A database management system based on architectural remote sensing images

Abstract

The present invention relates to the technical field of data management. The present invention discloses a database management system based on building remote sensing images; it includes identifying target images from building remote sensing images, dividing the target images into image sets, correspondingly importing the image sets into the data layer of the library architecture to generate an image database, building an association channel with breakpoints, configuring break conditions on the association channel, parsing query requirements from request data, and selecting corresponding query modes; compared with the prior art, the present invention can build channels for image association and query between different data levels in the image database, and at the same time, combined with the breakpoints with configured break conditions, ensure that the target images in the image database can be dynamically associated through the association channel while maintaining independence, thereby realizing the dynamic storage association effect of the target images in the image database and meeting the diverse query requirements of the image database.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and more particularly to a database management system based on building remote sensing images. Background Art

[0002] After buildings in a region are damaged by an earthquake, it is necessary to analyze the post-earthquake condition of the building structures in the region. Therefore, remote sensing images of building damage after real historical earthquakes are first collected, and then the building remote sensing images are aggregated into a database to achieve accurate management of building remote sensing images and facilitate users to query and use the required building remote sensing images. Therefore, it is necessary to establish a database to manage building remote sensing images.

[0003] Patent application with reference publication number CN112559534A discloses a remote sensing image data archiving management system and method, including a data integration unit configured to integrate received aerospace and aerial remote sensing image data, a data archiving unit configured to classify data, and store different types of data in different file formats, a data processing unit including multiple task processing nodes, each task processing node processing corresponding tasks in parallel, the tasks including data query, data cleaning, data scheduling, data feature extraction, stereo image global optimization matching, suspicious match detection, regional block adjustment, digital surface model extraction and splicing, and a data storage unit configured to store aerospace and aerial remote sensing image raw data and processing results;

[0004] Existing database management systems classify all building remote sensing images according to specific types and store the classified building remote sensing images in a unified manner in the database, thereby achieving classified query and management effects of building remote sensing images. For example, in the above-mentioned patent application, it normalizes, uniformly stores, and centrally manages massive multi-source remote sensing image data to achieve overall automated operation effects of data archiving, statistics, and other businesses. However, the overall unified storage and management method causes a large number of building remote sensing images with different degrees of correlation to be mixed together, and it is impossible to ensure that images with different degrees of correlation always maintain a dynamic and independent state. In addition, there is a lack of query mode switching measures between different types of building remote sensing images, which makes the query and management process of building remote sensing images less accurate, thereby increasing the probability of query failure and query errors in building remote sensing images in the database.

[0005] In view of this, the present invention proposes a database management system based on building remote sensing images to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a database management system based on building remote sensing images, comprising:

[0007] An image recognition module, which is used to receive the building remote sensing image of the target area, extract the basic parameters of the building remote sensing image, and identify the target image from the building remote sensing image;

[0008] An image classification module, which is used to extract the comprehensive image features of the target image. The comprehensive image features include image time, geographic coordinates, contour color, and building structure. Taking the comprehensive image features as the division standard, the target image is divided into an image set;

[0009] A database construction module, which is used to construct a library architecture with a data layer, and correspondingly import the image set into the data layer of the library architecture to generate an image database;

[0010] A channel building module, which is used to build an associated channel with breakpoints in the image database, and based on the comprehensive image features as the configuration basis, configure the break conditions for controlling the on-off state switching of the breakpoints on the associated channel;

[0011] A query selection module, which is used to parse the query requirements from the request data, combine the query requirements with the break conditions, control the on-off state of the breakpoints, and select the query mode corresponding to the on-off state.

[0012] Further, the basic parameters include the abnormal area ratio and the regional integrity;

[0013] The extraction method of the abnormal area ratio is as follows:

[0014] Taking the preset first length as the longitudinal segmentation standard and the preset second length as the transverse segmentation standard, each of the A building remote sensing images is segmented into B sub-regions;

[0015] Respectively count the number of all pixel points in the B sub-regions of the A building remote sensing images to obtain B regional values, and mark the sub-regions with regional values less than the regional calibration value as abnormal regions;

[0016] Count the total value of the abnormal regions in the A building remote sensing images one by one, record it as the abnormal value, and compare the abnormal value with the total number of sub-regions to obtain the abnormal area ratios of the A building remote sensing images;

[0017] The expression of the abnormal area ratio is:

[0018] ;

[0019] In the formula, is the abnormal area ratio of the th building remote sensing image, = 1, 2,..., A, is the abnormal value of the th building remote sensing image, is the total number of sub - regions of the th building remote sensing image.

[0020] Furthermore, the method for extracting the regional integrity is as follows:

[0021] Mark the pixel values of all pixel points in the B sub - regions of the A building remote sensing images one by one, and mark the pixel points with pixel values less than the pixel lower limit value and pixel values greater than the pixel upper limit value as abnormal points;

[0022] Connect the four inflection points of the B sub - regions cross - wise to form diagonals, and mark the line segments between the four inflection points on the two diagonals and the intersection point of the two diagonals as the median lines, obtaining four median lines;

[0023] Respectively, with the mid - points of the four median lines as the centers, draw four pixel circles with equal radii and adjacent ones circumscribing each other, and respectively count the number of abnormal points and the total number of pixel points within the four pixel circles;

[0024] Mark the pixel circles with the number of abnormal points less than four - fifths of the total number of pixel points as normal circles, and count the number of all normal circles in the A building remote sensing images to obtain A normal quantity values;

[0025] Measure the radius of the pixel circle, the length and width of the building remote sensing image through the scale, calculate the area of the normal circle based on the circle area formula, and after adding up the areas of all the normal circles, compare with the total area of the building remote sensing image to obtain A regional integrity values;

[0026] The expression of the regional integrity is:

[0027] ;

[0028] In the formula, is the regional integrity of the th building remote sensing image, is the normal quantity value of the th building remote sensing image, is the radius of the pixel circle, is the th length of the building remote sensing image, is the th width of the building remote sensing image.

[0029] Furthermore, the method for identifying the target image is as follows:

[0030] When the ratio of the abnormal area of the building remote sensing image is less than the abnormal area safety value and the regional integrity is greater than the regional integrity safety value, mark the building remote sensing image as the target image to obtain D target images;

[0031] When the ratio of the abnormal area is greater than or equal to the abnormal area safety value, or the regional integrity is less than or equal to the regional integrity safety value, the building remote sensing image is not recorded as the target image.

[0032] Furthermore, the method for extracting the contour color is as follows:

[0033] Using computer technology, identify the buildings in D target images one by one, identify the edge lines of the buildings through edge detection algorithms, and record the area inside the edge lines as the building area;

[0034] Mark the pixel values of the pixel points in all building areas on the D target images respectively, and summarize the pixel points with pixel values in the same color level to obtain E pixel sets;

[0035] Count the number of pixel points in the E pixel sets one by one, and record the color level with the maximum number of pixel points as the D effective levels;

[0036] Using natural language processing technology, identify the text semantics and digital semantics of the D effective levels, and after combining the text semantics and digital semantics at the beginning and end, generate D contour colors.

[0037] Furthermore, the image set includes a semi-hidden set and an open set, and the division method of the semi-hidden set and the open set is as follows:

[0038] In the order of the image time, with 1 as the first number, sequentially number the D target images in ascending order;

[0039] In the order from small to large of the numbers, summarize the target images with the same geographical coordinates to generate the first image group;

[0040] Among the target images with inconsistent geographical coordinates, summarize the target images with consistent contour colors and building structures to generate the second image group;

[0041] After combining all the target images in the first image group and the second image group, generate an open set, and after summarizing all the remaining target images, generate a semi-hidden set.

[0042] Furthermore, the method for generating the image database is as follows:

[0043] Establish a blank data group with a closed structure, construct two internal and external combined data layers in the blank data group, and record the data layer located inside as the internal layer and the data layer located outside as the external layer;

[0044] Respectively count the number of target images in the semi-hidden set and the open set to obtain the hidden quantity value and the open quantity value;

[0045] Mark out the same number of outer image positions as the open quantity value in the outer layer, and mark out the same number of inner image positions as the hidden quantity value in the inner layer to construct a library architecture;

[0046] Import all the target images in the semi-hidden set into the inner image positions of the inner layer one by one, forcing the inner layer to be converted into a hidden layer;

[0047] Import all the target images in the open set into the outer image positions of the outer layer one by one, forcing the outer layer to be converted into an open layer, and record the library architecture with a hidden layer and an open layer as an image database.

[0048] Furthermore, the method for building the association channel is as follows:

[0049] Randomly mark a point on the hidden layer and the open layer of the image database respectively, and record them as the inner connection point and the outer connection point;

[0050] Measure the distance between the inner connection point and the outer connection point to obtain the inner-outer connection value; [[ID=…]]

[0051] Continuously adjust the position of the outer connection point on the open layer until the inner-outer connection value reaches the minimum value, then stop adjusting the position of the outer connection point, and record one-fourth of the minimum value of the inner-outer connection value as the interval value;

[0052] Build an association channel with a two-way transmission link between the inner connection point and the adjusted outer connection point, and mark a point on the association channel corresponding to the length of one interval value away from the outer connection point, and record it as the connection break point.

[0053] Furthermore, the connection break state includes an open state and a closed state:

[0054] The connection break condition is: when the open layer is insufficient to meet the query requirement, control the connection break point to switch from the closed state to the open state.

[0055] Furthermore, the method for identifying the connection break state is as follows:

[0056] Identify the request semantics in the request data through natural language processing technology, and extract the keywords in the request semantics one by one;

[0057] Record time, coordinates, color, and structure as demand words, record the keywords in the request data that contain any one of the demand words as valid words, and after combining all the valid words, generate a query requirement;

[0058] Count the number of valid words in the query requirement, and record it as the valid quantity value;

[0059] When the valid quantity value is 1 and the valid word is coordinates, control the connection break point to be in the closed state;

[0060] When the effective quantity value is 1 and the effective word is not a coordinate, the control on-off point is in the on state;

[0061] When the effective quantity value is 2, 3 or 4, the control on-off point is in the on state;

[0062] The query modes include an independent query mode and a combined query mode. The selection methods for the independent query mode and the combined query mode are as follows:

[0063] When the on-off state of the on-off point is in the on state, select the combined query mode;

[0064] When the on-off state of the on-off point is in the off state, select the independent query mode.

[0065] The technical effects and advantages of a database management system based on building remote sensing images according to the present invention:

[0066] (1): By receiving the building remote sensing images of the target area, extracting the basic parameters of the building remote sensing images, and identifying the target images from the building remote sensing images, the quality of the building remote sensing images can be evaluated and analyzed from two data dimensions of resolution and integrity, so as to screen out the target images that meet the subsequent construction of the image database, avoid the negative impact of low-quality building remote sensing images on the database construction, and improve the accuracy of the image database construction;

[0067] (2): By constructing a library architecture with a data layer and importing the image set into the data layer of the library architecture correspondingly to generate an image database, an image database with different data layers can be constructed based on the image set and with the target images as the objects, so that the image database can not only perform storage management operations on the target images, but also ensure that different associated target images can be summarized orderly and remain relatively independent;

[0068] (3): By building an associated channel with an on-off point in the image database and configuring an on-off condition for controlling the on-off state switching of the on-off point on the associated channel based on the comprehensive image features, a channel for image association and query can be constructed between different data levels in the image database. At the same time, combined with the on-off point with the on-off condition configured, an accurate control effect can be achieved on whether the associated channel is open or closed, ensuring that the target images in the image database can be dynamically associated through the associated channel while maintaining independence, thereby realizing the dynamic storage association effect of the target images in the image database, greatly reducing the probability of query failure and query error, and improving the query accuracy;

[0069] (4) By parsing the query requirements from the request data, combining the query requirements with the on-off conditions, controlling the on-off state of the on-off point, and selecting the query mode corresponding to the on-off state, according to different actual query requirements, the opening and closing states of the associated channels can be accurately controlled, and the query mode of the corresponding building remote sensing image can be provided to the user side, ensuring that the user side can quickly, accurately and comprehensively query the required building remote sensing image from the image database. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 FIG. 6 is a schematic diagram of a database management system based on building remote sensing images provided in Embodiment 1 of the present invention;

[0071] Figure 2 FIG. 10 is a schematic flowchart of a database management method based on building remote sensing images provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0072] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0073] Embodiment 1: Please refer to Figure 1 As shown in FIG., a database management system based on building remote sensing images in this embodiment includes:

[0074] An image recognition module, which receives the building remote sensing image of the target area, extracts the basic parameters of the building remote sensing image, and identifies the target image from the building remote sensing image;

[0075] The target area refers to the specific geographical location represented by the building remote sensing image used to construct the database, so that the received building remote sensing image can provide a comprehensive and complete image representation of the overlooking angle of this geographical location. Since the building remote sensing image is taken from an aerial overlooking angle, in this embodiment, the acquisition methods of the building remote sensing image include but are not limited to satellite remote sensing photography, drone remote sensing photography, and aerial remote sensing photography, etc., as long as the shooting requirements of the target area can be met;

[0076] After obtaining the building remote sensing image, it is necessary to perform preliminary identification and analysis on the building remote sensing image, and extract the basic parameters from the building remote sensing image. At this time, the basic parameters can numerically represent the basic image quality situation in the building remote sensing image and serve as the basis for preliminary identification and screening of the building remote sensing image;

[0077] The basic parameters include the abnormal area ratio and the regional integrity;

[0078] The abnormal area ratio refers to the proportion between the number of abnormal areas identified as having low resolution in the building remote sensing image and the total number of areas, which can represent the overall resolution level of the building remote sensing image. When the abnormal area ratio is larger, it indicates that the proportion between the number of abnormal areas identified as having low resolution in the building remote sensing image and the total number of areas is larger, and thus the quality of the building remote sensing image is poorer.

[0079] The method for extracting the abnormal area ratio is as follows:

[0080] Using the preset first length as the longitudinal segmentation standard and the preset second length as the transverse segmentation standard, each of the A building remote sensing images is segmented into B sub-areas; the preset first length and the preset second length are respectively the length standards for segmenting the building remote sensing image in the vertical and horizontal directions to ensure that the building remote sensing image can be segmented into sub-areas of equal size, ensuring that the corresponding area sizes of all sub-areas are consistent and avoiding the interference effect of inconsistent sub-area sizes on the subsequent analysis results.

[0081] Count the total number of all pixel points in the B sub-areas of each of the A building remote sensing images to obtain B area values, and mark the sub-areas with area values less than the area calibration value as abnormal areas; the area calibration value refers to the minimum number of pixel points in the sub-areas identified as abnormal areas, which can be used as the numerical basis for judging whether a sub-area is an abnormal area.

[0082] Count the total value of the abnormal areas in each of the A building remote sensing images one by one, denoted as the abnormal value, and compare the abnormal value with the total number of sub-areas to obtain A abnormal area ratios.

[0083] The expression of the abnormal area ratio is:

[0084] ;

[0085] In the formula, is the abnormal area ratio of the th building remote sensing image, = 1, 2,..., A, is the abnormal value of the th building remote sensing image, is the th total number of sub-areas of the building remote sensing image.

[0086] The regional integrity refers to the ratio of the area of the region recognized as a normal gray-scale area in the building remote sensing image to the total area of the region, which can represent the overall gray-scale condition of the building remote sensing image. When the regional integrity is larger, it indicates that the ratio of the area of the region recognized as a normal gray-scale area in the building remote sensing image to the total area of the region is larger, and the quality of the building remote sensing image is better.

[0087] The extraction method of regional integrity is as follows:

[0088] Mark the pixel values of all pixel points in the B sub-regions of A building remote sensing images one by one, and mark the pixel points with pixel values less than the pixel lower limit value and pixel values greater than the pixel upper limit value as abnormal points; the pixel lower limit value and the pixel upper limit value are respectively used to limit the minimum and maximum values of the pixel values of all pixel points in the sub-region marked as abnormal points, so as to ensure that the pixel points with pixel values between the pixel lower limit value and the pixel upper limit value are not abnormal points; specifically, the pixel lower limit value and the pixel upper limit value can represent the brightness of the pixel points corresponding to the sub-region. The pixel points corresponding to the pixel lower limit value have lower brightness, and the pixel points corresponding to the pixel upper limit value have higher brightness.

[0089] Connect the four inflection points of the B sub-regions crosswise to form a diagonal line, and record the line segments between the four inflection points on the two diagonal lines and the intersection point of the two diagonal lines as the median lines, and obtain four median lines;

[0090] Respectively draw four pixel circles with equal radii and adjacent circumferences centered on the midpoints of the four median lines, and respectively count the number of abnormal points and the total number of pixel points in the four pixel circles; by drawing pixel circles, circular regions of equal size can be constructed within the sub-region, and the regular coverage of pixel points by the circular regions is used to accurately calculate the regional integrity.

[0091] Record the pixel circles with the number of abnormal points less than four-fifths of the total number of pixel points as normal circles, and count the number of all normal circles in A building remote sensing images to obtain A normal quantity values;

[0092] Measure the radius of the pixel circle, the length and width of the building remote sensing image respectively through the scale, calculate the area of the normal circle based on the circle area formula, and after adding up the areas of all the normal circles, compare with the total area of the building remote sensing image to obtain A regional integrity values;

[0093] The expression of regional integrity is:

[0094] ;

[0095] In the formula, is the regional integrity of the th building remote sensing image, is the The normal value of a building remote sensing image is the radius of the pixel circle is the length of the is the width of the

[0096] After parsing the basic parameters of the building remote sensing image, the building remote sensing image can be preliminarily screened according to the magnitudes of the basic parameters, and then the building remote sensing images with high resolution and high image integrity can be identified from the building remote sensing images and recorded as target images;

[0097] The identification method of the target image is as follows:

[0098] First, compare the abnormal area ratio of A building remote sensing images with the abnormal area safety value in turn; the abnormal area safety value refers to the maximum value of the abnormal area ratio of the building remote sensing image when it is identified as the target image, which can provide a numerical basis for judging the magnitude of the abnormal area ratio;

[0099] When the abnormal area ratio of the building remote sensing image is less than the abnormal area safety value, it indicates that the resolution of the building remote sensing image is relatively high;

[0100] Then, compare the regional integrity of the building remote sensing image with the regional integrity safety value; the regional integrity safety value refers to the minimum value of the regional integrity of the building remote sensing image when it is identified as the target image, which can provide a numerical basis for judging the magnitude of the regional integrity;

[0101] When the regional integrity of the building remote sensing image is greater than the regional integrity safety value, it indicates that the integrity of the building remote sensing image is relatively high, and then this building remote sensing image is recorded as the target image, and D target images are obtained.

[0102] It should be noted that when the abnormal area ratio is greater than or equal to the abnormal area safety value, or the regional integrity is less than or equal to the regional integrity safety value, it indicates that there are situations with relatively low resolution or poor integrity in the building remote sensing image, so this building remote sensing image cannot be used as the target image. Therefore, the selected target images need to maintain a relatively high level in terms of resolution and integrity, so as to provide a high-quality image basis for the subsequent construction of the database.

[0103] The image classification module extracts the comprehensive image features of the target images, and divides the target images into image sets based on the comprehensive image features as the classification criterion;

[0104] The comprehensive image features refer to the specific representation of the detailed information such as the type, attributes, and structure of the target image, and serve as the basis for classifying and managing the target image. Each target image has one and only one set of correct comprehensive image features, enabling the comprehensive and concise representation of the relevant information in the target image;

[0105] The comprehensive image features include image time, geographical coordinates, contour color, and building structure;

[0106] The image time is the representation of the corresponding timeline when the target image is taken, which can accurately refer to the chronological order of the shooting times of each target image, thus providing a reference basis on the timeline for differentiating the target images. The image time is obtained by querying the shooting times of D target images one by one through timestamps.

[0107] The geographical coordinates are the representation of the corresponding geographical longitude and latitude coordinates when the target image is taken, which can accurately refer to the shooting longitude and latitude positions of each target image, thus providing a reference basis on the geographical location for differentiating the target images. The geographical coordinates are obtained by querying the longitude and latitude of D target images one by one through the geographical information management system.

[0108] The contour color is the representation of the corresponding facade color when the target image is taken, which can accurately refer to the facade color of each target image, thus providing a reference basis on the facade color for differentiating the target images;

[0109] The extraction method of the contour color is as follows:

[0110] By using computer technology, identify the buildings in D target images one by one, identify the edge lines of the buildings through edge detection algorithms, and record the area inside the edge lines as the building area;

[0111] Mark the pixel values of the pixel points in all building areas on D target images respectively, and summarize the pixel points with pixel values within the same color level to obtain E pixel sets; The color level is the numerical range between the minimum value and the maximum value of the pixel values corresponding to different types of colors, which can be used as the judgment basis for determining whether the colors represented by the pixel points are the same color;

[0112] Count the number of pixel points in E pixel sets one by one, and record the color level with the maximum number of pixel points as the D valid levels;

[0113] Identify the literal semantics and numerical semantics of D valid levels through natural language processing technology. After combining the literal semantics and numerical semantics at the beginning and end, generate D contour colors. The literal semantics and numerical semantics are used to represent the specific color information and color numbers in the valid levels respectively, and the specific contour colors are formed by combining the literal semantics and numerical semantics.

[0114] The building structure is used to represent the structure type corresponding to the target image during shooting, that is, it can accurately refer to the structure type of each target image, thus providing a reference basis for the distinction of target images in terms of structure type; the building structure is obtained by querying the building design table after combining the image time, geographical coordinates and contour color of the target image.

[0115] After extracting the comprehensive image features of the target image, the target image can be orderly and accurately divided into multiple independent image sets with the comprehensive image features as the division criterion, ensuring that there is only one target image of the same or similar type in each image set.

[0116] The image sets include semi-hidden sets and open sets; a semi-hidden set refers to the state where the target images in the image set are in a semi-open and semi-hidden state, so that the target images in the image set cannot be directly queried and used, and an open set refers to the state where the target images in the image set are in an open state, so that the target images in the image set can be directly queried and used.

[0117] The division methods of semi-hidden sets and open sets are as follows:

[0118] In the order of the image time, with 1 as the first number, sequentially number the D target images in ascending order.

[0119] In the order of the numbers from small to large, sequentially compare the geographical coordinates of the D target images, and after summarizing the target images with the same geographical coordinates, generate the first image group.

[0120] Among the target images with inconsistent geographical coordinates, compare the contour colors and building structures, and after summarizing the target images with both the contour colors and building structures being the same, generate the second image group.

[0121] After combining all the target images in the first image group and the second image group, generate an open set, and after summarizing the remaining target images, generate a semi-hidden set.

[0122] It should be noted that the target images in the open set have certain characteristics such as the same coordinates, colors, or structures, enabling the target images within the open set to be associated with each other, allowing the target images within the open set to be directly used. However, there are no identical and associated characteristics among the target images in the semi-hidden set, making the target images in the semi-hidden set unable to be directly used.

[0123] The database construction module constructs a library architecture with a data layer and imports the image set into the data layer of the library architecture correspondingly to generate an image database.

[0124] After classifying and dividing the target images, the library architecture can be constructed based on the divided target images, enabling the library architecture to provide an infrastructure for the divided target images to form a database, ensuring that the subsequent constructed database can effectively and accurately manage all the target images and facilitating subsequent querying and retrieval.

[0125] During the process of constructing the library architecture, a data layer matching the image set needs to be constructed within the library architecture, enabling the data layer to provide a location limit for data import of the image set to ensure that the subsequent image database can match all the target images.

[0126] After constructing the library architecture, the image set and the library architecture can be effectively combined and imported, enabling the construction of an image database after the combination of the library architecture and the image set. At this time, the image database, as an overall data management library for qualified building remote sensing images in the target area, can provide a platform for subsequent querying and retrieval of relevant image data.

[0127] The method for generating the image database is as follows:

[0128] Establish a blank data group with a closed structure, construct two internally and externally combined data layers within the blank data group, and denote the data layer located inside as the internal layer and the data layer located outside as the external layer. The data layer is used to distinguish the positions of building remote sensing images with different degrees of association in the image database, thereby representing different degrees of openness for building remote sensing images with different degrees of association.

[0129] Respectively count the number of target images in the semi-hidden set and the open set to obtain the hidden quantity value and the open quantity value.

[0130] Mark the same number of external image positions equal to the open quantity value in the external layer and mark the same number of internal image positions equal to the hidden quantity value in the internal layer to construct the library architecture. The external image position is used to limit the import position of the building remote sensing images within the open set.

[0131] All target images within the semi-hidden set are imported one by one into the inner image positions of the inner layer, forcing the inner layer to be converted into a hidden layer; the inner image positions are used to define the import positions of the building remote sensing images within the hidden set.

[0132] All target images within the open set are imported one by one into the outer image positions of the outer layer, forcing the outer layer to be converted into an open layer, and the library architecture with the hidden layer and the open layer is recorded as an image database.

[0133] It should be noted that the constructed image database is a data set of building remote sensing images constructed based on all target images in the target area, which can be used as a set for subsequent users to query and retrieve the required building remote sensing images, and can effectively and accurately manage all target images in the target area as a whole.

[0134] The channel building module builds an associated channel with breakpoints in the image database, and based on the comprehensive image features as the configuration basis, configures the break conditions for controlling the on-off state switching of the breakpoints on the associated channel.

[0135] After constructing the image database, it is necessary to build an associated channel for the associated transmission and retrieval of target images in different data layers within the image database, so as to effectively connect the target images in different data layers within the image database.

[0136] When building the associated channel, it is necessary to set breakpoints on the associated channel to control the state of the associated channel, so that the breakpoints can be used as trigger points to control the opening and closing of the associated channel, and then form a protective control point within the image database.

[0137] The method for building the associated channel is as follows:

[0138] Randomly mark a point on the hidden layer and the open layer of the image database, denoted as the inner connection point and the outer connection point respectively.

[0139] Measure the distance between the inner connection point and the outer connection point to obtain the inner-outer connection value.

[0140] Continuously adjust the position of the outer connection point on the open layer until the inner-outer connection value reaches the minimum value, then stop adjusting the position of the outer connection point, and record one-fourth of the minimum value of the inner-outer connection value as the interval value.

[0141] Build an associated channel with a two-way transmission link between the inner connection point and the adjusted outer connection point, and mark a point on the associated channel corresponding to the length of one interval value away from the outer connection point, denoted as the breakpoint.

[0142] It should be noted that when the distance from the outer connection point to the inner connection point reaches the minimum value, the distance between the outer connection point and the inner connection point is the closest at this time, and the convenience of associating the target images in the open layer and the hidden layer is the highest. At this time, the operations of associative query and retrieval of the target images in the open layer and the hidden layer will be the most convenient.

[0143] After constructing an association channel with a connection break point, it is necessary to control the on-off state of the connection break point. At this time, it is necessary to configure an on-off condition that can control the switching of the connection break point based on the image features of the target image.

[0144] The on-off state is a specific representation of whether the working state of the connection break point is conducting, and it is used as a query restriction condition for the required building remote sensing images in the image database. Specifically, the on-off state includes an open state and a closed state. The open state means that the connection break point is in a conducting state, and at this time, the target images in the hidden layer and the open layer can perform bidirectional transmission and query operations through the association channel. The closed state means that the connection break point is in a blocked state, and at this time, the target images in the hidden layer and the open layer cannot perform bidirectional transmission and query operations through the association channel.

[0145] The on-off condition is: when the open layer is not sufficient to meet the query requirements, control the connection break point to switch from the closed state to the open state.

[0146] It should be noted that the connection break point of the association channel is in the closed state without query management, which can ensure the relative independence of all remote sensing images in the image database. That the open layer is not sufficient to meet the query requirements means that the target images in the open layer cannot meet the query and management requirements of the user terminal for building remote sensing images. At this time, it is necessary to extend the query range of the required building remote sensing images from the open layer to the hidden layer.

[0147] The query selection module parses the query requirements from the request data, combines the query requirements with the on-off condition, controls the on-off state of the connection break point, and selects a query mode corresponding to the on-off state.

[0148] The request data refers to all the data that can be used for query management and retrieval of the required building remote sensing images by the user terminal, and it is the original data input to the image database. Since there are many types of requirements and the content is complex in the request data, in order to extract concise and accurate requirement data from the request data, it is necessary to parse the query requirements from the request data, so that the query requirements can not only specifically represent the required building remote sensing image data and types in the request data, but also be used as the basis for subsequent satisfaction determination with the on-off condition. After matching and identifying the query requirements with the on-off condition, the on-off state of the connection break point is identified.

[0149] The method for identifying the on-off state is:

[0150] The request semantics in the request data are identified through natural speech processing technology, and the keywords in the request semantics are extracted one by one; the request semantics are a concise representation of the true meaning in the request data, and the keywords are the literal representations of the specific features represented in the request semantics;

[0151] Time, coordinates, color, and structure are recorded as demand words;

[0152] The keywords in the request data are compared with the demand words one by one, and the keywords containing any one of the demand words are recorded as valid words. After combining all the valid words, a query demand is generated;

[0153] The number of valid words in the query demand is counted and recorded as the valid quantity value;

[0154] When the valid quantity value is 1 and the valid word is coordinates, at this time, the query demand only needs to query the target images in the open layer of the image database, and there is no need to perform an associated query on the target images in the hidden layer, so the control on-off point is in the closed state;

[0155] When the valid quantity value is 1 and the valid word is not coordinates, at this time, the query demand not only needs to query the target images in the open layer of the image database, but also needs to perform an associated query on the target images in the hidden layer, so the control on-off point is in the open state;

[0156] When the valid quantity value is 2, 3, or 4, at this time, the query demand not only needs to query the target images in the open layer of the image database, but also needs to perform an associated query on the target images in the hidden layer, so the control on-off point is in the open state.

[0157] After the control on-off point is switched to the corresponding on-off state, the query mode corresponding to the on-off state can be selected according to the actual switched on-off state, so that the request data of the user side can quickly and accurately query the required building remote sensing images from the image database under the limitation of the query mode, thereby realizing the query management operation of the building remote sensing images after the earthquake in the target area, and facilitating the provision of reasonable and accurate data support for the buildings after the earthquake;

[0158] The query modes include an independent query mode and a combined query mode; the independent query mode refers to querying the required building remote sensing images only through the open layer, and the combined query mode refers to querying the required building remote sensing images through the open layer and the hidden layer;

[0159] The selection methods for the independent query mode and the combined query mode are as follows:

[0160] When the on-off state of the on-off point is the on state, a combined query operation on the target images in the open layer and the hidden layer needs to be performed through the associated channel at this time, so the combined query mode is selected;

[0161] When the on-off state of the on-off point is the off state, a combined query operation on the target images in the open layer and the hidden layer does not need to be performed through the associated channel at this time, so the independent query mode is selected.

[0162] In this embodiment, by receiving the building remote sensing image of the target area, extracting the basic parameters of the building remote sensing image, and identifying the target image from the building remote sensing image, the quality of the building remote sensing image can be evaluated and analyzed from two data dimensions of resolution and integrity, so as to screen out the target images that meet the subsequent construction of the image database, avoid the negative impact of low-quality building remote sensing images on the database construction, and improve the accuracy of the image database construction;

[0163] By extracting the comprehensive image features of the target images and using the comprehensive image features as the division criteria, the target images are divided into image sets. The target images with the same or similar comprehensive image features can be combined together in an orderly manner to form relatively independent image sets, and a data-level basis for the subsequent construction of the image database is provided;

[0164] By constructing a library architecture with a data layer and importing the image sets into the data layer of the library architecture correspondingly to generate an image database, an image database with different data layers can be constructed based on the image sets and with the target images as the objects, so that the image database can not only perform storage management operations on the target images, but also ensure that the target images with different associations can be summarized together in an orderly manner and remain relatively independent;

[0165] By building an associated channel with an on-off point in the image database and configuring an on-off condition for controlling the on-off state switching of the on-off point based on the comprehensive image features, a channel for image association and query can be constructed between different data levels in the image database. At the same time, combined with the on-off point with the on-off condition configured, an accurate control effect on the opening and closing of the associated channel can be achieved, ensuring that the target images in the image database can be dynamically associated through the associated channel while maintaining independence, thereby realizing the dynamic storage association effect of the target images in the image database, greatly reducing the probability of query failure and query error, and improving the query accuracy;

[0166] By parsing the query requirements from the request data, combining the query requirements with the on-off conditions, controlling the on-off state of the on-off point, and selecting the query mode corresponding to the on-off state, the opening and closing states of the associated channels can be accurately controlled according to different actual query requirements, and the query mode of the corresponding building remote sensing image can be provided to the user terminal to ensure that the user terminal can quickly, accurately and comprehensively query the required building remote sensing image from the image database.

[0167] Embodiment 2: Please refer to Figure 2 As shown, for the parts not described in detail in this embodiment, refer to the description in Embodiment 1. A database management method based on building remote sensing images is provided, which is implemented based on a database management system based on building remote sensing images, and includes:

[0168] S1: Receive the building remote sensing images of the target area, extract the basic parameters of the building remote sensing images, and identify the target images from the building remote sensing images;

[0169] S2: Extract the comprehensive image features of the target images. The comprehensive image features include image time, geographic coordinates, contour color, and building structure. Based on the comprehensive image features as the division standard, divide the target images into image sets;

[0170] S3: Construct a library architecture with a data layer, and correspondingly import the image sets into the data layer of the library architecture to generate an image database;

[0171] S4: Build an associated channel with an on-off point in the image database, and based on the comprehensive image features as the configuration basis, configure the on-off conditions for controlling the on-off state switching of the on-off point on the associated channel;

[0172] S5: Parse the query requirements from the request data, combine the query requirements with the on-off conditions, control the on-off state of the on-off point, and select the query mode corresponding to the on-off state.

[0173] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention.

Claims

1. A database management system based on architectural remote sensing images, characterized in that Including: An image recognition module, configured to receive the building remote sensing image of the target area, extract the basic parameters of the building remote sensing image, and identify the target image from the building remote sensing image; An image classification module, configured to extract the comprehensive image features of the target image. The comprehensive image features include image time, geographical coordinates, contour color, and building structure. Taking the comprehensive image features as the division criterion, the target image is divided into an image set, and the image set includes a semi-hidden set and an open set; A database construction module, configured to construct a library architecture with a data layer, and correspondingly import the image set into the data layer of the library architecture to generate an image database; The generation method of the image database is as follows: Establish a blank data group with a closed structure, construct two inner and outer combined data layers in the blank data group, and denote the data layer located inside as the inner layer and the data layer located outside as the outer layer; Respectively count the number of target images in the semi-hidden set and the open set to obtain the hidden quantity value and the open quantity value; Mark the same number of outer image positions as the open quantity value in the outer layer, and mark the same number of inner image positions as the hidden quantity value in the inner layer to construct the library architecture; Import all the target images in the semi-hidden set into the inner image positions of the inner layer one by one, forcing the inner layer to be converted into a hidden layer; Import all the target images in the open set into the outer image positions of the outer layer one by one, forcing the outer layer to be converted into an open layer, and denote the library architecture with a hidden layer and an open layer as the image database; A channel building module, configured to build an associated channel with breakpoints in the image database, and based on the comprehensive image features as the configuration basis, configure the break conditions for controlling the on-off state switching of the breakpoints on the associated channel. The on-off state includes the on state and the off state; The building method of the associated channel is as follows: Randomly mark a point position on the hidden layer and the open layer of the image database respectively, and denote them as the inner connection point and the outer connection point; Measure the distance between the inner connection point and the outer connection point to obtain the inner and outer connection value; Continuously adjust the position of the outer connection point on the open layer until the inner and outer connection value reaches the minimum value, then stop adjusting the position of the outer connection point, and denote one-fourth of the minimum value of the inner and outer connection value as the interval value; Build an associated channel with a two-way transmission link between the inner connection point and the adjusted outer connection point, and mark a point position corresponding to the length of one interval value away from the outer connection point on the associated channel, and denote it as the breakpoint; A query selection module, configured to parse the query requirements from the request data, combine the query requirements with the break conditions, control the on-off state of the breakpoint, and select the query mode corresponding to the on-off state.

2. The database management system based on building remote sensing images according to claim 1, wherein, The basic parameters include the abnormal area ratio and the area integrity; The extraction method of the abnormal area ratio is as follows: Taking the preset first length as the longitudinal segmentation criterion and the preset second length as the transverse segmentation criterion, divide A building remote sensing images into B sub-regions one by one; Respectively count the number of all pixel points in the B sub-regions of the A building remote sensing images to obtain B regional quantity values, and denote the sub-regions with the regional quantity value less than the regional calibration value as abnormal regions; Count the total quantity value of the abnormal areas in A building remote sensing images one by one, record it as the abnormal quantity value, and compare the abnormal quantity value with the total number of sub-areas to obtain the ratio of abnormal areas for A images; The expression of the ratio of abnormal areas is: ； Wherein, is the abnormal area ratio of the th building remote sensing image, = 1, 2, ..., A, is the abnormal value of the th building remote sensing image, is the total number of sub - regions of the th building remote sensing image.

3. The database management system based on building remote sensing images according to claim 2, wherein, The extraction method of regional integrity is: Mark the pixel values of all pixel points in B sub-areas of A building remote sensing images one by one, and mark the pixel points with pixel values less than the lower pixel limit value and pixel values greater than the upper pixel limit value as abnormal points; Connect the four inflection points of B sub-areas crosswise to form a diagonal line, and record the line segments between the four inflection points on the two diagonal lines and the intersection point of the two diagonal lines as the median lines, obtaining four median lines; Draw four pixel circles with equal radii and adjacent circumferences centered on the midpoints of the four median lines respectively, and count the number of abnormal points and the total number of pixel points within the four pixel circles respectively; Mark the pixel circles with the number of abnormal points less than four-fifths of the total number of pixel points as normal circles, and count the number of all normal circles in A building remote sensing images to obtain the normal quantity value for A images; Measure the radius of the pixel circle, the length and width of the building remote sensing image respectively through the scale, calculate the area of the normal circle based on the circle area formula, and after adding up the areas of all normal circles, compare with the total area of the building remote sensing image to obtain the regional integrity for A images; The expression of regional integrity is: ； In the formula, is the regional integrity of the th building remote sensing image, is the normal value of the th building remote sensing image, is the radius of the pixel circle, is the length of the th building remote sensing image, is the width of the th building remote sensing image.

4. The database management system based on building remote sensing images according to claim 3, characterized in that, The recognition method of the target image is: When the ratio of abnormal areas of the building remote sensing image is less than the abnormal area safety value and the regional integrity is greater than the regional integrity safety value, mark the building remote sensing image as the target image to obtain D target images; When there is a ratio of abnormal areas greater than or equal to the abnormal area safety value, or the regional integrity is less than or equal to the regional integrity safety value, do not mark the building remote sensing image as the target image.

5. The database management system based on building remote sensing images according to claim 4, characterized in that The extraction method of the contour color is: Identify the buildings in D target images one by one through computer technology, identify the edge lines of the buildings through the edge detection algorithm, and record the area inside the edge lines as the building area; Mark the pixel values of all pixel points in all building areas on D target images respectively, and summarize the pixel points with pixel values within the same color level to obtain E pixel sets; Count the number of pixel points in E pixel sets one by one, and mark the color level with the maximum number of pixel points as the D effective levels; Identify the text semantics and digital semantics of D effective levels through natural language processing technology, and combine the text semantics and digital semantics at the beginning and end to generate D contour colors.

6. The database management system based on building remote sensing images according to claim 5, characterized in that, The division method of the semi-hidden set and the open set is: In the order of the image time, take 1 as the first number, and sequentially number D target images in ascending order; Summarize the target images with the same geographical coordinates in ascending order of the number to generate the first image group; Among the target images with inconsistent geographical coordinates, summarize the target images with the same contour color and building structure to generate the second image group; Combine all the target images in the first image group and the second image group to generate an open set, and summarize all the remaining target images to generate a semi-hidden set.

7. A database management system based on building remote sensing images according to claim 6, characterized in that, The on-off condition is: when the open layer is insufficient to meet the query requirements, control the on-off point to switch from the closed state to the open state.

8. A database management system based on building remote sensing images according to claim 7, characterized in that, The method for identifying the on-off state is as follows: Identify the request semantics in the request data through natural language processing technology, and extract the keywords in the request semantics one by one; Record time, coordinates, color, and structure as demand words, record the keywords in the request data that contain any one of the demand words as valid words, and generate a query requirement after combining all the valid words; Count the number of valid words in the query requirement, and record it as the valid quantity value; When the valid quantity value is 1 and the valid word is the coordinate, control the on-off point to be in the closed state; When the valid quantity value is 1 and the valid word is not the coordinate, control the on-off point to be in the open state; When the valid quantity value is 2, 3, or 4, control the on-off point to be in the open state; The query modes include an independent query mode and a combined query mode. The selection methods for the independent query mode and the combined query mode are as follows: When the on-off state of the on-off point is the open state, select the combined query mode; When the on-off state of the on-off point is the closed state, select the independent query mode.

Images