A method and device for determining a ring target based on a remote sensing image

Abstract

The application discloses a method and device for determining a ring-shaped target based on a remote sensing image, and an algorithm for automatically identifying a ring-shaped target based on a remote sensing image. A candidate ring-shaped target is obtained, and a difference between a spectral average of the candidate ring-shaped target and a spectral average of a ring-shaped target sample is compared. If the difference is less than or equal to a preset spectral threshold, the candidate ring-shaped target is extracted as an archaeological ring-shaped target, so that the archaeological ring-shaped target can be automatically and accurately identified and extracted based on the remote sensing image.

Description

Technical Field

[0001] This application relates to the field of remote sensing archaeology technology, and in particular to a method and apparatus for determining ring targets based on remote sensing images. Background Technology

[0002] With the rapid development of remote sensing technology, remote sensing images have been widely used in research in various fields. In the current field of archaeological research, obtaining basic information about archaeological ring targets such as tombs from remote sensing images is one of the most important objectives of current remote sensing archaeological research.

[0003] Currently, obtaining basic information about archaeological targets from remote sensing images is mostly achieved through manual visual interpretation and computer-automated interpretation. Manual visual interpretation involves personnel directly observing or using interpretation instruments to acquire information about specific target features on remote sensing images. Computer-automated interpretation involves identifying and classifying the attributes of information in remote sensing images, recognizing the actual features corresponding to the image information, and extracting feature information. However, manual visual interpretation requires comprehensive intervention from archaeological researchers in image preparation, processing, and interpretation. Computer-automated interpretation, on the other hand, requires researchers to pre-determine which features are archaeological targets on the remote sensing images. Both methods still require significant manual intervention from professional archaeological researchers, consuming substantial time, manpower, and resources. Summary of the Invention

[0004] This application provides a method and apparatus for determining circular targets based on remote sensing images. It designs an algorithm for automatic identification and extraction of archaeological circular targets, reduces the intervention of archaeological researchers, and achieves the effect of automatically and accurately identifying and extracting real archaeological circular targets from remote sensing images.

[0005] In a first aspect, this application provides a method for determining a ring target based on remote sensing images, the method comprising:

[0006] The first image is sequentially processed using image morphology, edge detection, and circular algorithm detection to obtain the second image. The second image includes the curve of at least one candidate circular target. The first image is a preprocessed image of an archaeological remote sensing image that includes a circular target.

[0007] The average spectral value of the ring target sample in the first image is obtained, and the average spectral value of the third image is obtained within the curve range of each candidate ring target in the second image of the at least one candidate ring target.

[0008] If the spectral average value of the third image matches the spectral average value of the ring target sample, then the candidate ring target corresponding to the third image is determined to be an archaeological ring target.

[0009] Optionally, matching the spectral average value of the third image with the spectral average value of the annular target sample includes: the difference between the spectral average value of the third image and the spectral average value of the annular target sample is less than or equal to a preset spectral threshold.

[0010] Optionally, obtaining the spectral average value of the ring-shaped target sample in the first image includes:

[0011] At least one circular target belonging to the archaeological circular target is obtained from the first image, as a circular target sample;

[0012] The average spectral value of at least one annular target sample is obtained by statistically analyzing the spectral value of the annular target sample using spatial analysis methods.

[0013] Optionally, obtaining the spectral average of the third image for each candidate ring target within the curve range of at least one candidate ring target in the second image includes:

[0014] Obtain the third image corresponding to each candidate ring target in the second image;

[0015] The average spectral value of the third image corresponding to each candidate ring target is obtained by statistically analyzing the spatial analysis method.

[0016] Optionally, the method further includes:

[0017] Obtain the remote sensing images acquired by the sensor;

[0018] The remote sensing image is preprocessed to obtain the first image. The preprocessing operations include radiometric calibration, atmospheric correction and geometric correction.

[0019] Optionally, the first image is subjected to image morphological processing, edge detection, and circular algorithm detection in sequence to obtain the second image, including:

[0020] The first image is subjected to image morphology processing to obtain an enhanced image;

[0021] Edge information is extracted from the enhanced image using an edge detection algorithm to obtain an edge image;

[0022] The feature information of at least one candidate ring target in the edge image is extracted according to the circle detection algorithm, and a circular curve is drawn according to the feature information of at least one candidate ring target to obtain a second image. The feature information of at least one candidate ring target includes the center and radius of the candidate ring target.

[0023] Optionally, after determining that the candidate circular target corresponding to the third image is an archaeological circular target, the method further includes:

[0024] A fourth image is obtained, which is the image after the archaeological ring target is marked in the first image.

[0025] Secondly, this application provides an apparatus for determining ring targets based on remote sensing images, the apparatus comprising:

[0026] The first processing unit is used to sequentially perform image morphological processing, edge detection, and circular algorithm detection on the first image to obtain a second image. The second image includes the curve of at least one candidate circular target. The first image is a preprocessed image of an archaeological remote sensing image including a circular target.

[0027] The first obtaining unit is used to obtain the spectral average value of the ring target sample in the first image, and to obtain the spectral average value of the third image within the curve range of each candidate ring target in the second image, which is at least one candidate ring target.

[0028] The second processing unit determines the candidate ring target corresponding to the third image as an archaeological ring target if the average spectral value of the third image matches the average spectral value of the ring target sample.

[0029] Optionally, the second processing unit is specifically used for:

[0030] Calculate the difference between the spectral average of the third image and the spectral average of the ring target sample.

[0031] If the difference is less than or equal to the preset spectral threshold, then the candidate ring target corresponding to the third image is an archaeological ring target.

[0032] Optionally, the first obtaining unit is specifically used for:

[0033] At least one ring-shaped target belonging to the archaeological ring-shaped target is obtained from the first image as a ring-shaped target sample. The spectral average value of the at least one ring-shaped target sample is statistically analyzed according to the spatial analysis method to obtain the spectral average value of the ring-shaped target sample.

[0034] Obtain the third image corresponding to each candidate ring target in the second image, and statistically analyze the spectral average value of the third image corresponding to each candidate ring target using spatial analysis methods to obtain the spectral average value corresponding to that candidate ring target.

[0035] Optionally, the device further includes:

[0036] The third processing unit is used to preprocess the remote sensing images acquired by the sensor to obtain the first image.

[0037] Optionally, the first processing unit is specifically used for:

[0038] The first image is subjected to image morphology processing to obtain an enhanced image; edge information of the enhanced image is extracted according to an edge detection algorithm to obtain an edge image; feature information of at least one candidate ring target in the edge image is extracted according to a circle detection algorithm, and a circular curve is drawn according to the feature information of at least one candidate ring target to obtain the second image.

[0039] Optionally, the device further includes:

[0040] The second acquisition unit is used to acquire the image after the archaeological ring target is marked in the first image as the fourth image.

[0041] Thirdly, this application provides a device for determining ring targets based on remote sensing images, the device including a memory and a processor:

[0042] Memory is used to store computer programs;

[0043] The processor is used to execute the method provided in the first aspect above according to the computer program.

[0044] Fourthly, this application also provides a computer-readable storage medium for storing a computer program for performing the method provided in the first aspect above.

[0045] Therefore, this application has the following beneficial effects:

[0046] This application provides a method and apparatus for identifying circular targets based on remote sensing images. The method uses a circular target recognition algorithm to identify candidate circular targets in the remote sensing image. By comparing the spectral average value of the candidate circular targets with the spectral average value of a sample circular target, the candidate circular targets are extracted as archaeological circular targets. The technical solution of this application extracts candidate circular targets from the remote sensing image through image morphological processing, edge detection operators, and circle detection algorithms. Then, it obtains the spectral average value of the circular target sample and the spectral average value of the candidate circular targets. Finally, it compares the spectral average value of the circular target sample with the spectral average value within the curve range of the candidate circular target. If the spectral average value within the curve range of the candidate circular target matches the spectral average value of a circular target sample clearly identified as an archaeological target, then the candidate circular target is determined to be an archaeological target. This achieves automatic identification and extraction of archaeological circular targets from remote sensing images, reduces the intervention of archaeological researchers, and provides highly consistent identification results. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0048] Figure 1 This is a flowchart illustrating a method for determining a ring target based on remote sensing images in an embodiment of this application.

[0049] Figure 2 This is a schematic diagram of the edge image extracted by a method for determining a ring target based on remote sensing images in an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of an archaeological ring target image extracted by a method for determining ring targets based on remote sensing images in an embodiment of this application.

[0051] Figure 4 This is a flowchart illustrating an embodiment of a method for determining a ring target based on remote sensing images, as described in this application.

[0052] Figure 5 This is a schematic diagram of the structure of a device 500 for determining a ring target based on remote sensing images in an embodiment of this application;

[0053] Figure 6 This is a schematic diagram of the structure of a device 600 for determining a ring target based on remote sensing images, as described in an embodiment of this application. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] In the embodiments of this application, the word "first" in names such as "first processing unit" and "first obtaining unit" is only used for name identification and does not represent the first in order. This rule also applies to "second," "third," etc.

[0056] Currently, in the field of remote sensing archaeology, research on the baseline information (size, location, and structure) of circular archaeological targets, both domestically and internationally, mainly focuses on visual interpretation or human-computer interactive interpretation of multi-source remote sensing images. However, manual visual interpretation requires comprehensive intervention from archaeological researchers in image preparation, image processing, and image interpretation. Computer interpretation also requires archaeological researchers to pre-determine which parts of the remote sensing image are archaeological sites during the computer interpretation process. These research methods all require extensive manual intervention from archaeological researchers in obtaining information about circular archaeological targets, consuming significant time, manpower, and resources.

[0057] In this embodiment, the method for determining ring targets based on remote sensing images first performs image morphological processing, edge detection, and circular algorithm detection on a first image to obtain a second image including candidate ring target curves. Then, it obtains the spectral average value of the ring target samples and the spectral average value of a third image within the curve range of at least one candidate ring target in the second image. Finally, if the spectral average value of the third image matches the spectral average value of the ring target samples, the candidate ring target corresponding to the third image is determined to be an archaeological ring target. Specifically, this method may include: obtaining a first image based on a remote sensing image through image preprocessing; obtaining a second image containing at least one candidate ring target by sequentially performing image morphological processing, edge detection, and circular algorithm detection on the first image; obtaining the spectral average value of the ring target samples based on the first image using image processing and spatial analysis methods; obtaining the spectral average value of a third image within the curve range of at least one candidate ring target in the second image based on the second image using spatial analysis methods; determining whether the difference between the spectral average value of the third image and the spectral average value of the ring target samples is less than or equal to a preset spectral threshold; if the difference is less than or equal to the preset spectral threshold, the candidate ring target corresponding to the third image is determined to be an archaeological ring target. The method provided in this application can automatically identify and extract archaeological ring targets from remote sensing images by comparing the magnitude relationship between the spectral average value of the ring target sample and the spectral average value within the curve range of the candidate ring target, thereby reducing the intervention of archaeological researchers.

[0058] To facilitate understanding of the specific implementation of the method for determining ring targets based on remote sensing images provided in the embodiments of this application, the following description will be provided in conjunction with the accompanying drawings.

[0059] It should be noted that the main body implementing the method for determining ring targets based on remote sensing images can be the device for determining ring targets based on remote sensing images provided in the embodiments of this application. This device for determining ring targets based on remote sensing images can be carried in an electronic device or a functional module of an electronic device. The electronic device in the embodiments of this application can be any device capable of implementing the method for determining ring targets based on remote sensing images in the embodiments of this application, such as an Internet of Things (IoT) device.

[0060] Figure 1 This is a flowchart illustrating a method for determining a ring target based on remote sensing images, provided as an embodiment of this application. This method can be applied to an apparatus for determining a ring target based on remote sensing images, such as... Figure 5 The illustrated device 500 for determining ring targets based on remote sensing images, or the device for determining ring targets based on remote sensing images, may also be integrated into... Figure 6 The functional modules in the device 600 for determining ring targets based on remote sensing images are shown.

[0061] like Figure 1 As shown, the method includes the following steps:

[0062] S101: Perform image morphological processing, edge detection, and circular algorithm detection sequentially on the first image to obtain a second image. The second image includes the curve of at least one candidate circular target. The first image is a preprocessed image of an archaeological remote sensing image including a circular target.

[0063] Remote sensing images typically refer to images acquired by satellite sensors. Due to their macroscopic, objective, and convenient nature, remote sensing images have been applied in various research fields, such as archaeology. In this application's embodiments, the remote sensing image refers to an image acquired from an archaeological scene. The first image can be an image obtained after preprocessing the remote sensing image of the archaeological scene. Preprocessing operations can include, but are not limited to, one or more of radiometric calibration, atmospheric correction, and geometric correction. For example, if the sensor includes a function to perform atmospheric correction on the acquired remote sensing image, then the preprocessing operation of the device for determining linear targets based on the remote sensing image may not include atmospheric correction.

[0064] Currently, in the field of archaeological research, remote sensing images are also used to obtain information on ring-shaped targets such as tombs. To enable computers to automatically obtain ring-shaped archaeological targets, the method provided in this application first obtains the spectral average value of a ring-shaped target sample on a first image and extracts candidate ring-shaped targets from the remote sensing image. Then, the spectral average value within the curve range of the candidate ring-shaped targets is obtained. By determining whether the spectral average value within the curve range of each candidate ring-shaped target matches the spectral average value of the ring-shaped target sample, if the spectral average value within the curve range of the candidate ring-shaped target matches the spectral average value of the ring-shaped target sample, then the candidate ring-shaped target is determined to be an archaeological ring-shaped target. Therefore, this application embodiment obtains candidate ring-shaped targets through algorithmic operations in step S101, providing a prerequisite for subsequently obtaining the spectral average value of the candidate ring-shaped targets.

[0065] As an example, S101 may include: S1011, performing image morphological processing on the first image to reduce noise, improve image contrast, and enhance the circular edge features in the image to obtain an enhanced image; S1012, extracting edge information from the enhanced image according to an edge detection algorithm, removing some irrelevant interference and useless information from the enhanced image to obtain an edge image; S1013, extracting feature information of at least one candidate circular target in the edge image according to a circular detection algorithm, and drawing a circular curve based on the feature information of the at least one candidate circular target to obtain the second image.

[0066] In step S1013, drawing a circular curve based on the feature information of the at least one candidate annular target may, for example, include: for the at least one candidate annular target, drawing a circular curve using a computer-aided circle drawing algorithm based on the feature information of each candidate annular target to obtain a second image. The feature information of the at least one candidate annular target includes the center and radius of the candidate annular target.

[0067] S102: Obtain the spectral average value of the ring target sample in the first image, and obtain the spectral average value of the third image within the curve range of each candidate ring target of the at least one candidate ring target in the second image.

[0068] As an example, obtaining the spectral average value of the ring-shaped target sample in the first image in S102 can include: one case, obtaining a ring-shaped target belonging to the archaeological ring-shaped target from the first image through visual interpretation, as the ring-shaped target sample, and statistically analyzing the spectral average value of the pixels within the ring-shaped target sample according to spatial analysis methods, as the spectral average value of the ring-shaped target sample in S102; another case, obtaining multiple ring-shaped targets belonging to the archaeological ring-shaped target from the first image through visual interpretation, as multiple ring-shaped target samples, and statistically analyzing the spectral average value of the pixels within each of the multiple ring-shaped target samples according to spatial analysis methods, and then calculating the average of the spectral average values ​​of the multiple ring-shaped target samples as the spectral average value of the ring-shaped target sample in S102.

[0069] As an example, obtaining the spectral average value of the third image within the curve range of each candidate ring target in the second image in S102 may include: obtaining a third image containing each candidate ring target based on the second image, and statistically analyzing the spectral average value of the third image corresponding to each candidate ring target according to a spatial analysis method to obtain the spectral average value corresponding to the candidate ring target.

[0070] S103: If the spectral average value of the third image matches the spectral average value of the ring target sample, then the candidate ring target corresponding to the third image is determined to be an archaeological ring target.

[0071] The average spectral value of the third image matches the average spectral value of the ring target sample. For example, the difference between the average spectral value of the third image and the average spectral value of the ring target sample may be less than or equal to a preset spectral threshold.

[0072] In some implementations, after determining that the candidate circular target corresponding to the third image is an archaeological circular target, the archaeological circular target is displayed on the third image to obtain the fourth image.

[0073] It should be noted that the method provided in this application embodiment can be understood as a model for determining circular targets based on remote sensing images. Therefore, when a first image is input into this model, the model outputs a fourth image, which includes the archaeological circular targets present in the first image. For example, Figure 2 The first image shown is input into the model for determining the circular target based on remote sensing images. The output fourth image can be found in [reference needed]. Figure 3 As shown.

[0074] As can be seen, the method of this application embodiment obtains candidate ring targets based on remote sensing images and an algorithm for automatic identification of ring targets. By comparing the difference between the spectral average value of the candidate ring target and the spectral average value of the ring target sample, if the difference is less than or equal to a preset spectral threshold, the candidate ring target is extracted as an archaeological ring target. This achieves accurate identification and extraction of archaeological ring targets from remote sensing images. Furthermore, the method has a high degree of automation and high accuracy in identification results.

[0075] To make the methods provided in the embodiments of this application clearer and easier to understand, the following is combined with... Figure 4 A specific example of this method is then provided.

[0076] S401: Acquire raw remote sensing images.

[0077] The acquired raw remote sensing image can be a high-resolution image of the area corresponding to the archaeological ring target, showing a clear sky with less than 10% cloud cover. The image can be captured at any time of year, and each pixel in the image corresponds to an area of ​​0.09 square meters (m²). 2 )~1m 2 The preferred value is 0.09m 2 ~0.25m 2 .

[0078] As an example, S401 may include: acquiring multi-band high-resolution remote sensing images of the study area taken by the Worldview-2 satellite, and obtaining multispectral image data with a resolution of 2 meters (m) in the four bands of blue light, green light, red light, and near infrared, and panchromatic image data with a resolution of 0.5 meters.

[0079] S402: Preprocess the original remote sensing image to obtain a first image.

[0080] To improve the accuracy of identifying and extracting ring targets, it is necessary to preprocess the original remote sensing images.

[0081] As an example, S402 may include: firstly, performing radiometric correction (including radiometric calibration and atmospheric correction) on the multispectral and panchromatic data of WV-2 image data using the atmospheric radiative transfer 6S model, wherein the preferred radiometric calibration method is the formula: L(λ)=Gain·DN+Bias, where L(λ) is the radiance value at the sensor entrance pupil, Gain is the gain coefficient, DN is the observed gray value, and Bias is the bias coefficient; then, performing geometric correction on the Worldview-2 image data using a regional network adjustment model; then, performing orthorectification and other processing on the Worldview-2 image data using the collected ground control points; finally, using the Gram-Schmidt algorithm, performing image fusion of multispectral and panchromatic data to obtain color fusion data with a resolution of 0.5m in four bands: blue, green, red, and near-infrared.

[0082] S403: Obtain a ring target sample belonging to an archaeological ring target based on the first image.

[0083] S404: Obtain the average spectral value of the ring-shaped target sample.

[0084] S405: Perform image morphological processing on the first image to obtain an enhanced image.

[0085] In order to preserve the edge information of the first image while filtering out noise, image morphology processing is required.

[0086] As an example, S405 may include: when processing the first image using the top-hat-bottom-hat joint transformation, not only taking into account the difference in grayscale between the image background and the foreground, but also their similarity in grayscale, and adaptively performing morphological processing on the image through a nonlinear combination of the two.

[0087] S406: Extract the edge information of the enhanced image according to the edge detection algorithm to obtain the edge image.

[0088] As an example, S406 may include: performing edge information detection on the enhanced image using an improved Canny operator to obtain an edge image. Specific steps include: S4061, smoothing the image using a Gaussian filter to suppress noise; S4062, using the Sobel operator as the gradient operator to calculate the gradient components G of each pixel in the image along the x and y directions. x and G y This allows us to obtain the gradient magnitude at each point. and direction θ(x,y)=arctan(G y / G xS4063, perform non-maximum suppression on the gradient magnitude, detect the maximum point of the gradient magnitude along the gradient direction angle, take the maximum point as the edge point, and set the pixel gray value to 0; S4064, adaptively determine the non-maximum suppression threshold of the Canny operator according to the gradient magnitude histogram of the image, and use the non-maximum suppression threshold to perform non-maximum suppression on the image to obtain the edge feature image; S4065, scan the edge feature image, when encountering a non-zero gray value pixel p(x,y), trace the contour line starting from p(x,y) until the end of the contour line to obtain the edge image.

[0089] S407: Extract feature information of candidate ring targets in the edge image according to the circular detection algorithm, and draw a circular curve according to the feature information of the candidate ring targets to obtain a second image.

[0090] As an example, S407 may include: obtaining Hough peak points indicating ring features in the edge image based on the CHT transform circular detection algorithm, calculating (x,y) using the (a,b,r) coordinates of the peak points and drawing the circular curve of the corresponding candidate ring target, thereby realizing the identification and extraction of ring targets.

[0091] S408: Obtain the spectral average of the third image within the curve range of each candidate ring target in the second image.

[0092] S409: Calculate the difference between the spectral average value of the third image and the spectral average value of the ring target sample.

[0093] To distinguish archaeological ring targets from other ring targets in remote sensing images, it is necessary to determine whether the spectral average value is within a certain range. Therefore, it is necessary to calculate the difference between the spectral average value of the third image and the spectral average value of the ring target sample.

[0094] S410: If the difference is less than or equal to a preset spectral threshold, then the candidate ring target corresponding to the third image is extracted as an archaeological ring target, and a fourth image is obtained.

[0095] The preset spectral threshold can be flexibly set according to the attributes of the remote sensing image.

[0096] As an example, S410 may include: extracting the candidate circular targets corresponding to the third image as archaeological circular targets and displaying them in red, then the circular targets displayed in red on the fourth image are archaeological circular targets.

[0097] Based on remote sensing images and an algorithm for automatic identification of circular targets, candidate circular targets are obtained. By comparing the difference between the spectral average of the candidate circular target and the spectral average of the circular target sample, if the difference is less than or equal to a preset spectral threshold, the candidate circular target is extracted as an archaeological circular target. This achieves accurate identification and extraction of archaeological circular targets from remote sensing images. Furthermore, this method has a high degree of automation and high accuracy in identification results.

[0098] This application provides a method for determining ring targets based on remote sensing images. The method involves preprocessing the acquired remote sensing images to obtain a first image; obtaining ring target samples belonging to archaeological ring targets and their spectral average values ​​based on the first image; then, performing image morphological processing, edge detection, and circularity detection based on the first image to obtain a second image; obtaining the spectral average value of a third image within the curve range of at least one candidate ring target based on the second image; finally, calculating the difference between the spectral average value of the third image and the spectral average value of the ring target samples. If the difference is less than or equal to a preset spectral threshold, the candidate ring target corresponding to the third image is an archaeological ring target, and this archaeological ring target is marked in the first image, thereby obtaining a fourth image.

[0099] This application's embodiments have designed an algorithm for the automatic identification and extraction of archaeological circular targets, which enables remote sensing archaeological exploration and investigation to have a high degree of automation, thereby reducing the need for intervention by archaeological researchers and achieving the goal of automatically identifying and extracting archaeological circular targets based on remote sensing images, with high accuracy of the identification results.

[0100] See Figure 5 This application provides an apparatus 500 for determining a ring target based on remote sensing images. The apparatus 500 includes:

[0101] The first processing unit 501 is used to sequentially perform image morphological processing, edge detection and circular algorithm detection on the first image to obtain a second image. The second image includes the curve of at least one candidate circular target. The first image is a preprocessed image of an archaeological remote sensing image including a circular target.

[0102] The first obtaining unit 502 is used to obtain the spectral average value of the ring target sample in the first image, and to obtain the spectral average value of the third image within the curve range of each candidate ring target in the second image, which is at least one candidate ring target.

[0103] The second processing unit 503 is used to determine the candidate ring target corresponding to the third image as an archaeological ring target if the spectral average value of the third image matches the spectral average value of the ring target sample.

[0104] Optionally, the second processing unit 503 is specifically used for:

[0105] Calculate the difference between the spectral average of the third image and the spectral average of the ring target sample.

[0106] If the difference is less than or equal to the preset spectral threshold, then the candidate ring target corresponding to the third image is an archaeological ring target.

[0107] Optionally, the first obtaining unit 502 is specifically used for:

[0108] At least one ring-shaped target belonging to the archaeological ring-shaped target is obtained from the first image as a ring-shaped target sample. The spectral average value of the at least one ring-shaped target sample is statistically analyzed according to the spatial analysis method to obtain the spectral average value of the ring-shaped target sample.

[0109] Obtain the third image corresponding to each candidate ring target in the second image, and statistically analyze the spectral average value of the third image corresponding to each candidate ring target using spatial analysis methods to obtain the spectral average value corresponding to that candidate ring target.

[0110] Optionally, the device 500 further includes:

[0111] The third processing unit is used to preprocess the remote sensing images acquired by the sensor to obtain the first image.

[0112] Optionally, the first processing unit 501 is specifically used for:

[0113] The first image is subjected to image morphology processing to obtain an enhanced image; edge information of the enhanced image is extracted according to the edge detection algorithm to obtain an edge image; feature information of at least one candidate ring target in the edge image is extracted according to the circle detection algorithm, and a circular curve is drawn according to the feature information of at least one candidate ring target to obtain a second image.

[0114] Optionally, the device 500 further includes:

[0115] The second acquisition unit is used to acquire the image after the archaeological ring target is marked in the first image as the fourth image.

[0116] This application also provides an apparatus 600 for determining ring targets based on remote sensing images, such as... Figure 6 As shown, the device 600 includes a memory 601 and a processor 602:

[0117] Memory 601 is used to store computer programs;

[0118] Processor 602 is used to execute the above according to the computer program. Figure 1 or Figure 4 The methods provided.

[0119] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus a general-purpose hardware platform. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0120] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate. Components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the objectives of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0121] The above description is merely an exemplary implementation of this application and is not intended to limit the scope of protection of this application.

Claims

1. A method for annular target determination based on remote sensing images, characterized in that, The method comprises the following steps: carrying out image morphology processing, edge detection and circle algorithm detection on a first image in sequence to obtain a second image, the second image comprising a curve of at least one candidate annular target, the first image being a preprocessed image of an archaeological remote sensing image comprising an annular target; obtaining a spectral average of an annular target sample in the first image, and obtaining a spectral average of a third image in a curve range of each candidate annular target of the at least one candidate annular target in the second image; wherein the step of obtaining the spectral average of the annular target sample in the first image comprises: obtaining at least one annular target belonging to an archaeological annular target from the first image as the annular target sample; and obtaining the spectral average of the annular target sample by statistically analyzing the spectral average of the at least one annular target sample according to a spatial analysis method; if the spectral average of the third image matches the spectral average of the annular target sample, determining that the candidate annular target corresponding to the third image is an archaeological annular target; wherein the step of matching the spectral average of the third image with the spectral average of the annular target sample comprises: the difference between the spectral average of the third image and the spectral average of the annular target sample being less than or equal to a preset spectral threshold.

2. The method of claim 1, wherein, The step of obtaining the spectral average of the third image in the curve range of each candidate annular target of the at least one candidate annular target in the second image comprises: obtaining a third image corresponding to each candidate annular target in the second image; obtaining the spectral average of each candidate annular target by statistically analyzing the spectral average of the third image corresponding to the candidate annular target according to a spatial analysis method.

3. The method of claim 1, wherein, The method further comprises: obtaining the remote sensing image collected by a sensor; performing a preprocessing operation on the remote sensing image to obtain the first image, the preprocessing operation comprising radiation calibration, atmospheric correction and geometric correction.

4. The method of claim 1, wherein, The step of carrying out image morphology processing, edge detection and circle algorithm detection on the first image in sequence to obtain the second image comprises: performing the image morphology processing on the first image to obtain an enhanced image; extracting edge information of the enhanced image according to the edge detection algorithm to obtain an edge image; extracting feature information of the at least one candidate annular target in the edge image according to the circle detection algorithm, and drawing a circle curve according to the feature information of the at least one candidate annular target to obtain the second image, the feature information of the at least one candidate annular target comprising a center and a radius of the candidate annular target.

5. The method according to any one of claims 1 to 4, characterized in that, After determining that the candidate annular target corresponding to the third image is an archaeological annular target, the method further comprises: obtaining a fourth image, the fourth image being an image in which the archaeological annular target is labeled in the first image.

6. An apparatus for annular target determination based on remote sensing images, characterized in that, The method comprises the following steps: The first processing unit is configured to sequentially perform image morphology processing, edge detection and circle algorithm detection on the first image to obtain a second image, the second image comprising a curve of at least one candidate ring target, and the first image being a preprocessed image of an archaeological remote sensing image comprising a ring target; The first obtaining unit is configured to obtain a spectral average of ring target samples in the first image, and obtain a spectral average of a third image in a curve range of each candidate ring target of the at least one candidate ring target in the second image; The first obtaining unit is configured to obtain at least one ring target belonging to an archaeological ring target from the first image as the ring target samples when obtaining the spectral average of the ring target samples in the first image, and obtain the spectral average of the ring target samples by statistically analyzing the spectral average of the at least one ring target sample according to a spatial analysis method; The second processing unit is configured to determine that the candidate ring target corresponding to the third image is an archaeological ring target if the spectral average of the third image matches the spectral average of the ring target samples. The second processing unit is configured to calculate a difference between the spectral average of the third image and the spectral average of the ring target samples, and determine that the candidate ring target corresponding to the third image is an archaeological ring target if the difference is less than or equal to a preset spectral threshold.

7. An apparatus for annular target determination based on remote sensing images, characterized in that, The device comprises a memory and a processor, the processor is configured to execute a program stored in the memory, and run the method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium is configured to store a computer program, and the computer program is configured to execute the method of any one of claims 1-5.

Images