CN115511836B - Bridge crack grade assessment method and system based on reinforcement learning algorithm - Google Patents
Bridge crack grade assessment method and system based on reinforcement learning algorithm Download PDFInfo
- Publication number
- CN115511836B CN115511836B CN202211191901.4A CN202211191901A CN115511836B CN 115511836 B CN115511836 B CN 115511836B CN 202211191901 A CN202211191901 A CN 202211191901A CN 115511836 B CN115511836 B CN 115511836B
- Authority
- CN
- China
- Prior art keywords
- crack
- bridge
- image
- trend
- length
- 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.)
- Active
Links
- 230000002787 reinforcement Effects 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000013210 evaluation model Methods 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 21
- 230000000877 morphologic effect Effects 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 9
- 125000003275 alpha amino acid group Chemical group 0.000 claims description 8
- 150000001875 compounds Chemical class 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000005259 measurement Methods 0.000 abstract description 4
- 230000036541 health Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Abstract
The invention provides a bridge crack grade assessment method and system based on a reinforcement learning algorithm, and belongs to the field of bridge structure health monitoring. The evaluation method comprises the following steps: collecting a crack image, preprocessing, performing threshold segmentation, extracting width characteristics, length characteristics, trend characteristics, bit surface characteristics and longitudinal position information of the crack, constructing a crack basic database, and dividing the crack basic database into a training set and a testing set; constructing a bridge crack grade evaluation model based on a reinforcement learning algorithm, and obtaining a stable crack grade evaluation model after training; and acquiring a crack image to be evaluated, preprocessing the crack image, extracting length characteristics, width characteristics and trend characteristics of the crack, acquiring crack position surface characteristics and longitudinal position information through space coordinates of the unmanned plane in cruising, and inputting the crack position surface characteristics and longitudinal position information into a crack evaluation model to obtain a crack grade evaluation result. The invention reduces errors caused by manual measurement and improves the efficiency and accuracy of crack detection and evaluation.
Description
Technical Field
The invention belongs to the field of bridge structure health monitoring, and particularly relates to a bridge crack grade assessment method and system based on a reinforcement learning algorithm.
Technical Field
Bridge assessment work is an important part of bridge management work and one of the most basic works. In a normally operated bridge, crack distribution and development trend of a main bearing structure are one of the most important indexes in the detection and evaluation process.
At present, a traditional manual mode is generally adopted for detection and evaluation of cracks, however, the traditional manual detection and evaluation method is long in time consumption, large in workload, high in subjectivity and unstable in evaluation result, and particularly when detection personnel face a large number of bridge groups to be detected, corresponding problems are more prominent, so that the efficiency and accuracy of detection and evaluation work are reduced.
Disclosure of Invention
In view of the above-mentioned defects or shortcomings in the prior art, the invention aims to provide a bridge crack grade assessment method and system based on reinforcement learning algorithm, which is based on automatic acquisition of crack images, extracts characteristic information of cracks through a crack identification program, digitizes the characteristics of the cracks, reduces errors caused by manual measurement, further classifies the cracks by using a crack grade assessment model, effectively reduces subjective influence of detection personnel, and improves efficiency and accuracy of crack detection assessment.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical scheme:
in a first aspect, an embodiment of the present invention provides a bridge crack grade evaluation method based on a reinforcement learning algorithm, where the evaluation method includes:
collecting a crack image through an unmanned aerial vehicle;
preprocessing the crack image;
performing crack image threshold segmentation on the preprocessed crack image, and extracting crack morphological characteristics; the crack morphological characteristics comprise width characteristics, length characteristics and trend characteristics of the crack;
acquiring a position surface of a crack image according to a flight track of the unmanned aerial vehicle, and extracting position surface characteristics;
acquiring a longitudinal coordinate of a crack center point on a bridge axis according to the unmanned aerial vehicle flight track and shooting parameters, and normalizing the longitudinal coordinate to obtain longitudinal position information of the crack;
judging the crack grade according to the width characteristic, the length characteristic, the trend characteristic, the bit surface characteristic and the longitudinal position information of the crack, generating a crack code, and constructing crack basic data, wherein the crack basic data comprises three layers of crack information, and the three layers of crack information are respectively: bridge level information: bridge coding and structural system; information on component hierarchy: structure type, component coding, component longitudinal/transverse/vertical dimensions; crack level information: crack coding, width characteristics, length characteristics, trend characteristics, bit plane characteristics, positions and grades;
arranging the crack basic data corresponding to all the crack images according to codes to construct a data set, and dividing the data set into a training set and a testing set;
constructing a bridge crack grade assessment model based on a reinforcement learning algorithm, training the assessment model by adopting the training set, and verifying the training model by utilizing the testing set to obtain a stable crack grade assessment model;
and acquiring a crack image to be evaluated, preprocessing the crack image, extracting length characteristics, width characteristics, trend characteristics, bit surface characteristics and longitudinal position information of the crack, and inputting the length characteristics, the width characteristics, the trend characteristics, the bit surface characteristics and the longitudinal position information into a model to obtain a crack grade evaluation result.
As a preferred embodiment of the present invention, when acquiring a crack image, the method comprises the following steps:
s11, collecting bridge images; when the bridge image is acquired, all parts of the bridge are acquired in all directions;
step S12, carrying out crack identification on the acquired bridge image, and marking the identified positions meeting the crack condition;
and S13, carrying out local image acquisition again on the identified crack position to obtain a crack image.
As a preferred embodiment of the present invention, when acquiring a crack image, the method comprises the following steps:
s11, collecting bridge images; when the bridge image is acquired, all parts of the bridge are acquired in all directions;
step S12, carrying out crack identification on the acquired bridge image, and marking the identified positions meeting the crack condition;
and S14, dividing the crack image at the crack position in the bridge image to obtain a crack image.
As a preferred embodiment of the present invention, the extracting the morphological feature of the crack includes:
step S31, acquiring a starting point and an ending point of the crack, calculating a center point of the crack image, and dividing the crack image by the center point to acquire a shortest distance edge point and a longest distance edge point which take the center point as a symmetrical center. In the step, when image segmentation is carried out, an SVM model is adopted by a core algorithm;
step S32, judging the trend of the crack according to the included angle between the connecting line of the starting point and the end point of the crack and the longitudinal axis of the bridge, and compiling a crack trend code as a trend characteristic;
step S33, calculating width characteristics by taking the distance between the shortest distance edge points as the crack width;
in step S34, the length characteristic is calculated using the distance between the longest distance edge points as the crack length.
As a preferred embodiment of the present invention, the determining the crack direction in step S32 and compiling a crack direction code as a direction feature includes:
for the cracks of the bottom surface or the top surface, the three types of the transverse cracks, the longitudinal cracks and the oblique cracks are included, wherein the included angle between the transverse cracks and the longitudinal axis is between 75 and 90 degrees, the included angle between the oblique cracks and the longitudinal axis is between 15 and 75 degrees, and the included angle between the longitudinal cracks and the longitudinal axis is between 0 and 15 degrees;
for the side surface cracks, the vertical cracks, the longitudinal cracks and the inclined cracks are included, wherein the included angle between the vertical cracks and the longitudinal axis is between 75 degrees and 90 degrees, the included angle between the inclined cracks and the longitudinal axis is between 15 degrees and 75 degrees, and the included angle between the longitudinal cracks and the longitudinal axis is between 0 degrees and 15 degrees;
on the basis of judging the trend of the crack, constructing four-dimensional vectors as trend codes, and coding and compiling crack trend characteristics, wherein each trend corresponds to one vector; when the current trend is judged, the value is 1; otherwise, the value is set to 0.
As a preferred embodiment of the present invention, the width feature is characterized by a relative width, as shown in formula (1):
in the formula (1), the components are as follows,representing the relative width of the crack; d represents the actual width of the crack; d, d Limiting the limit Representing the width limit of the crack.
As a preferred embodiment of the present invention, the length feature is characterized by a relative length, as shown in formula (2):
in the formula (2), the amino acid sequence of the compound,representing the relative length of the fracture; l represents the projection length of the crack in the projection direction, the crack length is projected in three directions of a three-dimensional space rectangular coordinate system, the longest projection length is taken as the projection length, and the coordinate axis where the longest projection is positioned is the projection direction; l represents the structural dimension of the member in the projection direction.
As a preferred embodiment of the present invention, the bit face of the crack comprises a bottom face, a top face and side faces, and a three-dimensional vector is constructed to represent the bit face features; each dimension in the three-dimensional vector represents a bit plane, and the value of the bit plane located at the current bit plane is 1, otherwise, the bit plane is 0.
As a preferred embodiment of the invention, the algorithm network used for constructing the bridge crack grade assessment model based on the reinforcement learning algorithm has four layers of networks, including an input layer, two hidden layers and an output layer, wherein the input information of the input layer comprises crack bit surface characteristics, crack length characteristics, crack width characteristics and crack trend characteristics in the basic data of the crack, the hidden layer 1 has 10 unit nodes, the hidden layer 2 has 5 unit nodes, the output layer has 5 unit nodes, the activation function is a RELU function, and the output result is the crack grade corresponding to the score value Q of the corresponding crack assessment result.
In a second aspect, an embodiment of the present invention further provides a bridge crack level evaluation system based on a reinforcement learning algorithm, where the system includes: the system comprises a crack image acquisition module, an image preprocessing module, a morphological feature extraction module, a bit surface feature extraction module, a longitudinal position information extraction module, a training database, an evaluation model construction module and a result output module which are carried on the unmanned aerial vehicle; wherein:
the crack image acquisition module is used for acquiring a bridge crack image for model training and a bridge crack image to be evaluated through an unmanned aerial vehicle;
the image preprocessing module is used for preprocessing the acquired crack image;
the morphological feature extraction module is used for carrying out crack image threshold segmentation on the preprocessed crack image and extracting crack morphological features; the crack morphological characteristics comprise width characteristics, length characteristics and trend characteristics of the crack;
the position face feature extraction module is used for obtaining the position face of the crack image according to the flight track of the unmanned aerial vehicle and extracting position face features;
the longitudinal position information extraction module is used for acquiring the longitudinal coordinates of the crack center point on the bridge axis according to the flight track and shooting parameters of the unmanned aerial vehicle, and normalizing the longitudinal coordinates to obtain longitudinal position information of the crack;
the training database is used for judging crack grades according to the width characteristics, the length characteristics, the trend characteristics, the bit surface characteristics and the longitudinal position information of the cracks, generating crack codes, constructing crack basic data, arranging the crack basic data corresponding to all crack images according to the codes to construct a data set, and dividing the data set into a training set and a testing set; the crack basic data comprises three layers of crack information, which are respectively: bridge level information: bridge coding and structural system; information on component hierarchy: structure type, component coding, component longitudinal/transverse/vertical dimensions; crack level information: crack coding, width characteristics, length characteristics, trend characteristics, bit plane characteristics, positions and grades;
the evaluation model construction module is used for constructing a bridge crack grade evaluation model based on a reinforcement learning algorithm, training the evaluation model by adopting the training set, and verifying the training model by utilizing the testing set to obtain a stable crack grade evaluation model;
the result output module is used for inputting the bridge crack image to be evaluated acquired according to the image acquisition module into the stable crack grade evaluation model in the evaluation model construction module and outputting the crack grade evaluation result of the bridge to be evaluated.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
according to the bridge crack grade assessment method and system based on the reinforcement learning algorithm, provided by the embodiment of the invention, based on automatic acquisition of crack images, the characteristic information of the cracks is extracted through the crack identification program, the characteristics of the cracks are digitalized, errors caused by manual measurement are reduced, the cracks are further graded by using a crack grade assessment model, the subjective influence of detection personnel is effectively reduced, and the efficiency and accuracy of crack detection assessment are improved; meanwhile, the technical threshold of detection is reduced, so that common bridge inspection maintenance personnel (technical personnel without deep professional literacy) can also make accurate judgment on cracks existing in the bridge, a maintenance management department can make timely and reasonable maintenance decisions, and intelligent informatization management in the bridge maintenance process is realized.
Of course, it is not necessary for any one product or method of practicing the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a flowchart of a bridge crack grade evaluation method based on a reinforcement learning algorithm according to an embodiment of the invention;
FIG. 2 is a schematic diagram of the type division of the bottom or top surface crack in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a side crack type classification in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a fracture artwork collected in an embodiment of the present invention;
FIG. 5 is a graph showing the effect of the crack gray scale change in the embodiment of the present invention;
FIG. 6 is a diagram showing the effect of enhancing the crack filtering in the embodiment of the present invention;
FIG. 7 is a schematic diagram of a split segmentation in an embodiment of the present invention;
FIG. 8 is a diagram of a crack status data structure in an embodiment of the present invention;
FIG. 9 is a schematic diagram of a network structure of a crack level evaluation model according to an embodiment of the present invention;
FIG. 10 is a graph of a crack evaluation training result in an embodiment of the present invention;
FIG. 11 is a graph showing the recognition effect obtained by the evaluation of the crack level in the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. It should be noted that, in the case of no conflict, the embodiments of the present invention and features in the embodiments may also be combined with each other.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. In the description of the present invention, the terms "first," "second," "third," "fourth," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
The embodiment of the invention provides a bridge crack grade assessment method and a system based on a reinforcement learning algorithm, which are used for extracting characteristic information of a crack based on an automatically acquired crack image, digitizing the characteristic information, constructing a crack grade assessment model based on the reinforcement learning algorithm, and assessing the current crack grade after training, wherein the accuracy reaches 97% while improving the crack grade assessment efficiency, and the accuracy of crack grade assessment is effectively improved.
As shown in fig. 1, the bridge crack grade evaluation method based on the reinforcement learning algorithm provided by the embodiment of the invention comprises the following steps:
step S1, collecting a crack image through an unmanned aerial vehicle.
When the image acquisition of the crack is carried out in the step, a preset time period or a selected bridge is taken as an object. And carrying out image acquisition by using the unmanned plane carrying the camera device.
In one embodiment, when image acquisition is performed, the method comprises the following steps:
and S11, acquiring bridge images. And when the bridge image is acquired, the main girder of the bridge is acquired in all directions.
And S12, carrying out crack identification on the acquired bridge image, and marking the identified positions meeting the crack condition.
And S13, carrying out local image acquisition again on the identified crack position to obtain a crack image.
In another embodiment, when the image acquisition of the crack is performed in this step, after the above steps S11 to S12 are completed, the steps are performed:
and S14, dividing the crack image at the crack position in the bridge image to obtain a crack image.
The crack image is obtained by acquiring the original bridge image again or cutting the original bridge image, and the mode is selected according to actual conditions.
And S2, preprocessing the crack image, wherein the preprocessing comprises graying, filtering enhancement and the like. By this step, the crack image in the crack image is enhanced.
And S3, performing crack image threshold segmentation on the preprocessed crack image, and extracting crack morphological characteristics. The crack morphology features comprise width features, length features and trend features of the crack. The width characteristic, the length characteristic and the trend characteristic adopt nondimensional crack data.
The method specifically comprises the following steps:
step S31, acquiring a starting point and an ending point of the crack, calculating a center point of the crack image, and dividing the crack image by the center point to acquire a shortest distance edge point and a longest distance edge point which take the center point as a symmetrical center. In the step, when image segmentation is carried out, an SVM model is adopted in a core algorithm.
And S32, judging the trend of the crack according to the included angle between the connecting line of the starting point and the end point of the crack and the longitudinal axis of the bridge, and compiling a crack trend code as a trend characteristic.
In practical applications, the crack types generally include a transverse crack, a longitudinal crack, a vertical crack, and an oblique crack, which correspond to the four crack trends. As shown in fig. 2, for the cracks of the bottom surface (top surface), the three types of the transverse cracks, the longitudinal cracks and the oblique cracks are included, wherein the included angle between the transverse cracks and the longitudinal axis is between 75 and 90 degrees, the included angle between the oblique cracks and the longitudinal axis is between 15 and 75 degrees, and the included angle between the longitudinal cracks and the longitudinal axis is between 0 and 15 degrees; as shown in fig. 3, the side surface cracks comprise three types of vertical cracks, longitudinal cracks and inclined cracks, wherein the included angle between the vertical cracks and the longitudinal axis is between 75 and 90 degrees, the included angle between the inclined cracks and the longitudinal axis is between 15 and 75 degrees, and the included angle between the longitudinal cracks and the longitudinal axis is between 0 and 15 degrees.
On the basis of judging the trend of the crack, constructing four-dimensional vectors as trend codes, and coding and compiling crack trend characteristics, wherein each trend corresponds to one vector; when the current trend is judged, the value is 1; otherwise, the value is set to 0. The fracture strike codes are shown in table 1.
TABLE 1
| Fracture strike type | Fracture strike characterization |
| Transverse direction | (1,0,0,0) |
| Longitudinal direction | (0,1,0,0) |
| Vertical direction | (0,0,1,0) |
| Slant is inclined | (0,0,0,1) |
In step S33, the width feature is calculated by using the distance between the shortest distance edge points as the crack width.
In this step, the width feature is characterized by a relative width, as shown in formula (1):
in the formula (1), the components are as follows,representing the relative width of the crack; d representsThe actual width of the crack (unit: mm); d, d Limiting the limit Representing the width limit of the crack, in the range of 0.05-0.2mm, preferably d in this embodiment Limiting the limit 0.2mm was taken.
In step S34, the length characteristic is calculated using the distance between the longest distance edge points as the crack length.
In this step, the length features are characterized by using a relative length, as shown in formula (2):
in the formula (2), the amino acid sequence of the compound,representing the relative length of the fracture; l represents the projection length (unit: m) of the crack in the projection direction, wherein the transverse and oblique cracks at the bottom face are projected along the transverse direction of the bridge; the vertical and oblique cracks on the side face are projected along the vertical direction of the bridge; longitudinal projections of the longitudinal slit lapping bridge at the bottom surface and the side surface; l represents the structural dimension (unit: m) of the member in the projection direction.
For four different fracture types, the corresponding relative length calculation formulas are shown in formulas (3) - (6), respectively:
for transverse cracks:
in the formula (3), the amino acid sequence of the compound,representing the relative length of the transverse slit; l (L) Transverse bar Representing the projection length (unit: m) of the transverse crack in the transverse bridge direction; l (L) Transverse bar Represents the transverse dimension (unit: m) of the member;
for longitudinal cracking:
in the formula (4), the amino acid sequence of the compound,representing the relative length of the transverse slit; l (L) Longitudinal direction Representing the projection length (unit: m) of the transverse crack in the transverse bridge direction; l (L) Longitudinal direction Represents the transverse dimension (unit: m) of the member;
for vertical cracks:
in the formula (5), the amino acid sequence of the compound,representing the relative length of the vertical fracture; l (L) Vertical column Representing the projection length (unit: m) of the vertical crack in the vertical direction; l (L) Vertical column Representing the vertical dimension (unit: m) of the component;
for oblique cracks:
in the formula (6), the amino acid sequence of the compound,represents the relative length of the oblique fracture; l (L) Vertical column Representing the projection length (unit: m) of the oblique fracture in the vertical (or horizontal) direction; l (L) Vertical column Representing the dimension (in: m) of the component in the vertical (or lateral) direction.
And S4, acquiring a position surface of the crack image according to the flight track of the unmanned aerial vehicle, and extracting the position surface characteristics.
In this step, the bit plane includes three types of bottom, top and side surfaces, and a three-dimensional vector is constructed to represent the bit plane characteristics. Each dimension in the three-dimensional vector represents a bit plane, and the value of the bit plane located at the current bit plane is 1, otherwise, the bit plane is 0.
The bit planes of the cracks were encoded by means of single-hot encoding, the specific encoding being shown in table 2.
TABLE 2
| The surface where the crack is located | Bit plane features |
| Bottom surface | (1,0,0) |
| Side surface | (0,1,0) |
| Top surface | (0,0,1) |
In practical applications, the crack in the top surface is generally not detected. However, from the overall completion, there are still top surface cracks in the structure in individual cases, so the bit-plane characteristics of the top surface cracks remain in table 2.
And S5, acquiring the longitudinal coordinates of the center point of the crack on the bridge axis according to the flight track (the space position of the crack during image acquisition) of the unmanned aerial vehicle and the shooting parameters, and normalizing the longitudinal coordinates to obtain longitudinal position information of the crack. The normalization process is shown in formula (7).
In the formula (7), the amino acid sequence of the compound,representative ofThe relative position of the crack center in the longitudinal direction; x represents the actual distance between the center of the crack and the beginning end of the beam end, and m; l represents the length of the member across which the crack is located, m.
Step S6, judging the grade of the crack and generating a crack code according to the width characteristic, the length characteristic, the trend characteristic, the bit surface characteristic and the longitudinal position information of the crack, and constructing crack basic data, wherein the crack basic data comprises three layers of crack information, namely:
bridge level information: bridge coding and structural system;
information on component hierarchy: structure type, component coding, component longitudinal/transverse/vertical dimensions;
crack level information: crack coding, width features, length features, strike features, bit plane features, location, and grade.
And S7, arranging the crack basic data corresponding to all the crack images according to codes to construct a data set, and dividing the data set into a training set and a testing set.
And S8, constructing a bridge crack grade evaluation model based on a reinforcement learning algorithm, training the evaluation model by adopting the training set, and verifying the training model by utilizing the testing set to obtain a stable crack grade evaluation model.
In this step, the algorithm network used to construct the bridge crack level assessment model based on the reinforcement learning algorithm has four layers of network, including an input layer, two hidden layers and an output layer, where the input information of the input layer includes crack bit surface features, crack length features, crack width features, crack trend features and longitudinal position information in the basic data of the crack, the hidden layer 1 has 10 unit nodes, the hidden layer 2 has 5 unit nodes, the output layer has 5 unit nodes, the activation function is a RELU function, and the output result is a crack level corresponding to the score Q of the corresponding crack assessment result.
And 9, acquiring a crack image to be evaluated, preprocessing the crack image, extracting length characteristics, width characteristics, trend characteristics, position surface characteristics and longitudinal position information of the crack, and inputting the length characteristics, the width characteristics, the trend characteristics, the position surface characteristics and the longitudinal position information into a model to obtain a crack grade evaluation result.
Based on the same thought, the embodiment of the invention also provides a bridge crack grade evaluation system based on a reinforcement learning algorithm, which comprises the following steps: the system comprises a crack image acquisition module, an image preprocessing module, a morphological feature extraction module, a bit surface feature extraction module, a longitudinal position information extraction module, a training database, an evaluation model construction module and a result output module which are carried on the unmanned aerial vehicle; wherein:
the crack image acquisition module is used for acquiring a bridge crack image for model training and a bridge crack image to be evaluated through an unmanned aerial vehicle;
the image preprocessing module is used for preprocessing the acquired crack image;
the morphological feature extraction module is used for carrying out crack image threshold segmentation on the preprocessed crack image and extracting crack morphological features; the crack morphological characteristics comprise width characteristics, length characteristics and trend characteristics of the crack;
the position face feature extraction module is used for obtaining the position face of the crack image according to the flight track of the unmanned aerial vehicle and extracting position face features;
the longitudinal position information extraction module is used for acquiring the longitudinal coordinates of the crack center point on the bridge axis according to the flight track and shooting parameters of the unmanned aerial vehicle, and normalizing the longitudinal coordinates to obtain longitudinal position information of the crack;
the training database is used for judging crack grades according to the width characteristics, the length characteristics, the trend characteristics, the bit surface characteristics and the longitudinal position information of the cracks, generating crack codes, constructing crack basic data, arranging the crack basic data corresponding to all crack images according to the codes to construct a data set, and dividing the data set into a training set and a testing set; the crack basic data comprises three layers of crack information, which are respectively: bridge level information: bridge coding and structural system; information on component hierarchy: structure type, component coding, component longitudinal/transverse/vertical dimensions; crack level information: crack coding, width characteristics, length characteristics, trend characteristics, bit plane characteristics, positions and grades;
the evaluation model construction module is used for constructing a bridge crack grade evaluation model based on a reinforcement learning algorithm, training the evaluation model by adopting the training set, and verifying the training model by utilizing the testing set to obtain a stable crack grade evaluation model;
the result output module is used for inputting the bridge crack image to be evaluated acquired according to the image acquisition module into the stable crack grade evaluation model in the evaluation model construction module and outputting the crack grade evaluation result of the bridge to be evaluated.
The modules in this embodiment are implemented by a processor, and the memory is appropriately increased when storage is required. The processor may be, but is not limited to, a microprocessor MPU, a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), other programmable logic devices, discrete gates, transistor logic devices, discrete hardware components, or the like. The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
In addition, it should be noted that the bridge fracture level evaluation system based on the reinforcement learning algorithm and the bridge fracture level evaluation method based on the reinforcement learning algorithm in this embodiment are corresponding, and description and limitation of the method are applicable to the system as well, and are not repeated here.
The present invention will be described in further detail by way of a specific example.
Taking a continuous beam and a small box beam of the bridge coded as S01 as an example, a crack image is acquired based on an image acquisition module. In this embodiment, the image acquisition module includes unmanned aerial vehicle, cloud platform, camera, infrared range finder and angle sensor. The unmanned plane and the cradle head are used as instrument mounting platforms, can fly according to a set route, and can record longitudinal position information of cracks. The camera is used for collecting crack pictures. The infrared range finder and the angle sensor provide physical conversion parameters for later crack feature extraction.
As shown in table 3, the element parameters of each component in the image acquisition module employed in this example are shown.
TABLE 3 Table 3
| Image sensor | COMS |
| Image sensor size | 23.6*15.8mm |
| Total pixel | 1310 thousands of |
| Effective pixel | 1230 ten thousand |
| Color filter | RGB primary color filter |
| Maximum resolution | 4.288*2.848 |
| Still image size | 4.288*2.848[L]，3.126*2.136[J] |
| Static image format | JPEG,RAW |
As shown in table 3, in the image acquisition module composed of the unmanned plane, the cradle head, the camera, the infrared range finder and the angle sensor, the unmanned plane can cruise according to a pre-planned flight path and can automatically avoid the obstacle; the cradle head is used for carrying a camera, an infrared range finder and an angle sensor, and the rotation angle of the cradle head is +85 degrees to-85 degrees; the infrared range finder is fixed on a cradle head carried by the unmanned plane and used for determining the vertical distance from the image acquisition equipment to the plane where the crack is located and calibrating the digital characteristic information of the crack; the angle sensor is used for acquiring an included angle between the sight line of the lens and the structural surface where the crack is located so as to convert the actual size of the crack from the imaging size. As shown in fig. 4, a schematic diagram of the image of the crack acquired by the image acquisition module is shown.
Graying the acquired crack image, the result is shown in fig. 5; filtering and enhancing are carried out, and the result is shown in figure 6; the maximum threshold segmentation is performed to obtain fracture morphology features, as shown in fig. 7. Then, the crack information is extracted from the existing data, and the crack information of the part of the crack state database is shown in table 4. As shown in table 4 and fig. 8, the constructed fracture basic information and the data structure in the training database include three layers including a bridge layer, a member layer and a fracture layer.
Table 4 crack status database example
And carrying out data normalization and dimensionless treatment on the crack characteristic information in the crack state database. The 400 cracks data collected are divided into a training set and a test set, wherein the training set comprises 300 cracks and the test set comprises 100 cracks. And reading the crack data from the crack data training set for training, wherein the network structure of the crack training model is shown in fig. 9, and the training result is shown in fig. 10. The test set data was imported into the trained model and the predicted results are shown in table 5.
TABLE 5
As can be seen from the prediction results in Table 5, 97 samples of 100 prediction samples are correctly classified, and the overall prediction accuracy reaches 97%, so that the requirements are met. The 3 samples with the evaluation errors are respectively numbered S0100102, S0200501 and S0300501, the samples with the evaluation errors of the crack grades are 2 types and 3 types of cracks through analysis, in the existing bridge detection specification, the evaluation limits of the 2 types and the 3 types of cracks are fuzzy, and deviation can be generated during artificial evaluation. Meanwhile, the 100 samples are respectively rated manually and mechanically, the time length of the crack rating evaluation method based on the reinforcement learning algorithm is 5 minutes, and the time length of the crack rating evaluation method based on the manual operation is 1 hour.
The crack image is acquired by the data acquisition device, the crack morphological feature information is extracted, and part of the extraction result is shown in fig. 11. The extracted fracture characteristic information and longitudinal position information are subjected to dimensionless pretreatment and are imported into a fracture grade evaluation model, and the prediction results are shown in table 6.
TABLE 6
As can be seen from the prediction results of Table 6 and FIG. 11, the overall prediction accuracy is 96.6%, and the crack evaluation method based on the reinforcement learning algorithm is adopted, so that the overall accuracy can reach 96.6% while the evaluation efficiency is improved, and the method has higher feasibility.
According to the bridge crack grade assessment method and system based on the reinforcement learning algorithm, provided by the embodiment of the invention, the characteristic information of the crack is extracted through the crack identification program based on automatic acquisition of the crack image, the crack characteristic is digitalized, errors caused by manual measurement are reduced, the crack is further graded by using a crack grade assessment model, the subjective influence of detection personnel is effectively reduced, and the efficiency and accuracy of crack detection assessment are improved.
The above description is only of the preferred embodiments of the present invention and the description of the technical principles applied is not intended to limit the scope of the invention as claimed, but merely represents the preferred embodiments of the present invention. It will be appreciated by persons skilled in the art that the scope of the invention referred to in the present invention is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
Claims (9)
1. The bridge crack grade evaluation method based on the reinforcement learning algorithm is characterized by comprising the following steps of:
collecting a crack image through an unmanned aerial vehicle;
preprocessing the crack image;
performing crack image threshold segmentation on the preprocessed crack image, and extracting crack morphological characteristics; the crack morphological characteristics comprise width characteristics, length characteristics and trend characteristics of the crack;
acquiring a position surface of a crack image according to a flight track of the unmanned aerial vehicle, and extracting position surface characteristics;
acquiring a longitudinal coordinate of a crack center point on a bridge axis according to the unmanned aerial vehicle flight track and shooting parameters, and normalizing the longitudinal coordinate to obtain longitudinal position information of the crack;
judging the crack grade according to the width characteristic, the length characteristic, the trend characteristic, the bit surface characteristic and the longitudinal position information of the crack, generating a crack code, and constructing crack basic data, wherein the crack basic data comprises three layers of crack information, and the three layers of crack information are respectively: bridge level information: bridge coding and structural system; information on component hierarchy: structure type, component coding, component longitudinal/transverse/vertical dimensions; crack level information: crack coding, width characteristics, length characteristics, trend characteristics, bit plane characteristics, positions and grades;
arranging the crack basic data corresponding to all the crack images according to codes to construct a data set, and dividing the data set into a training set and a testing set;
constructing a bridge crack grade assessment model based on a reinforcement learning algorithm, training the assessment model by adopting the training set, and verifying the training model by utilizing the testing set to obtain a stable crack grade assessment model;
acquiring a crack image to be evaluated, preprocessing the crack image, extracting length characteristics, width characteristics, trend characteristics, bit plane characteristics and longitudinal position information of the crack, and inputting the length characteristics, the width characteristics, the trend characteristics, the bit plane characteristics and the longitudinal position information into a model to obtain a crack grade evaluation result;
the extracting crack morphology features includes:
step S31, acquiring a starting point and an ending point of a crack, calculating a center point of a crack image, and dividing the crack image by the center point to acquire a shortest distance edge point and a longest distance edge point which take the center point as a symmetrical center; in the step, when image segmentation is carried out, an SVM model is adopted by a core algorithm;
step S32, judging the trend of the crack according to the included angle between the connecting line of the starting point and the end point of the crack and the longitudinal axis of the bridge, and compiling a crack trend code as a trend characteristic;
step S33, calculating width characteristics by taking the distance between the shortest distance edge points as the crack width;
in step S34, the length characteristic is calculated using the distance between the longest distance edge points as the crack length.
2. The bridge crack level assessment method according to claim 1, wherein when acquiring the crack image, comprising the steps of:
s11, collecting bridge images; when the bridge image is acquired, all parts of the bridge are acquired in all directions;
step S12, carrying out crack identification on the acquired bridge image, and marking the identified positions meeting the crack condition;
and S13, carrying out local image acquisition again on the identified crack position to obtain a crack image.
3. The bridge crack level assessment method according to claim 1, wherein the step of performing crack image acquisition comprises the steps of:
s11, collecting bridge images; when the bridge image is acquired, all parts of the bridge are acquired in all directions;
step S12, carrying out crack identification on the acquired bridge image, and marking the identified positions meeting the crack condition;
and S14, dividing the crack image at the crack position in the bridge image to obtain a crack image.
4. The bridge crack level assessment method according to claim 1, wherein the step S32 of judging the crack trend and compiling a crack trend code as a trend feature comprises:
for the cracks of the bottom surface or the top surface, the three types of the transverse cracks, the longitudinal cracks and the oblique cracks are included, wherein the included angle between the transverse cracks and the longitudinal axis is between 75 and 90 degrees, the included angle between the oblique cracks and the longitudinal axis is between 15 and 75 degrees, and the included angle between the longitudinal cracks and the longitudinal axis is between 0 and 15 degrees;
for the side surface cracks, the vertical cracks, the longitudinal cracks and the inclined cracks are included, wherein the included angle between the vertical cracks and the longitudinal axis is between 75 degrees and 90 degrees, the included angle between the inclined cracks and the longitudinal axis is between 15 degrees and 75 degrees, and the included angle between the longitudinal cracks and the longitudinal axis is between 0 degrees and 15 degrees;
on the basis of judging the trend of the crack, constructing four-dimensional vectors as trend codes, and coding and compiling crack trend characteristics, wherein each trend corresponds to one vector; when the current trend is judged, the value is 1; otherwise, the value is set to 0.
5. The bridge crack level assessment method according to claim 1, wherein the width characteristic is characterized by a relative width as shown in formula (1):
in the formula (1), the components are as follows,representing the relative width of the crack; d represents the actual width of the crack; d, d Limiting the limit Representing the width limit of the crack.
6. The bridge crack level assessment method according to claim 1, wherein the length characteristics are characterized by a relative length as shown in formula (2):
in the formula (2), the amino acid sequence of the compound,representing the relative length of the fracture; l represents the projection length of the crack in the projection direction, the crack length is projected in three directions of a three-dimensional space rectangular coordinate system, the longest projection length is taken as the projection length, and the coordinate axis where the longest projection is positioned is the projection direction; l represents the structure of the member in the projection directionSize.
7. The bridge fracture rating method according to claim 1, wherein the bit face of the fracture comprises a bottom face, a top face and side faces, and a three-dimensional vector is constructed to represent the bit face characteristics; each dimension in the three-dimensional vector represents a bit plane, and the value of the bit plane located at the current bit plane is 1, otherwise, the bit plane is 0.
8. The bridge fracture level assessment method according to claim 1, wherein the reinforcement learning algorithm is used to construct the bridge fracture level assessment model, the algorithm network is four-layer network, the four-layer network comprises an input layer, two hidden layers and an output layer, the input information of the input layer comprises fracture site characteristics, fracture length characteristics, fracture width characteristics and fracture trend characteristics in the fracture basic data, the hidden layer 1 has 10 unit nodes, the hidden layer 2 has 5 unit nodes, the output layer has 5 unit nodes, the activation function is a RELU function, and the output result is a fracture level corresponding to the score Q of the corresponding fracture assessment result.
9. A bridge fracture rating system based on a reinforcement learning algorithm, the system comprising: the system comprises a crack image acquisition module, an image preprocessing module, a morphological feature extraction module, a bit surface feature extraction module, a longitudinal position information extraction module, a training database, an evaluation model construction module and a result output module which are carried on the unmanned aerial vehicle; wherein:
the crack image acquisition module is used for acquiring a bridge crack image for model training and a bridge crack image to be evaluated through an unmanned aerial vehicle;
the image preprocessing module is used for preprocessing the acquired crack image;
the morphological feature extraction module is used for carrying out crack image threshold segmentation on the preprocessed crack image and extracting crack morphological features; the crack morphological characteristics comprise width characteristics, length characteristics and trend characteristics of the crack;
the position face feature extraction module is used for obtaining the position face of the crack image according to the flight track of the unmanned aerial vehicle and extracting position face features;
the longitudinal position information extraction module is used for acquiring the longitudinal coordinates of the crack center point on the bridge axis according to the flight track and shooting parameters of the unmanned aerial vehicle, and normalizing the longitudinal coordinates to obtain longitudinal position information of the crack;
the training database is used for judging crack grades according to the width characteristics, the length characteristics, the trend characteristics, the bit surface characteristics and the longitudinal position information of the cracks, generating crack codes, constructing crack basic data, arranging the crack basic data corresponding to all crack images according to the codes to construct a data set, and dividing the data set into a training set and a testing set; the crack basic data comprises three layers of crack information, which are respectively: bridge level information: bridge coding and structural system; information on component hierarchy: structure type, component coding, component longitudinal/transverse/vertical dimensions; crack level information: crack coding, width characteristics, length characteristics, trend characteristics, bit plane characteristics, positions and grades;
the evaluation model construction module is used for constructing a bridge crack grade evaluation model based on a reinforcement learning algorithm, training the evaluation model by adopting the training set, and verifying the training model by utilizing the testing set to obtain a stable crack grade evaluation model;
the result output module is used for inputting the bridge crack image to be evaluated acquired according to the image acquisition module into the stable crack grade evaluation model in the evaluation model construction module and outputting the crack grade evaluation result of the bridge to be evaluated;
the morphological feature extraction module is specifically configured to:
acquiring a starting point and an ending point of a crack, calculating a center point of a crack image, dividing the crack image by the center point, and acquiring a shortest distance edge point and a longest distance edge point which take the center point as a symmetry center; in the step, when image segmentation is carried out, an SVM model is adopted by a core algorithm;
judging the trend of the crack according to the included angle between the connecting line of the starting point and the end point of the crack and the longitudinal axis of the bridge, and compiling a crack trend code as a trend characteristic;
calculating width characteristics by taking the distance between the shortest distance edge points as the crack width;
and calculating the length characteristic by taking the distance between the longest distance edge points as the crack length.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211191901.4A CN115511836B (en) | 2022-09-28 | 2022-09-28 | Bridge crack grade assessment method and system based on reinforcement learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211191901.4A CN115511836B (en) | 2022-09-28 | 2022-09-28 | Bridge crack grade assessment method and system based on reinforcement learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115511836A CN115511836A (en) | 2022-12-23 |
| CN115511836B true CN115511836B (en) | 2023-10-27 |
Family
ID=84506892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211191901.4A Active CN115511836B (en) | 2022-09-28 | 2022-09-28 | Bridge crack grade assessment method and system based on reinforcement learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115511836B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116434087B (en) * | 2023-04-04 | 2024-01-23 | 中建二局土木工程集团有限公司 | Concrete crack identification method and device based on GOA-SVM cooperative algorithm and unmanned aerial vehicle |
| CN116128380B (en) * | 2023-04-13 | 2023-06-30 | 沧州路桥工程有限责任公司 | Bridge health monitoring method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279790A (en) * | 2014-06-13 | 2016-01-27 | 中国石油化工股份有限公司 | Fracture network 3D digital core modeling method |
| CN108051450A (en) * | 2017-11-01 | 2018-05-18 | 中铁大桥科学研究院有限公司 | A kind of bridge health monitoring system and method based on unmanned plane |
| CN108985363A (en) * | 2018-07-03 | 2018-12-11 | 长安大学 | A kind of cracks in reinforced concrete bridge classifying identification method based on RBPNN |
| CN109521019A (en) * | 2018-11-09 | 2019-03-26 | 华南理工大学 | A kind of bridge bottom crack detection method based on unmanned plane vision |
| CN110378950A (en) * | 2019-06-18 | 2019-10-25 | 上海同岩土木工程科技股份有限公司 | A kind of tunnel structure crack identification method merged based on gray scale and gradient |
| CN110866872A (en) * | 2019-10-10 | 2020-03-06 | 北京邮电大学 | Pavement crack image preprocessing intelligent selection method and device and electronic equipment |
| KR102239377B1 (en) * | 2019-12-26 | 2021-04-13 | 주식회사 딥인스펙션 | System and method for safety inspection on bridge facilities based on image and xai |
| CN112750200A (en) * | 2021-01-14 | 2021-05-04 | 中路高科交通检测检验认证有限公司 | Bridge disease implementation method and device based on BIM technology |
| CN114913162A (en) * | 2022-05-25 | 2022-08-16 | 广西大学 | Bridge concrete crack detection method and device based on lightweight transform |
| CN114937016A (en) * | 2022-05-25 | 2022-08-23 | 广西大学 | Bridge concrete crack real-time detection method and device based on edge calculation and Transformer |
-
2022
- 2022-09-28 CN CN202211191901.4A patent/CN115511836B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105279790A (en) * | 2014-06-13 | 2016-01-27 | 中国石油化工股份有限公司 | Fracture network 3D digital core modeling method |
| CN108051450A (en) * | 2017-11-01 | 2018-05-18 | 中铁大桥科学研究院有限公司 | A kind of bridge health monitoring system and method based on unmanned plane |
| CN108985363A (en) * | 2018-07-03 | 2018-12-11 | 长安大学 | A kind of cracks in reinforced concrete bridge classifying identification method based on RBPNN |
| CN109521019A (en) * | 2018-11-09 | 2019-03-26 | 华南理工大学 | A kind of bridge bottom crack detection method based on unmanned plane vision |
| CN110378950A (en) * | 2019-06-18 | 2019-10-25 | 上海同岩土木工程科技股份有限公司 | A kind of tunnel structure crack identification method merged based on gray scale and gradient |
| CN110866872A (en) * | 2019-10-10 | 2020-03-06 | 北京邮电大学 | Pavement crack image preprocessing intelligent selection method and device and electronic equipment |
| KR102239377B1 (en) * | 2019-12-26 | 2021-04-13 | 주식회사 딥인스펙션 | System and method for safety inspection on bridge facilities based on image and xai |
| CN112750200A (en) * | 2021-01-14 | 2021-05-04 | 中路高科交通检测检验认证有限公司 | Bridge disease implementation method and device based on BIM technology |
| CN114913162A (en) * | 2022-05-25 | 2022-08-16 | 广西大学 | Bridge concrete crack detection method and device based on lightweight transform |
| CN114937016A (en) * | 2022-05-25 | 2022-08-23 | 广西大学 | Bridge concrete crack real-time detection method and device based on edge calculation and Transformer |
Non-Patent Citations (3)
| Title |
|---|
| CRACK DETECTION AND REFINEMENT VIA DEEP REINFORCEMENT LEARNING;Park, J等;IEEE International Conference on Image Processing (ICIP);全文 * |
| 基于YOLOv5和U-Net3+的桥梁裂缝智能识别与测量;余加勇 等;湖南大学学报(自然科学版);全文 * |
| 大跨桥梁结构健康诊断和管养决策的机器学习方法研究;魏世银;中国博士学位论文全文数据库工程科技II辑;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115511836A (en) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115511836B (en) | Bridge crack grade assessment method and system based on reinforcement learning algorithm | |
| CN110738127B (en) | Helmet identification method based on unsupervised deep learning neural network algorithm | |
| CN104166841A (en) | Rapid detection identification method for specified pedestrian or vehicle in video monitoring network | |
| CN108073898B (en) | Method, device and equipment for identifying human head area | |
| CN105930768A (en) | Spatial-temporal constraint-based target re-identification method | |
| CN110751099A (en) | Unmanned aerial vehicle aerial video track high-precision extraction method based on deep learning | |
| CN108846331B (en) | Video identification method for judging whether screw fastener of motor train unit chassis falls off or not | |
| CN114049356B (en) | Method, device and system for detecting structure apparent crack | |
| Zhao et al. | Image-based comprehensive maintenance and inspection method for bridges using deep learning | |
| CN115482491A (en) | Bridge defect identification method and system based on transformer | |
| Dadrasjavan et al. | Automatic crack detection of road pavement based on aerial UAV imagery | |
| CN115223246A (en) | Personnel violation identification method, device, equipment and storage medium | |
| CN114627021A (en) | Point cloud and deep learning based defect detection method and system | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
| CN112884753A (en) | Track fastener detection and classification method based on convolutional neural network | |
| CN112115770A (en) | Method and system for identifying autonomous inspection defects of unmanned aerial vehicle of overhead line | |
| Shatnawi | Automatic pavement cracks detection using image processing techniques and neural network | |
| Hassan et al. | Real-time road cracks detection based on improved deep convolutional neural network | |
| CN112861762B (en) | Railway crossing abnormal event detection method and system based on generation countermeasure network | |
| Pinto et al. | LOW-COST UAS PHOTOGRAMMETRY FOR ROAD INFRASTRUCTURES’INSPECTION | |
| CN116052110B (en) | Intelligent positioning method and system for pavement marking defects | |
| CN116229511A (en) | Identification re-recognition method based on golden monkey trunk feature extraction | |
| CN116363088A (en) | Expressway concrete pavement crack detection method based on unmanned aerial vehicle, electronic equipment and storage medium | |
| Boudet et al. | A supervised classification approach towards quality self-diagnosis of 3D building models using digital aerial imagery | |
| CN113033443B (en) | Unmanned aerial vehicle-based automatic pedestrian crossing facility whole road network checking method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |