Historical building remote monitoring and early warning device based on Internet of Things

Abstract

The invention discloses a historical building remote monitoring and early warning device based on the Internet of Things, which comprises a monitoring module, a monitoring and early warning system, an early warning notification module, a touchable display panel and a building repair unit, and relates to the technical field of image communication. According to the historical building remote monitoring and early warning device based on the Internet of Things, video images are collected through the monitoring module, image data are processed and transmitted according to the monitoring and early warning system, and the specific condition of monitored content is judged according to the processing result; and the monitoring result is transmitted to the touch display panel and the building repair unit through communication by the early warning notification module to display the monitoring result in time, and early warning and repair operation of corresponding personnel are performed according to the result, so that the personnel can be notified to perform processing operation in time when a problem is found without observing the video all the time by the personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of image communication, and in particular to a historical building remote monitoring and early warning device based on the Internet of Things. Background Art

[0002] Historical buildings refer to those buildings that have been determined and announced by the city or county people's government to have certain protection value and can reflect the historical features and local characteristics. Due to their long history, the buildings are easily damaged, so they need to be protected.

[0003] The reference patent name is: A video editing method, device, equipment and storage medium (patent publication number: CN117749959A, patent publication date: 2024-03-22). The method includes: first, in response to a preset trigger operation for a target video template, displaying at least one material adding entry corresponding to the target video template, receiving a first video material added for a first material adding entry in at least one material adding entry, and generating a first video clip and a freeze-frame video clip based on the first video material according to the video editing operation indicated by the target video template, and synthesizing the target video based on the first video clip and the freeze-frame video clip. The first video clip and the freeze-frame video clip can be automatically generated based on the first video material added by the user for synthesizing the target video, enriching the video editing method and improving the user experience.

[0004] Based on the description in the above-mentioned documents, existing historical buildings may have safety issues due to their age. During the monitoring process, even if video monitoring of an area is completed, personnel are still needed to observe the specific situation after the transmission of the video content. For example, when cracks form on the surface of the supporting wood of a historical building, it is not possible to determine whether it is a crack or an attachment during the image communication process, so that there is a safety hazard and personnel cannot be informed in time. For this reason, the present invention provides a remote monitoring and early warning device for historical buildings based on the Internet of Things. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a remote monitoring and early warning device for historical buildings based on the Internet of Things, which solves the problem that during the monitoring process, even if video monitoring of an area is completed, personnel are still required to observe the specific situation after the transmission of the video content. For example, when cracks are formed on the surface of the supporting wood of a historical building, it is not possible to determine whether it is a crack or an attachment during the image communication process.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a historical building remote monitoring and early warning device based on the Internet of Things, comprising: The monitoring module includes multiple acquisition sensors for collecting image data of the historical building itself, as well as monitoring and collecting data on the surrounding weather and temperature; The monitoring and early warning system is used to complete the transmission and processing of collected data, including: A data classification unit, which classifies the collected data according to different information categories to form a data set; The data processing unit extracts the data to be processed, determines the characteristic part after processing the data, establishes a spatial judgment model to judge the specific category of the characteristic, and generates an early warning signal based on the category result; The data transmission unit transmits the parameter results to the touch display panel, and sends the signal to the early warning notification module through the local area network to generate instructions for processing operations; The warning notification module is used to convert the received warning signal into instructions that need to be implemented and transmit it to inform personnel or perform processing operations; The touch display panel is used to display the real-time parameter information of the monitoring, and can also be used for personnel to control the instructions; The building restoration unit is used to inform personnel to complete local restoration operations on historical buildings through restoration equipment.

[0007] Preferably, the operation for data extraction in the data processing unit is: A1. Receive video images from video monitors in different directions; A2, and processing the video image according to different directions, by forming a frame image according to the segmentation algorithm of the video image; A3. According to the order of segmentation, the images containing historical building features are retained, and the image parts that do not contain historical building features are filtered to form a data set of frame images. .

[0008] Preferably, the specific steps of the segmentation algorithm in A2 are: a21. Select a video image in one direction and divide the image into video segments according to a set threshold; a22, dividing the video segment into a plurality of frame image data according to the number of frames and arranging them in order, performing feature comparison on adjacent frame images in the frame image data, and retaining the feature frame image as the frame image data of this video segment according to the result; a23. If the features of adjacent frame images in the frame image data change after comparison, the rear frame image arranged in sequence is retained as the feature frame image. Conversely, if the features of adjacent frame images in the frame image data do not change after comparison, the front image arranged in sequence is retained as the feature frame image, and the feature frame images of each video clip are classified in sequence.

[0009] Preferably, the specific algorithm used by the data processing unit to determine the characteristic part after processing the data is: B1. Take out a plurality of processed frame image data sets R, and select any feature frame image in any data set for recognition; B2, by establishing an enlarged moving window S (u, v) to move from the top to the bottom of the feature frame image, and determine the suspected feature part according to the change of pixel value; B3. Find the feature frame image in the frame image data set R that is located in the same position as the first feature frame image but is monitored in other directions, and establish a spatial judgment model based on the feature frame images in each direction to judge the suspicious feature part.

[0010] Preferably, the specific steps of the B2 window S for determining the suspicious feature part are: b21, by enlarging the moving window S (u, v) and moving it from top to bottom on the feature frame image, two pixel points in the moving window S are determined, and pixel recognition is performed according to the expression of the enlarged moving window S (u, v); b22, and the feature parts located in the enlarged moving window S (u, v) will be sharpened and displayed through new pixel values; b23. When the pixel value changes, the enlarged moving window S (u, v) will calculate the new pixel value according to the features in the window, and establish the edge of the pixel segmentation according to the new pixel value. The enlarged moving window S (u, v) will gradually move downward to obtain a complete closed-loop segmentation edge, and the part within the closed loop of the segmentation edge is the suspected feature part.

[0011] Preferably, the expression of the b21 enlarged moving window S (u, v) is: ; Among them, w(u, v) represents the weight of the enlarged moving window S(u, v), I(e, f) represents the pixel value of the first pixel, and I(e+u, f+v) represents the pixel value of the second pixel.

[0012] Preferably, the calculation steps of the pixel value change in the enlarged moving window S (u, v) in b22 are: C1, when the enlarged moving window S (u, v) moves to the feature frame image, its original pixel value is I1; C2, and the average pixel value of the feature frame image located at the enlarged moving window S (u, v) is calculated as I2; C3, and the new pixel value formula is: I3=I1-I2; And I3 is the new pixel value, which is the sharpened pixel value displayed by the enlarged moving window S (u, v).

[0013] Preferably, the steps of establishing the space judgment model in B3 are: D11, taking the processed feature frame image with the suspected feature part as the first plane, and taking the lower left corner node of the first plane as the starting point of the spatial coordinate axis in the spatial judgment model, and the extending directions along the edge of the first plane are respectively the X-axis direction and the Y-axis direction; D12, determining the suspected feature part and the common feature part, and using the common feature part to determine the feature frame images obtained in other directions as a plane to be inserted into the spatial coordinate axis of the spatial judgment model, and determining that the starting points of the images are the same, and after the starting points coincide, the edge of the feature frame image that is perpendicular to the edge of the first plane is used as the Z-axis direction; D13. Based on the edge boundary pixel points of the corresponding characteristic part on the plane, and according to the positions of the edge boundary pixel points on different axial planes in the coordinate system, the spatial position points about the edge boundary pixel points are formed, and finally the entity characteristic part is formed.

[0014] Preferably, the specific judgment steps of the B3 space judgment model for the suspicious feature part are: D21, select any pixel point inside the suspicious feature part, and mark the pixel point in the first plane as ; D22, judging whether the suspected feature part is a crack feature according to the coordinate values ​​of the pixel point in other planes; D23. At this time, the first plane is facing the direction of the suspected feature part. If the pixel point P is located on the Y / Z axis side or is not visible when it is located on the X / Z axis side, then the suspected feature part is concave, that is, it is a crack feature. Conversely, if the pixel point P is located on the Y / Z axis side or is visible when it is located on the X / Z axis side, then the suspected feature part is convex, that is, it is not a crack feature.

[0015] Preferably, the monitoring module includes multiple azimuth monitoring cameras located around the historical building, and meteorological collection sensors for weather and temperature monitoring, and both the monitoring cameras and the meteorological collection sensors complete data interaction with the touch display panel and the remote control terminal through a wireless local area network.

[0016] The present invention provides a historical building remote monitoring and early warning device based on the Internet of Things. Compared with the prior art, it has the following beneficial effects: (1) The IoT-based remote monitoring and early warning device for historical buildings collects video images through the monitoring module, processes and transmits image data based on the monitoring and early warning system, determines the specific situation of the monitored content based on the processing results, and communicates and transmits the monitoring results to the touch display panel and the building restoration unit through the early warning notification module to display the monitoring results in a timely manner, and makes early warnings and performs restoration operations on the corresponding personnel based on the results. In this way, there is no need for personnel to observe the video all the time, and when problems are found, personnel can be notified in a timely manner to perform processing operations.

[0017] (2) The IoT-based historical building remote monitoring and early warning device is provided with a data processing unit. The data processing unit forms frame image data after video segmentation, and processes the frame image data to determine the characteristic part and the suspected characteristic part according to a movable magnified moving window. In this way, the monitoring and early warning system is relied upon to complete the processing of the video image in the process of image communication, and problems are discovered in a timely manner. In order to avoid problems that are not clearly confirmed, the identification and judgment operation is performed on the suspected characteristic part to improve the efficiency and quality of monitoring.

[0018] (3) The IoT-based remote monitoring and early warning device for historical buildings establishes a spatial judgment model and forms a three-dimensional model of the physical object based on the image. It makes a judgment based on any pixel point inside the suspected feature part. By confirming the suspected feature part in one plane and observing whether the pixel points of the suspected feature part in other planes appear, it can more quickly judge whether the suspected feature part is a crack feature or other feature, and can more accurately discover problems and promptly inform personnel to handle them, thereby improving the protection of historical buildings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a principle block diagram of the remote monitoring and early warning device of the present invention; Figure 2 A schematic diagram of a feature judged as a non-crack by the spatial judgment model of the present invention; Figure 3 It is a schematic diagram of crack features judged by the spatial judgment model of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] See also Figure 1-Figure 3 , the present invention provides two technical solutions: Embodiment 1: A historical building remote monitoring and early warning device based on the Internet of Things, comprising: The monitoring module includes multiple acquisition sensors for collecting image data of the historical building itself, as well as monitoring and collecting data on the surrounding weather and temperature; The monitoring and early warning system is used to complete the transmission and processing of collected data, including: A data classification unit, which classifies the collected data according to different information categories to form a data set; The data processing unit extracts the data to be processed, determines the characteristic part after processing the data, establishes a spatial judgment model to judge the specific category of the characteristic, and generates an early warning signal based on the category result; The data transmission unit transmits the parameter results to the touch display panel, and sends the signal to the early warning notification module through the local area network to generate instructions for processing operations; The warning notification module is used to convert the received warning signal into instructions that need to be implemented and transmit it to inform personnel or perform processing operations; The touch display panel is used to display the real-time parameter information of the monitoring, and can also be used for personnel to control the instructions; The building restoration unit is used to inform personnel to complete local restoration operations on historical buildings through restoration equipment.

[0022] Among them, video images are collected through the monitoring module, and image data is processed and transmitted based on the monitoring and early warning system. The specific situation of the monitored content is judged according to the processing result, and the early warning notification module is used to communicate and transmit it to the touch display panel and the building repair unit to display the monitoring results in time, and make early warnings and corresponding personnel repair operations based on the results. In this way, there is no need for personnel to observe the video all the time, and when problems are found, they can be notified in time to perform processing operations.

[0023] In the embodiment of the present invention, the operation for data extraction in the data processing unit is: A1. Receive video images from video monitors in different directions; A2, and processing the video image according to different directions, by forming a frame image according to the segmentation algorithm of the video image; A3. According to the order of segmentation, the images containing historical building features are retained, and the image parts that do not contain historical building features are filtered to form a data set of frame images.

[0024] In the embodiment of the present invention, the specific steps of the segmentation algorithm in A2 are: a21. Select a video image in one direction and divide the image into video segments according to a set threshold; a22, dividing the video segment into a plurality of frame image data according to the number of frames and arranging them in order, performing feature comparison on adjacent frame images in the frame image data, and retaining the feature frame image as the frame image data of this video segment according to the result; a23. If the features of adjacent frame images in the frame image data change after comparison, the rear frame image arranged in sequence is retained as the feature frame image. Conversely, if the features of adjacent frame images in the frame image data do not change after comparison, the front image arranged in sequence is retained as the feature frame image, and the feature frame images of each video clip are classified in sequence.

[0025] Among them, by setting up a data processing unit, the video is divided into frame image data, and the frame image data is processed to determine the characteristic part and the suspected characteristic part according to the movable enlarged moving window. In this way, in the process of completing the image communication, the monitoring and early warning system is relied on to complete the processing of the video image and discover the problem in time. However, in order to avoid unclear problems, the identification and judgment operation is performed on the suspected characteristic part to improve the efficiency and quality of monitoring.

[0026] In the embodiment of the present invention, the specific algorithm for determining the characteristic part after the data processing unit processes the data is: B1. Take out a plurality of processed frame image data sets R, and select any feature frame image in any data set for recognition; B2, by establishing an enlarged moving window S (u, v) to move from the top to the bottom of the feature frame image, and determine the suspected feature part according to the change of pixel value; B3. Find the feature frame image in the frame image data set R that is located in the same position as the first feature frame image but is monitored in other directions, and establish a spatial judgment model based on the feature frame images in each direction to judge the suspicious feature part.

[0027] In the embodiment of the present invention, the specific steps of the B2 window S for determining the suspicious feature part are: b21, by enlarging the moving window S (u, v) and moving it from top to bottom on the feature frame image, two pixel points in the moving window S are determined, and pixel recognition is performed according to the expression of the enlarged moving window S (u, v); b22, and the feature parts located in the enlarged moving window S (u, v) will be sharpened and displayed through new pixel values; b23. When the pixel value changes, the enlarged moving window S (u, v) will calculate the new pixel value according to the features in the window, and establish the edge of the pixel segmentation according to the new pixel value. The enlarged moving window S (u, v) will gradually move downward to obtain a complete closed-loop segmentation edge, and the part within the closed loop of the segmentation edge is the suspected feature part.

[0028] Among them, the pixel value is the most basic unit of information in a digital image, and its size represents the brightness or color of the pixel. The calculation of the pixel value is to represent the brightness of the pixel through the pixel value in the existing grayscale image, usually represented by an integer of 0-255. The brightness of each pixel in the image can be obtained by averaging the values ​​of its corresponding RGB three components, which is an existing calculation method.

[0029] In the embodiment of the present invention, the expression of b21 enlarging the moving window S (u, v) is:

[0030] Among them, w(u, v) represents the weight of the enlarged moving window S(u, v), I(e, f) represents the pixel value of the first pixel, and I(e+u, f+v) represents the pixel value of the second pixel.

[0031] In the embodiment of the present invention, the calculation steps of the pixel value change in the enlarged moving window S (u, v) in b22 are: C1, when the enlarged moving window S (u, v) moves to the feature frame image, its original pixel value is I1; C2, and the average pixel value of the feature frame image located at the enlarged moving window S (u, v) is calculated as I2; C3, and the new pixel value formula is: I3=I1-I2; And I3 is the new pixel value, which is the sharpened pixel value displayed by the enlarged moving window S (u, v).

[0032] In the embodiment of the present invention, the steps of establishing the space judgment model in B3 are: D11, taking the processed feature frame image with the suspected feature part as the first plane, and taking the lower left corner node of the first plane as the starting point of the spatial coordinate axis in the spatial judgment model, and the extending directions along the edge of the first plane are respectively the X-axis direction and the Y-axis direction; D12, determining the suspected feature part and the common feature part, and using the common feature part to determine the feature frame images obtained in other directions as a plane to be inserted into the spatial coordinate axis of the spatial judgment model, and determining that the starting points of the images are the same, and after the starting points coincide, the edge of the feature frame image that is perpendicular to the edge of the first plane is used as the Z-axis direction; D13. Based on the edge boundary pixel points of the corresponding characteristic part on the plane, and according to the positions of the edge boundary pixel points on different axial planes in the coordinate system, the spatial position points about the edge boundary pixel points are formed, and finally the entity characteristic part is formed.

[0033] In the embodiment of the present invention, the specific judgment steps of the B3 space judgment model for the suspicious feature part are: D21, select any pixel point inside the suspicious feature part, and mark the pixel point in the first plane as ; D22, judging whether the suspected feature part is a crack feature according to the coordinate values ​​in other planes where the pixel point is located; D23. At this time, the first plane is facing the direction of the suspected feature part. If the pixel point P is located on the Y / Z axis side or is not visible when it is located on the X / Z axis side, then the suspected feature part is concave, that is, it is a crack feature. Conversely, if the pixel point P is located on the Y / Z axis side or is visible when it is located on the X / Z axis side, then the suspected feature part is convex, that is, it is not a crack feature.

[0034] Furthermore, after the suspected feature parts are detected in other azimuth planes, the spatial position of a certain pixel point of the suspected feature part can also be determined through the operations of D21-D23, thereby realizing the determination operation of the suspected feature part.

[0035] Among them, by establishing a spatial judgment model, and based on the spatial three-dimensional model of the real object composed of the image, and based on any pixel point inside the suspected feature part, judgment is made. By confirming the suspected feature part in one plane, observing whether the pixel points of the suspected feature part in other planes appear, it is possible to more quickly judge whether the suspected feature part is a crack feature or other feature, and to more accurately discover problems, and promptly inform personnel to deal with them, thereby improving the protection of historical buildings.

[0036] Embodiment 2: The difference compared with Embodiment 1 is that the monitoring module includes multiple azimuth monitoring cameras located around the historical building, and meteorological collection sensors for weather and temperature monitoring, and both the monitoring cameras and the meteorological collection sensors complete data interaction with the touch display panel and the remote control terminal through a wireless LAN.

[0037] The remote control terminal is a controller that can be directly controlled by personnel, and the remote control terminal interacts with the touch display panel to facilitate the output and acceptance of instructions.

[0038] Comparative experiment Now we conduct monitoring operations on buildings A and B, where the number of specific problems is known, and conduct synchronous video monitoring and acquisition operations by using the existing remote monitoring and early warning device and the remote monitoring and early warning device using the monitoring and early warning system. Now we conduct statistics and comparison on the building problems identified by the existing remote monitoring and early warning device and the remote monitoring and early warning device using the monitoring and early warning system at the same time. The specific results of the percentage of problems found by monitoring are as follows: In summary, by performing synchronous video monitoring and collection operations through the existing remote monitoring and early warning device and the remote monitoring and early warning device using the monitoring and early warning system, the remote monitoring and early warning device using the monitoring and early warning system can discover more building problems and has a lower error rate in misjudgment of the problems discovered. Therefore, the remote monitoring and early warning device using the monitoring and early warning system is more convenient to use and has a higher accuracy rate, while the existing monitoring and early warning device can still be used.

[0039] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0040] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0041] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A historical building remote monitoring and early warning device based on the Internet of Things, characterized by: include: The monitoring module includes multiple acquisition sensors for collecting image data of the historical building itself, as well as monitoring and collecting data on the surrounding weather and temperature; The monitoring and early warning system is used to complete the transmission and processing of collected data, including: A data classification unit, which classifies the collected data according to different information categories to form a data set; The data processing unit extracts the data to be processed, and determines the characteristic part after processing the data. The specific algorithm for determining the characteristic part after processing the data is: B1. Select any feature frame image in any data set for recognition; B2, by establishing an enlarged moving window S (u, v) to move from the top to the bottom of the feature frame image, and determine the suspected feature part according to the change of pixel value; B3, searching for feature frame images in the data set that are located in the same position as the first feature frame image but are monitored in other directions, and establishing a spatial judgment model based on the feature frame images in each direction to judge the suspicious feature part; The data transmission unit transmits the parameter results to the touch display panel, and sends the signal to the early warning notification module through the local area network to generate instructions for processing operations; The warning notification module is used to convert the received warning signal into instructions that need to be implemented and transmit it to inform personnel or perform processing operations; Touchable display panel, used to display real-time parameter information of monitoring; The building restoration team informs personnel to perform local restoration operations on historical buildings through restoration equipment.

2. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 1 is characterized in that: The operations for data extraction in the data processing unit are: A1. Receive video images from video monitors in different directions; A2, and processing the video image according to different directions, by forming a frame image according to the segmentation algorithm of the video image; A3. According to the order of segmentation, the images containing historical building features are retained, and the image parts that do not contain historical building features are filtered to form a data set of frame images. .

3. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 2 is characterized in that: The specific steps of the segmentation algorithm in A2 are: a21. Select a video image in one direction and divide the image into video segments according to a set threshold; a22, dividing the video segment into a plurality of frame image data according to the number of frames and arranging them in order, performing feature comparison on adjacent frame images in the frame image data, and retaining the feature frame image as the frame image data of this video segment according to the result; a23. If the features of adjacent frame images in the frame image data change after comparison, the rear frame image arranged in sequence is retained as the feature frame image. Conversely, if the features of adjacent frame images in the frame image data do not change after comparison, the front image arranged in sequence is retained as the feature frame image, and the feature frame images of each video clip are classified in sequence.

4. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 1 is characterized in that: The specific steps of the B2 window S for determining the suspicious feature part are: b21, by enlarging the moving window S (u, v) and moving it from top to bottom on the feature frame image, two pixel points in the moving window S are determined, and pixel recognition is performed according to the expression of the enlarged moving window S (u, v); b22, and the feature parts located in the enlarged moving window S (u, v) will be sharpened and displayed through new pixel values; b23. When the pixel value changes, the enlarged moving window S (u, v) will calculate the new pixel value according to the features in the window, and establish the edge of the pixel segmentation according to the new pixel value. The enlarged moving window S (u, v) will gradually move downward to obtain a complete closed-loop segmentation edge, and the part within the closed loop of the segmentation edge is the suspected feature part.

5. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 4 is characterized in that: The expression of the b21 enlarged moving window S (u, v) is: ; Wherein, w(u, v) represents the weight of the enlarged moving window S(u, v), I(e, f) represents the pixel value of the first pixel, and I(e+u, f+v) represents the pixel value of the second pixel.

6. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 5 is characterized by: The calculation steps of the pixel value change in the enlarged moving window S (u, v) in b22 are as follows: C1, when the enlarged moving window S (u, v) moves to the feature frame image, its original pixel value is I1; C2, and the average pixel value of the feature frame image located at the enlarged moving window S (u, v) is calculated as I2; C3, and the new pixel value formula is: I3=I1-I2; And I3 is the new pixel value, which is the sharpened pixel value displayed by the enlarged moving window S (u, v).

7. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 1 is characterized in that: The steps for establishing the spatial judgment model in B3 are: D11, taking the processed feature frame image with the suspected feature part as the first plane, and taking the lower left corner node of the first plane as the starting point of the spatial coordinate axis in the spatial judgment model, and the extending directions along the edge of the first plane are respectively the X-axis direction and the Y-axis direction; D12, determining the suspected feature part and the common feature part, and using the common feature part to determine the feature frame images obtained in other directions as a plane to be inserted into the spatial coordinate axis of the spatial judgment model, and determining that the starting points of the images are the same, and after the starting points coincide, the edge of the feature frame image that is perpendicular to the edge of the first plane is used as the Z-axis direction; D13. Based on the edge boundary pixel points of the corresponding characteristic part on the plane, and according to the positions of the edge boundary pixel points on different axial planes in the coordinate system, the spatial position points about the edge boundary pixel points are formed, and finally the entity characteristic part is formed.

8. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 7 is characterized in that: The specific judgment steps of the B3 space judgment model for the suspicious feature part are: D21, select any pixel point inside the suspicious feature part, and mark the pixel point in the first plane as ; D22, judging whether the suspected feature part is a crack feature according to the coordinate values ​​of the pixel point in other planes; D23. At this time, the first plane is facing the direction of the suspected feature part. If the pixel point P is located on the Y / Z axis side or is not visible when it is located on the X / Z axis side, then the suspected feature part is concave, that is, it is a crack feature. Conversely, if the pixel point P is located on the Y / Z axis side or is visible when it is located on the X / Z axis side, then the suspected feature part is convex, that is, it is not a crack feature.

9. The device for remote monitoring and early warning of historical buildings based on the Internet of Things according to claim 1 is characterized in that: The monitoring module includes multiple azimuth monitoring cameras located around the historical building, and meteorological collection sensors for weather and temperature monitoring. The monitoring cameras and meteorological collection sensors can interact with the touch display panel and the remote control terminal through a wireless local area network to achieve data interaction.

Images