CN116189017A - Concrete bridge crack recognition system based on unmanned aerial vehicle - Google Patents
Concrete bridge crack recognition system based on unmanned aerial vehicle Download PDFInfo
- Publication number
- CN116189017A CN116189017A CN202211691745.8A CN202211691745A CN116189017A CN 116189017 A CN116189017 A CN 116189017A CN 202211691745 A CN202211691745 A CN 202211691745A CN 116189017 A CN116189017 A CN 116189017A
- Authority
- CN
- China
- Prior art keywords
- crack
- bridge
- module
- sub
- aerial vehicle
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of bridge detection, in particular to a concrete bridge crack identification system based on an unmanned aerial vehicle, which comprises an image acquisition module, a bridge modeling module and a crack measurement module, wherein the image acquisition module is used for shooting a bridge through the unmanned aerial vehicle so as to acquire a bridge body image and a crack image; the bridge modeling module is used for acquiring data of the image acquisition module so as to establish a bridge model with crack marks according to the bridge body image and the crack image; and the crack measurement module is used for analyzing and acquiring the size of the crack according to the data of the bridge modeling module. According to the unmanned aerial vehicle-based concrete bridge crack identification system, the crack can be detected through the unmanned aerial vehicle, so that the detection cost is effectively reduced, the limit of the geographic environment is small, and the crack detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of bridge detection, in particular to a concrete bridge crack identification system based on an unmanned plane.
Background
The bridge is taken as one of important infrastructures in daily life of people, and brings great convenience for vehicles and pedestrians to pass through. Along with the construction and traffic of the bridge, the maintenance and management of the bridge become the key for guaranteeing the safety operation of the bridge. The reasons for bridge collapse are that scientific and timely bridge disease detection is not carried out, so that a scientific and reasonable method is required to be selected to inspect the bridge disease and evaluate the health condition of the bridge at regular intervals. During bridge construction and use, concrete cracks often appear. And some cracks are continuously expanded under the action of using load or external physical and chemical factors, so that the attractiveness of the concrete surface is affected, the thickness of a concrete protective layer of the reinforced steel bar is reduced, the peeling of a concrete surface layer is easily caused, the corrosion of the reinforced steel bar is accelerated, the freezing resistance and durability of the concrete are reduced, even collapse accidents occur in severe cases, the safety operation of a bridge is seriously affected, and therefore, the cracks of the bridge are required to be detected.
At present, the appearance detection means of the bridge mainly depend on manual visual observation or auxiliary tools (such as bridge inspection vehicles, telescope and the like); therefore, the bridge inspection has the following general defects: high detection difficulty, high risk, high cost of labor and instruments, low detection efficiency, narrow inspection angle and the like.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the background art, and provides the unmanned aerial vehicle-based concrete bridge crack identification system, which can detect cracks through an unmanned aerial vehicle, effectively reduces the detection cost, is little limited by the geographical environment, and improves the crack detection efficiency.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a concrete bridge crack identification system based on unmanned aerial vehicle, which comprises an image acquisition module, a bridge modeling module and a crack measurement module,
the image acquisition module is used for shooting the bridge through the unmanned aerial vehicle so as to acquire a bridge body image and a crack image;
the bridge modeling module is used for acquiring data of the image acquisition module so as to establish a bridge model with crack marks according to the bridge body image and the crack image;
and the crack measurement module is used for analyzing and acquiring the size of the crack according to the data of the bridge modeling module.
Further, the bridge modeling module comprises a bridge construction mold module, a crack positioning sub-module and a crack construction mold module,
the bridge body building mold module is used for obtaining data of the image obtaining module and building a bridge body model through the bridge body image;
the crack positioning sub-module is used for acquiring data of the image acquisition module, and the crack positioning sub-module marks the positions of cracks in the bridge body model according to the positions of the cracks in the bridge body image;
the crack construction module is used for acquiring data of the image acquisition module and the crack positioning sub-module, the crack construction module performs semantic segmentation on the crack image through a unet model, and the crack construction module combines the crack image subjected to the semantic segmentation with the bridge body model to obtain the bridge model with the crack mark.
Further, the bridge body image and the crack image have position data of the bridge so that the bridge model has position information; and the crack measurement module is used for measuring the size of the crack according to the position information of the bridge model.
Further, the inspection module comprises a history crack inspection sub-module and a new crack inspection sub-module,
the historical crack inspection submodule is used for shooting historical cracks of the bridge regularly through an unmanned aerial vehicle, and the historical crack inspection submodule sends image data of the historical cracks to the image acquisition module so that the bridge modeling module can update crack labels of the bridge model according to the images of the historical cracks;
the new crack inspection submodule is used for regularly shooting the bridge and all cracks through the unmanned aerial vehicle, and the new crack inspection submodule sends data of the bridge image and all crack images to the image acquisition module so that the bridge modeling module establishes a new bridge body model.
Further, the inspection module further comprises a historical crack analysis submodule, wherein the historical crack analysis submodule is used for acquiring data of the historical crack inspection submodule, the bridge modeling module and the crack measurement module so that the historical crack analysis submodule can acquire data of a plurality of historical sizes of each crack; the historical crack analysis submodule generates a graph according to data of a plurality of historical sizes of each crack, the historical crack analysis submodule obtains a crack change rate related to time according to the graph, when the crack change rate exceeds an abnormal threshold, the historical crack analysis submodule judges that the crack is abnormal, and the historical crack analysis submodule sends an abnormal signal to the bridge modeling module so that the corresponding crack in the bridge model is highlighted.
Further, the bridge is provided with a weather station to acquire environmental quantity data of the bridge, and the historical crack analysis submodule acquires a change curve chart of each environmental quantity according to the environmental quantity data to acquire a corresponding time-related environmental quantity change rate; the historical crack analysis submodule compares the crack change rate with the environmental quantity change rate through a machine learning algorithm to judge whether the abnormal signal is caused by the environment.
Further, the inspection module further comprises a new crack analysis submodule, wherein the new crack analysis submodule is used for acquiring data of the bridge modeling module and the crack measuring module so as to acquire position data and size data of the new crack;
the new crack analysis sub-module is provided with different early warning thresholds according to different positions of the bridge, and when the size of the new crack is larger than a first early warning threshold of a corresponding position, the new crack analysis sub-module sends an early warning signal to the bridge modeling module so that the corresponding new crack in the bridge model is subjected to flicker display.
Further, the new crack analysis sub-module is connected with a strain gauge buried in the bridge, so that the new crack analysis sub-module obtains an influence coefficient through strain gauge data of the bridge corresponding to the new crack position; when the size of the new crack is larger than a first early warning threshold value at a corresponding position and the product of the size of the new crack and the influence coefficient is larger than a second early warning threshold value, the new crack analysis submodule sends an alarm signal to the bridge modeling module so that the corresponding new crack in the bridge model is subjected to highlight and flicker display.
Further, a plurality of detection points are uniformly distributed on one side of the bridge, each detection point comprises a mounting frame and an infrared emitter, one surface of the mounting frame is fixedly connected with the bridge, a placing groove is concavely formed in the other surface of the mounting frame, a notch communicated with the placing groove is formed in the bottom of the mounting frame, and the infrared emitters are obliquely arranged in the placing groove; the cloud platform of unmanned aerial vehicle is provided with infrared send-receiver, infrared send-receiver is used for infrared transmitter's signal reception, unmanned aerial vehicle can be according to infrared send-receiver's signal confirms self position, so that unmanned aerial vehicle can both shoot with the same angle and the same position at every turn the bridge.
The beneficial effects of the invention are as follows:
1. the bridge body and the cracks of the bridge are shot through the unmanned aerial vehicle, so that the bridge modeling module can model the bridge through the bridge body image and the crack image, and the crack length and the crack width can be measured under the action of the crack measuring module due to crack marking in the bridge model. According to the invention, the unmanned aerial vehicle is used as a detection tool to replace a method for artificially detecting the cracks, so that the detection risk is reduced, the detection cost is reduced, the limit of the geographical environment is small, and the crack detection efficiency is improved.
2. The bridge body modeling submodule establishes a bridge body model according to the bridge body image, and marks the cracks of the bridge body model through the crack positioning submodule so as to obtain the position information of the bridge where the cracks are located; the crack modeling module performs fine modeling according to the crack image to obtain a bridge model with high-precision crack data, so that the accuracy of the crack measurement module on the crack size measurement can be improved.
3. According to the invention, the bridge is regularly monitored through the historical crack inspection sub-module and the new crack inspection sub-module, and the change condition of the bridge crack and the condition of the newly added crack are timely found, so that a worker can timely process the crack, and the safe operation of the bridge is ensured.
Drawings
Fig. 1 is a block diagram of a concrete bridge crack recognition system based on an unmanned aerial vehicle according to a preferred embodiment of the present invention.
Fig. 2 is a schematic diagram of a bridge construction of a concrete bridge crack recognition system based on an unmanned aerial vehicle according to a preferred embodiment of the present invention.
Fig. 3 is a schematic diagram of a detection point structure of a concrete bridge crack recognition system based on an unmanned plane according to a preferred embodiment of the present invention.
In the figure, a 10-unmanned plane, a 101-bridge, a 1-image acquisition module, a 2-bridge modeling module, a 21-bridge body building module, a 22-crack positioning sub-module, a 23-crack building module, a 3-crack measuring module, a 4-inspection module, a 41-history crack inspection sub-module, a 42-new crack inspection sub-module, a 43-history crack analysis sub-module, a 44-new crack analysis sub-module, a 5-detection point, a 51-mounting frame, a 52-infrared transmitter and a 53-infrared receiver.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or intervening elements may also be present. When a component is considered to be "connected" to another component, it can be directly connected to the other component or intervening components may also be present. When an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1 to 3, an unmanned aerial vehicle-based concrete bridge crack recognition system according to a preferred embodiment of the present invention includes an image acquisition module 1, a bridge modeling module 2, a crack measurement module 3, and a patrol module 4.
The image acquisition module 1 is used for shooting the bridge 101 through the unmanned aerial vehicle 10 so as to acquire a bridge body image and a crack image.
The bridge modeling module 2 is used for acquiring data of the image acquisition module 1 so as to establish a bridge model with crack marks according to the bridge body image and the crack image.
The bridge modeling module 2 includes a bridge construction sub-module 21, a crack positioning sub-module 22, and a crack construction sub-module 23.
The bridge construction sub-module 21 is used for data acquisition of the image acquisition module 1, and the bridge construction sub-module 21 establishes a bridge construction model through a bridge image.
The crack positioning sub-module 22 is used for acquiring data of the image acquisition module 1, and the crack positioning sub-module 22 identifies the position of the crack in the bridge body model according to the position of the crack in the bridge body image.
The crack construction sub-module 23 is used for acquiring data of the image acquisition module 1 and the crack positioning sub-module 22, the crack construction sub-module 23 performs semantic segmentation on the crack image through the unet model, and the crack construction sub-module 23 combines the crack image after the semantic segmentation with the bridge body model to obtain the bridge model with the crack mark.
The bridge body building mold module 21 builds a bridge body model according to the bridge body image, and marks the cracks of the bridge body model through the crack positioning sub-module 22 so as to obtain the position information of the bridge where the cracks are located; the crack creation module 23 performs fine modeling based on the crack image to obtain a bridge model with high-precision crack data, so that the accuracy of the subsequent crack size measurement can be improved.
The crack measuring module 3 is used for obtaining the size of the crack according to the data analysis of the bridge modeling module 2. The bridge body image and the crack image have position data of the bridge 101 so that the bridge model has position information; the crack measuring module 3 measures the size of the crack according to the position information of the bridge model.
According to the invention, the unmanned aerial vehicle is used for shooting the bridge body and the cracks of the bridge 101, so that the bridge modeling module 2 can model the bridge through the bridge body image and the crack image, and the crack length and the crack width can be measured under the action of the crack measuring module 3 due to the crack marking in the bridge model. According to the invention, the unmanned aerial vehicle is used as a detection tool to replace a method for artificially detecting the cracks, so that the detection risk is reduced, the detection cost is reduced, the limit of the geographical environment is small, and the crack detection efficiency is improved.
The inspection module 4 includes a historical crack inspection sub-module 41, a new crack inspection sub-module 42, a historical crack analysis sub-module 43, and a new crack analysis sub-module 44.
The historical crack inspection sub-module 41 is used for regularly shooting the historical cracks of the bridge 101 through the unmanned aerial vehicle 10, and the historical crack inspection sub-module 41 sends image data of the historical cracks to the image acquisition module 1 so that the bridge modeling module 2 updates the crack labels of the bridge model according to the images of the historical cracks. In this embodiment, the historical crack inspection sub-module 41 updates the crack of the bridge model through the crack positioning sub-module 22.
The historical crack analysis sub-module 43 is used for acquiring data of the historical crack inspection sub-module 41, the bridge modeling module 2 and the crack measurement module 3, so that the historical crack analysis sub-module 43 acquires data of a plurality of historical sizes of each crack; the historical crack analysis sub-module 43 generates a graph according to the data of a plurality of historical sizes of each crack, the historical crack analysis sub-module 43 obtains a crack change rate related to time according to the graph, when the crack change rate exceeds an abnormal threshold, the historical crack analysis sub-module 43 judges that the crack is abnormal, and the historical crack analysis sub-module 43 sends an abnormal signal to the bridge modeling module 2 so as to highlight the corresponding crack in the bridge model.
The historical crack analysis submodule 43 of the embodiment judges whether the crack is suddenly changed according to the crack change rate, and when the mutation data of the crack exceeds the normal range, the bridge is proved to be abnormal, and the corresponding crack in the bridge model is highlighted to remind a worker to process as soon as possible.
The bridge 101 is provided with a weather station to acquire environmental quantity data of the bridge 101, and the historical crack analysis sub-module 43 acquires a change curve chart of each environmental quantity according to the environmental quantity data to acquire a corresponding time-dependent environmental quantity change rate; the historical crack analysis sub-module 43 compares the crack rate of change to the environmental quantity rate of change via a machine learning algorithm to determine if the anomaly signal is caused by the environment. The environmental quantity of the embodiment comprises humidity, temperature and rainfall data, and when the crack and the environmental quantity data are suddenly changed at the same time, the environment proves that the size of the crack is changed in a large range, so that a worker can maintain the corresponding position of the bridge according to the position of the crack, and continuous abnormality of the crack is avoided; when the crack is suddenly changed and the environmental quantity change is not abnormal, the problem of the strain in the bridge is proved, and the staff should measure the data of the bridge to find the cause of the crack abnormality and solve the problem. And carrying out text annotation on the corresponding cracks in the bridge model according to different conditions.
The new crack inspection sub-module 42 is configured to periodically photograph the bridge 101 and all cracks through the unmanned aerial vehicle 10, and the new crack inspection sub-module 42 sends data of the bridge 101 image and all crack images to the image acquisition module 1, so that the bridge modeling module 2 builds a new bridge body model. In this embodiment, the new crack inspection sub-module 42 establishes a new bridge body model by the bridge body establishing mold module 21, the crack establishing mold module 22, and the crack establishing mold module 23.
In this embodiment, the new crack analysis sub-module 44 is used for obtaining the data of the bridge modeling module 2 and the crack measurement module 3, so as to obtain the position data and the size data of the new crack.
The new crack analysis sub-module 44 is provided with different early warning thresholds according to different positions of the bridge 101, and when the size of the new crack is larger than the first early warning threshold of the corresponding position, the new crack analysis sub-module 44 sends an early warning signal to the bridge modeling module 2 so that the corresponding new crack in the bridge model is subjected to flicker display.
Because the severity of cracks existing at different positions of the bridge is different, according to the embodiment, different early warning thresholds are set at different positions of the bridge 101, when the size of the crack is larger than the first early warning threshold at the corresponding position, the key position of the bridge is proved to be newly increased with abnormal cracks, the new cracks are displayed in a bridge model in a flashing mode, and workers are reminded of timely processing the newly increased cracks. When the size of the crack is smaller than the first early warning threshold value of the corresponding position, the historical crack inspection sub-module 41 can be used for carrying out periodic detection.
In this embodiment, the new crack analysis sub-module 44 is connected with the strain gauge buried in the bridge 101, so that the new crack analysis sub-module 44 obtains an influence coefficient through the strain gauge data of the bridge 101 corresponding to the new crack position; when the size of the new crack is greater than the first early warning threshold value of the corresponding position and the product of the size of the new crack and the influence coefficient is greater than the second early warning threshold value, the new crack analysis sub-module 44 sends an alarm signal to the bridge modeling module 2 so as to highlight and flicker the corresponding new crack in the bridge model.
The strain gauge data of the bridge 101 are used for detecting the bridge internal stress, and when the size of the new crack is larger than the first early warning threshold value of the corresponding position and the product of the size of the new crack and the influence coefficient is larger than the second early warning threshold value, the crack caused by the load is proved, and the crack is required to be immediately processed by a worker, so that the occurrence of unexpected situations is avoided.
In this embodiment, the bridge modeling module 2 is provided with a storage unit, and the storage unit can store the data of the bridge modeling module 2, and can call out the data of the bridge model on the same day by selecting the date, so that the staff can analyze the problems of the bridge specifically. By clicking the crack of the bridge modeling module 2, a corresponding crack image can be displayed, and a worker can manually detect the crack, so that the accuracy of crack detection is improved.
A plurality of detection points 5 are uniformly distributed on one side of the bridge 101, each detection point 5 comprises a mounting frame 51 and an infrared emitter 52, one surface of the mounting frame 51 is fixedly connected with the bridge 101, a placing groove 511 is concavely formed in the other surface of the mounting frame 51, a notch 512 communicated with the placing groove 511 is formed in the bottom of the mounting frame 51, and the infrared emitters 52 are obliquely arranged in the placing groove 511; the cradle head of the unmanned aerial vehicle 10 is provided with an infrared receiver 53, the infrared receiver 53 is used for receiving signals of the infrared transmitter 52, and the unmanned aerial vehicle 10 can determine the position of the cradle head according to the signals of the infrared receiver 53, so that the unmanned aerial vehicle 10 can shoot the bridge 101 at the same angle and the same position every time. The infrared receiver 53 of this embodiment can be powered by a distribution box on the bridge, and can be remotely turned on when detection is required. The unmanned aerial vehicle is provided with a historical crack inspection mode and a new crack inspection mode, and in the historical crack inspection mode, the unmanned aerial vehicle shoots a detection point 5 corresponding to the historical crack; in the new crack inspection mode, the unmanned aerial vehicle photographs all the inspection points 5.
In this embodiment, through setting up unmanned aerial vehicle's shooting point for unmanned aerial vehicle all shoots the crack at the same position at every turn, acquires in infrared transmitter 52's signal according to infrared receiver 53, adjusts the angle of cloud platform, makes unmanned aerial vehicle all shoot the bottom of bridge at the same angle at every turn, shoots bridge 101 through at the same angle and same position at every turn, makes the crack in every crack image have the same angle and the same proportion, thereby reduces the modeling degree of difficulty of bridge modeling module 2 and improves the measurement accuracy of crack measurement module 3.
The bridge model building steps of the embodiment are as follows:
s1, carrying a visible light camera on a cradle head of an unmanned aerial vehicle, and controlling the unmanned aerial vehicle to fly around a bridge 101 so as to acquire a bridge body image; the unmanned aerial vehicle is controlled to shoot at the detection point 5, a picture with a crack is selected to obtain a crack image, and the image acquisition module 1 stores the bridge body image and the crack image.
S2, the bridge body building module 21 builds a bridge body model according to the bridge body image.
And S3, the crack positioning sub-module 22 marks the positions of the cracks in the bridge body model according to the positions of the cracks in the bridge body image.
S4, the crack building module 23 performs semantic segmentation on the crack image through the unet model, and combines the crack image subjected to semantic segmentation with the bridge body model to obtain the bridge model with the crack mark.
S5, the crack measuring module 3 measures the size of the crack according to the position information of the bridge model so as to obtain the width and length data of the crack.
Claims (9)
1. A concrete bridge crack recognition system based on an unmanned aerial vehicle is characterized by comprising an image acquisition module (1), a bridge modeling module (2) and a crack measurement module (3),
the image acquisition module (1) is used for shooting the bridge (101) through the unmanned aerial vehicle (10) so as to acquire a bridge body image and a crack image;
the bridge modeling module (2) is used for acquiring data of the image acquisition module (1) so as to establish a bridge model with crack marks according to the bridge body image and the crack image;
the crack measuring module (3) is used for obtaining the size of the crack according to the data analysis of the bridge modeling module (2).
2. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 1, wherein: the bridge modeling module (2) comprises a bridge construction mold module (21), a crack positioning sub-module (22) and a crack construction mold module (23),
the bridge construction sub-module (21) is used for acquiring data of the image acquisition module (1), and the bridge construction sub-module (21) establishes a bridge model through the bridge image;
the crack positioning sub-module (22) is used for acquiring data of the image acquisition module (1), and the crack positioning sub-module (22) marks the position of the crack in the bridge body model according to the position of the crack in the bridge body image;
the crack construction sub-module (23) is used for acquiring data of the image acquisition module (1) and the crack positioning sub-module (22), the crack construction sub-module (23) performs semantic segmentation on the crack image through a unet model, and the crack construction sub-module (23) combines the crack image subjected to the semantic segmentation with the bridge body model so as to obtain a bridge model with crack marking.
3. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 2, wherein: the bridge body image and the crack image have position data of the bridge (101) so that the bridge model has position information; and the crack measuring module (3) is used for measuring the size of the crack according to the position information of the bridge model.
4. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 1, wherein: the inspection module (4) comprises a history crack inspection sub-module (41) and a new crack inspection sub-module (42),
the historical crack inspection submodule (41) is used for shooting historical cracks of the bridge (101) regularly through the unmanned aerial vehicle (10), and the historical crack inspection submodule (41) sends image data of the historical cracks to the image acquisition module (1) so that the bridge modeling module (2) updates crack marks of the bridge model according to the images of the historical cracks;
the new crack inspection sub-module (42) is used for regularly shooting the bridge (101) and all cracks through the unmanned aerial vehicle (10), and the new crack inspection sub-module (42) sends data of the bridge (101) image and all crack images to the image acquisition module (1) so that the bridge modeling module (2) establishes a new bridge body model.
5. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 4, wherein: the inspection module (4) further comprises a historical crack analysis sub-module (43), wherein the historical crack analysis sub-module (43) is used for acquiring data of the historical crack inspection sub-module (41), the bridge modeling module (2) and the crack measuring module (3) so that the historical crack analysis sub-module (43) can acquire data of a plurality of historical sizes of each crack; the historical crack analysis submodule (43) generates a graph according to data of a plurality of historical sizes of each crack, the historical crack analysis submodule (43) obtains a crack change rate related to time according to the graph, when the crack change rate exceeds an abnormal threshold, the historical crack analysis submodule (43) judges that the crack is abnormal, and the historical crack analysis submodule (43) sends an abnormal signal to the bridge modeling module (2) so that the corresponding crack in the bridge model is highlighted.
6. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 4, wherein: the bridge (101) is provided with a weather station to acquire environmental quantity data of the bridge (101), and the historical crack analysis sub-module (43) acquires a change curve chart of each environmental quantity according to the environmental quantity data to acquire a corresponding time-related environmental quantity change rate; the historical crack analysis sub-module (43) compares the crack rate of change to the environmental quantity rate of change via a machine learning algorithm to determine whether the anomaly signal is caused by an environment.
7. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 4, wherein: the inspection module (4) further comprises a new crack analysis sub-module (44), and the new crack analysis sub-module (44) is used for acquiring data of the bridge modeling module (2) and the crack measurement module (3) so as to acquire position data and size data of the new crack;
the new crack analysis sub-module (44) is provided with different early warning thresholds according to different positions of the bridge (101), and when the size of the new crack is larger than a first early warning threshold of a corresponding position, the new crack analysis sub-module (44) sends an early warning signal to the bridge modeling module (2) so that the corresponding new crack in the bridge model is subjected to flicker display.
8. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 7, wherein: the new crack analysis sub-module (44) is connected with a strain gauge buried in the bridge (101) so that the new crack analysis sub-module (44) can obtain an influence coefficient through strain gauge data corresponding to the bridge (101) at the new crack position; when the size of the new crack is larger than a first early warning threshold value of the corresponding position and the product of the size of the new crack and the influence coefficient is larger than a second early warning threshold value, the new crack analysis submodule (44) sends an alarm signal to the bridge modeling module (2) so as to enable the corresponding new crack in the bridge model to be subjected to highlight and flicker display.
9. The unmanned aerial vehicle-based concrete bridge crack recognition system according to claim 1, wherein: a plurality of detection points (5) are uniformly distributed on one side of the bridge (101), each detection point (5) comprises a mounting frame (51) and an infrared emitter (52), one surface of each mounting frame (51) is fixedly connected with the bridge (101), a placing groove (511) is concavely formed in the other surface of each mounting frame, a notch (512) communicated with each placing groove (511) is formed in the bottom of each mounting frame (51), and each infrared emitter (52) is obliquely arranged in each placing groove (511); the cradle head of the unmanned aerial vehicle (10) is provided with an infrared receiver (53), the infrared receiver (53) is used for receiving signals of the infrared transmitter (52), and the unmanned aerial vehicle (10) can determine the position of the cradle head according to the signals of the infrared receiver (53), so that the unmanned aerial vehicle (10) can shoot the bridge (101) at the same angle and the same position every time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211691745.8A CN116189017A (en) | 2022-12-28 | 2022-12-28 | Concrete bridge crack recognition system based on unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211691745.8A CN116189017A (en) | 2022-12-28 | 2022-12-28 | Concrete bridge crack recognition system based on unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116189017A true CN116189017A (en) | 2023-05-30 |
Family
ID=86439527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211691745.8A Pending CN116189017A (en) | 2022-12-28 | 2022-12-28 | Concrete bridge crack recognition system based on unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116189017A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743830A (en) * | 2023-12-28 | 2024-03-22 | 张家港保税区金港建设工程质量检测有限公司 | Bridge crack detection method and system |
-
2022
- 2022-12-28 CN CN202211691745.8A patent/CN116189017A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743830A (en) * | 2023-12-28 | 2024-03-22 | 张家港保税区金港建设工程质量检测有限公司 | Bridge crack detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117037406B (en) | Intelligent monitoring and early warning system for forest fire | |
| CN104751603A (en) | Rockfall monitoring and early warning system and rockfall monitoring and early warning method | |
| CN116189017A (en) | Concrete bridge crack recognition system based on unmanned aerial vehicle | |
| CN109738091B (en) | System and method for predicting road surface temperature based on road geographic environment | |
| CN103266559A (en) | BP bridge safety inspection vehicle and method for obtaining bridge surface physiognomy | |
| CN104240239A (en) | Method for detecting local road segment hazy weather based on road image | |
| CN110645899B (en) | Distributed optical fiber monitoring method and device for structural crack | |
| CN112781518B (en) | House deformation monitoring method and system | |
| CN112288692B (en) | Crack monitoring and management system and monitoring and management method | |
| CN109541022A (en) | A kind of bridge structure crack health monitoring analysis method | |
| CN112380599A (en) | Bridge intelligent online monitoring and early warning system based on big data analysis | |
| CN110673643A (en) | Intelligent environment-friendly monitoring system and method for unmanned aerial vehicle | |
| CN112556760A (en) | Bridge crack monitoring system | |
| CN114973148B (en) | Municipal facilities on-line monitoring digital intelligent management platform based on smart city construction | |
| CN112643719A (en) | Tunnel security detection method and system based on inspection robot | |
| CN115994901A (en) | Automatic road disease detection method and system | |
| CN116989679A (en) | Highway high slope displacement integrated monitoring method based on image processing | |
| CN117217097A (en) | Method and system for constructing digital twin body of ship industry in platformization mode | |
| CN115035249A (en) | A visual real-time monitoring system that wisdom building site construction progress that is used for | |
| CN117217739B (en) | Intelligent electric power inspection system | |
| CN114240115A (en) | Road operation internet of things method and system | |
| CN112985289A (en) | Tunnel multi-section measurement monitoring system and monitoring method | |
| CN117058855A (en) | Cloud edge communication method for Internet of things | |
| CN111912488A (en) | Water network monitoring device and monitoring method based on unmanned aerial vehicle image sensor | |
| CN113959339B (en) | Method and device for acquiring crack width, crack monitor and monitoring system |
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 |