An archeological auxiliary system based on aerial remote sensing hyperspectral data

Abstract

The application discloses an archeology auxiliary system based on aerial remote sensing hyperspectral data, which comprises an image acquisition module, an identification model construction module, an identification module and a storage module.The image acquisition module is used for collecting archeology images and pre-processing the collected archeology images to obtain binary images.The identification model construction module is connected with the image acquisition module and is used for constructing an identification model according to the binary images.The identification module is connected with the identification model construction module and is used for identifying the archeology images through the identification model to obtain identification results.The storage module is connected with the identification model construction module and is used for storing the identification results of the identification model.The query module is connected with the storage module and is used for querying the archeology images and the positions corresponding to the archeology images according to the identification results.The system can detect each region in real time through the characteristics of aerial remote sensing, can obtain clear archeology images and accurately detect the shape of the detected objects through hyperspectrum, and can accurately find the address of the ancient buildings through the identification results.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of archaeological excavation, and particularly relates to an archaeological auxiliary system based on aerial remote sensing hyperspectral data. BACKGROUND

[0002] With the emergence of imaging spectral technology, optical remote sensing has entered the hyperspectral remote sensing stage. As a major breakthrough in earth observation technology, the development potential of hyperspectral remote sensing technology is incomparable to that of previous several remote sensing technology development stages. Among them, aerial hyperspectral remote sensing is increasingly showing important practical value, and will also lay a preliminary technical foundation for the development of space hyperspectral remote sensing.

[0003] Archaeology is an important pillar of historical research. Through archaeological data, the culture of ancient social life can be explored and studied, such as ancient temples, tombs, art, paintings, coins, etc. Archaeology can reveal historical facts that have been obscured for many years, and on the basis of these historical facts, historians can more deeply study the development process of ancient society and people's living customs. Historical books can only investigate ancient society from written records, but after years of changes, it is easy to change the truth of history. Archaeology can help us restore the true appearance of history through such folk relics as tombs and geographical environmental information such as the location of the site. For example, during the Western Zhou Dynasty, through the tombs of aristocratic residents as a breakthrough point, the overall state of the culture and economy of the society at that time can be reconstructed.

[0004] However, ancient buildings are scattered in different areas and are difficult to find. If artificial searching and statistics are performed, a large amount of manpower and material resources need to be consumed, and the effect is often doubled. Therefore, how to find ancient buildings through hyperspectral remote sensing technology is crucial for archaeology. SUMMARY

[0005] To solve the above technical problems, the application provides an archaeological auxiliary system based on aerial remote sensing hyperspectral data to solve the problem that there is no aerial exploration of archaeological sites in the prior art.

[0006] To achieve the above purpose, the application provides an archaeological auxiliary system based on aerial remote sensing hyperspectral data, which comprises:

[0007] An image acquisition module is configured to collect archaeological images and pre-process the collected archaeological images to obtain binary images.

[0008] An identification model construction module is connected to the image acquisition module and configured to construct an identification model according to the binary images.

[0009] An identification module is connected to the identification model construction module and configured to identify the archaeological images through the identification model to obtain identification results.

[0010] a storage module, connected with the recognition model construction module, configured to store a recognition result of the recognition model;

[0011] a query module, connected with the storage module, configured to query an archaeological image and a position corresponding to the archaeological image according to the recognition result.

[0012] Preferably, the image acquisition module comprises an image acquisition unit, an image processing unit and a transmission unit.

[0013] The image acquisition unit is configured to acquire the archaeological image.

[0014] The image processing unit is configured to optimize the archaeological image.

[0015] The transmission unit is configured to transmit the optimized archaeological image to the recognition model construction module.

[0016] Preferably, the image acquisition unit comprises a first acquisition unit and a second acquisition unit.

[0017] The first acquisition unit is configured to search for the archaeological image from a network.

[0018] The second acquisition unit is configured to acquire aerial remote sensing hyperspectral data and convert the data into the archaeological image, and calibrate the position of the archaeological image.

[0019] Preferably, the image processing unit comprises a correction unit, a cropping unit and a binarization processing unit.

[0020] The correction unit is configured to eliminate image distortion caused by radiation error.

[0021] The cropping unit is configured to crop the corrected archaeological image and only keep the part of the image related to archaeology.

[0022] The binarization processing unit is configured to perform binarization processing on the cropped image to obtain a binarized image.

[0023] Preferably, the correction unit comprises a radiation calibration unit and an atmospheric correction unit.

[0024] The radiation calibration unit is configured to convert the brightness gray value of the image into absolute radiation brightness.

[0025] The atmospheric correction unit is configured to eliminate radiation error caused by atmospheric influence.

[0026] Preferably, the recognition model construction module comprises a feature extraction unit, a model construction unit and a training unit.

[0027] The feature extraction unit is configured to extract features of the binarized image.

[0028] The model construction unit is configured to construct an identification model based on the binary image features.

[0029] The training unit is configured to train the identification model based on the binary images.

[0030] Preferably, the storage module comprises a grading unit and a storage unit.

[0031] The grading unit is configured to divide the archaeological images into three levels according to the importance of the identification results.

[0032] The storage unit is configured to save the archaeological images according to the divided levels.

[0033] Preferably, the query module comprises a retrieval unit and a display unit.

[0034] The retrieval unit is configured to input an area where archaeological research is desired.

[0035] The display unit is configured to display the archaeological images corresponding to the archaeological area and the positions corresponding to the archaeological images.

[0036] Preferably, the archaeological auxiliary system further comprises an intelligent recommendation module configured to recommend equipment required for archaeological research according to terrain and climate factors.

[0037] Compared with the prior art, the present application has the following advantages and technical effects:

[0038] The archaeological auxiliary system based on aerial remote sensing hyperspectral data can detect each area in real time through the characteristics of aerial remote sensing, obtain clear archaeological images and accurately detect the shape of the detected object through hyperspectral data, and accurately find the address of the ancient building through the identification results. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings, which form a part of this application, are intended to provide further understanding of the application and are incorporated herein in their entirety, and the illustrative embodiments thereof are used to explain the present application and are not intended to limit the present application. In the drawings:

[0040] Figure 1 The accompanying drawings, which form a part of this application, are intended to provide further understanding of the application and are incorporated herein in their entirety, and the illustrative embodiments thereof are used to explain the present application and are not intended to limit the present application. In the drawings: DETAILED DESCRIPTION

[0041] It should be noted that the embodiments and features in the present application can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0042] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0043] The application provides an archaeological auxiliary system based on aerial remote sensing hyperspectral data, comprising:

[0044] An image acquisition module is configured to collect archaeological images and pre-process the collected archaeological images to obtain binary images.

[0045] An identification model construction module is connected to the image acquisition module and configured to construct an identification model according to the binary images.

[0046] An identification module is connected to the identification model construction module and configured to identify archaeological images through the identification model to obtain identification results.

[0047] A storage module is connected to the identification model construction module and configured to store the identification results of the identification model.

[0048] A query module is connected to the storage module and configured to query archaeological images and positions corresponding to the archaeological images according to the identification results.

[0049] Further optimization scheme, the image acquisition module includes an image acquisition unit, an image processing unit and a transmission unit;

[0050] The image acquisition unit is configured to collect archaeological images.

[0051] The image processing unit is configured to optimize the archaeological images.

[0052] The transmission unit is configured to transmit the optimized archaeological images to the identification model construction module.

[0053] Further optimization scheme, the image acquisition unit includes a first acquisition unit and a second acquisition unit;

[0054] The first acquisition unit is configured to search for archaeological images from a network.

[0055] The second acquisition unit is configured to collect aerial remote sensing hyperspectral data and convert it into archaeological images, and calibrate the positions of the archaeological images.

[0056] Further optimization scheme, the image processing unit includes a correction unit, a cropping unit and a binary processing unit;

[0057] The correction unit is configured to eliminate image distortion caused by radiation errors.

[0058] The cropping unit is used for cropping the corrected archaeological image to only keep the part of the image related to the archaeology;

[0059] The binarization processing unit is used for binarization processing the cropped image to obtain a binarization image.

[0060] In a further optimization, the correction unit comprises a radiation calibration unit and an atmospheric correction unit;

[0061] The radiation calibration unit is used for converting the brightness gray value of the image into absolute radiation brightness;

[0062] The atmospheric correction unit is used for eliminating the radiation error caused by the atmospheric influence.

[0063] In a further optimization, after the radiation calibration, the image PSF is detected: a direct detection method is performed according to the physical definition of the point spread function, a parametric point spread model is used to perform surface fitting on each sub-pixel target response data to determine the peak position of each target response, and then the sub-pixel interpolation point spread response is obtained by position registration of the sub-pixel target response value or count value of the 3*3 array of non-integer pixel intervals, so as to reduce the influence of system sampling effect and random noise, the point spread function of the optical remote sensing satellite imaging system is obtained by fitting the parametric Gaussian model, the modulation transfer function of the optical remote sensing satellite imaging system is obtained by taking the modulus and normalizing the obtained system point spread function, and the image quality is evaluated through the modulation transfer function.

[0064] In a further optimization, the atmospheric correction method is as follows: the ratio of the background pixel radiance at the satellite entrance pupil to the target pixel radiance at the satellite entrance pupil can represent the relative size of the adjacency effect, the ratio is different when the combination of target reflectivity and background reflectivity is different, and the ratio increases with the increase of the background pixel reflectivity and decreases with the increase of the target pixel reflectivity. Therefore, the ratio is used to represent the relative size of the difference between the background pixel reflectivity and the target pixel reflectivity to the contribution weight value of each background pixel to the adjacency effect. The ratio and the average background reflectance expression in 6S-AC are combined to obtain an equivalent average background reflectance expression, then the equivalent average background reflectance is used to replace the average background reflectance in 6S-AC, and an adaptive atmospheric correction algorithm is obtained based on the equivalent average background reflectance, and the atmospheric correction is performed through the adaptive atmospheric correction algorithm.

[0065] In a further optimization, the recognition model construction module comprises a feature extraction unit, a model construction unit and a training unit;

[0066] The feature extraction unit is used for extracting the features of the binarization image;

[0067] The model construction unit is used for constructing a recognition model based on the features of the binarization image;

[0068] The training unit is configured to train the recognition model based on the binary image pairs.

[0069] In a further optimization, the feature extraction process includes segmenting features from the network searched archaeological images, then shuffling the order of feature values of each feature, and measuring the influence of the order change on the accuracy of the model. For unimportant features, shuffling the order has little effect on the accuracy of the model, but for important features, shuffling the order will reduce the accuracy of the model, and this is used as a basis to obtain the required image features.

[0070] In a further optimization, a model structure is built, which includes three convolutional layers, a hidden layer and an output layer, and then the obtained image features are input into the recognition model structure as standard samples, and then 1000 real-time photographed images are taken and divided according to 7:3, of which 700 are used as training images to train the recognition model, and when the training result is greater than the set training threshold, the training is ended, and the remaining 300 images are input into the recognition model as a verification set, and when the verification is successful, the final recognition model is obtained, otherwise the training is repeated.

[0071] In a further optimization, the recognition module identifies the archaeological images through the recognition model to obtain a recognition result.

[0072] In a further optimization, the storage module includes a grading unit and a storage unit.

[0073] The grading unit is configured to divide the archaeological images into three levels according to the importance of the recognition result.

[0074] The storage unit is configured to save the archaeological images according to the divided levels.

[0075] In a further optimization, the method of dividing into three levels according to the importance is as follows: according to the terrain, buildings and objects of the discovered relics, the terrain is classified as three levels, the buildings are classified as two levels, and the discovered antiques are classified as one level, the indicator light on the display is green for three levels, the indicator light on the display is yellow for two levels, and the indicator light on the display is red and an alarm is sounded for one level.

[0076] Further optimization scheme, when classifying and grading the pictures, the Hierarchical cluster algorithm is used for operation, the Pearson correlation coefficient is used as the basis, two images are converted into data sets, two groups of data sets are judged to be fitted with a straight line, the correlation degree is judged, when the calculation result of the Pearson correlation coefficient tends to 1, the two are more relevant, that is, the two groups are of the same class, then two groups of data are used as a group of data sets and compared with data sets formed by another two groups of data sets, a new cluster is generated, the old cluster is deleted, until three groups of data sets based on three characteristics are left, and the pictures are classified based on this, the important level is set by thinking, and when images are collected in the later period, the images are classified into the above three types according to the characteristics.

[0077] Further optimization scheme, the query module comprises a retrieval unit and a display unit;

[0078] The retrieval unit is used for inputting an area that wants to carry out archaeological research;

[0079] The display unit is used for displaying the archaeological images corresponding to the archaeological areas and the accurate positions corresponding to the archaeological images based on the distance.

[0080] Further optimization scheme, the archaeological auxiliary system further comprises an intelligent recommendation module, the intelligent recommendation module is used for recommending equipment required by the archaeological research according to terrain and climate factors, for example, special articles such as ice picks need to be carried when climbing snow mountains, and water tanks need to be carried more when going to the desert, so as to avoid that the excavation cannot be completed due to water source limitation.

[0081] Further optimization scheme, when the intelligent recommendation is carried out, the name of the archaeological tool and the function of the archaeological tool are collected first, then the terrain and climate and other environmental information are extracted from the image, the extracted information and the name of the archaeological tool and the function of the archaeological tool are matched through the KMP algorithm, and after the matching is completed, the matched tool name is displayed to the archaeological personnel through the display screen.

[0082] As can be seen from the above, the significant advantages of the present application compared with the prior art are as follows:

[0083] 1) The present application can detect each area in real time through the characteristics of aerial remote sensing, clear archaeological images can be obtained through hyperspectrum, and the shape of the detected object can be accurately detected, and the address of the ancient building can be accurately found through the identification result;

[0084] 2) The present application can recommend the equipment required by the archaeological research according to terrain and climate factors through the intelligent recommendation module, so as to reduce the time waste caused by the lack of archaeological equipment.

[0085] The above merely provides the preferred embodiments of the present application, and the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed by the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An archaeological assistance system based on aerial remote sensing hyperspectral data, characterized in that, include: The image acquisition module is used to acquire archaeological images and preprocess the acquired archaeological images to obtain binarized images; The image acquisition module includes an image acquisition unit, an image processing unit, and a transmission unit; The image acquisition unit is used to acquire archaeological images; The image processing unit is used to optimize archaeological images; The transmission unit is used to transmit the optimized archaeological images to the recognition model construction module; The image processing unit includes a correction unit, a cropping unit, and a binarization unit; The correction unit is used to eliminate image distortion caused by radiation error; The cropping unit is used to crop and correct archaeological images, retaining only the parts of the image that are relevant to archaeology; The binarization processing unit is used to perform binarization processing on the cropped image to obtain a binarized image; A recognition model construction module, connected to the image acquisition module, is used to construct a recognition model based on the binarized image; The recognition model construction module includes a feature extraction unit, a model construction unit, and a training unit; The feature extraction unit is used to extract features from the binarized image; The model building unit is used to build a recognition model based on the binarized image features; The training unit is used to train the recognition model based on the binarized image; The recognition module, connected to the recognition model construction module, is used to recognize archaeological images through the recognition model and obtain recognition results; A storage module, connected to the recognition model construction module, is used to store the recognition results of the recognition model; The query module, connected to the storage module, is used to query archaeological images and their corresponding locations based on the recognition results.

2. The archaeological auxiliary system based on airborne remote sensing hyperspectral data according to claim 1, characterized in that, The image acquisition unit includes a first acquisition unit and a second acquisition unit; The first acquisition unit is used to search for archaeological images from the network; The second acquisition unit is used to acquire aerial remote sensing hyperspectral data and convert it into archaeological images, and to mark the location of the archaeological images.

3. The archaeological auxiliary system based on airborne remote sensing hyperspectral data according to claim 1, characterized in that, The correction unit includes a radiation calibration unit and an atmospheric correction unit; The radiometric calibration unit is used to convert the brightness grayscale values ​​of the image into absolute radiometric values; The atmospheric correction unit is used to eliminate radiation errors caused by atmospheric effects.

4. The archaeological auxiliary system based on airborne remote sensing hyperspectral data according to claim 1, characterized in that, The storage module includes a hierarchical unit and a storage unit; The grading unit is used to classify archaeological images into three levels according to their importance based on the recognition results; The storage unit is used to save archaeological images according to the classification levels.

5. The archaeological auxiliary system based on airborne remote sensing hyperspectral data according to claim 1, characterized in that, The query module includes a retrieval unit and a display unit; The search unit is used to input the region where archaeological research is desired; The display unit is used to display archaeological images corresponding to the archaeological area and the locations corresponding to the archaeological images. 6.The system of claim 1, wherein the system further comprises an intelligent recommendation module configured to recommend equipment needed for the archaeological survey based on terrain and climate factors. ​

Images