] In step 201, time series remote sensing images of a target area are acquired.

[0075] In step 202, based on a preset condition and the time series remote sensing images of the target area, a plurality of second vegetation indices that satisfy the preset condition are selected from a set of vegetation indices.

[0076] It can be understood that, according to the separation degree formula, if the vegetation index value is less than or equal to 0, the value will be incorrect, that is, the vegetation index must be greater than 0 during the phenological period of all crops (limiting condition 1); and according to the separation degree formula, if the vegetation index of the site area is greater than the vegetation index of the non-site area, the value will be calculated as a negative number, so this type of vegetation index also needs to be removed (limiting condition 2). The vegetation indices in the set of vegetation indices can be selected according to the above limiting conditions (i.e., the preset condition) to determine the plurality of second vegetation indices.

[0077] In step 203, for each second vegetation index, based on the time series remote sensing images of the target area, the separation degrees between the site area and each non-site area sample are statistically analyzed to determine a separation degree statistical index of each second vegetation index.

[0078] For example, the plurality of non-site area samples can include a first non-site area sample, a second non-site area sample, and a third non-site area sample. For a certain second vegetation index, the process of statistically analyzing the separation degrees between the site area and each non-site area sample can include analyzing a first separation degree between the site area and the first non-site area sample, analyzing a second separation degree between the site area and the second non-site area sample, and analyzing a third separation degree between the site area and the third non-site area sample, and statistically analyzing the first separation degree, the second separation degree, and the third separation degree to obtain the separation degree statistical index of the second vegetation index.

[0079] In step 204, based on the separation degree statistical index of each second vegetation index, a plurality of first vegetation indices are determined from the plurality of second vegetation indices.

[0080] It can be understood that, by comparing the separation degree statistical indexes of the various second vegetation indices, a plurality of first vegetation indices suitable for the target area can be selected from the plurality of second vegetation indices.

[0081] In step 205, based on the time series remote sensing images of the target region and the plurality of first vegetation indexes, the integral images corresponding to the plurality of first vegetation indexes are obtained through vegetation index time series integral calculation.

[0082] Therefore, through the above-mentioned preset conditions, the first screening of the vegetation index can be performed, the second screening of the vegetation index can be performed through the comparison of the separation degree statistical indexes of the plurality of second vegetation indexes, and the plurality of first vegetation indexes suitable for the target region can be screened out from the vegetation index set through the two screenings, so that the effective vegetation index is selected for site detection, and the success rate of extracting the site information under the crop coverage can be improved.

[0083] Optionally, according to the crop coverage site remote sensing image processing method provided by the application, the separation degrees between the site area and each non-site area sample are statistically analyzed based on the time series remote sensing images of the target region, and the separation degree statistical indexes of the plurality of second vegetation indexes are determined, including:

[0084] The separation degrees between the site area and each non-site area sample are analyzed based on the third vegetation index and the time series remote sensing images of the target region, and a plurality of separation degree values are determined, the third vegetation index being any one of the plurality of second vegetation indexes.

[0085] Based on the plurality of separation degree values, the separation degree statistical index of the third vegetation index is determined through the statistical method of calculating the average value, or the separation degree statistical index of the third vegetation index is determined through the statistical method of screening the minimum value based on the plurality of separation degree values.

[0086] Specifically, Figure 3 is a third flowchart of the crop coverage site remote sensing image processing method provided by the application, as shown in Figure 3 The crop coverage site remote sensing image processing method includes steps 301 to 307.

[0087] In step 301, the time series remote sensing images of the target region are obtained.

[0088] In step 302, based on the preset conditions and the time series remote sensing images of the target region, a plurality of second vegetation indexes meeting the preset conditions are screened out from the vegetation index set.

[0089] In step 303, one third vegetation index is selected from the plurality of second vegetation indexes, the separation degrees between the site area and each non-site area sample are analyzed based on the third vegetation index and the time series remote sensing images of the target region, and a plurality of separation degree values are determined.

[0090] Step 304, based on the plurality of separation values, determining a separation statistical index of the third vegetation index by a target statistical method.

[0091] Optionally, the target statistical method can be a statistical method of calculating an average value or a statistical method of screening a minimum value.

[0092] Step 305, judging whether the plurality of second vegetation indexes have been statistically analyzed, if yes, executing step 306, and if not, executing step 303.

[0093] Step 306, determining a plurality of first vegetation indexes from the plurality of second vegetation indexes based on the separation statistical indexes of the second vegetation indexes.

[0094] Step 307, based on the plurality of first vegetation indexes and the time series remote sensing image of the target area, obtaining integral images corresponding to the first vegetation indexes by vegetation index time series integral calculation.

[0095] It can be understood that after determining the plurality of second vegetation indexes, the influence of the selection of the sample on the separation value of the vegetation index can be analyzed, the separation statistical index corresponding to each second vegetation index can be determined by the target statistical method, and the vegetation index can be screened by comparing the separation statistical indexes of the second vegetation indexes, so as to screen the plurality of first vegetation indexes suitable for the target area, select effective vegetation indexes for site detection, and improve the success rate of extracting site information under crop coverage.

[0096] Optionally, according to the crop coverage under the site remote sensing image processing method provided by the application, the plurality of first vegetation indexes are determined from the plurality of second vegetation indexes based on the separation statistical indexes of the second vegetation indexes, and the method comprises the following steps of:

[0097] Based on the separation statistical indexes of the second vegetation indexes, the separation statistical index sorting is determined according to the sorting mode from large to small of the separation statistical indexes.

[0098] Based on the first N second vegetation indexes in the separation statistical index sorting, the plurality of first vegetation indexes are determined, and N is an integer, and N is greater than 1.

[0099] Specifically, Figure 4 is a fourth flowchart of the crop coverage under the site remote sensing image processing method provided by the application, as Figure 4 shown, the crop coverage under the site remote sensing image processing method comprises steps 401 to 406.

[0100] Step 401, obtaining a time series remote sensing image of a target area.

[0101] At step 402, based on the preset condition and the time sequence remote sensing image of the target region, a plurality of second vegetation indexes satisfying the preset condition are screened out from the set of vegetation indexes.

[0102] At step 403, for each second vegetation index, based on the time sequence remote sensing image of the target region, the separation degree between the site area and each non-site area sample is statistically analyzed to determine a separation degree statistical index of each second vegetation index.

[0103] At step 404, based on the separation degree statistical index of each second vegetation index, a separation degree statistical index ranking is determined according to the order from large to small of the separation degree statistical index.

[0104] At step 405, based on the first N second vegetation indexes in the separation degree statistical index ranking, a plurality of first vegetation indexes are determined.

[0105] For example, if N is equal to 2, the first two second vegetation indexes in the separation degree statistical index ranking can be selected as the plurality of first vegetation indexes; for example, if N is equal to 3, the first three second vegetation indexes in the separation degree statistical index ranking can be selected as the plurality of first vegetation indexes, for example, if N is equal to 5, the first five second vegetation indexes in the separation degree statistical index ranking can be selected as the plurality of first vegetation indexes, and so on.

[0106] It can be understood that selecting the first N second vegetation indexes in the separation degree statistical index ranking as the plurality of first vegetation indexes can ensure that the most suitable vegetation index for the target region is screened out, and selecting the effective vegetation index for site detection can improve the success rate of extracting the information of the site under the crop cover.

[0107] Optionally, for the plurality of first vegetation indexes, the information entropy of the known site area can be calculated to evaluate the remote sensing image corresponding to each first vegetation index.

[0108] At step 406, based on the plurality of first vegetation indexes and the time sequence remote sensing image of the target region, an integral image corresponding to each first vegetation index is obtained through vegetation index time sequence integral calculation.

[0109] Optionally, according to the crop cover under the site remote sensing image processing method provided by the application, the integral image corresponding to each first vegetation index is obtained through vegetation index time sequence integral calculation based on the plurality of first vegetation indexes and the time sequence remote sensing image of the target region, which includes:

[0110] For each first vegetation index, the time sequence remote sensing image of the target region is processed based on the first vegetation index to obtain a vegetation index time sequence image corresponding to the first vegetation index.

[0111] Based on the vegetation index time series image corresponding to the first vegetation index, the integral image corresponding to the first vegetation index is obtained by integral calculation on the vegetation index.

[0112] Specifically, Figure 5 is a flowchart of the fifth method for processing the remote sensing image of the site under crop coverage provided by the application, as shown in Figure 5 The method for processing the remote sensing image of the site under crop coverage comprises steps 501 to 505.

[0113] Step 501: Obtain the time series remote sensing image of the target area.

[0114] Step 502: Based on the vegetation index set and the time series remote sensing image of the target area, determine a plurality of first vegetation indexes in the vegetation index set by calculating the separation degree between the site area and the non-site area samples.

[0115] Step 503: Select a first vegetation index from the plurality of first vegetation indexes, and process the time series remote sensing image of the target area based on the first vegetation index to obtain the vegetation index time series image corresponding to the first vegetation index.

[0116] Step 504: Based on the vegetation index time series image corresponding to the first vegetation index, the integral image corresponding to the first vegetation index is obtained by integral calculation on the vegetation index.

[0117] Step 505: Determine whether the integral images corresponding to various first vegetation indexes have been obtained, if yes, end, if not, execute step 503.

[0118] It can be understood that by integral calculation on the vegetation index, the difference in vegetation index integral value between the site area and the non-site area can be expanded, and the plurality of first vegetation indexes correspond to integral images, which can assist the archaeologists to efficiently and accurately find the abnormal vegetation marks.

[0119] Optionally, according to the method for processing the remote sensing image of the site under crop coverage provided by the application, after the integral images corresponding to various first vegetation indexes are obtained by integral calculation on the vegetation index time series based on the plurality of first vegetation indexes and the time series remote sensing image of the target area, the method further comprises:

[0120] Based on the integral images corresponding to various first vegetation indexes, the normalized integral images corresponding to various first vegetation indexes are obtained by normalization processing;

[0121] Based on the normalized integral images corresponding to various first vegetation indexes, the integral image weight coefficients corresponding to various first vegetation indexes are determined by calculating the average value of the separation degree of the image;

[0122] Based on the normalized integral image corresponding to various first vegetation indices and the integral image weight coefficient, weighted calculation is performed to obtain the crop mark distribution map of the target region.

[0123] Specifically, the integral images corresponding to various first vegetation indices can be normalized and the integral image weight coefficient can be determined, and then the integral images corresponding to various first vegetation indices can be weighted calculated to obtain the crop mark distribution map of the target region. By fusing the crop mark distribution maps obtained by the integral images corresponding to various first vegetation indices, the archeological personnel can efficiently analyze the range of the excavated underground site according to the existing archeological report and vegetation mark integral interval, and predict the possibility and approximate range of the unexcavated site.

[0124] Optionally, according to the crop-covered relic remote sensing image processing method provided by the application, after the integral images corresponding to various first vegetation indices are obtained by the vegetation index time series integral calculation based on the plurality of first vegetation indices and the time series remote sensing image of the target region, the method further comprises:

[0125] Based on the plurality of integral intervals, the integral images corresponding to various first vegetation indices are subjected to grid color segmentation processing according to the vegetation index time series integral value, color-enhanced integral images corresponding to various first vegetation indices are obtained, and the color configurations corresponding to each integral interval are different from each other.

[0126] Specifically, Figure 6 is a flowchart of the crop-covered relic remote sensing image processing method provided by the application, as shown in Figure 6 The crop-covered relic remote sensing image processing method comprises steps 601 to 604.

[0127] Step 601: Obtain the time series remote sensing image of the target region.

[0128] Step 602: Based on the vegetation index set and the time series remote sensing image of the target region, the plurality of first vegetation indices are determined in the vegetation index set by calculating the separation degree between the site area and the non-site area sample.

[0129] Step 603: Based on the plurality of first vegetation indices and the time series remote sensing image of the target region, the integral images corresponding to various first vegetation indices are obtained by vegetation index time series integral calculation.

[0130] Step 604: Based on the plurality of integral intervals, the integral images corresponding to various first vegetation indices are subjected to grid color segmentation processing according to the vegetation index time series integral value, color-enhanced integral images corresponding to various first vegetation indices are obtained, and the color configurations corresponding to each integral interval are different from each other.

[0131] It can be understood that, by using the grid color segmentation processing, the grid color segmentation interval is refined, the vegetation sign is more likely to be exposed, the effect of using the vegetation index to detect the site is enhanced, and the archeological personnel can efficiently analyze the range of the excavated underground site according to the existing archeological report and the vegetation sign interval, and predict the possibility and the approximate range of the unexcavated site.

[0132] Optionally, according to the crop-covered site remote sensing image processing method provided by the present application, before determining a plurality of first vegetation indexes suitable for crop sign extraction in the vegetation index set based on the vegetation index set and the time sequence remote sensing image of the target area, the method further comprises:

[0133] generating a plurality of first random points in the target area by randomly generating points;

[0134] determining a target buffer zone based on the site area and the buffer distance;

[0135] screening the plurality of first random points based on the target buffer zone to determine a plurality of second random points;

[0136] determining the plurality of non-site area samples based on the plurality of second random points.

[0137] Specifically, Figure 7 is a seventh flowchart of the crop-covered site remote sensing image processing method provided by the present application, as shown in Figure 7 the crop-covered site remote sensing image processing method comprises steps 701 to 707.

[0138] Step 701, acquiring a time sequence remote sensing image of a target area.

[0139] Step 702, generating a plurality of first random points in the target area by randomly generating points.

[0140] Step 703, determining a target buffer zone based on the site area and the buffer distance.

[0141] For example, if the buffer distance is 100 m, a buffer zone with a known site range of 100 m can be added.

[0142] Step 704, screening the plurality of first random points based on the target buffer zone to determine a plurality of second random points.

[0143] Step 705, determining a plurality of non-site area samples based on the plurality of second random points.

[0144] At step 706, based on the set of vegetation indices and the time series remote sensing images of the target region, a plurality of first vegetation indices are determined in the set of vegetation indices by calculating the separation degree between the site area and the non-site area samples.

[0145] At step 707, based on the plurality of first vegetation indices and the time series remote sensing images of the target region, integral images corresponding to the plurality of first vegetation indices are obtained by vegetation index time series integral calculation.

[0146] It can be understood that by making a buffer zone of the known site area (for example, increasing the buffer zone of the known site area by 100m) and deleting random points in the buffer zone, the accuracy of selecting non-site area samples can be improved, and a plurality of non-site area samples under the same climate at the same latitude as the target region can be obtained.

[0147] Optionally, the following takes a new fort site in a winter wheat planting area as an example to evaluate the trace detection capability of a plurality of vegetation indices using the site area and non-site area separation degree formula, and to enhance the difference between the site area and the non-site area using the vegetation index time series integral formula. Figure 8 is the eighth flowchart of the crop-covered trace remote sensing image processing method provided by the present application, as shown in Figure 8 The crop-covered trace remote sensing image processing method includes steps 801 to 806.

[0148] At step 801, time series remote sensing images of a study area (i.e. a target region) within a year are collected.

[0149] Optionally, the time series remote sensing images can be preprocessed to enhance the resolution of the images.

[0150] At step 802, a set of vegetation indices is determined.

[0151] Optionally, a plurality of vegetation indices can be selected from the following 18 vegetation indices to construct the vegetation index set: (1) Enhanced Vegetation Index (EVI); (2) Green NDVI; (3) Normalized Difference Vegetation Index (NDVI); (4) Simple Ratio (SR); (5) Modified Simple Ratio (MSR); (6) Modified Triangular Vegetation Index (MTVI2); (7) Renormalized Difference Vegetation Index (RDVI); (8) PVI; (9) RVI; (10) Improved Transformed Soil-Adjusted Vegetation Index (TSAVI); (11) Modified Soil-Adjusted Vegetation Index (MSAVI); (12) Atmospherically Resistant Vegetation Index (ARVI); (13) Global Environment Monitoring Index (GEMI); (14) Soil and Atmospherically Resistant Vegetation Index (SARVI); (15) Optimized Soil-Adjusted Vegetation Index (OSAVI); (16) Difference Vegetation Index (DVI); (17) Simple Ratio Combined with Normalized Vegetation Index (SR NDVI); and (18) Soil-Adjusted Vegetation Index (SAVI).

[0152] (1) The Enhanced Vegetation Index (EVI) can be determined by the following formula:

[0153] VI1=2.5(ρ NIR -ρ red ) / (ρ NIR ×6×ρ red -7.5ρ blue +1);

[0154] wherein VI1represents the Enhanced Vegetation Index, ρ NIR represents the reflectivity of the near-infrared band, ρ red represents the reflectivity of the red light band, and ρ blue represents the reflectivity of the blue light band.

[0155] (2) Green Normalized Difference Vegetation Index (Green NDVI) can be determined by the following formula:

[0156] VI2 = (p NIR - p green ) / (p NlR + p green );

[0157] wherein VI2 represents the Green Normalized Difference Vegetation Index, p NIR represents the reflectance of the near-infrared band, and p green represents the reflectance of the green band.

[0158] (3) Normalized Difference Vegetation Index (NDVI) can be determined by the following formula:

[0159] VI3 = (p NIR - p red ) / (p NIR + p red );

[0160] wherein VI3 represents the Normalized Difference Vegetation Index, p NIR represents the reflectance of the near-infrared band, and p red represents the reflectance of the red band.

[0161] (4) Simple Ratio Vegetation Index (SR) can be determined by the following formula:

[0162] VI4 = p NIR / p red ;

[0163] wherein VI4 represents the Simple Ratio Vegetation Index, p NIR represents the reflectance of the near-infrared band, and p red represents the reflectance of the red band.

[0164] (5) Modified Simple Ratio Vegetation Index (MSR) can be determined by the following formula:

[0165] VI5 = p red / (p NIR / p red + 1) 0.5 ;

[0166] wherein VI5 represents the Modified Simple Ratio Vegetation Index, p red represents the reflectance of the red band, and p NIE represents the reflectance of the near-infrared band.

[0167] (6) Modified Triangular Vegetation Index (MTVI2) can be determined by the following formula:

[0168] VI6 = [1.5(1.2*(p NIE - p green )-2.5(p red - p green )] / [(2p NIR +1) 2 -(6p NIR -5p red 0.5 )-0.5] 0.5 ;

[0169] wherein VI6 represents the improved triangular vegetation index, p NIR represents the reflectivity of the near-infrared band, p green represents the reflectivity of the green light band, and p red represents the reflectivity of the red light band.

[0170] (7) The Renormalized Difference Vegetation Index (RDVI) can be determined by the following formula:

[0171] VI7 = (p NIR - p red ) / (p NIR + p red ) 0.5 ;

[0172] wherein VI7 represents the Renormalized Difference Vegetation Index, p NIR represents the reflectivity of the near-infrared band, and p red represents the reflectivity of the red light band.

[0173] (8) The Perpendicular Vegetation Index (PVI) can be determined by the following formula:

[0174] VI8 = (p NIR - a p red - b) / (1 + a 2 );

[0175] a = p NIR,soil , b = p red,soil ;

[0176] wherein VI8 represents the Perpendicular Vegetation Index, p NIR represents the reflectivity of the near-infrared band, p red represents the reflectivity of the red light band, p NIR,soil represents the near-infrared band soil reflectivity, and p red,soil represents the red band soil reflectivity.

[0177] (9) The Ratio Vegetation Index (RVI) can be determined by the following formula:

[0178] VI9 = p red / pNIR ;

[0179] where VI9 represents a ratio vegetation index, p red represents reflectance in the red band, p NIR represents reflectance in the near infrared band.

[0180] (10) The modified transformed soil adjusted vegetation index (TSAVI) can be determined by the following equation:

[0181] VI10 = [a(p NIR -a p red -b)] / [(p red +a p NIR -ab + 0.08(1 + a 2 ))] ;

[0182] a = p NIR,soil , b = p red,soil ;

[0183] where VI10 represents a modified transformed soil adjusted vegetation index, p NIR represents reflectance in the near infrared band, p red represents reflectance in the red band, p NIR,soil represents near infrared band soil reflectance, p red,soil represents red band soil reflectance.

[0184] (11) The modified soil adjusted vegetation index (MSAVI) can be determined by the following equation:

[0185] VI11 = [2 p NiR +1-[(2 p NIR +1) 2 -8(p Nir -p red )] 0.5 ] / 2;

[0186] where VI11 represents a modified soil adjusted vegetation index, p NIr represents reflectance in the near infrared band, p red represents reflectance in the red band.

[0187] (12) The atmospheric resistance vegetation index (ARVI) can be determined by the following equation:

[0188] VI12 = (p NIR -p rb ) / (p NIR +p rb );

[0189] p rb = p red- y(p blue - p red ) ;

[0190] where VI12represents an atmospheric resistance vegetation index, p NIR represents reflectance in the near-infrared band, p red represents reflectance in the red band, p blue represents reflectance in the blue band, and y represents a correction factor (e.g., can have a value of 1.0).

[0191] (13) A global environment monitoring index (GEMI) can be determined by the following equation:

[0192] VI13= n(l - 0.25n)(p red - 0.125) / (l - p red ) ;

[0193] n = [2(p NIR 2 - p red 2 ) + 1.5p NIR + 0.5p red ] / (p NIR + p red + 0.5) ;

[0194] where VI13represents a global environment monitoring index, p red represents reflectance in the red band, and p NIR represents reflectance in the near-infrared band.

[0195] (14) A soil and atmosphere resistance vegetation index (SARVI) can be determined by the following equation:

[0196] VI14= (1 + 0.5)(p NIR - p rb ) / (p NIR + p rb + 0.5) ;

[0197] p rb = p red - y(p blue - p red ) ;

[0198] where VI14represents a soil and atmosphere resistance vegetation index, p NIR represents reflectance in the near-infrared band, p red represents reflectance in the red band, p blue represents reflectance in the blue band, and y represents a correction factor (e.g., can have a value of 1.0).

[0199] (15) Optimized soil adjusted vegetation index (OSAVI) can be determined by the following formula:

[0200] VI15 = (p NIR - p red ) / (p NIR + p red + 0.16);

[0201] wherein VI15 represents the optimized soil adjusted vegetation index, p NIR represents the reflectance of the near-infrared band, and p red represents the reflectance of the red light band.

[0202] (16) Difference vegetation index (DVI) can be determined by the following formula:

[0203] VI16 = p NIR - p red ;

[0204] wherein VI16 represents the difference vegetation index, p NIR represents the reflectance of the near-infrared band, and p red represents the reflectance of the red light band.

[0205] (17) Simple ratio combined normalized difference vegetation index (SR NDVI) can be determined by the following formula:

[0206] VI17 = (p NIR 2 - p red ) / (p NIR + p red 2 );

[0207] wherein VI17 represents the simple ratio combined normalized difference vegetation index, p NIR represents the reflectance of the near-infrared band, and p red represents the reflectance of the red light band.

[0208] (18) Soil adjusted vegetation index (SAVI) can be determined by the following formula:

[0209] VI18 = (p NIR - p red ) / (p NIR + p red + L) x (1 + L);

[0210] wherein VI18 represents the soil adjusted vegetation index, p NIR represents the reflectance of the near-infrared band, and p redThe reflectivity in the red light band, L is the soil brightness correction factor (for example, the value can be 0.5), and represents the green vegetation coverage.

[0211] It can be understood that, by systematically evaluating and experimentally verifying the archaeological exploration ability of the common 18 vegetation indices, exploring the effective method of archaeological exploration in the planting area, an effective technical means can be provided for field archaeological investigation.

[0212] Step 803: Determine the site area and a plurality of non-site area samples.

[0213] Specifically, the non-site area samples can be initially selected by randomly generating points, a known site area buffer zone (for example, a buffer zone with a known site range of 100 m is added) is made, and then the random points in the buffer zone are deleted to improve the accuracy of the selection of the non-site area samples, thereby obtaining a plurality of non-site area samples (for example, three non-site area samples) in the same latitude and under the same climate as the research area.

[0214] Step 804: Screen the vegetation indices in the vegetation index set by calculating the separation degree of the site area and the selected non-site area samples, and determine at least one first vegetation index.

[0215] Specifically, as can be seen from the above separation degree formula, if the winter wheat vegetation index value is less than or equal to 0, the value will be incorrect, which means that there are still requirements for the selection of the vegetation index, that is, the vegetation index of the winter wheat must be greater than 0 during all the winter wheat phenological periods (limiting condition 1); and as can be seen from the above separation degree formula, if the winter wheat vegetation index of the site area is greater than the winter wheat vegetation index of the non-site area, the value will be calculated as a negative number, so this type of vegetation index also needs to be removed (limiting condition 2). The vegetation indices in the vegetation index set can be screened according to the above limiting conditions to determine a plurality of second vegetation indices.

[0216] Specifically, after determining the plurality of second vegetation indices, the influence of the selection of the samples on the separation degree value of the vegetation index can be analyzed, the separation degree statistical index corresponding to each second vegetation index is determined according to the target statistical method (for example, a statistical method of calculating the average value or a statistical method of screening the minimum value, etc.), and then at least one first vegetation index can be selected from the plurality of second vegetation indices according to the order from high to low of the separation degree statistical index.

[0217] For example, three vegetation indices with the top three separation degree statistical indexes can be selected from the plurality of second vegetation indices according to the order from high to low of the separation degree statistical index.

[0218] It can be understood that, by using the separation degree formula of the site area and the non-site area, the ability of the vegetation index to detect underground relics can be quantified, the number of vegetation indices selected in traditional research can be expanded, and the effect of using vegetation indices for relic detection can be enhanced.

[0219] Step 805: Based on at least one first vegetation index and time series remote sensing images of the study area, the integral images corresponding to various first vegetation indexes are obtained by vegetation index time series integral calculation.

[0220] Specifically, each first vegetation index time series image can be calculated according to the above-mentioned vegetation index time series integral formula to become a corresponding integral image.

[0221] Step 806: Based on a plurality of integral intervals, each integral image is subjected to grid color segmentation processing.

[0222] Specifically, a plurality of integral intervals can be divided, and each of the plurality of integral intervals can be configured with a color, and the colors corresponding to each of the plurality of integral intervals are different from each other.

[0223] It can be understood that by using grid color segmentation processing and refining the grid color segmentation interval, the vegetation mark can be more easily exposed, thereby enhancing the effect of using vegetation index for trace detection, and assisting the archaeologists in efficiently analyzing the range of the excavated underground site according to the existing archaeological report and the vegetation mark integral interval, and predicting the possibility and approximate range of the unexcavated site.

[0224] It can be understood that most studies use the conventional normalized difference vegetation index (NDVI) for trace detection under crops, but the distribution range of the trace is wide, and the occurrence climate environment is complex, and a single vegetation index is not suitable for trace detection in different environments. The crop-covered trace remote sensing image processing method provided by the present application can select effective vegetation indexes for site detection from a plurality of vegetation indexes, which can improve the success rate of extracting trace information under crops, and assist the archaeologists in efficiently and accurately analyzing the position of the unexcavated site in the study area from the result map, and reducing the range of detecting underground sites.

[0225] The crop-covered trace remote sensing image processing device provided by the present application will be described below. The crop-covered trace remote sensing image processing device described below can be correspondingly referred to the crop-covered trace remote sensing image processing method described above.

[0226] Figure 9 is a structural schematic diagram of the crop-covered trace remote sensing image processing device provided by the present application, as Figure 9 shown, the device comprises a first acquisition module 901, a determination module 902 and a second acquisition module 903, wherein:

[0227] The first acquisition module 901 is configured to acquire time sequence remote sensing images of a target region, the target region comprising a site area and a plurality of non-site area samples, the non-site area samples being areas around the site area;

[0228] The determination module 902 is configured to determine a plurality of first vegetation indexes suitable for crop mark extraction in the set of vegetation indexes by calculating a separation degree between the site area and the non-site area samples based on the set of vegetation indexes and the time sequence remote sensing images of the target region.

[0229] The second acquisition module 903 is configured to acquire integral images corresponding to the plurality of first vegetation indexes by vegetation index time sequence integral calculation based on the plurality of first vegetation indexes and the time sequence remote sensing images of the target region.

[0230] The crop-covered site remote sensing image processing device provided by the application can filter a plurality of first vegetation indexes suitable for the target region in the set of vegetation indexes by the determination module based on the time sequence remote sensing images of the target region for various vegetation indexes in the set of vegetation indexes, and then the second acquisition module can perform integral calculation based on the plurality of first vegetation indexes and the time sequence remote sensing images of the target region to expand the vegetation index integral value difference between the site area and the non-site area, so that the plurality of first vegetation indexes corresponding to the integral images can assist the archeologists to efficiently and accurately find crop marks, analyze the distribution direction of potential sites in the unexcavated site area, and reduce the detection range of the underground site, and the crop-covered site remote sensing image processing device can adapt to site detection and archeological investigation work in different environments.

[0231] Figure 10 is a structural schematic diagram of an electronic device provided by the application, as Figure 10 shown, the electronic device can include: a processor 1010, a communications interface 1020, a memory 1030 and a communications bus 1040, wherein the processor 1010, the communications interface 1020, the memory 1030 complete mutual communication through the communications bus 1040. The processor 1010 can invoke the logical instructions in the memory 1030 to execute the crop-covered site remote sensing image processing method, the method comprising:

[0232] Acquiring time sequence remote sensing images of a target region, the target region comprising a site area and a plurality of non-site area samples, the non-site area samples being areas around the site area;

[0233] Based on a set of vegetation indexes and time-series remote sensing images of the target region, a plurality of first vegetation indexes suitable for crop mark extraction are determined in the set of vegetation indexes by calculating the separation degree between the site area and the non-site area samples.

[0234] Based on the plurality of first vegetation indexes and the time-series remote sensing images of the target region, integral images corresponding to the various first vegetation indexes are obtained through vegetation index time-series integral calculation.

[0235] In addition, the logical instructions in the memory 1030 described above can be implemented in the form of a software function unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0236] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which is executed by a processor to implement the crop-covered site remote sensing image processing method provided by the above-mentioned methods, the method comprising:

[0237] Obtaining time-series remote sensing images of a target region, the target region including a site area and a plurality of non-site area samples, the non-site area samples being areas around the site area;

[0238] Based on a set of vegetation indexes and time-series remote sensing images of the target region, a plurality of first vegetation indexes suitable for crop mark extraction are determined in the set of vegetation indexes by calculating the separation degree between the site area and the non-site area samples;

[0239] Based on the plurality of first vegetation indexes and the time-series remote sensing images of the target region, integral images corresponding to the various first vegetation indexes are obtained through vegetation index time-series integral calculation.

[0240] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0241] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0242] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing remote sensing images of relics under crop cover, characterized in that, include: Acquire time-series remote sensing images of a target area, which includes archaeological sites and multiple non-archaeological site samples, wherein the non-archaeological site samples are the areas surrounding the archaeological sites. Based on the vegetation index set and the time-series remote sensing images of the target area, by calculating the separation degree between samples from the archaeological site area and non-archaeological site area, a variety of first vegetation indices suitable for crop marker extraction are determined in the vegetation index set. Based on the various first vegetation indices and the time-series remote sensing images of the target area, the integrated images corresponding to the various first vegetation indices are obtained by calculating the time-series integration of the vegetation indices. The time-series remote sensing imagery of the target area, based on a set of vegetation indices and the target area, determines several first vegetation indices suitable for crop marker extraction from the set of vegetation indices by calculating the separation between samples from the archaeological site area and non-archaeological site area, including: Based on preset conditions and time-series remote sensing images of the target area, multiple second vegetation indices that meet the preset conditions are selected from the set of vegetation indices. For various second vegetation indices, based on the time-series remote sensing images of the target area, the separation degree between the samples of the archaeological site area and each non-archaeological site area is statistically analyzed to determine the separation degree statistical index of various second vegetation indices. Based on the separation statistics of various second vegetation indices, a variety of first vegetation indices are determined among the various second vegetation indices. The preset conditions include: the vegetation index value is greater than 0 and the vegetation index value of the same location in the archaeological site is less than the vegetation index value of the sample in the non-archaeological site area.

2. The method for processing remote sensing images of relics under crop cover according to claim 1, characterized in that, The method involves statistically analyzing the separation degree between samples from the archaeological site and various non-archaeological site areas based on time-series remote sensing images of the target region for various second vegetation indices, and determining the separation degree statistical indicators for various second vegetation indices, including: Based on the third vegetation index and the time-series remote sensing images of the target area, the separation degree between the samples of the archaeological site and each non-archaeological site is analyzed, and multiple separation degree values ​​are determined. The third vegetation index is any one of the multiple second vegetation indices. Based on the multiple separation values, the separation statistical index of the third vegetation index is determined by calculating the average value; or, based on the multiple separation values, the separation statistical index of the third vegetation index is determined by selecting the minimum value.

3. The method for processing remote sensing images of relics under crop cover according to claim 1, characterized in that, The separation statistic based on various second vegetation indices determines various first vegetation indices from among the various second vegetation indices, including: Based on the separation statistics of various second vegetation indices, the separation statistics are ranked from largest to smallest. Based on the top N second vegetation indices in the separation statistic ranking, the various first vegetation indices are determined, where N is an integer and is greater than 1.

4. The method for processing remote sensing images of relics under crop cover according to claim 1, characterized in that, The method, based on the various first vegetation indices and the time-series remote sensing images of the target area, obtains integrated images corresponding to various first vegetation indices through time-series integration calculation of vegetation indices, including: For various first vegetation indices, based on the first vegetation index, the time series remote sensing images of the target area are processed to obtain the vegetation index time series images corresponding to the first vegetation index. Based on the vegetation index time series image corresponding to the first vegetation index, the integrated image corresponding to the first vegetation index is obtained by integrating the vegetation index.

5. The method for processing remote sensing images of relics under crop cover according to any one of claims 1-4, characterized in that, After obtaining the integrated images corresponding to each of the various first vegetation indices by integrating the vegetation index time series remote sensing images based on the multiple first vegetation indices and the target area, the method further includes: Based on the integral images corresponding to various first vegetation indices, normalization processing is performed to obtain normalized integral images corresponding to various first vegetation indices. Based on the normalized integral images corresponding to various first vegetation indices, the weight coefficients of the integral images corresponding to various first vegetation indices are determined by calculating the average separation of the images. Based on the normalized integral images and integral image weight coefficients corresponding to various first vegetation indices, a weighted calculation is performed to obtain the crop indicator distribution map of the target area.

6. The method for processing remote sensing images of relics under crop cover according to any one of claims 1-4, characterized in that, After obtaining the integrated images corresponding to each of the various first vegetation indices by integrating the vegetation index time series remote sensing images based on the multiple first vegetation indices and the target area, the method further includes: Based on multiple integration intervals, the integrated images corresponding to various first vegetation indices are processed by raster color segmentation according to the time series integrated values ​​of vegetation indices to obtain color-enhanced integrated images corresponding to various first vegetation indices. The color configurations corresponding to each integration interval are different.

7. The method for processing remote sensing images of relics under crop cover according to any one of claims 1-4, characterized in that, Before determining multiple first vegetation indices suitable for crop marker extraction from the vegetation index set by calculating the separation degree between samples from the archaeological site area and non-archaeological site areas based on the time-series remote sensing imagery of the target area, the method further includes: Multiple first random points are generated within the target area by randomly generating points; Based on the site area and buffer distance, determine the target buffer zone; Based on the target buffer, the plurality of first random points are filtered to determine a plurality of second random points; Based on the multiple second random points, the multiple non-archival area samples are determined.

8. A remote sensing image processing device for relics under crop cover, characterized in that, include: The first acquisition module is used to acquire time-series remote sensing images of a target area, the target area including a site area and multiple non-site area samples, the non-site area samples being the area surrounding the site area; The determination module is used to determine, based on the vegetation index set and the time-series remote sensing image of the target area, multiple first vegetation indices suitable for crop marker extraction from the vegetation index set by calculating the separation degree between samples from the archaeological site area and non-archaeological site area; The second acquisition module is used to acquire integrated images corresponding to various first vegetation indices based on the multiple first vegetation indices and the time series remote sensing images of the target area by calculating the vegetation index time series integral. The time-series remote sensing imagery of the target area, based on a set of vegetation indices and the target area, determines several first vegetation indices suitable for crop marker extraction from the set of vegetation indices by calculating the separation between samples from the archaeological site area and non-archaeological site area, including: Based on preset conditions and time-series remote sensing images of the target area, multiple second vegetation indices that meet the preset conditions are selected from the set of vegetation indices. For various second vegetation indices, based on the time-series remote sensing images of the target area, the separation degree between the samples of the archaeological site area and each non-archaeological site area is statistically analyzed to determine the separation degree statistical index of various second vegetation indices. Based on the separation statistics of various second vegetation indices, a variety of first vegetation indices are determined among the various second vegetation indices. The preset conditions include: the vegetation index value is greater than 0 and the vegetation index value of the same location in the archaeological site is less than the vegetation index value of the sample in the non-archaeological site area.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the remote sensing image processing method for traces under crop cover as described in any one of claims 1 to 7.

Images