A method and system for diagnosing structural damage of water-passing buildings based on flow video monitoring

Through a system based on flow-state video monitoring, the water surface line profile is processed using high-definition fog camera and image analysis module, the problems of complex construction and poor durability in the existing technology are solved, and the lossless and non-stable state of the structure of the water-passing building is achieved. Contact-based real-time monitoring reduces economic and labor costs.

CN113155860BActive Publication Date: 2024-11-15HUANENG LANCANG RIVER HYDROPOWER CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011503647.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-17
Publication Date
2024-11-15
Estimated Expiration
2040-12-17

AI Technical Summary

Technical Problem

The existing structural damage diagnosis methods for overwater buildings have problems such as complex construction, poor sensor durability, and difficulty in fully reflecting the overall working nature of the structure, resulting in the inability to detect damage in time and take measures.

Method used

The system based on flow-state video monitoring is adopted, including high-definition fog camera, intelligent wiper module, dedicated workstation and backend database. The water surface line profile is processed through the image analysis module, and the coordinates of characteristic points with normal working conditions are compared. If abnormal, the alarm will be activated. Stored in an abnormal flow database to realize lossless and contactless structural health status monitoring.

Benefits of technology

It realizes lossless and non-contact real-time observation of the healthy state of the structure of overwater buildings, reduces economic losses and labor costs, improves monitoring levels, and avoids potential defects and durability problems caused by sensor construction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113155860B_ABST
    Figure CN113155860B_ABST
Patent Text Reader

Abstract

The present invention relates to a method and system for diagnosing structural damage of water-passing buildings based on flow state video monitoring, the system comprising a high-definition mist-penetrating camera, a base, a special workstation and a computer display; the high-definition mist-penetrating camera is installed on the base; a cavity is provided in the base; the network interface and power interface of the high-definition mist-penetrating camera are installed in the cavity; an intelligent wiper module is installed on the high-definition mist-penetrating camera; the power interface, the computer display and the special workstation are respectively connected to the power supply through a power line; the network interface is connected to the special workstation through a data transmission line; the special workstation comprises an image analysis module, a background database and an alarm module. The present invention innovates a method of using video to monitor the flow state of the discharge and the water surface line to diagnose whether the structure of the water-passing building is damaged, which can timely discover abnormal flow states in the discharge process and take measures to stop the loss in time, and can be widely used in the fields of safety monitoring of discharge facilities, teaching and research.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of water conservancy and hydropower engineering and video monitoring, and in particular relates to a method and system for diagnosing structural damage of water-passing buildings based on flow video monitoring. Background Art

[0002] Water-passing structures undertake the important tasks of flood discharge and flow. Especially when the flood flow is large during the flood season, water-passing structures are in a long-term discharge state, and the flow velocity of water-passing structures in large hydropower projects is often as high as 40-50m / s. Under the long-term scouring of high-speed water flow, the probability of damage to water-passing structures is very high. According to incomplete statistics, 1 / 3 of water-passing structures have suffered varying degrees of damage, some of which are quite serious. If water-passing structures are damaged during the discharge, they cannot be discovered in time and measures cannot be taken in time due to various reasons such as untimely inspection by personnel, inability to observe clearly due to the influence of atomization, and water flow being blocked by structures, resulting in losses. With the development of high-definition camera technology, long-distance, fog-penetrating, and high-definition camera technology can replace manual real-time monitoring of the discharge process. Equipped with high-speed and high-reliability image processing and analysis technology, it can timely detect abnormal conditions of the discharge flow state and water surface line, thereby realizing the function of diagnosing structural damage to water-passing structures. Therefore, studying the structural damage diagnosis method of water-passing buildings based on flow video monitoring has important theoretical significance and practical value for realizing real-time monitoring of the operating status of water-passing buildings, ensuring structural safety, reducing economic losses and labor costs, and improving the monitoring level.

[0003] At present, the structural damage diagnosis method of water-passing buildings basically adopts sensor technology, which has the following main shortcomings: (1) The layout of sensors generally needs to be constructed on the structure of the water-passing building, which requires a lot of preparation work, complicated processes, many coordination parties, and a long time. In addition, construction quality defects will become a new cause of damage to water-passing buildings; (2) Sensor equipment is exposed to high-speed water flow for a long time, has poor durability, and has a high failure rate; (3) Sensor monitoring is all "point" observation, which is difficult to truly and comprehensively reflect the overall working state changes of the discharge structure. Therefore, how to overcome the shortcomings of the existing technology is a problem that needs to be solved urgently in this technical field. Summary of the invention

[0004] The purpose of the present invention is to solve the deficiencies of the prior art and to provide a method and system for diagnosing structural damage of water-passing buildings based on flow video monitoring.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] A structural damage diagnosis system for water-passing buildings based on flow-state video monitoring, comprising a high-definition fog-penetrating camera, a base, a dedicated workstation and a computer display;

[0007] The high-definition fog-penetrating camera is installed on a base; a cavity is provided in the base; a network interface and a power interface of the high-definition fog-penetrating camera are installed in the cavity;

[0008] The HD fog-penetrating camera is equipped with an intelligent wiper module, which is used to clean water droplets on the lens of the HD fog-penetrating camera in time to keep the lens clean.

[0009] The power interface, the computer monitor, and the dedicated workstation are connected to the power source through a power cord respectively;

[0010] The network interface is connected to a dedicated workstation via a data transmission line;

[0011] The dedicated workstation includes an image analysis module, a background database, and an alarm module;

[0012] The image analysis module is connected to the background database, the alarm module, and the computer display respectively;

[0013] The image analysis module is used to process the images captured by the high-definition fog-penetrating camera, analyze the water surface contour, and then compare the feature point coordinates of the obtained water surface contour with the image feature point coordinates of the corresponding normal working conditions in the background database. If the comparison result is abnormal, a command is sent to the alarm module to alarm;

[0014] The backend database is also used to store the images before processing by the image analysis module and the processed data;

[0015] The computer monitor is used to display the image before being processed by the image analysis module and the data obtained by the processing.

[0016] Furthermore, preferably, it also includes a protective cover; the protective cover is arranged outside the base and the high-definition fog-penetrating camera to protect the base and the high-definition fog-penetrating camera.

[0017] Furthermore, preferably, the background database also includes a normal flow state database and an abnormal flow state database; when the image analysis module compares the water surface line contour of the image captured by the high-definition fog-penetrating camera with the normal flow state data in the background database, if the comparison result is abnormal, the image before processing by the image analysis module and the processed data are stored in the abnormal flow state database; otherwise, they are stored in the normal flow state database.

[0018] The specific steps of water surface profile analysis are as follows:

[0019] a. Scan the image row by row and column by column to obtain the RGB color value of each pixel and save them as R i,j , G i,j , B i,j , where i is the pixel row number and j is the pixel column number;

[0020] b. Set the RGB similarity threshold a0 for adjacent pixel points in each row, set the discontinuous comparison number threshold n0, and set the continuous comparison number threshold m0;

[0021] c. Calculate the similarity values of adjacent pixel points from left to right:

[0022]

[0023] If a i,j ≥ a0, the discontinuous comparison number n 边 of the side wall area is 0; if a i,j < a0, then n 边 = n 边 + 1; when n 边 = n0, record the pixel coordinate value x i,左墙 of the clear left boundary of the side wall in the i-th row;

[0024] d. Continue to compare to the right from x i,左墙 If a i,j ≥ a0, the continuous comparison number m 水 of the water surface area is m 水 + 1; if a i,j < a0, then m 水 = 0; when m 水 = m0, record the pixel coordinate value x i,左水 of the clear left boundary of the water surface in the i-th row, and take the average of x i,左墙 and x i,左水 as the left boundary coordinate x i,左 of the water surface line;

[0025] e. Continue to compare to the right from x i,左水 If a i,j ≥ a0, the discontinuous comparison number n 水 of the water surface area is 0; if a i,j < a0, then n 水 = n 水 + 1; when n 水 = n0, record the pixel coordinate value x i,右水 of the clear right boundary of the water surface in the i-th row;

[0026] f. Continue to compare to the right from x i,右水 If a i,j ≥ a0, the continuous comparison number m 边 of the side wall area is m 边 + 1; if a i,j < a0, then m 边 = 0; when m 边 = m0, record the pixel coordinate value x i,右墙 of the clear right boundary of the water surface and the side wall in the i-th row, and take the average of x i,右水 and x i,右墙The mean of the right boundary coordinates of the water surface line is x i,右 ;

[0027] g. Calculate row by row according to steps c to f, and connect x i,左 and x i,右 As the left and right contours of the water surface line.

[0028] Furthermore, preferably, a0 is 0.85-0.95; n0 is 1-5; and m0 is 2-5.

[0029] Furthermore, it is preferred that the water surface contour feature point coordinates H i (X, Y) and the image feature point coordinates H′ corresponding to the normal working condition in the background database i (X,Y) comparison, when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X,Y)>10%, it is considered as abnormal flow state, the alarm is activated and the data is stored in the abnormal flow state database; when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X,Y)<10%, it is regarded as normal flow state and stored in the normal flow state database.

[0030] The present invention also provides a method for diagnosing structural damage of a water-passing building based on flow state video monitoring. The method uses the above-mentioned system for diagnosing structural damage of a water-passing building based on flow state video monitoring, and comprises the following steps:

[0031] Step (1), according to the flow characteristics of the leakage, several characteristic points are arranged on site to cover the entire shooting range as much as possible, anti-scouring and easy-to-identify marks are placed at the characteristic points, and their coordinates are measured and entered into the background database;

[0032] Step (2), storing the discharge flow pattern, water surface line and characteristic point data of the water-passing structure under normal working conditions, as well as the prototype observation data obtained in real time on site, in a normal flow pattern database; storing the discharge flow pattern, water surface line and characteristic point data of the water-passing structure under abnormal working conditions, as well as the abnormal original observation data actually occurring on site, in an abnormal flow pattern database;

[0033] Step (3), turn on the high-definition fog-penetrating camera, aim it at the discharge flow of the water-passing building, adjust the shooting height until the captured image covers the entire water surface and the side walls of the water-passing building; start the intelligent wiper module, adjust the aperture, focal length, exposure parameters and shutter speed to ensure that the captured image is clear;

[0034] Step (4), after obtaining an image with a resolution that meets the requirements, formal shooting is carried out, a high-definition image is taken every 10 minutes, and image processing and analysis are performed to determine the water surface line contour;

[0035] Step (5): calculate the water surface contour feature point coordinates H i (X, Y) and the image feature point coordinates H′ corresponding to the normal working condition in the background database i (X,Y) comparison, when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X,Y)>10%, it is considered as abnormal flow state, the alarm is activated and the data is stored in the abnormal flow state database; when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X,Y)≤10%, it is regarded as normal flow state and stored in the normal flow state database;

[0036] Step (6), after the leakage is completed, the high-definition fog-penetrating camera is turned off and all images are stored in the background database.

[0037] When the system of the present invention is in use, the water surface line profile is compared with the situation observed manually. If the situation does not match well, a0, n0, and m0 can be modified, and steps c to f can be repeated until the analysis accuracy requirements are met.

[0038] In the present invention, the principle of feature point selection is to cover the entire water surface contour as evenly as possible and include a certain number of fixed points with known coordinates.

[0039] In the present invention, the abnormal flow pattern database is mainly used to accumulate data for the subsequent analysis of the correlation between damage characteristics and leakage flow patterns. When the amount of data is large, it can also be used to review and compare data of frequently occurring abnormal working conditions.

[0040] The structural damage diagnosed in the present invention refers to the extent of structural damage including erosion pits, abrasion pits, cavitation pits, etc., which has caused an impact on the flow pattern of water flow that exceeds the tolerance range, that is, 10%.

[0041] In the present invention, the high-definition fog-penetrating camera has rainproof, fog-penetrating and vibration-resistant functions, adopts a relatively high shutter speed, satisfies the shooting effect of 40-50m / s high-speed dynamic water flow, and realizes the clear shooting function in the atomization area of ​​high-speed water flow.

[0042] The installation position of the base should be determined according to the image size, lens focal length, target size and actual conditions on site. The base has stability and anti-scouring characteristics. The base is equipped with a network interface and a power interface. The power interface can be used to charge the high-definition fog-penetrating camera and transmit the captured images to a dedicated workstation in real time.

[0043] The dedicated workstation has powerful image processing capabilities, large capacity, high speed and high reliability.

[0044] In the present invention, the feature points refer to the feature points extracted from the image where the target is clear, easy to identify, and the position does not change in order to improve the accuracy of image registration. After the image analysis, the alarm function is activated when the difference in the water surface line is greater than the specified threshold.

[0045] The background database stores discharge flow state images, water surface line data and feature point data of water-passing structures, which are obtained through prototype observation, numerical simulation, physical model test and other methods and have been verified to meet the measurement accuracy requirements, including normal working status database and abnormal working status database of water-passing structures.

[0046] High-definition fog-penetrating cameras and bases should be equipped with protective covers to prevent adverse weather conditions or human damage when working in the field.

[0047] The image processing of the image analysis module includes water surface line analysis, feature point extraction, and feature point abnormality judgment; the background database stores flow diagrams, water surface lines and feature point data under various working conditions of water-passing buildings.

[0048] The installation operation of the system of the present invention is as follows: on the side perpendicular to the water flow direction of the water-passing building, determine the shooting position according to the image size, lens focal length, target object size and actual conditions on site; install a base at the shooting position; place the high-definition fog-penetrating camera on the base and fix it, and connect the power interface and network interface; according to the transmission distance requirements and the on-site network conditions, install a dedicated workstation at the corresponding position, connect it to the network interface of the high-definition fog-penetrating camera, and receive the image data transmitted by the high-definition fog-penetrating camera in real time.

[0049] The high-definition resolution of the high-definition fog-penetrating camera of the present invention is required to be no less than 2560*1440.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] (1) Achieve non-destructive and non-contact observation of the structural health status of water-passing buildings. The present invention uses long-distance, fog-penetrating, high-definition camera technology to shoot the flow pattern of the discharge, and uses the causal relationship that structural damage will have a certain impact on the flow pattern of the water to perform structural health diagnosis. It does not require destructive construction on the structure of the water-passing building itself, and avoids the disadvantage of forming new defect inducements due to the installation of sensors on the structure.

[0052] (2) It can fully and truly reflect the overall health status of the drainage structure. The present invention does not observe certain "points", but observes the overall drainage flow pattern, because defects at any point and defects with certain threats will inevitably lead to changes in the drainage flow pattern. Therefore, by observing the drainage flow pattern, it can be determined whether the structure itself has been damaged.

[0053] (3) Economical, convenient and fast. The present invention does not require coordination of approval and scheduling by all parties, has a small amount of preparation work, a simple process, requires few people, and the equipment can be recycled, with low labor and equipment costs.

[0054] (4) High reliability and durability. The present invention does not directly contact the high-speed water flow, thus avoiding the failure of the sensor caused by the high-speed water flow. The high-definition fog-penetrating camera is turned on during shooting and protected when not in use, with high reliability and durability.

[0055] In summary, the structural damage diagnosis method for water-passing buildings based on flow state video monitoring provided by the present invention is economical, simple, fast, highly reliable, and durable, and can comprehensively and truly reflect the health status of the discharge structure, and can perform non-destructive and non-contact real-time observation of the structural health status of water-passing buildings. It is widely used in safety monitoring of water-passing buildings in hydropower engineering and other industries, high-speed water flow state monitoring, scientific research, education and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0057] Figure 1 It is a structural schematic diagram of a water-passing building structural damage diagnosis system based on flow state video monitoring of the present invention;

[0058] Figure 2 It is a diagram of the software and hardware system architecture of the present invention;

[0059] Figure 3 This is a schematic diagram of the structural damage identification and diagnosis process of flooded buildings based on flow video monitoring;

[0060] Figure 4 It is a schematic diagram of the water surface profile analysis process;

[0061] Figure 5 This is a real shot of the discharge flow pattern of the water-passing structure;

[0062] Figure 6 It is the result of water surface contour analysis;

[0063] Figure 7 A map of the water surface and its contour lines.

[0064] In the figure, 1-high-definition fog-penetrating camera; 2-intelligent wiper module; 3-base; 4-network interface; 5-power interface; 6-power cord; 7-data transmission line; 8-computer monitor; 9-dedicated workstation; 10-protective cover; 11-power supply; 12-image analysis module; 13-backend database; 14-alarm module. DETAILED DESCRIPTION

[0065] The present invention is further described in detail below in conjunction with embodiments.

[0066] Those skilled in the art will appreciate that the following examples are only used to illustrate the present invention and should not be considered to limit the scope of the present invention. If no specific techniques or conditions are specified in the examples, the techniques or conditions described in the literature in the art or the product specifications are used. If the manufacturer of the materials or equipment used is not specified, they are all conventional products that can be purchased.

[0067] Those skilled in the art will appreciate that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" to another element, it may be directly connected to the other element, or there may be intermediate elements. In addition, the "connection" used herein may include wireless connections.

[0068] In the description of the present invention, unless otherwise specified, "plurality" means two or more than two. The terms "inside", "upper", "lower", etc., indicating positions or state relationships, are based on the positions or state relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific position, be constructed and operate in a specific position, and therefore cannot be understood as limiting the present invention.

[0069] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "provided with" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention will be understood according to specific circumstances.

[0070] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0071] like Figure 1 As shown, a structural damage diagnosis system for water-passing buildings based on flow video monitoring includes a high-definition fog-penetrating camera 1, a base 3, a dedicated workstation 9 and a computer display 8;

[0072] The high-definition fog-penetrating camera 1 is installed on the base 3; a cavity is provided in the base 3; a network interface 4 and a power interface 5 of the high-definition fog-penetrating camera 1 are installed in the cavity;

[0073] The high-definition fog-penetrating camera 1 is equipped with an intelligent wiper module 2; the intelligent wiper module 2 is used to clean water droplets on the lens of the high-definition fog-penetrating camera 1 in time to keep the lens clean;

[0074] The power interface 5, the computer display 8, and the dedicated workstation 9 are connected to the power source 11 via a power line 6 respectively;

[0075] The network interface 4 is connected to the dedicated workstation 9 via a data transmission line 7;

[0076] The dedicated workstation 9 includes an image analysis module 12, a backend database 13 and an alarm module 14;

[0077] The image analysis module 12 is connected to the backend database 13, the alarm module 14, and the computer display 8 respectively;

[0078] The image analysis module 12 is used to process the image captured by the high-definition fog-penetrating camera 1, analyze the water surface line contour, and then compare the obtained feature point coordinates of the water surface line contour with the image feature point coordinates corresponding to the normal working condition in the background database 13. If the comparison result is abnormal, a command is sent to the alarm module 14 to alarm;

[0079] The backend database 13 is also used to store the images before being processed by the image analysis module 12 and the data obtained by the processing;

[0080] The computer display 8 is used to display the image before being processed by the image analysis module 12 and the data obtained by the processing.

[0081] Preferably, a protective cover 10 is also included; the protective cover 10 is arranged outside the base 3 and the high-definition fog-penetrating camera 1 to protect the base 3 and the high-definition fog-penetrating camera 1.

[0082] Preferably, the background database 13 also includes a normal flow state database and an abnormal flow state database; when the image analysis module 12 compares the water surface line contour of the image captured by the high-definition haze-penetrating camera 1 with the normal flow state data in the background database and the comparison result is abnormal, the image and the data obtained after the processing by the image analysis module 12 are stored in the abnormal flow state database; otherwise, they are stored in the normal flow state database.

[0083] The specific steps for the water surface line contour analysis are as follows:

[0084] a. Scan the image row by row and column by column to obtain the RGB color values of each pixel point, and save them as R i,j , G i,j , B i,j , where i is the pixel row number and j is the pixel column number;

[0085] b. Set the RGB similarity threshold a0 for adjacent pixel points in each row, set the discontinuous comparison number threshold n0, and set the continuous comparison number threshold m0;

[0086] c. Calculate the similarity value of adjacent pixel points from left to right:

[0087]

[0088] If a i,j ≥ a0, the discontinuous comparison number n 边 of the side wall area = 0; if a i,j < a0, then n 边 = n 边 + 1; when n 边 = n0, record the pixel coordinate value x i,左墙 of the clear boundary of the left side wall of the i-th row;

[0089] d. Continue to compare from x i,左墙 to the right. If a i,j ≥ a0, the continuous comparison number m 水 of the water surface area = m 水 + 1; if a i,j < a0, then m 水 = 0; when m 水 = m0, record the pixel coordinate value x i,左水 of the clear left boundary of the water surface in the i-th row, and take the average value of x i,左墙 and x i,左水 as the left boundary coordinate x i,左 of the water surface line;

[0090] e. Continue to compare from x i,左水 to the right. If a i,j ≥ a0, the discontinuous comparison number n 水 of the water surface area = 0; if a i,j < a0, then n水 = n 水 + 1; When n 水 = n0, record the pixel coordinate value x of the clear right boundary of the water surface in the i-th row i,右水 ;

[0091] f. Continue to compare to the right from x i,右水 . If a i,j ≥ a0, the continuous comparison number m of the side wall area 边 = m 边 + 1; If a i,j < a0, then m 边 = 0; When m 边 = m0, record the pixel coordinate value x of the clear right boundary of the side wall of the water surface in the i-th row i,右墙 , take the average value of x i,右水 and x i,右墙 as the right boundary coordinate x of the water surface line i,右 ;

[0092] g. Calculate row by row according to steps c to f, and connect x i,左 and x i,右 respectively as the left and right contours of the water surface line.

[0093] Preferably, a0 is 0.85 - 0.95; n0 is 1 - 5; m0 is 2 - 5.

[0094] Preferably, compare the coordinate H i (X, Y) of the characteristic points of the water surface line contour with the coordinate H' i (X, Y) of the corresponding image characteristic points under normal working conditions in the background database 13. When |H i (X, Y) - H' i (X, Y)| / H' i (X, Y)> 10%, it is regarded as an abnormal flow pattern, start the alarm and store the data in the abnormal flow pattern database; when |H i (X, Y) - H' i (X, Y)| / H' i (X, Y)< 10%, it is regarded as a normal flow pattern and stored in the normal flow pattern database.

[0095] The method for diagnosing the structural damage of a water conveyance structure based on flow pattern video monitoring, using the above-mentioned system for diagnosing the structural damage of a water conveyance structure based on flow pattern video monitoring, includes the following steps:

[0096] Step (1), aiming at the characteristics of the discharge flow pattern, arrange several characteristic points on site to cover the entire shooting range as much as possible. Place erosion-resistant and easily recognizable marks at the characteristic points, measure their coordinates, and input them into the background database;

[0097] Step (2), storing the discharge flow pattern, water surface line and characteristic point data of the water-passing structure under normal working conditions, as well as the prototype observation data obtained in real time on site, in a normal flow pattern database; storing the discharge flow pattern, water surface line and characteristic point data of the water-passing structure under abnormal working conditions, as well as the abnormal original observation data actually occurring on site, in an abnormal flow pattern database;

[0098] Step (3), turn on the high-definition fog-penetrating camera, aim it at the discharge flow of the water-passing building, adjust the shooting height until the captured image covers the entire water surface and the side walls of the water-passing building; start the intelligent wiper module, adjust the aperture, focal length, exposure parameters and shutter speed to ensure that the captured image is clear;

[0099] Step (4), after obtaining an image with a resolution that meets the requirements, formal shooting is carried out, a high-definition image is taken every 10 minutes, and image processing and analysis are performed to determine the water surface line contour;

[0100] Step (5): calculate the water surface contour feature point coordinates H i (X, Y) and the image feature point coordinates H′ corresponding to the normal working condition in the background database i (X,Y) comparison, when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X,Y)>10%, it is considered as abnormal flow state, the alarm is activated and the data is stored in the abnormal flow state database; when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X,Y)≤10%, it is regarded as normal flow state and stored in the normal flow state database;

[0101] Step (6), after the leakage is completed, the high-definition fog-penetrating camera is turned off and all images are stored in the background database.

[0102] Application Example 1

[0103] like Figure 1 As shown, the structural damage diagnosis device for flooded buildings based on flow video monitoring includes a high-definition fog-penetrating camera 1 embedded with an intelligent wiper module 2, a base 3 for installing the high-definition fog-penetrating camera 1, a network interface 4 and a power interface 5 installed in the cavity of the base 3, a data transmission line 7 connecting the high-definition fog-penetrating camera 1 and a dedicated workstation 9, a power line 6 connecting the high-definition fog-penetrating camera 1 and a power supply 11, a dedicated workstation 9 equipped with an image analysis module 12, a computer display 8 connected to the dedicated workstation 9 for displaying analysis results, and a protective cover 10 for covering the high-definition fog-penetrating camera 1 and the base 3.

[0104] The installation operation is as follows: the intelligent wiper module 2 is embedded into the high-definition fog-penetrating camera 1, and the installation position of the high-definition fog-penetrating camera 1 is determined on the side perpendicular to the water flow direction of the flood-passing building according to the image size, lens focal length, target size and actual conditions on site; the base 3 is installed at the shooting position, and the bottom of the base 3 is set as a cavity, and the cavity is provided with a network interface 4 and a power interface 5; the high-definition fog-penetrating camera 1 is fixed on the base 3, and the power interface 5 and the network interface 4 are connected; according to the transmission distance requirements and the on-site network conditions, a dedicated workstation 9 is installed at the corresponding position, connected to the network interface 4 of the high-definition fog-penetrating camera 1, and used to receive the image data transmitted by the high-definition fog-penetrating camera 1 in real time; an image analysis module 12 is installed on the dedicated workstation 9 for water surface line analysis, feature point extraction, and feature point abnormality judgment; a background database 13 is constructed on the dedicated workstation 9 for storing flow diagrams, water surface lines and feature point data under various working conditions of flood-passing buildings; after the discharge is completed, the high-definition fog-penetrating camera 1 is disassembled and placed in a dedicated box, and the protective cover 10 is covered on the base 3.

[0105] The protective cover 10 is not covered during the shooting process. After the shooting is finished, if the camera is not used for a long time, the camera should be removed and placed in a special box. If the shooting is only temporarily interrupted, such as waiting for working conditions to be adjusted, the protective cover should be covered on the base 3 and the high-definition fog-penetrating camera 1.

[0106] A method for identifying and diagnosing structural damage of a water-passing building based on flow video monitoring, using the above device, and the steps are as follows:

[0107] (1) Connect the power cable 6 and the data transmission cable 7, turn on the high-definition fog-penetrating camera 1, aim at the discharge flow of the water-passing building, adjust the shooting height and shooting angle, and try to take several images. The captured images should cover the entire water surface and the side walls of the water-passing building;

[0108] (2) Start the smart wiper module 2, adjust the aperture, focal length, exposure parameters and shutter speed, and take a few test photos to ensure that the captured images are clear;

[0109] (3) According to the adjusted shooting height, angle and shooting parameters, a high-definition image is taken every 10 minutes, transmitted to the dedicated workstation 9, and the image analysis module 12 is run to perform image processing and analysis;

[0110] (4) Observe the analysis results of the image processing and analysis software 12 in real time on the computer display 8, and handle the warning abnormal information in time;

[0111] (5) After the image is captured, the intelligent wiper module 2 and the high-definition fog-penetrating camera 1 are turned off, and the high-definition fog-penetrating camera 1 is removed and placed in a dedicated box; the protective cover 10 is covered on the base 3;

[0112] (6) Determine the water surface line profile analysis parameters, and the steps are as follows. The on-site actual shooting of the discharge flow pattern of the water conveyance structure is as shown in Figure 5 the figure. Taking this photo as an example, conduct water surface line analysis.

[0113] a. Scan the image row by row and column by column, obtain the RGB color values of each pixel point, and save them as R i,j , G i,j , B i,j respectively, where i is the pixel row number (i = 1 to 2101), and j is the pixel column number (j = 1 to 1931);

[0114] b. For the example object Figure 5 The water surface line is of the up-and-down type. Therefore, it is necessary to compare the pixel values of the image column by column. Set the RGB similarity threshold a0 = 0.95 for adjacent pixel points in each column, set the discontinuous comparison number threshold n0 = 1, and set the continuous comparison number threshold m0 = 3;

[0115] c. Calculate the similarity value of adjacent pixel points from top to bottom. Taking the comparison of the pixel points in the first row and the second row of the first column as an example, R 1,1 = 88, G 1,1 = 116, B 1,1 = 156, R 2,1 = 86, G 2,1 = 114, B 2,1 = 154, then The discontinuous comparison number n 边 in the side wall area = 0. Continue to compare downward. When j = 713, a 713,1 = 0.94 < a0. At this time, n 边 = 1 = n0. Record the pixel coordinate value x 上边界,1 of the clear boundary of the upper boundary of the first column = 713;

[0116] d. Continue to compare downward from i = x 1,上边界 . a 714,1 = 0.91 < a0, then the continuous comparison number m 水 in the water surface area = 0, a 715,1 = 0.86 < a0, then m 水 = 0, a 716,1 = 0.93 < a0, then m 水 = 0, a 717,1 = 0.98 ≥ a0, then m 水 = 1, a 718,1 = 0.99 ≥ a0, then m 水 = 2, a 719,1 = 0.99 ≥ a0. At this time, m 水 = 3 = m0. Record the pixel coordinate value x 上水,1 of the clear boundary on the water surface of the first column = 719. Take x 上边界,1and x 上水,1 The mean value x of 上,1 = 716 is used as the upper coordinate of the water surface line;

[0117] e. Starting from i = x 上水,1 Continue to compare downward until j = 1019, at this time a 1019,1 = 0.94 < a0, and at this time n 水 = 1 = n0, record the pixel coordinate value x of the clear boundary under the water surface in the first column 下水,1 = 1019;

[0118] f. Starting from i = x 下水,1 Continue to compare downward, a 1020,1 = 0.94 < a0, then the continuous comparison number m of the water surface area 水 = 0, a 1021,1 = 0.95 ≥ a0, then m 水 = 1, a 1022,1 = 0.96 ≥ a0, then m 水 = 2, a 1023,1 = 0.98 ≥ a0, then m 水 = 3, at this time m 水 = m0, record the pixel coordinate value x of the clear boundary under the first column 下边界,1 = 1023, take the mean value x of x 下边界,1 and x 下水,1 The mean value x of 下,1 = 1021 is used as the lower coordinate of the water surface line;

[0119] g. Calculate column by column according to steps c to f, and connect x 上,j (j = 1 ~ 1931) as the upper contour of the water surface line, connect x 下,j (j = 1 ~ 1931) as the lower contour of the water surface line, as Figure 6 Shown by the two black lines above and below, through manual observation and comparison, it is found that the recognized water surface line contour better envelopes the white highly aerated water body in the figure, and the recognition accuracy meets the analysis requirements.

[0120] (7) Taking the upper contour line of the water surface line shown in Figure 6 as an example, extract 10 feature points along the x direction, evenly covering the entire contour line. The coordinate values of the extracted feature points are (1, 716), (211, 622), (421, 549), (631, 556), (841, 557), (1051, 588), (1261, 647), (1471, 740), (1681, 811), (1891, 951).

[0121] (8) The extracted feature point coordinates are compared with the coordinates in the background database under normal conditions. The X coordinates are selected to be consistent during the comparison. The results are shown in Table 1. It can be seen that the difference between the extracted feature point Y coordinate and the coordinate Y' in the background database under normal conditions is within 10%. Therefore, this is a normal state, and no alarm is activated. The coordinate data is stored in the normal flow state database.

[0122] Table 1

[0123] X Extract feature point Y Database normal status Y' difference(%) 1 716 666 7 211 622 585 6 421 549 505 8 631 556 595 7 841 557 574 3 1051 588 553 6 1261 647 589 9 1471 740 784 6 1681 811 827 2 1891 951 903 5

[0124] Application Example 2

[0125] The difference between Application Example 2 and Application Example 1 is that the last two steps are different, and the rest are the same.

[0126] (7) Figure 7 Taking the right contour line of the water surface line shown in the figure as an example to extract feature points, 10 feature points are selected along the y direction to evenly cover the entire contour line. The coordinates of the extracted feature points are (207, 5), (209, 45), (210, 85), (212, 125), (221, 165), (260, 205), (314, 245), (294, 285), (299, 325), (366, 365), and (392, 405).

[0127] (8) The extracted feature point coordinates are compared with the coordinates in the background database under normal conditions. The Y coordinates are selected to be consistent during the comparison. The results are shown in Table 2. It can be seen that starting from Y=205, the difference between the extracted feature point X coordinate and the coordinate X' in the background database under normal conditions exceeds 10%, and even reaches 20-44%, indicating that the structure has been severely damaged at this time. The alarm is activated and the data is stored in the abnormal flow state database.

[0128] Table 2

[0129]

[0130]

[0131] The existing methods basically rely on naked eye recognition, which has the disadvantages of being untimely and inaccurate. On-site inspection personnel cannot observe clearly due to various reasons such as fogging, structural obstruction, etc., and cannot observe 24 hours a day due to physical tolerance. They often go to the site for observation after the leakage is over, resulting in the inability to discover abnormal phenomena in time. The high-definition fog-penetrating camera of the present invention is equipped with an intelligent wiper module, which can solve the impact of atomized water droplets on clarity, and can be placed in a position not obstructed by structures to obtain the best observation field of view, and can observe 24 hours a day.

[0132] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A structural damage diagnosis system for flooded buildings based on flow video monitoring, characterized in that: It includes a high-definition fog-penetrating camera (1), a base (3), a dedicated workstation (9) and a computer monitor (8); The high-definition fog-penetrating camera (1) is mounted on a base (3); a cavity is provided in the base (3); a network interface (4) and a power interface (5) of the high-definition fog-penetrating camera (1) are mounted in the cavity; The high-definition fog-penetrating camera (1) is equipped with an intelligent wiper module (2); the intelligent wiper module (2) is used to promptly clean water droplets on the lens of the high-definition fog-penetrating camera (1) to keep the lens clean; The power interface (5), the computer display (8), and the dedicated workstation (9) are respectively connected to a power source (11) via a power line (6); The network interface (4) is connected to a dedicated workstation (9) via a data transmission line (7); The dedicated workstation (9) includes an image analysis module (12), a background database (13) and an alarm module (14); The image analysis module (12) is respectively connected to the backend database (13), the alarm module (14), and the computer display (8); The image analysis module (12) is used to process the image captured by the high-definition fog-penetrating camera (1), analyze the water surface line contour, and then compare the obtained feature point coordinates of the water surface line contour with the image feature point coordinates corresponding to normal working conditions in the background database (13); if the comparison result is abnormal, a command is sent to the alarm module (14) to issue an alarm; The backend database (13) is also used to store the image before being processed by the image analysis module (12) and the data obtained by the processing; The computer display (8) is used to display the image before being processed by the image analysis module (12) and the data obtained by the processing; The specific steps of water surface profile analysis are as follows: a. Scan the image row by row and column by column to obtain the RGB color value of each pixel and save them as R i,j , G i,j , B i,j , where i is the pixel row number and j is the pixel column number; b. Set the RGB similarity threshold a0 for each row of adjacent pixels, the discontinuous contrast number threshold n0, and the continuous contrast number threshold m0; c. Calculate the similarity values ​​of adjacent pixels from left to right: ; If a i,j ≥ a0, the discontinuous comparison number n of the side wall area 边 = 0; if a i,j < a0, then n 边 = n 边 + 1; when n 边 = n0, record the pixel coordinate value x of the clear boundary of the left side wall of the i-th row i , 左墙 ; d. From x i , 左墙 Continue to compare to the right. If a i,j ≥ a0, the continuous comparison number m of the water surface area 水 = m 水 + 1; if a i,j < a0, then m 水 = 0; when m 水 = m0, record the pixel coordinate value x of the left clear boundary of the water surface in the i-th row i , 左水 , take the average of x i , 左墙 and x i , 左水 as the left boundary coordinate x of the water surface line i , 左 ; e. From x i , 左水 Continue to compare to the right. If a i,j ≥ a0, the discontinuous comparison number n of the water surface area 水 = 0; if a i,j < a0, then n 水 = n 水 + 1; when n 水 = n0, record the pixel coordinate value x of the right clear boundary of the water surface in the i-th row i , 右水 ; f. From x i , 右水 Continue to compare to the right. If a i,j ≥ a0, the continuous comparison count m in the side wall area 边 = m 边 + 1; if a i,j < a0, then m 边 = 0; when m 边 = m0, record the pixel coordinate value x of the clear boundary of the right side wall of the water surface in the i-th row i , 右墙 , take x i , 右水 and x i , 右墙 and take the average value as the right boundary coordinate x of the water surface line i , 右 ; g. Calculate row by row according to steps c to f, and connect x i , 左 and x i , 右 As the left and right contours of the water surface line.

2. The structural damage diagnosis system for flooded buildings based on flow video monitoring according to claim 1 is characterized in that: It also includes a protective cover (10); the protective cover (10) is arranged outside the base (3) and the high-definition fog-penetrating camera (1) and is used to protect the base (3) and the high-definition fog-penetrating camera (1).

3. The structural damage diagnosis system for flooded buildings based on flow video monitoring according to claim 1 is characterized in that: The background database (13) also includes a normal flow state database and an abnormal flow state database; when the image analysis module (12) compares the water surface contour of the image captured by the high-definition fog-penetrating camera (1) with the normal flow state data in the background database, and the comparison result is abnormal, the image before processing by the image analysis module (12) and the processed data are stored in the abnormal flow state database; Otherwise, it is stored in the normal flow database.

4. The structural damage diagnosis system for flooded buildings based on flow video monitoring according to claim 1 is characterized in that: a0 is 0.85~0.95; n0 is 1~5; m0 is 2~5.

5. The structural damage diagnosis system for flooded buildings based on flow video monitoring according to claim 1 is characterized in that: The water surface contour feature point coordinates H i (X, Y) and the image feature point coordinates H′ corresponding to the normal working condition in the background database (13) i (X,Y) comparison, when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X, Y)>10%, it is considered as abnormal flow state, the alarm is activated and the data is stored in the abnormal flow state database; when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X, Y) < 10%, it is regarded as a normal flow state and stored in the normal flow state database.

6. A method for diagnosing structural damage of a flooded building based on flow video monitoring, using a system for diagnosing structural damage of a flooded building based on flow video monitoring as claimed in any one of claims 1 to 5, characterized in that: The steps include: Step (1), according to the flow characteristics of the leakage, several characteristic points are arranged on site to cover the entire shooting range as much as possible, anti-scouring and easy-to-identify marks are placed at the characteristic points, and their coordinates are measured and entered into the background database; Step (2), storing the discharge flow pattern, water surface line and characteristic point data of the water-passing structure under normal working conditions, as well as the prototype observation data obtained in real time on site, in a normal flow pattern database; storing the discharge flow pattern, water surface line and characteristic point data of the water-passing structure under abnormal working conditions, as well as the abnormal original observation data actually occurring on site, in an abnormal flow pattern database; Step (3), turn on the high-definition fog-penetrating camera, aim it at the discharge flow of the water-passing structure, and adjust the shooting height until the captured image covers the entire water surface and the side walls of the water-passing structure; Start the smart wiper module, adjust the aperture, focal length, exposure parameters and shutter speed to ensure clear images; Step (4), after obtaining an image with a resolution that meets the requirements, formal shooting is carried out, a high-definition image is taken every 10 minutes, and image processing and analysis are performed to determine the water surface line contour; Step (5): calculate the water surface contour feature point coordinates H i (X, Y) and the image feature point coordinates H′ corresponding to the normal working condition in the background database i (X,Y) comparison, when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X, Y)>10%, it is considered as abnormal flow state, the alarm is activated and the data is stored in the abnormal flow state database; when |H i (X,Y)-H′ i (X,Y)| / H′ i When (X, Y) ≤ 10%, it is regarded as a normal flow state and stored in the normal flow state database; Step (6), after the leakage is completed, the high-definition fog-penetrating camera is turned off and all images are stored in the background database.