Unmanned aerial vehicle carried infrared imager high-rise outer wall detection method based on BIM (Building Information Modeling) technology

Abstract

An unmanned aerial vehicle carried infrared imager high-rise outer wall detection method based on a BIM technology comprises an unmanned aerial vehicle image acquisition device, a BIM model module and a detection database, and the detection method comprises the following detection steps: S1, planning a detection path in combination with a detected high-rise BIM model; s2, the planned detection path data is transmitted to a controller module of an unmanned aerial vehicle image acquisition device through a data transmission module via a ground station; s3, an unmanned aerial vehicle image acquisition device is provided with a laser ranging module, a camera and an infrared imager, and according to the detection path planned in the step S1, the infrared imager is adopted to carry out image data acquisition on the high-rise outer wall; and S4, transmitting the image data acquired by the unmanned aerial vehicle image acquisition device in the step S3 to a detection database for calculation and comparison. And through the unmanned aerial vehicle, the wall surface condition of the high-rise outer wall can be detected, wall surface defects can be found in time, maintenance can be carried out in time, and further loss expansion is avoided.

Description

Technical Field

[0001] The invention relates to a high-rise exterior wall detection method based on BIM technology and equipped with an infrared imager by an unmanned aerial vehicle. Background Art

[0002] In my country, there have always been many common problems in the quality of building exterior walls that have plagued the construction industry, such as hollowing, falling off, cracks, etc. These problems not only affect the beauty and service life of the building, but also seriously affect the personal safety of residents. With the acceleration of urbanization, high-rise buildings are increasingly becoming an important part of urban buildings. However, the repair and maintenance of high-rise building exterior walls are facing unprecedented challenges.

[0003] An important reason for defects such as aging, cracking and falling off of exterior walls is the lack of regular inspection and maintenance. Summary of the invention

[0004] In order to solve the above problems, a high-rise exterior wall inspection method using a drone equipped with an infrared imager based on BIM technology is provided, which can effectively detect building quality problems and repair them in time to eliminate dangers in the bud.

[0005] To achieve the above object, the present invention is solved by the following technical solution: a high-rise exterior wall detection method using an infrared imager mounted on a drone based on BIM technology, comprising: a drone image acquisition device, a BIM model module and a detection database, and the detection steps are as follows: S1: Plan the inspection route based on the BIM model of the high-rise building being inspected; S2: Transmitting the planned detection path data to the controller module of the UAV image acquisition device through the ground station via the data transmission module; S3: The drone image acquisition device is equipped with a laser ranging module, a camera and an infrared imager. According to the detection path planned in step S1, the infrared imager is used to collect image data of the high-rise exterior wall; S4: The image data collected by the drone image acquisition device in step S3 is transmitted to the detection database for calculation and comparison.

[0006] Furthermore, in step S1, the BIM model needs to plan the detection path in combination with the parameters of the UAV image acquisition device. The parameters of the UAV image acquisition device include the field of view size of the UAV camera. The surface of the inspection area is decomposed according to the field of view size of the UAV camera, and each decomposed area is projected into a grid centroid. The projection result generates a viewpoint set, and the shortest path is determined according to the genetic algorithm to obtain the optimal path of the UAV.

[0007] Furthermore, after determining the shortest path according to the genetic algorithm, battery refueling points are set, and finally the optimal path of the UAV is obtained.

[0008] Furthermore, the infrared imager collects image data of the high-rise exterior walls. The exterior walls are reflected to the infrared imager by solar radiation to form an infrared image. Image recognition technology is used to extract exterior wall defect features in the infrared image.

[0009] Furthermore, the detection database includes an exterior wall infrared image recognition model based on deep learning.

[0010] Furthermore, the exterior wall infrared image recognition model includes a number of hidden danger features, each hidden danger feature corresponds to a hidden danger code, and the infrared imager includes a coding program consistent with the exterior wall infrared image recognition model.

[0011] The present invention is beneficial in that: 1. Drones can be used to inspect the condition of high-rise exterior walls, detect wall defects in a timely manner, and carry out repairs in a timely manner to avoid further losses.

[0012] 2. The combination of drone technology and BIM technology can plan corresponding inspection routes and plans for different high-rise buildings, which can effectively improve the inspection accuracy and efficiency.

[0013] 3. By collecting infrared images through the infrared imager of the drone, the characteristics and types of wall defects can be quickly obtained through coding recognition and comparison with the detection database. The detection content includes not only the wall surface, but also the inside of the wall. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The figure is a schematic diagram of the overall process of the high-rise exterior wall detection method using an infrared imager mounted on a drone based on BIM technology of the present invention.

[0015] Figure 2 It is a schematic diagram of the detection process of the high-rise exterior wall detection method using an infrared imager equipped with a drone based on BIM technology of the present invention.

[0016] Figure 3 This is a schematic diagram of path formation in the high-rise exterior wall detection method using an infrared imager mounted on a drone based on BIM technology of the present invention.

[0017] Figure 4 This is an actual imaging diagram of the infrared imager in the high-rise exterior wall detection method using an infrared imager mounted on a drone based on BIM technology of the present invention.

[0018] Figure 5 This is a working principle diagram of the infrared imager mounted on a drone in the high-rise exterior wall detection method using the infrared imager mounted on a drone based on BIM technology of the present invention.

[0019] Figure numerals: wall 1, defective moisturizing layer 2, normal insulation layer 3, infrared instrument 4, drone 5, wall 6, drone camera field of view size 7, viewpoint set 8, inspection path 9 DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0021] Based on BIM technology, the method of high-rise exterior wall detection using an infrared camera mounted on a drone is proposed. Starting from the traditional building exterior wall detection method, path planning research, and BIM application research summary, a method based on the BIM model combined with the infrared technology mounted on drones to detect quality and safety hazards of high-rise building exterior walls is proposed. Specifically, the building model is preprocessed through the initial BIM model, and the model is simplified to determine the model of the area that needs to be inspected. Then the drone flight detection path is optimized, and the relevant parameters of the drone flight are determined, including the endurance time, flight safety distance, camera field of view size, etc., to find the optimal path of the UAV, and solve the route mission parameters, and link information with the building model. Finally, the collected image information is evaluated and analyzed to find out the quality and safety hazards of the building exterior wall.

[0022] Among them, after preprocessing the building model and simplifying the model, it is necessary to intervene in the parameters such as the field of view size of the drone camera, the safe flight distance and the endurance time to adjust and optimize the UAV path. The specific optimization process is as follows: Set the flight trajectory of the drone and set the coordinate system with X-axis, Y-axis and Z-axis. The X-axis is the horizontal axis, the Y-axis is the vertical axis, and the Z-axis is the vertical wall axis.

[0023] Based on the inspection path obtained by the BIM model, the UAV flight safety distance S is added to the Z axis. During the flight inspection, the Z axis value of the UAV flight process is controlled in real time through the laser ranging module.

[0024] Based on the inspection path obtained by the BIM model, the field of view size of the drone camera is introduced, and the BIM path model is cut and decomposed according to the field of view size of the drone camera. The grid centroid projection is performed on each decomposed area, and the projection result generates a viewpoint set. The shortest path is determined by the genetic algorithm to obtain the optimal UAV path. This step is mainly used to adjust the X-axis value and Y-axis value of the preliminary inspection path.

[0025] After obtaining the optimal path for the UAV, the UAV endurance value is intervened according to the path distance, thereby adding a return point or a battery refueling point to the final optimal path for the UAV.

[0026] In the detection database, there is an external wall infrared image recognition model based on deep learning. Based on a large number of wall defect thermal imaging pictures and their definitions, deep learning is performed, and various types of defect pictures are encoded. When solar radiation is irradiated to the wall surface, the heat is reflected through the wall surface to the thermal imager on the drone. The thermal imaging results of walls in different states are different. For example, the defective insulation layer and the normal insulation layer on the wall reflect radiation differently. At the same time, the image is encoded using the same encoding program and matched with the defect code in the detection database (as shown in Table 1), so as to quickly derive the defect type. At the same time, the defect is sent to the ground control center in the form of flight coordinates to quickly find the defect location.

[0027] Question Type Code Chinese description English description issueType-001-002-001 Cracks on the stone panel stone crack issueType-001-002-005 Stone panel pollution stone pollution issueType-001-002-007 Damaged stone panel stone come off issueType-001-003-004 Metal panel contamination metal pollution issueType-003-003-001 Silicone sealant cracking sealant crack issueType-003-003-003 Silicone sealant has gaps or is missing sealant gap issueType-003-002-001 Sealing strip falls off strip fallen off issueType-003-002-002 Sealing strip damaged strip damage issueType-007-001-001 Brick facing has stains face brick pollution issueType-007-001-003 Facing brick panel falling off face brick come off issueType-007-001-006 Cracks in facing bricks face brick crack issueType-007-002-002 Exterior wall paint surface cracks wall crack issueType-007-002-003 Exterior wall paint surface has stains wall pollution issueType-007-002-004 External wall mortar surface peeling wall come off Table 1 Comparison of codes and descriptions of hidden dangers identified by infrared devices mounted on drones It is obvious to those skilled in the art that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes within the meaning and scope of the equivalent elements of the claims are included in the present invention.

Claims

1. A high-rise exterior wall detection method using an infrared camera mounted on a drone based on BIM technology, characterized in that: include: UAV image acquisition device, BIM model module and detection database, the detection steps are as follows: S1: Plan the inspection route based on the BIM model of the high-rise building being inspected; S2: Transmitting the planned detection path data to the controller module of the UAV image acquisition device through the ground station via the data transmission module; S3: The drone image acquisition device is equipped with a laser ranging module, a camera and an infrared imager. According to the detection path planned in step S1, the infrared imager is used to collect image data of the high-rise exterior wall; S4: The image data collected by the drone image acquisition device in step S3 is transmitted to the detection database for calculation and comparison.

2. The high-rise exterior wall detection method using an infrared camera mounted on a drone based on BIM technology according to claim 1 is characterized in that: Step S1, the BIM model needs to plan the inspection path in combination with the parameters of the UAV image acquisition device. The parameters of the UAV image acquisition device include the field of view size of the UAV camera. The surface of the inspection area is decomposed according to the field of view size of the UAV camera, and each decomposed area is projected into the grid centroid. The projection result generates a viewpoint set, and the shortest path is determined according to the genetic algorithm to obtain the optimal path of the UAV.

3. The high-rise exterior wall detection method using an infrared camera mounted on a drone based on BIM technology according to claim 2 is characterized in that: After determining the shortest path according to the genetic algorithm, the battery refueling points are set, and finally the optimal path for the UAV is obtained.

4. The high-rise exterior wall detection method using an infrared camera mounted on a drone based on BIM technology according to claim 3 is characterized in that: The infrared imager collects image data of high-rise exterior walls. The exterior walls are reflected by solar radiation to the infrared imager to form infrared images. Image recognition technology is used to extract exterior wall defect features in the infrared images.

5. The high-rise exterior wall detection method using an infrared camera mounted on a drone based on BIM technology according to claim 4 is characterized in that: The detection database includes an exterior wall infrared image recognition model based on deep learning.

6. The high-rise exterior wall detection method using an infrared camera mounted on a drone based on BIM technology according to claim 5 is characterized in that: The exterior wall infrared image recognition model includes several hidden danger features, each hidden danger feature corresponds to a hidden danger code, and the infrared camera includes a coding program consistent with the exterior wall infrared image recognition model.

Images