Active thermal imaging detection method and system for superficial damage of external protective wall

Abstract

The present invention discloses an active thermal imaging detection method and system for superficial damage of an outer protective wall, which relates to the field of building detection technology, and includes the steps of: obtaining a flight detection planning path of an unmanned aerial vehicle, the unmanned aerial vehicle is equipped with a heating lamp and a shooting camera, and the flight detection planning path includes a plurality of heating shooting points arranged in time sequence; when shooting and collecting the detection bi-light image corresponding to the shooting area of ​​the current heating shooting point, preheating the heating area corresponding to the next heating shooting point by the heating lamp; identifying wall damage and locating the damage position based on the detection bi-light image. The method provided by the present invention uses active thermal imaging to detect superficial damage on the wall, which can improve the environmental adaptability of infrared thermal imaging, improve detection accuracy, and automatically locate the damage position by detecting the spatial coordinate matching relationship between bi-light images.

Description

Technical Field

[0001] The present invention relates to the technical field of building detection, and in particular to an active thermal imaging detection method and system for superficial damage of an outer protective wall. Background Art

[0002] The main reasons for hollowing of building exterior walls are poor construction quality, aging or the influence of the external environment, which causes the bonding strength between the finishing layer and the base layer to gradually decrease over time. When the bonding strength does not meet the requirements, it may cause partial debonding of the finishing layer, forming hollows. If not reinforced in time, the hollow area will gradually expand, eventually leading to complete debonding of the finishing layer and causing accidents such as falling objects from high altitude.

[0003] At present, the main methods for detecting defects in building exterior wall finishes are the knocking method, the pull-out method, and the infrared thermal imaging method. Although the knocking method has a simple detection procedure, it has low detection efficiency, high risk, and lacks objectivity in the results; the pull-out method is destructive to wall facing tiles and is not suitable for large-scale detection; compared with other methods, the infrared thermal imaging method can scan the wall surface over a long distance and over a large area, and has the advantages of high efficiency and low cost. Although infrared thermal imaging has shown certain potential in identifying superficial damage, there are still some problems to be solved if this technology is to be applied to engineering practice on a large scale. The first is that the detection results are greatly affected by the interference of the external environment. When the meteorological conditions are not good (such as cloudy days, continuous low temperatures, etc.), the temperature difference of the wall will be very small, which greatly reduces the detection accuracy of infrared thermal imaging; secondly, it is cumbersome to rely on manual operation to take pictures one by one and it is difficult to locate the damage position.

[0004] In view of this, it is necessary to propose an active thermal imaging detection method and system for superficial damage of an exterior protective wall to solve or at least alleviate some of the above-mentioned defects. Summary of the invention

[0005] The main purpose of the present invention is to provide an active thermal imaging detection method and system for superficial damage of an outer protective wall, aiming to solve the technical problems in the prior art of inaccurate detection due to the influence of natural conditions on thermal infrared imaging, and cumbersome manual operation of sequential shooting and difficulty in locating the damage position.

[0006] To achieve the above object, the present invention provides an active thermal imaging detection method for superficial damage of an external protective wall, comprising the steps of:

[0007] S10, obtaining a flight inspection planning path of the UAV, the UAV is equipped with a heating lamp and a shooting camera, the flight inspection planning path is an S shape covering the area to be inspected, the flight inspection planning path includes a plurality of heating shooting points arranged in time sequence, when the UAV is at the current heating shooting point position, the shooting camera has a corresponding shooting area, when the UAV is at the current heating shooting point position, the heating lamp has a heating area for preheating the next adjacent heating shooting point;

[0008] S20, when capturing a detection bi-light image corresponding to a shooting area at a current heating shooting point, preheating a heating area corresponding to a next heating shooting point by a heating lamp;

[0009] If the flight test planning path extends horizontally, the drone works in the first posture. When working in the first posture, the heating lamp deflects horizontally along the current heating shooting point toward the next heating shooting point. The heating area is heated at an angle, wherein , is the imaging length, is the camera focal length, is the vertical distance between the camera and the wall to be detected. is the length of the heating area;

[0010] S30, identifying wall damage and locating the damage position based on detecting the bi-optical image.

[0011] Furthermore, using the formula Calculate and obtain the current acquisition frequency of the camera when working in the first posture, where: is the current horizontal flight speed of the drone, For the preheating cycle of the heating lamp, It is the preset overlap ratio of the detected bi-light images corresponding to horizontally adjacent heating shooting points.

[0012] Furthermore, using the formula Calculate and obtain the current preheating working power of the heating lamp, where: is the wall surface emissivity of the next heating shooting point, is a constant, is the heat absorption rate of the wall to be tested, k is the diffusion attenuation coefficient of the thermal radiation energy of the heating lamp, and Δt is the target temperature rise value of the heating lamp in the current preheating cycle.

[0013] Furthermore, if the planned path is to extend in a vertical direction, the drone works in the second posture, and the heating lamp deflects downward along the current shooting point toward the next shooting point in the second posture. angle;

[0014] in, is the imaging height dimension, is the camera focal length, is the vertical distance between the camera and the wall. is the height of the heating area.

[0015] Furthermore, using the formula Calculate and obtain the current acquisition frequency of the camera when working in the second posture, where: is the current vertical flight speed of the UAV, For the preheating cycle of the heating lamp, It is the preset overlap ratio of the detected bi-light images corresponding to the vertically adjacent heating shooting points.

[0016] Further, ≥ .

[0017] Furthermore, at the initial heating shooting point, the heating lamp and the lens of the shooting camera are controlled to face the wall, so that the current heating area coincides with the center point of the current shooting area; the heating area corresponding to the initial heating shooting point is heated; the lens of the shooting camera is kept unchanged, and the angle of the heating lamp is adjusted to Angle, preheat the heating area corresponding to the next heating shooting point.

[0018] Furthermore, the current posture of the drone is determined according to the coordinates of the current heating shooting point and the coordinates of the next heating shooting point. If there is a change in the lateral coordinate point, the drone works in the first posture; if there is a change in the longitudinal coordinate point, the drone works in the second posture.

[0019] Further, step S30 specifically includes:

[0020] S31, after the collected detection bi-optical image sequence is subjected to noise reduction and enhancement processing, a damage contour map of the crack and hollow area is obtained by an image segmentation method based on threshold and edge detection, and geometric information of the damage area is calculated according to the number of pixels in the damage contour map;

[0021] S32, converting the detected bi-optical image into a temperature grayscale image according to the temperature matrix, and then performing grayscale homogenization processing on the pixels with the same grayscale value in different images, obtaining the infrared orthophoto of the wall according to feature point matching and spatial physical information calculation, and realizing temperature standardization processing of the detected bi-optical image sequence;

[0022] S33, marking the identified damaged area contour map and geometric information at the corresponding position on the infrared orthophoto:

[0023] S34, obtaining a visible light orthophoto of the wall surface according to feature point matching and spatial physical information calculation;

[0024] S35, mapping the damaged area marked in the infrared orthophoto to the visible light orthophoto according to the spatial coordinate matching relationship.

[0025] Furthermore, an active thermal imaging detection system for superficial damage to an outer protective wall includes an unmanned aerial vehicle, a ground control system, and a ground computing system. The unmanned aerial vehicle is equipped with a shooting camera, a heating lamp, and an edge computing unit. The shooting camera is a thermal infrared and visible light camera. The heating lamp is directly below the shooting camera. The heating lamp can be set horizontally and movably. The heating lamp can be set downwardly and movably. The edge computing unit is used to determine the damage information in the detected dual-light image and feed the result back to the ground control system. The edge computing unit is also used to adjust the heating operating parameters of the heating lamp. The heating operating parameters include the pre-heating angle. The ground control system is used to adjust the flight parameters of the unmanned aerial vehicle. The ground computing system is used to implement the above-mentioned active thermal imaging detection method for superficial damage to the outer protective wall.

[0026] Compared with the prior art, the active thermal imaging detection method for superficial damage of an external protective wall provided by the present invention has the following beneficial effects:

[0027] The present invention provides an active thermal imaging detection method for superficial damage of an outer protective wall. First, the flight detection planning path of the drone is set to an S-shape extending downward and bending. The flight detection planning path includes multiple heating shooting points arranged in time sequence. When the drone is at the heating shooting point position, the dual-light camera has a corresponding shooting area. When the drone is at the current heating shooting point position, the heating lamp has a corresponding heating area. The drone can obtain all the detection dual-light images of the area to be detected by shooting in sequence along the detection planning path; when the detection dual-light image of the current shooting area is obtained at the current heating shooting point, the next shooting area is adaptively preheated, and the wall is actively preheated and the detection dual-light image is collected after heating to avoid the influence of natural low temperature on thermal infrared imaging; finally, the wall damage is identified and the damage position is located based on the detection dual-light image. The method of the present invention uses active thermal imaging to detect superficial damage on the wall, which can improve the environmental adaptability of infrared thermal imaging, improve the detection accuracy, and automatically locate the damage position by detecting the spatial coordinate matching relationship between dual-light images. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] 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 the structures shown in these drawings without paying creative work.

[0029] Figure 1 It is a schematic flow chart of an active thermal imaging detection method for superficial damage of an external protective wall in one embodiment of the present invention;

[0030] Figure 2 1 is a schematic diagram of a flight detection planning path in an embodiment of the present invention;

[0031] Figure 3 It is a schematic diagram of preheating the next heating shooting point when capturing and detecting a bi-light image at the current heating shooting point in one embodiment of the present invention;

[0032] Figure 4 is a schematic diagram of setting the horizontal deflection angle in one embodiment of the present invention;

[0033] Figure 5 is a schematic diagram of imaging of a binocular camera in an embodiment of the present invention;

[0034] Figure 6 The figure is a schematic structural diagram of an active thermal imaging detection system for superficial damage of an outer protective wall in one embodiment of the present invention.

[0035] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0036] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0037] 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.

[0038] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0039] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0040] Please refer to the attached Figure 1 , Figure 2 , Figure 3 , Figure 4 as well as Figure 5 The present invention provides an active thermal imaging detection method for superficial damage of an external protective wall, comprising the steps of:

[0041] S10, obtaining a flight inspection planning path of the UAV, the UAV is equipped with a heating lamp and a shooting camera, the flight inspection planning path is an S shape covering the area to be inspected, the flight inspection planning path includes a plurality of heating shooting points arranged in time sequence, when the UAV is at the current heating shooting point position, the shooting camera has a corresponding shooting area, when the UAV is at the current heating shooting point position, the heating lamp has a heating area for preheating the next adjacent heating shooting point (shooting area);

[0042] S20, when capturing the detection bi-light image corresponding to the shooting area at the current heating shooting point, preheating the heating area corresponding to the next heating shooting point (shooting area) by means of a heating lamp;

[0043] If the flight test planning path extends horizontally, the drone works in the first posture. When working in the first posture, the heating lamp deflects horizontally along the current heating shooting point toward the next heating shooting point. The heating area is heated at an angle, wherein , is the imaging length, is the camera focal length, is the vertical distance between the camera and the wall to be detected. is the length of the heating area;

[0044] S30, identifying wall damage and locating the damage position based on detecting the bi-optical image.

[0045] The present invention provides an active thermal imaging detection method for superficial damage of an outer protective wall. First, the flight detection planning path of the drone is set to an S-shape extending downward and bending. The flight detection planning path includes multiple heating shooting points arranged in time sequence. When the drone is at the heating shooting point position, the dual-light camera has a corresponding shooting area. When the drone is at the current heating shooting point position, the heating lamp has a corresponding heating area. The drone can obtain all the detection dual-light images of the area to be detected by shooting in sequence along the detection planning path; when the detection dual-light image of the current shooting area is obtained at the current heating shooting point, the next shooting area is adaptively preheated, and the wall is actively preheated and the detection dual-light image is collected after heating to avoid the influence of natural low temperature on thermal infrared imaging; finally, the wall damage is identified and the damage position is located based on the detection dual-light image. The method of the present invention uses active thermal imaging to detect superficial damage on the wall, which can improve the environmental adaptability of infrared thermal imaging, improve the detection accuracy, and automatically locate the damage position by detecting the spatial coordinate matching relationship between dual-light images.

[0046] It can be understood that the flight detection planning path is an S-shape that extends horizontally and bends vertically and cyclically to cover the area to be detected. In the solution of the present invention, the heating lamp can be a flash lamp, and the shooting camera can be a dual-light camera. The flash lamp and the dual-light camera are used in coordination, and the heating angle of the flash lamp is adjusted so that the next area to be tested is preheated while the dual-light image is collected and detected, and the time for heat energy conduction is increased, so that the next area to be tested can obtain sufficient heat radiation and heat conduction time before image acquisition, and the next area to be tested can achieve the optimal temperature difference when the image is collected, which can improve the environmental adaptability of infrared thermal imaging and improve the detection accuracy of wall damage.

[0047] Furthermore, using the formula Calculate and obtain the current acquisition frequency of the camera when working in the first posture, where: is the current horizontal flight speed of the drone, For the preheating cycle of the heating lamp, is the preset overlap ratio of the detected bi-light images corresponding to the horizontally adjacent heating shooting points. It can be understood that It is a preset overlap ratio between the detected bi-light image corresponding to the current heating shooting point and the detected bi-light image corresponding to the next horizontally adjacent heating shooting point.

[0048] In the solution of the present invention, the current acquisition frequency is determined based on the current horizontal flight speed, the preheating period, and the preset overlap rate of the detected bi-light images in the horizontal direction.

[0049] Specifically, please refer to Figure 3 , Figure 4 as well as Figure 5When shooting in horizontal direction, the heating angle of the flash The actual calculation includes:

[0050] ;

[0051] In the formula, a1 is the length of the infrared camera CMOS, f is the focal length of the infrared camera, H is the vertical distance between the drone and the wall when working, b1 is the length of the heating area, and a is the shooting length.

[0052] Specifically, the preheating cycle The design needs to be determined comprehensively based on factors such as the excitation energy of the flash lamp, the type of the finishing layer, and the environmental conditions;

[0053] Thermal imager acquisition frequency The calculation formula is as follows:

[0054] ;

[0055] Where T is the heating period, is the flight time of the UAV between adjacent horizontal shooting points, n1% is the overlap rate of adjacent infrared images, and v 1 is the horizontal flight speed of the UAV.

[0056] Furthermore, using the formula Calculate and obtain the current preheating working power of the heating lamp, where: is the wall surface emissivity of the next heating shooting point, is a constant, is the heat absorption rate of the wall to be tested, k is the diffusion attenuation coefficient of the thermal radiation energy of the heating lamp, and Δt is the target temperature rise value of the heating lamp in the current preheating cycle.

[0057] In the solution of the present invention, based on the wall surface emissivity of the next heating shooting point and the heat absorption rate of the wall to be detected 、 The heat radiation energy diffusion attenuation coefficient and the target temperature rise value of the heating lamp are adaptively set to adjust the current preheating working power of the heating lamp.

[0058] Furthermore, if the planned path is to extend in a vertical direction, the drone works in the second posture, and the heating lamp deflects downward along the current shooting point toward the next shooting point in the second posture. angle;

[0059] in, is the imaging height dimension, is the camera focal length, is the horizontal distance between the camera and the wall. is the height of the heating area.

[0060] Furthermore, using the formula Calculate and obtain the current acquisition frequency of the camera when working in the second posture, where: is the current vertical flight speed of the UAV, For the preheating cycle of the heating lamp, It is the preset overlap ratio of the detected bi-light images corresponding to the vertically adjacent heating shooting points.

[0061] In the scheme of the present invention, not only preheating of the drone when flying in the horizontal direction is considered, but also preheating of the drone when flying in the vertical direction is considered. Preheating is performed when obtaining the heating areas corresponding to the remaining heating shooting points in the area to be detected except the first one.

[0062] It can be understood that the lens of the shooting camera is facing the wall to obtain the detection bi-light image in the normal direction; if the image to be detected is a square image, = .

[0063] Furthermore, since the vibration of the drone in vertical flight is greater than that in horizontal flight, the control ≥ It is beneficial to improve the comprehensiveness of preheating in the vertical direction.

[0064] Furthermore, at the initial heating shooting point, the heating lamp and the lens of the shooting camera are controlled to face the wall, so that the current heating area coincides with the center point of the current shooting area; the shooting area corresponding to the initial heating shooting point is heated; the lens of the shooting camera is kept unchanged, and the angle of the heating lamp is adjusted to Angle, preheat the heating area corresponding to the next shooting area.

[0065] Furthermore, the working posture is pre-adjusted based on the coordinate transformation of the next heating shooting point relative to the current heating shooting point. Specifically, the current posture of the drone is determined according to the coordinates of the current heating shooting point and the coordinates of the next heating shooting point. If there is a change in the lateral coordinate point, it works in the first posture, and if there is a change in the longitudinal coordinate point, it works in the second posture.

[0066] In a specific embodiment of the present invention, first, the flight inspection path of the drone is planned for the building to be inspected, which is required to prevent missed inspections and meet the minimum preset overlap rate requirement when adjacent images are stitched; then, according to the internal parameters of the flash and infrared camera carried by the drone, the type of exterior wall finishing layer, environmental conditions and other factors, the horizontal distance H between the drone and the wall, the flash heating angle, and the infrared camera angle are designed when the drone is working. , , flash lamp heating power W, heating cycle T, thermal imager acquisition frequency m 1 , m 2 The system operating parameters are set to heat the area to be tested in advance while collecting images, ensuring that the area to be tested can obtain sufficient heat radiation and heat conduction time after the T heating cycle ends and before image collection, and achieve the heating target of temperature increase Δt. Taking the drone starting from the initial heating shooting point and flying to the right as an example, the operation process is as follows:

[0067] At the starting heating shooting point, the flash lamp and the dual-light camera lens are controlled to face the wall, so that the heating area of ​​the flash lamp coincides with the center point of the shooting area of ​​the dual-light camera;

[0068] Controlling the flash lamp to heat the initial heating area;

[0069] Keep the dual-light camera lens unchanged and adjust the heating angle of the flash to the right. Angle, until the left boundary of the area to be heated corresponding to the next heating shooting point coincides with the right boundary of the shooting area;

[0070] Preheating the area to be tested, while collecting the detection bi-light image of the shooting area, and ending the heating at the same time when the collection is completed;

[0071] Get the preheating angle of the flash when the drone flies to the next heating shooting point , the drone flies to the next heating shooting point to collect and detect the dual-light image and preheat the next adjacent heating area; repeat the steps until the last heating shooting point is preheated while flying horizontally to the right;

[0072] Get the preheating angle of the flash when the drone flies to the next heating shooting point , the UAV flies to the next heating shooting point to collect and detect the bi-light image and preheat the next adjacent heating area, and preheats the first heating shooting point of the next horizontal flight track;

[0073] Get the preheating angle of the flash when the drone flies to the next heating shooting point , the drone flies to the next heating shooting point to collect and detect the dual-light image and preheat the next adjacent heating area; repeat the steps until the last heating shooting point is preheated when flying horizontally to the left;

[0074] Repeat the steps until you reach the last heating shooting point of the flight detection planning path.

[0075] Further, step S30 specifically includes:

[0076] S31, after the collected detection bi-optical image sequence is subjected to noise reduction and enhancement processing, a damage contour map of the crack and hollow area is obtained by an image segmentation method based on threshold and edge detection, and geometric information of the damage area is calculated according to the number of pixels in the damage contour map;

[0077] S32, converting the detected bi-optical image into a temperature grayscale image according to the temperature matrix, and then performing grayscale homogenization processing on the pixels with the same grayscale value in different images, obtaining the infrared orthophoto of the wall according to feature point matching and spatial physical information calculation, and realizing temperature standardization processing of the detected bi-optical image sequence;

[0078] S33, marking the identified damaged area contour map and geometric information at the corresponding position on the infrared orthophoto:

[0079] S34, obtaining a visible light orthophoto of the wall surface according to feature point matching and spatial physical information calculation;

[0080] S35, mapping the damaged area marked in the infrared orthophoto to the visible light orthophoto according to the spatial coordinate matching relationship.

[0081] It can be understood that image denoising and enhancement processing includes methods such as spatial domain and frequency domain filtering, contrast-limited adaptive histogram equalization (CLAHE), etc.; the outline of the damaged area is extracted by an image segmentation method based on threshold and edge detection, and the geometric information of the damaged area is calculated by counting the number of pixels in the outline; the initial thermal image is converted into a temperature grayscale image according to the temperature matrix, and the pixels with the same grayscale value in different images are grayscale-identified, so that during the image stitching process, the grayscale of the pixels in the overlapping area is consistent, that is, the feature points are consistent; the geometric information of the damaged area includes area, length, width and other information.

[0082] In the scheme of the present invention, the temperature difference between the hollow area and the normal area is amplified by active heating; the contrast of the defect is improved by image noise reduction and enhancement, so as to locate the hollow position; the contour of the damaged area is identified by image segmentation, so as to calculate the geometric information of the damaged area; the dual-light orthophoto of the wall is obtained by temperature standardization processing and according to feature point matching and spatial physical information calculation; the automatic positioning of the damage is achieved by mapping the damaged area marked on the infrared orthophoto to the visible light orthophoto according to the spatial coordinate matching relationship; the exterior wall can also be inspected when encountering adverse weather conditions such as cloudy days, windy days, low temperatures, etc., which effectively reduces the influence of the environment on the infrared thermal imaging effect.

[0083] The present invention also provides an active thermal imaging detection system for superficial damage to an outer protective wall, comprising an unmanned aerial vehicle, a ground control system and a ground computing system. The unmanned aerial vehicle is equipped with a shooting camera, a heating lamp and an edge computing unit. The shooting camera is a thermal infrared and visible light camera. The heating lamp is directly below the shooting camera. The heating lamp can be set horizontally and movably. The heating lamp can be set downwardly and movably. The edge computing unit is used to determine the damage information in the detected dual-light image and feed the result back to the ground control system. The edge computing unit is also used to adjust the heating working parameters of the heating lamp. The heating working parameters include the pre-heating angle. The ground control system is used to adjust the flight parameters of the unmanned aerial vehicle. The ground computing system is used to implement the above-mentioned active thermal imaging detection method for superficial damage to the outer protective wall.

[0084] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An active thermal imaging detection method for superficial damage of an external protective wall, characterized in that: Includes steps: S10, obtaining a flight inspection planning path of the UAV, wherein the UAV is equipped with a heating lamp and a shooting camera, the flight inspection planning path is an S shape covering the area to be inspected, the flight inspection planning path includes a plurality of heating shooting points arranged in time sequence, when the UAV is at the current position of the heating shooting point, the shooting camera has a corresponding shooting area, and when the UAV is at the current position of the heating shooting point, the heating lamp has a heating area for preheating the next adjacent heating shooting point; S20, when capturing a detection bi-light image corresponding to a shooting area at a current heating shooting point, preheating a heating area corresponding to a next heating shooting point by means of the heating lamp; If the flight detection planning path extends horizontally, the UAV works in a first posture, and when working in the first posture, the heating lamp deflects horizontally along the current heating shooting point toward the next heating shooting point The heating area is heated at an angle, wherein , is the imaging length, is the camera focal length, is the vertical distance between the camera and the wall to be detected. is the length of the heating area; S30, identifying wall damage and locating the damage position based on the detected bi-optical image.

2. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 1 is characterized in that: Using formula Calculate and obtain the current acquisition frequency of the camera when working in the first posture, where: is the current horizontal flight speed of the drone, For the preheating cycle of the heating lamp, It is the preset overlap ratio of the detected bi-light images corresponding to horizontally adjacent heating shooting points.

3. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 2 is characterized in that: Using formula The current preheating working power of the heating lamp is calculated and obtained, wherein: is the wall surface emissivity of the next heating shooting point, is a constant, is the heat absorption rate of the wall to be tested, k is the diffusion attenuation coefficient of the thermal radiation energy of the heating lamp, and Δt is the target temperature increase value of the heating lamp in the current preheating cycle.

4. The active thermal imaging detection method for superficial damage of an outer protective wall according to any one of claims 2 or 3, characterized in that: If the planned path is extended in a vertical direction, the drone works in the second posture. In the second posture, the heating lamp deflects downward along the current shooting point toward the next shooting point. angle; in, is the imaging height dimension, is the camera focal length, is the vertical distance between the camera and the wall. is the height of the heating area.

5. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 4 is characterized in that: Using formula Calculate and obtain the current acquisition frequency of the camera when working in the second posture, where: is the current vertical flight speed of the UAV, For the preheating cycle of the heating lamp, It is the preset overlap ratio of the detected bi-light images corresponding to the vertically adjacent heating shooting points.

6. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 5 is characterized in that: ≥ 。 7. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 4 is characterized in that: At the initial heating shooting point, the heating lamp and the camera lens are controlled to face the wall so that the center point of the current heating area coincides with the center point of the current shooting area; Heating the heating area corresponding to the initial heating shooting point; Keep the camera lens unchanged and adjust the angle of the heating lamp to Angle, preheating the heating area corresponding to the next heating shooting point.

8. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 4 is characterized in that: The current posture of the drone is determined according to the coordinates of the current heating shooting point and the coordinates of the next heating shooting point. If there is a change in the lateral coordinate point, it works in the first posture, and if there is a change in the longitudinal coordinate point, it works in the second posture.

9. The active thermal imaging detection method for superficial damage of the outer protective wall according to claim 4 is characterized in that: Step S30 specifically includes: S31, after the collected detection bi-optical image sequence is subjected to noise reduction and enhancement processing, a damage contour map of the crack and hollow area is obtained by an image segmentation method based on threshold and edge detection, and geometric information of the damage area is calculated according to the number of pixels in the damage contour map; S32, converting the detected bi-optical image into a temperature grayscale image according to the temperature matrix, and then performing grayscale homogenization processing on the pixels with the same grayscale value in different images, obtaining the infrared orthophoto of the wall according to feature point matching and spatial physical information calculation, and realizing temperature standardization processing of the detected bi-optical image sequence; S33, marking the identified damaged area contour map and geometric information at the corresponding position on the infrared orthophoto: S34, obtaining a visible light orthophoto of the wall surface according to feature point matching and spatial physical information calculation; S35, mapping the damaged area marked in the infrared orthophoto to the visible light orthophoto according to the spatial coordinate matching relationship.

10. An active thermal imaging detection system for superficial damage of an external protective wall, characterized in that: Including UAV, ground control system and ground computing system; The drone is equipped with a shooting camera, a heating lamp and an edge computing unit. The shooting camera is a thermal infrared and visible light camera. The heating lamp is directly below the shooting camera. The heating lamp can be movably arranged horizontally or downwardly. The edge computing unit is used to determine the damage information in the dual light image and feed the result back to the ground control system. The edge computing unit is also used to adjust the heating working parameters of the heating lamp, and the heating working parameters include the preheating angle. The ground control system is used to adjust the flight parameters of the UAV; The ground computing system is used to implement the active thermal imaging detection method for superficial damage of the outer protective wall as described in any one of claims 1 to 9.

Images