CN114750954A - High-rise building wall monitoring device and method based on image recognition - Google Patents
High-rise building wall monitoring device and method based on image recognition Download PDFInfo
- Publication number
- CN114750954A CN114750954A CN202210605998.2A CN202210605998A CN114750954A CN 114750954 A CN114750954 A CN 114750954A CN 202210605998 A CN202210605998 A CN 202210605998A CN 114750954 A CN114750954 A CN 114750954A
- Authority
- CN
- China
- Prior art keywords
- wall
- plate
- image
- rise building
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000012806 monitoring device Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013016 damping Methods 0.000 claims abstract description 13
- 238000009434 installation Methods 0.000 claims abstract description 13
- 230000003139 buffering effect Effects 0.000 claims abstract description 4
- 238000012544 monitoring process Methods 0.000 claims description 28
- 230000035939 shock Effects 0.000 claims description 20
- 238000010521 absorption reaction Methods 0.000 claims description 17
- 239000000463 material Substances 0.000 claims description 11
- 238000002474 experimental method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000005489 elastic deformation Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 3
- 239000004033 plastic Substances 0.000 description 8
- 238000000429 assembly Methods 0.000 description 7
- 230000000712 assembly Effects 0.000 description 7
- 239000003550 marker Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000011514 reflex Effects 0.000 description 2
- 229920003002 synthetic resin Polymers 0.000 description 2
- 239000000057 synthetic resin Substances 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000003197 catalytic effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000006482 condensation reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000945 filler Substances 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 239000000314 lubricant Substances 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 239000000049 pigment Substances 0.000 description 1
- 239000004014 plasticizer Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000003381 stabilizer Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C25/00—Alighting gear
- B64C25/32—Alighting gear characterised by elements which contact the ground or similar surface
- B64C25/58—Arrangements or adaptations of shock-absorbers or springs
- B64C25/62—Spring shock-absorbers; Springs
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
- B64D47/08—Arrangements of cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U10/00—Type of UAV
- B64U10/10—Rotorcrafts
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16F—SPRINGS; SHOCK-ABSORBERS; MEANS FOR DAMPING VIBRATION
- F16F15/00—Suppression of vibrations in systems; Means or arrangements for avoiding or reducing out-of-balance forces, e.g. due to motion
- F16F15/02—Suppression of vibrations of non-rotating, e.g. reciprocating systems; Suppression of vibrations of rotating systems by use of members not moving with the rotating systems
- F16F15/04—Suppression of vibrations of non-rotating, e.g. reciprocating systems; Suppression of vibrations of rotating systems by use of members not moving with the rotating systems using elastic means
- F16F15/08—Suppression of vibrations of non-rotating, e.g. reciprocating systems; Suppression of vibrations of rotating systems by use of members not moving with the rotating systems using elastic means with rubber springs ; with springs made of rubber and metal
- F16F15/085—Use of both rubber and metal springs
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Working Measures On Existing Buildindgs (AREA)
Abstract
The invention discloses a high-rise building wall monitoring device and method based on image recognition, and discloses a wall monitoring device and method which can be installed on an unmanned aerial vehicle to shoot the surface of a high-rise building wall to obtain a wall image and a crack image and corresponding shooting distances and analyze the images without manual inspection. Its characterized in that is including the installation component that is used for being connected with unmanned aerial vehicle for the image acquisition subassembly that acquires wall body image and crack image and be used for unmanned aerial vehicle to acquire the damping component that the subassembly carries out buffering protection when falling to the ground to the image, the installation component sets up on the image acquisition subassembly, damping component sets up on the image acquisition subassembly, the installation component has two, two the installation component symmetry sets up on the image acquisition subassembly.
Description
Technical Field
The invention discloses a high-rise building wall monitoring device and method based on image recognition, relates to a device and method for monitoring high-rise building wall cracks on the basis of image recognition, and belongs to the technical field of building wall monitoring.
Background
The building can receive factor influences such as temperature stress under long-time natural environment such as weather exposure, wall material can produce the clearance, the possible catalytic amplification in clearance and then produce the crack on the surface, along with the crack constantly enlarges, can cause the potential safety hazard, especially high-rise building is when taking place the crack, if not in time discover to overhaul will destroy the holistic intensity of building and stability, at present to the cracked detection of building mainly rely on the manual work to patrol and examine, work load is big, and to high-rise building, ground patrol and examine personnel and cracked perpendicular distance far away, the cracked actual conditions is difficult to observe with the accuracy to the naked eye, if be close to high-rise building's wall body and observe, then will have certain danger.
Publication number CN111612846A discloses a concrete crack width determination method based on U-net CNN image recognition and pixel calibration, comprising the following steps: acquiring photos of a plurality of concrete structure surface cracks with known shooting distances and focal lengths by using a single lens reflex and a laser range finder; training a U-net CNN network to realize automatic crack identification and crack morphology extraction; marking the width direction of the crack, and extracting the number of pixels in the width direction of the crack; an indoor target experiment, wherein a nonlinear model of shooting distance, focal length and pixel actual size is constructed, and the pixel actual size is calibrated; by adopting the method, the wall crack photo is difficult to obtain for the high-rise building wall, the wall crack photo needs to be manually lifted to the high-rise wall crack by means of equipment such as a hanging basket and the like, and then the wall crack image and the shooting distance are obtained by using the single-lens reflex camera and the laser range finder, so that danger is easy to occur, and the method is not suitable for monitoring the high-rise building wall crack.
Publication No. CN105910540A discloses a method for in-situ detection of cracks in a building wall, comprising the following steps: taking a camera device adopting a CMOS image sensor, and fixing the camera device right in front of a wall body with a crack; measuring the distance between the camera and the wall; shooting a picture of a wall surface with cracks; calculating the actual length and width of the wall surface in the picture according to the transverse and longitudinal field angles of the camera; finding out the number of pixels occupied by the width of the crack and the included angle between the crack and the horizontal line according to the difference of the pixel values of the crack and the wall surface in the picture; by adopting the method, for the wall body of the high-rise building, a fixed structure of the camera device can not be arranged right in front of the wall body, the camera device needs to be manually held to shoot the wall body cracks of the high-rise building, the acquisition of the pictures of the wall body cracks is difficult, and the method is not suitable for monitoring the wall body cracks of the high-rise building.
Publication No. CN106595497A discloses a real-time monitoring and early warning system for a building surface crack and an early warning method thereof, wherein the early warning system comprises a marker which is arranged at the position of the building surface crack and deforms synchronously along with the crack, and a data acquisition system for acquiring deformation data of the marker; the data acquisition system comprises M data acquisition devices, wherein M is a positive integer; the data acquisition device comprises monitoring equipment, and the monitoring equipment acquires marker deformation data and is connected with the data processing terminal through the signal transceiver; the data processing terminal obtains and displays the transformation data of the building surface cracks according to the marker movement data, the early warning system needs to manually install the markers at the building surface cracks, and for the high-rise building wall, the manual installation is easy to cause danger, and the early warning system is not suitable for monitoring the high-rise building wall cracks.
Disclosure of Invention
In order to improve the situation, the high-rise building wall monitoring device and the method thereof based on image recognition provide the wall monitoring device and the method thereof which can be installed on an unmanned aerial vehicle to shoot the surface of the high-rise building wall to obtain the wall image and the crack image and the corresponding shooting distance and analyze the images without manual inspection, are suitable for crack monitoring of the high-rise building wall, can timely master the change situation of the wall crack relative to the wall width, and are convenient for monitoring personnel to timely take corresponding measures.
The invention relates to a high-rise building wall monitoring device based on image recognition, which is realized by the following steps: the invention relates to a high-rise building wall monitoring device based on image recognition, which comprises an installation component connected with an unmanned aerial vehicle, an image acquisition component used for acquiring wall images and crack images, and a damping component used for buffering and protecting the image acquisition component when the unmanned aerial vehicle lands on the ground,
wherein the mounting assembly is disposed on the image capture assembly, the dampening assembly is disposed on the image capture assembly,
preferably, there are two of the mounting assemblies, two of the mounting assemblies are symmetrically disposed on the image capturing assembly, and two of the shock absorbing assemblies are symmetrically disposed on the image capturing assembly,
the image acquisition assembly consists of a camera, a support plate, a laser range finder, a camera fixing plate, a fixing groove, a limiting groove and a range finder fixing plate, wherein the fixing groove is formed in the middle of the top surface of the support plate, the camera fixing plate is arranged in the fixing groove, the camera is arranged at the central position of the camera fixing plate, the limiting groove is formed in the middle of the bottom surface of the support plate, the range finder fixing plate is arranged in the limiting groove, the laser range finder is arranged on the range finder fixing plate,
preferably, the central line of the laser range finder and the central line of the camera are on the same straight line, the laser range finder and the camera are flush with each other,
preferably, one side surface of the supporting plate is of an arc-shaped structure, the width of the supporting plate is gradually increased from the middle to the two ends,
the mounting component consists of a connecting plate, a fixed limit plate and a mounting plate, the fixed limit plate is arranged on the supporting plate through a fastening bolt, one end of the connecting plate is hinged with the fixed limit plate through a hinge shaft, the other end of the connecting plate is connected with the mounting plate,
preferably, the connecting plate is of an arc-shaped structure,
preferably, the mounting plate is provided with a reserved mounting hole, the plane of the mounting plate is vertical to the support plate,
the damping component consists of a rotating sliding cylinder, a supporting sliding rod, an automatic telescopic rod, a hinging seat, a damping supporting leg, a hinging lug, a buffer spring and a limiting sliding plate, wherein the hinging lug is arranged on the bottom surface of the supporting plate, the bottom of the rotating sliding cylinder is hinged with the hinging lug through the hinging seat, one end of the supporting sliding rod is arranged in the rotating sliding cylinder in a sliding way, the other end of the supporting sliding rod penetrates through the opening of the rotating sliding cylinder and is connected with one end of the damping supporting leg,
preferably, the diameter of the opening of the rotating sliding cylinder is smaller than that of the cylinder bottom,
preferably, the diameter of the shock-absorbing leg is gradually increased from one end to the other end, the shock-absorbing leg is made of rubber material,
the limiting sliding plate is arranged at one end of the supporting sliding rod,
preferably, the limiting slide plate is positioned in the rotating slide cylinder, the side wall of the limiting slide plate is contacted with the inner wall of the rotating slide cylinder,
the buffer spring is arranged in the rotating sliding barrel, one end of the buffer spring is connected with the bottom of the rotating sliding barrel, the other end of the buffer spring is connected with the limiting sliding plate,
one end of the automatic telescopic rod is hinged with the rotary sliding barrel through a connecting lug,
preferably, the connecting lug is close to the opening of the rotary slide cylinder,
the other end of the automatic telescopic rod is hinged with the bottom surface of the supporting plate;
the invention also relates to a using method of the high-rise building wall monitoring device based on image recognition, which is characterized by comprising the following steps of:
1) mounting the wall monitoring device on a fixed seat of the unmanned aerial vehicle through a reserved mounting hole on the mounting plate;
2) the unmanned aerial vehicle drives the wall monitoring device to ascend, so that the camera and the laser range finder are opposite to the wall of the high-rise building, when the unmanned aerial vehicle ascends, the automatic telescopic rod is in a telescopic state, the damping component is close to the supporting plate, the gravity center is close to the unmanned aerial vehicle, and the ascending process of the unmanned aerial vehicle is more stable;
3) shooting the surface of a high-rise building wall by using a camera to obtain a wall image and a wall crack image, and simultaneously measuring a corresponding shooting distance by using a laser range finder;
4) when the unmanned aerial vehicle falls, the automatic telescopic rod extends to push the rotating sliding cylinder to rotate so as to enable the rotating sliding cylinder to be perpendicular to the ground;
5) when the shock absorption support leg falls to the ground, the shock absorption support leg is firstly contacted with the ground, then the support slide bar is pushed to slide in the rotary slide cylinder, the buffer spring is compressed to generate elastic deformation, and hard collision generated when the shock absorption support leg falls to the ground is buffered, so that the camera and the laser range finder are prevented from being damaged;
the invention also relates to a method for monitoring the cracks of the high-rise building wall by using the high-rise building wall monitoring device based on image recognition, which is characterized by comprising the following steps:
1) acquiring a wall panoramic image by using a high-rise building wall monitoring device, wherein the distance from a camera to a wall is L1;
2) carrying out gray level processing on the wall panoramic image, carrying out background separation, extracting wall image information and measuring the wall width at the distance of L1;
preferably, the width of the wall surface is obtained through manual measurement, namely, a monitoring person measures the width of the wall surface by using a ruler;
3) acquiring a wall crack image by using a high-rise building wall monitoring device, wherein the distance from a camera to a wall is L2;
4) performing gray level processing on the wall crack image, and measuring the maximum width of the wall crack as the wall crack width at the distance of L2;
5) converting the wall surface width at the distance L1 into width information W1 at a preset standard distance L, and simultaneously converting the wall surface crack width at the distance L2 into width information W2 at the preset standard distance L;
preferably, the width conversion model is obtained through an early stage experiment, a standard distance L is set, an indoor experiment is carried out, a camera is calibrated, a large number of ranges s and the size a of a single target in a picture under the corresponding range are obtained through an indoor target experiment, and a functional relation a is established,＝F(s,a,L)；
Wherein, a,Is the size of the target size a at a standard distance L in degrees centigrade;
6) substituting W1 and W2 into a ratio formula f = α (W2/W1), wherein α is a correction coefficient;
comparing the obtained result with a preset threshold range, and when the result is smaller than the preset threshold range, monitoring personnel do not need to take action; when the result is within the set threshold range, monitoring personnel need to monitor the crack at a higher frequency; when the result exceeds a set threshold range, monitoring personnel need to repair the crack;
preferably, the threshold range is determined according to the material and thickness of the wall, the height of the wall where the crack is located, the external temperature and humidity where the wall is located.
Has the beneficial effects.
The unmanned aerial vehicle can be used for acquiring the wall body image and the crack image of the high-rise building and corresponding distance information, manual inspection shooting is not needed, time and labor are saved, and the unmanned aerial vehicle is suitable for monitoring the wall body of the high-rise building.
And secondly, the change condition of the wall crack relative to the width of the wall can be mastered in time, and monitoring personnel can take corresponding measures in time.
Three, can cushion the hard collision that produces ground when unmanned aerial vehicle whereabouts, prevent that camera and laser range finder from receiving vibrations and damaging.
Drawings
FIG. 1 is a three-dimensional structure diagram of a high-rise building wall monitoring device based on image recognition;
FIG. 2 is a schematic structural diagram of a shock-absorbing assembly of a high-rise building wall monitoring device based on image recognition according to the present invention;
fig. 3 is a schematic structural diagram of a high-rise building wall monitoring device based on image recognition, which only shows the structure of a supporting plate.
In the attached drawings
Wherein the following steps are as follows: connecting plate (1), camera (2), fixed limiting plate (3), backup pad (4), rotation slide cartridge (5), support slide bar (6), automatic telescopic link (7), laser range finder (8), articulated seat (9), shock attenuation landing leg (10), articulated ear (11), camera fixed plate (12), mounting panel (13), buffer spring (14), spacing slide (15), fixed slot (16), spacing groove (17), distancer fixed plate (18).
The specific implementation mode is as follows:
the invention relates to a high-rise building wall monitoring device based on image recognition, which comprises an installation component connected with an unmanned aerial vehicle, an image acquisition component used for acquiring wall images and crack images, and a damping component used for buffering and protecting the image acquisition component when the unmanned aerial vehicle lands on the ground,
wherein the mounting assembly is disposed on the image capture assembly, the dampening assembly is disposed on the image capture assembly,
preferably, there are two mounting assemblies, two of the mounting assemblies are symmetrically arranged on the image acquisition assembly, there are two shock absorption assemblies, two of the shock absorption assemblies are symmetrically arranged on the image acquisition assembly,
the image acquisition assembly consists of a camera (2), a support plate (4), a laser range finder (8), a camera fixing plate (12), a fixing groove (16), a limiting groove (17) and a range finder fixing plate (18), wherein the fixing groove (16) is formed in the middle of the top surface of the support plate (4), the camera fixing plate (12) is arranged in the fixing groove (16), the camera (2) is arranged at the central position of the camera fixing plate (12), the limiting groove (17) is formed in the middle of the bottom surface of the support plate (4), the range finder fixing plate (18) is arranged in the limiting groove (17), the laser range finder (8) is arranged on the range finder fixing plate (18),
preferably, the central line of the laser range finder (8) and the central line of the camera (2) are on the same straight line, the laser range finder (8) and the camera (2) are flush with each other,
preferably, one side surface of the supporting plate (4) is of an arc-shaped structure, the width of the supporting plate (4) is gradually increased from the middle to the two ends,
the mounting component consists of a connecting plate (1), a fixed limiting plate (3) and a mounting plate (13), the fixed limiting plate (3) is arranged on the supporting plate (4) through a fastening bolt, one end of the connecting plate (1) is hinged with the fixed limiting plate (3) through a hinge shaft, the other end is connected with the mounting plate (13),
preferably, the connecting plate (1) is of an arc-shaped structure,
preferably, the mounting plate (13) is provided with a reserved mounting hole, the plane of the mounting plate (13) is vertical to the support plate (4),
the damping component consists of a rotating sliding barrel (5), a supporting sliding rod (6), an automatic telescopic rod (7), an articulated seat (9), a damping supporting leg (10), an articulated lug (11), a buffer spring (14) and a limiting sliding plate (15), wherein the articulated lug (11) is arranged on the bottom surface of the supporting plate (4), the barrel bottom of the rotating sliding barrel (5) is articulated with the articulated lug (11) through the articulated seat (9), one end of the supporting sliding rod (6) is arranged in the rotating sliding barrel (5) in a sliding way, and the other end penetrates through the barrel mouth of the rotating sliding barrel (5) and is connected with one end of the damping supporting leg (10),
preferably, the diameter of the opening of the rotating sliding cylinder (5) is smaller than that of the bottom of the cylinder,
preferably, the diameter of the shock absorption leg (10) is gradually increased from one end to the other end, the shock absorption leg (10) is made of rubber materials,
the limiting sliding plate (15) is arranged at one end of the supporting sliding rod (6),
preferably, the limiting sliding plate (15) is positioned in the rotating sliding barrel (5), the side wall of the limiting sliding plate (15) is contacted with the inner wall of the rotating sliding barrel (5),
the buffer spring (14) is arranged in the rotating sliding barrel (5), one end of the buffer spring (14) is connected with the barrel bottom of the rotating sliding barrel (5), the other end is connected with the limiting sliding plate (15),
one end of the automatic telescopic rod (7) is hinged with the rotary sliding barrel (5) through a connecting lug,
preferably, the connecting lug is close to the opening of the rotating sliding barrel (5),
the other end of the automatic telescopic rod (7) is hinged with the bottom surface of the supporting plate (4);
preferably, the support plate (4) is a plastic plate, the plastic plate is a plate made of plastic, the plastic is a synthetic high molecular compound and can freely change the shape and the style, the plastic is a material polymerized by monomer raw materials through synthesis or condensation reaction, and is composed of synthetic resin, fillers, plasticizers, stabilizers, lubricants, pigments and other additives, the main component of the plastic plate is the synthetic resin, the plastic plate is resistant to chemical erosion, has luster, is partially transparent or semitransparent, is mostly a good insulator, is light and firm, can be easily processed in large scale and is cheap;
preferably, the connection plate (1) is made of a plastic material;
the invention relates to a high-rise building wall monitoring device based on image recognition, which comprises the following steps:
1) the wall monitoring device is installed on a fixed seat of the unmanned aerial vehicle through a reserved installation hole on the installation plate (13);
2) the unmanned aerial vehicle drives the wall monitoring device to ascend, so that the camera (2) and the laser range finder (8) are opposite to the wall of the high-rise building, when the unmanned aerial vehicle ascends, the automatic telescopic rod (7) is in a telescopic state, the damping assembly is close to the supporting plate (4), the gravity center is close to the unmanned aerial vehicle, and the ascending process of the unmanned aerial vehicle is more stable;
3) shooting the surface of a high-rise building wall by using a camera (2) to obtain a wall image and a wall crack image, and simultaneously measuring a corresponding shooting distance by using a laser range finder (8);
4) when shooting is finished, the unmanned aerial vehicle falls, and when the unmanned aerial vehicle falls, the automatic telescopic rod (7) extends to push the rotating sliding cylinder (5) to rotate so as to enable the rotating sliding cylinder to be vertical to the ground;
5) when the shock absorption type laser range finder falls to the ground, the shock absorption supporting legs (10) are firstly contacted with the ground, then the supporting slide bars (6) are pushed to slide in the rotating slide cylinders (5), the buffer springs (14) are compressed to generate elastic deformation, and hard collision generated when the shock absorption type laser range finder falls to the ground is buffered, so that the camera (2) and the laser range finder (8) are prevented from being damaged;
the invention discloses a method for monitoring cracks of a high-rise building wall by using a high-rise building wall monitoring device based on image recognition, which comprises the following steps:
1) the wall panoramic image is obtained by utilizing the high-rise building wall monitoring device, and the distance from the camera (2) to the wall is L1;
2) carrying out gray level processing on the wall panoramic image, carrying out background separation, extracting wall image information and measuring the wall width at the distance of L1;
preferably, the width of the wall surface is obtained through manual measurement, namely, a monitoring person measures the width of the wall surface by using a ruler;
3) acquiring a wall crack image by using a high-rise building wall monitoring device, wherein the distance from a camera (2) to a wall is L2;
4) performing gray level processing on the wall crack image, and measuring the maximum width of the wall crack as the wall crack width at the distance of L2;
5) converting the wall surface width at the distance L1 into width information W1 at a preset standard distance L, and simultaneously converting the wall surface crack width at the distance L2 into width information W2 at the preset standard distance L;
preferably, the width conversion model is obtained through an early stage experiment, a standard distance L is set, an indoor experiment is carried out, a camera is calibrated, a large number of ranges s and the size a of a single target in a picture under the corresponding range are obtained through an indoor target experiment, and a functional relation a is established,＝F(s,a,L)；
Wherein, a,Is the size of the target size a at a standard distance L in degrees centigrade;
6) substituting W1 and W2 into a ratio formula f = α (W2/W1), wherein α is a correction coefficient;
the obtained result is compared with a preset threshold range, and when the result is smaller than the preset threshold range, monitoring personnel do not need to take action; when the result is within the set threshold range, monitoring personnel need to monitor the crack at a higher frequency; when the result exceeds a set threshold range, monitoring personnel need to repair the crack;
preferably, the threshold range is determined according to the material and thickness of the wall, the height of the wall where the crack is located, the external temperature and humidity where the wall is located.
One side face of the supporting plate (4) is of an arc-shaped structure, the width of the supporting plate (4) is gradually increased from the middle to the two ends, avoidance can be formed on the camera (2) and the laser range finder (8), and the side face of the supporting plate (4) is prevented from shielding the camera (2) and the laser range finder (8) to influence shooting and ranging;
the connecting plate (1) is designed to be of an arc-shaped structure, so that the tensile capacity of the connecting plate (1) can be improved, the distance between the connecting plate (1) and the camera (2) can be increased, and the connecting plate (1) is prevented from shielding the camera (2) to influence the acquisition of wall images;
one end of the connecting plate (1) is hinged with the fixed limiting plate (3) through a hinge shaft, and can be matched with the mounting plate (13) to enable the supporting plate (4) to be always kept in a vertical state under the action of gravity, so that the supporting plate (4) is prevented from being inclined to influence the acquisition of wall images and crack images;
the diameter of the opening of the rotating sliding cylinder (5) is smaller than that of the bottom of the cylinder, and the limiting sliding plate (15) can be matched to limit the supporting sliding rod (6) so as to prevent the supporting sliding rod (6) from sliding out of the rotating sliding cylinder (5);
the diameter of the shock absorption supporting leg (10) is gradually increased from one end to the other end, the shock absorption supporting leg (10) is made of rubber materials, the ground gripping force of the shock absorption supporting leg (10) can be improved, the shock absorption supporting leg (10) is enabled to be more stable when being contacted with the ground, meanwhile, the rubber materials can buffer hard collision generated with the ground to a certain extent, and the shock absorption protection effect on the camera (2) and the laser range finder (8) is improved;
the purpose that can install shoot on unmanned aerial vehicle and acquire wall body image and crack image and the shooting distance that corresponds and carry out the analysis, need not the manual work and patrol and examine to high-rise building wall surface is reached.
The above embodiments are preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that changes may be made without departing from the scope of the invention, and it is intended that all matter contained in the above description or shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense.
Claims (10)
1. The utility model provides a high-rise building wall monitoring device based on image recognition, is including being used for the installation component who is connected with unmanned aerial vehicle for the image acquisition subassembly that obtains wall body image and crack image and be used for unmanned aerial vehicle to fall to the ground the image acquisition subassembly carry out the damper assembly of buffering protection, its characterized in that: the installation component sets up on the image acquisition component, damper assembly sets up on the image acquisition component, the installation component has two, two the installation component symmetry sets up on the image acquisition component, damper assembly has two, two damper assembly symmetry sets up on the image acquisition component.
2. The high-rise building wall monitoring device based on image recognition as claimed in claim 1, wherein the image acquisition assembly is composed of a camera, a support plate, a laser range finder, a camera fixing plate, a fixing groove, a limiting groove and a range finder fixing plate, the fixing groove is formed in the middle of the top surface of the support plate, the camera fixing plate is arranged in the fixing groove, the camera is arranged at the center of the camera fixing plate, the limiting groove is formed in the middle of the bottom surface of the support plate, the range finder fixing plate is arranged in the limiting groove, and the laser range finder is arranged on the range finder fixing plate.
3. The high-rise building wall monitoring device based on image recognition as claimed in claim 1, wherein the mounting assembly is composed of a connecting plate, a fixed limiting plate and a mounting plate, the fixed limiting plate is arranged on the supporting plate through a fastening bolt, one end of the connecting plate is hinged with the fixed limiting plate through a hinge shaft, and the other end of the connecting plate is connected with the mounting plate.
4. The high-rise building wall monitoring device based on image recognition as claimed in claim 1, wherein the shock-absorbing assembly is composed of a rotary slide cylinder, a support slide rod, an automatic telescopic rod, a hinge seat, a shock-absorbing leg, a hinge lug, a buffer spring and a limit slide plate, the hinge lug is arranged on the bottom surface of the support plate, the bottom of the rotary slide cylinder is hinged with the hinge lug through the hinge seat, one end of the support slide rod is slidably arranged in the rotary slide cylinder, the other end of the support slide rod penetrates through the opening of the rotary slide cylinder and is connected with one end of the shock-absorbing leg, the limit slide plate is arranged at one end of the support slide rod and is positioned in the rotary slide cylinder, the side wall of the limit slide plate is in contact with the inner wall of the rotary slide cylinder, the buffer spring is arranged in the rotary slide cylinder, one end of the buffer spring is connected with the bottom of the rotary slide cylinder, the other end of the buffer spring is connected with the limit slide plate, one end of the automatic telescopic rod is hinged with the rotary slide cylinder through the connecting lug, the other end of the automatic telescopic rod is hinged with the bottom surface of the supporting plate.
5. The high-rise building wall monitoring device based on image recognition as claimed in claim 2, wherein the center line of the laser range finder and the center line of the camera are on the same straight line, the laser range finder and the camera are flush with each other, one side of the support plate is of an arc structure, and the width of the support plate is gradually increased from the middle to the two ends.
6. The high-rise building wall monitoring device based on image recognition as claimed in claim 3, wherein the connecting plate is an arc-shaped structure, the mounting plate is provided with a reserved mounting hole, and the plane of the mounting plate is perpendicular to the supporting plate.
7. The high-rise building wall monitoring device based on image recognition as claimed in claim 4, wherein the diameter of the opening of the rotating slide cylinder is smaller than the diameter of the bottom of the rotating slide cylinder, the diameter of the shock absorption leg is gradually increased from one end to the other end, the shock absorption leg is made of rubber materials, and the connecting lug is close to the opening of the rotating slide cylinder.
8. A use method of a high-rise building wall monitoring device based on image recognition is characterized by comprising the following steps:
1) mounting the wall monitoring device on a fixed seat of the unmanned aerial vehicle through a reserved mounting hole on the mounting plate;
2) the unmanned aerial vehicle drives the wall monitoring device to ascend, so that the camera and the laser range finder are opposite to the wall of the high-rise building, when the unmanned aerial vehicle ascends, the automatic telescopic rod is in a telescopic state, the damping component is close to the supporting plate, the gravity center is close to the unmanned aerial vehicle, and the ascending process of the unmanned aerial vehicle is more stable;
3) shooting the surface of a high-rise building wall by using a camera to obtain a wall image and a wall crack image, and simultaneously measuring a corresponding shooting distance by using a laser range finder;
4) when the unmanned aerial vehicle falls, the automatic telescopic rod extends to push the rotating sliding cylinder to rotate so as to enable the rotating sliding cylinder to be perpendicular to the ground;
5) when falling to the ground, the shock attenuation landing leg contacts with ground earlier, then promotes to support the slide bar and slide in rotating the slide cartridge, and buffer spring is compressed and is produced elastic deformation, cushions the hard collision that produces when falling to the ground, prevents that camera and laser range finder from taking place to damage.
9. A method for monitoring cracks in a high-rise wall by using the high-rise wall monitoring device as claimed in claim 1, which is characterized by comprising the following steps:
1) acquiring a wall panoramic image by using a high-rise building wall monitoring device, wherein the distance from a camera to a wall is L1;
2) carrying out gray level processing on the wall panoramic image, carrying out background separation, extracting wall image information and measuring the wall width at the distance of L1;
3) acquiring a wall crack image by using a high-rise building wall monitoring device, wherein the distance from a camera to a wall is L2;
4) performing gray level processing on the wall crack image, and measuring the maximum width of the wall crack as the wall crack width at the distance of L2;
5) converting the wall surface width at the distance L1 into width information W1 at a preset standard distance L, and simultaneously converting the wall surface crack width at the distance L2 into width information W2 at the preset standard distance L;
6) substituting W1 and W2 into a ratio formula f = alpha (W2/W1), wherein alpha is a correction coefficient, the obtained result is compared with a preset threshold range, and when the correction coefficient is smaller than the preset threshold range, a monitoring person does not need to take action; when the result is within a set threshold range, monitoring personnel need to monitor the crack at a higher frequency; when the result exceeds the set threshold range, monitoring personnel need to repair the crack.
10. The method for monitoring cracks in a wall of a high-rise building according to claim 9, wherein the width of the wall surface is obtained by manual measurement, i.e. measuringMeasuring the width of the wall surface by a monitoring person by using a scale; the width conversion model is obtained through early-stage experiments, a standard distance L is set, indoor experiments are conducted, a camera is calibrated, a large number of range s and the size a of a single target in a picture under the corresponding range are obtained through indoor target experiments, and a functional relation a is established,F (s, a, L); wherein, a,Is the size of the target size a at a standard distance L in degrees centigrade; the threshold range is determined according to the material and thickness of the wall, the height of the wall where the crack is located, the external temperature and humidity where the wall is located.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210605998.2A CN114750954A (en) | 2022-05-31 | 2022-05-31 | High-rise building wall monitoring device and method based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210605998.2A CN114750954A (en) | 2022-05-31 | 2022-05-31 | High-rise building wall monitoring device and method based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114750954A true CN114750954A (en) | 2022-07-15 |
Family
ID=82336477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210605998.2A Withdrawn CN114750954A (en) | 2022-05-31 | 2022-05-31 | High-rise building wall monitoring device and method based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114750954A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115790400A (en) * | 2023-01-17 | 2023-03-14 | 中大智能科技股份有限公司 | Machine vision target calibration method applied to bridge and tunnel structure safety |
-
2022
- 2022-05-31 CN CN202210605998.2A patent/CN114750954A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115790400A (en) * | 2023-01-17 | 2023-03-14 | 中大智能科技股份有限公司 | Machine vision target calibration method applied to bridge and tunnel structure safety |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108106801B (en) | Bridge and tunnel disease non-contact detection system and detection method | |
| CN114750954A (en) | High-rise building wall monitoring device and method based on image recognition | |
| CN104020060B (en) | Impact collision simulation test bed and method for ball mill | |
| CN109979468B (en) | Lightning stroke optical path monitoring system and method | |
| CN207231440U (en) | A kind of bridge pad monitoring device | |
| CN111445522B (en) | Passive night vision intelligent lightning detection system and intelligent lightning detection method | |
| WO2019153876A1 (en) | Method and device for evaluating severity of head injury incurred by cyclist after impact with road surface, and testing method | |
| CN113537016A (en) | Method for automatically detecting and early warning road damage in road patrol | |
| CN105163072A (en) | Intelligent measurement accident disposing device | |
| KR20060018909A (en) | Dynamic movement measuring system for structure based on image processing for diagnosing and monitoring construction | |
| CN106284071A (en) | Bridge defect intelligent video-detect system | |
| CN110095083B (en) | Hot casting measuring method and device based on compressed sensing algorithm | |
| EP2342534B1 (en) | Electro-optical inclination measurement system | |
| TWI676028B (en) | Flying exterior wall detecting device and system thereof | |
| CN108108706B (en) | Method and system for optimizing sliding window in target detection | |
| CN216081957U (en) | Bridge deflection measuring device | |
| CN215725919U (en) | Aerial remote sensing photogrammetric instrument with high safety | |
| CN114893669A (en) | Monitoring device and monitoring method applied to installation of tower crane attachment device | |
| CN112816120B (en) | Cable force measuring method | |
| CN102620660A (en) | Ultra-remote detection method for cracks of buildings and structures | |
| CN210464878U (en) | Camera imaging quality detection device | |
| CN208334874U (en) | A kind of camera with level meter | |
| CN209894722U (en) | Automatic identification device for measuring cracks of bridge structure | |
| CN110006368B (en) | Rope swing angle measuring method and system based on vision measurement | |
| Mas et al. | Image based subpixel techniques for movement and vibration tracking |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220715 |
|
| WW01 | Invention patent application withdrawn after publication |