CN117333824A - BIM-based bridge construction safety monitoring method and system - Google Patents
BIM-based bridge construction safety monitoring method and system Download PDFInfo
- Publication number
- CN117333824A CN117333824A CN202311628136.2A CN202311628136A CN117333824A CN 117333824 A CN117333824 A CN 117333824A CN 202311628136 A CN202311628136 A CN 202311628136A CN 117333824 A CN117333824 A CN 117333824A
- Authority
- CN
- China
- Prior art keywords
- bridge
- image
- gray
- frame
- feature point
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000010276 construction Methods 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000006073 displacement reaction Methods 0.000 claims abstract description 24
- 230000036541 health Effects 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 14
- 230000008859 change Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0008—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings of bridges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0041—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by determining deflection or stress
- G01M5/005—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by determining deflection or stress by means of external apparatus, e.g. test benches or portable test systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
- G01M5/0066—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by exciting or detecting vibration or acceleration
-
- 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
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- 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
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Aviation & Aerospace Engineering (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a bridge construction safety monitoring method and system based on BIM, comprising the following steps: acquiring a 1 st frame bridge gray level image and a 2 nd frame bridge gray level image in each minute in the bridge image; acquiring a target surrounding neighborhood of each feature point according to the gray complexity in the initial surrounding neighborhood of each feature point in the 1 st frame bridge gray image in the bridge image per minute; according to the possibility that each pixel point in the target surrounding neighborhood of each feature point is a noise pixel point, acquiring the updated target surrounding neighborhood of each feature point, and further acquiring all matching feature point pairs of the 1 st frame bridge gray level image every two adjacent minutes; and further obtaining the bridge displacement length of the 1 st frame bridge gray level image every two adjacent minutes, and further evaluating the structural health condition of the bridge. The invention improves the accuracy of monitoring the bridge structure condition by combining the whole vibration data with BIM.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a bridge construction safety monitoring method and system based on BIM.
Background
Bridge construction safety monitoring is critical to ensuring engineering quality and ensuring worker safety, bridge construction involves certain risks, such as structural damage, material problems, worker injury, and the like, safety monitoring helps to reduce these risks and take measures to reduce the possibility of accidents, and monitoring systems can provide real-time data in certain aspects so that constructors can quickly take action to cope with problems, help to quickly make decisions and solve problems, and reduce potential risks.The sensor and the monitoring device can be integrated to acquire the data of the bridge structure in real time, and the data can be combined with +.>Model to provide real-time security monitoring, +.>The application in bridge construction safety monitoring can provide better real-time monitoring, visual analysis, compliance management and cooperative work, so that the safety and quality control are improved, the potential risk is reduced, the smooth proceeding of the bridge construction process is ensured, and the possible problems are reduced.
During bridge construction, abnormal vibration of the bridge may cause some potential safety hazards, and the vibration detector is limited by the effective range and sensitivity, so that global vibration detection on vibration of the bridge cannot be performed well.The algorithm can be used to match different views in the bridge construction scene, at +.>Such matching may be used to detect changes in the structure, to perform safety monitoring, or to reconstruct three-dimensionally from embodied data, so that bridge vibration changes and displacement differences are more easily identified and tracked. But->The algorithm is easy to be affected by noise, the characteristic descriptors constructed by the algorithm do not consider the self-adaptive change of the neighborhood size according to the pixel characteristics of the neighborhood around the characteristic sub-blocks, the accuracy of the algorithm result is affected, various noises are easy to generate when data are collected in the bridge construction environment, and the characteristic points corresponding to the characteristic descriptors are selected randomly due to the complexity of the construction environment, so that the problem of mismatching of the characteristic points is possibly caused.
Disclosure of Invention
In order to solve the problems, the invention provides a bridge construction safety monitoring method and system based on BIM.
The embodiment of the invention provides a bridge construction safety monitoring method based on BIM, which comprises the following steps:
acquiring a 1 st frame bridge gray level image and a 2 nd frame bridge gray level image in each minute in the bridge image;
acquiring all characteristic points of a 1 st frame bridge gray level image in each minute; acquiring an initial surrounding neighborhood of each feature point by presetting a neighborhood side length; acquiring gray complexity in the initial surrounding neighborhood of each feature point according to gray value distribution of pixel points in the initial surrounding neighborhood of each feature point; acquiring the target surrounding neighborhood side length of each feature point according to the gray complexity in the initial surrounding neighborhood of each feature point and the preset neighborhood side length; acquiring the target surrounding neighborhood of each feature point according to the target surrounding neighborhood side length of each feature point;
according to the gray difference of each pixel point in the vicinity of the target of each feature point of the 1 st frame of bridge gray image per minute and the pixel point at the same position of the 2 nd frame of bridge gray image per minute, the possibility that each pixel point in the vicinity of the target of each feature point is a noise pixel point is obtained; screening noise pixel points according to the possibility that each pixel point in the target surrounding neighborhood of each feature point is a noise pixel point, updating the gray value of the noise pixel point, and obtaining the updated target surrounding neighborhood of each feature point; according to the updated target surrounding neighborhood of each feature point, matching the feature points in the 1 st frame bridge gray level image of every two adjacent minutes to obtain all matching feature point pairs; acquiring a feature matching direction of each matching feature point pair according to the position difference of each matching feature point pair; according to the feature matching direction of each matching feature point pair, acquiring all target matching feature point pairs of the 1 st frame bridge gray level image of every two adjacent minutes;
according to all target matching characteristic point pairs of the 1 st frame bridge gray level image of every two adjacent minutes, obtaining bridge displacement length of the 1 st frame bridge gray level image of every two adjacent minutes; and acquiring vibration data of the bridge according to the bridge displacement length of the 1 st frame of bridge gray level image every two adjacent minutes, and evaluating the structural health condition of the bridge according to the vibration data of the bridge.
Preferably, the method for obtaining the initial surrounding neighborhood of each feature point by presetting the neighborhood side length includes the following specific steps:
for any one feature point in a 1 st frame bridge gray level image of any one minute in a bridge image, taking the feature point as a central pixel point of a window, and acquiring the window with the size ofWindow of->And representing the side length of a preset neighborhood, and taking all pixel points in the window as the initial surrounding neighborhood of the characteristic point.
Preferably, the specific formula for obtaining the gray complexity in the initial surrounding neighborhood of each feature point according to the gray value distribution of the pixel points in the initial surrounding neighborhood of each feature point is as follows:
in the method, in the process of the invention,representing the%>The 1 st frame of bridge gray image in minutes +.>Gray scale complexity in the initial surrounding neighborhood of each feature point; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Standard deviation of gray values of all pixel points in the initial surrounding neighborhood of each feature point; />Representing the%>Standard deviation of gray values of all pixels of the 1 st frame bridge gray image in minutes.
Preferably, the obtaining the target surrounding neighborhood side length of each feature point according to the gray complexity in the initial surrounding neighborhood of each feature point and the preset neighborhood side length includes the following specific steps:
will preset the neighborhood side lengthAnd the first part in the bridge image>The 1 st frame of bridge gray image in minutes +.>Gray complexity product in the initial surrounding neighborhood of each feature point, denoted as +.>A first product of the feature points; will be->The result value of the first product of the feature points rounded up is recorded as +.>The edge length of the neighborhood around the object of each feature point>。
Preferably, the specific formula for obtaining the possibility that each pixel point in the vicinity of the target of each feature point is a noise pixel point according to the gray scale difference between each pixel point in the vicinity of the target of each feature point in the 1 st bridge gray scale image per minute and the pixel point in the same position of the 2 nd bridge gray scale image per minute is:
in the method, in the process of the invention,representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>The pixel points are noise pixel point possibility; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Gray values of the individual pixels; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>The pixel points are corresponding to the first pixel point in the bridge image>Gray values of pixel points at the same position in the 2 nd frame bridge gray image in minutes; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Eighth +.>Gray values of the individual pixels; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Eighth +.>The pixel points are corresponding to the first pixel point in the bridge image>Gray values of pixel points at the same position in the 2 nd frame bridge gray image in minutes; />The representation takes absolute value; />An exponential function based on a natural constant is represented.
Preferably, the filtering the noise pixel according to the possibility that each pixel in the vicinity around the target of each feature point is a noise pixel, updating the gray value of the noise pixel, and obtaining the vicinity around the target after updating each feature point includes the following specific methods:
if the first image of the bridgeThe 1 st frame of bridge gray image in minutes +.>The +.>The probability that each pixel point is a noise pixel point is greater than or equal to the +.>All pixels in the neighborhood around the target of each feature point are the average value of the possibility of noise pixels, and the +.>The pixel points are marked as noise pixel points, and the +.>The 1 st frame of bridge gray image in minutes +.>The +.>A pixel point corresponding to the +.>Gray values of pixel points at the same position in the 2 nd frame bridge gray image of minutes are taken as +.>Gray values of the individual pixels; and then screening and updating all noise pixel points in the target surrounding neighborhood of each characteristic point in the 1 st frame bridge gray level image in each minute in the bridge image to obtain the target surrounding neighborhood updated by each characteristic point in the 1 st frame bridge gray level image in each minute in the bridge image.
Preferably, the matching is performed on the feature points in the 1 st frame bridge gray level image of every two adjacent minutes according to the updated target surrounding neighborhood of each feature point, and all matching feature point pairs are obtained, including the following specific methods:
for the first of bridge imagesThe 1 st frame of bridge gray image in minutes +.>Characteristic points, obtain->Feature descriptor coding of feature points and the first +.>The Hamming distance between feature descriptor codes of all feature points in the 1 st frame bridge gray level image of minute, and the feature point with the minimum Hamming distance is taken as the +.>Feature points to be matched of the feature points are to be +.>Characteristic points and->And marking the feature points to be matched of the feature points as matched feature point pairs, and further obtaining all matched feature point pairs of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image.
Preferably, the feature matching direction of each matching feature point pair is obtained according to the position difference of each matching feature point pair; according to the feature matching direction of each matching feature point pair, all target matching feature point pairs of the 1 st frame bridge gray level image of every two adjacent minutes are obtained, and the specific method comprises the following steps:
image the first bridgeThe 1 st frame of bridge gray image in minutes +.>Characteristic points and->Matching characteristic point pair consisting of characteristic points to be matched of the characteristic points is marked as +.>The matching feature point pairs are the first ∈of the bridge image>Minute and the firstNo. 1 bridge gray image of frame 1 of minutes>The calculation method of the feature matching direction of the matching feature point pairs comprises the following steps:
in the method, in the process of the invention,representing a bridgeThe (th) of the image>Minute and->No. 1 bridge gray image of frame 1 of minutes>Feature matching directions of the feature point pairs; />Representing the%>The 1 st frame of bridge gray image in minuteImage position ordinate values of the feature points; />Representing the%>The 1 st frame of bridge gray image in minuteThe ordinate values of the image positions of the feature points to be matched of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Image position abscissa values of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The image position abscissa value of the feature points to be matched of the feature points; />The representation takes absolute value;
the first of bridge imagesMinute and->No. 1 bridge gray image of frame 1 of minutes>The feature matching direction of the matching feature point pairs is smaller than or equal to the +.>Minute and->The average value of the characteristic matching directions of all the matching characteristic point pairs of the 1 st frame bridge gray level image in the minute is +.>And marking the matched characteristic point pairs as target characteristic points to be matched.
Preferably, the bridge vibration data is obtained according to the bridge displacement length of the 1 st frame of bridge gray level image every two adjacent minutes, and the structural health condition of the bridge is estimated according to the bridge vibration data, comprising the following specific methods:
the bridge displacement length of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image is formed into a bridge displacement length sequence, the bridge displacement length sequence is used as vibration data of the bridge, the variance of the vibration data of the bridge is subjected to linear normalization and is used as a bridge risk index, ifBridge risk index is greater than or equal to preset thresholdThen at +.>And displaying a prompt in the environment: "risk exists in structural health status of bridge", if bridge risk index is smaller than preset threshold +.>Then atAnd displaying a prompt in the environment: "structural health of bridge is good".
The invention also provides a bridge construction safety monitoring system based on BIM, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any bridge construction safety monitoring method based on BIM when executing the computer program.
The technical scheme of the invention has the beneficial effects that: the invention is realized by the following steps ofThe feature descriptors constructed by the algorithm perform self-adaptive neighborhood change, the problem that mismatching occurs in feature point matching is solved, the accuracy of feature point matching of the feature descriptors is improved, noise point influence in bridge construction environment is reduced when feature points are matched, acquisition of bridge integral vibration data is completed, global vibration monitoring is performed on the bridge, and integral vibration data combination is improved>And (5) monitoring the condition of the bridge structure.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of a bridge construction safety monitoring method based on BIM of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the concrete implementation, structure, characteristics and effects of the BIM-based bridge construction safety monitoring method and system according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 concrete scheme of the bridge construction safety monitoring method and system based on BIM provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of a bridge construction safety monitoring method based on BIM according to an embodiment of the present invention is shown, and the method includes the following steps:
step S001: and acquiring a 1 st frame bridge gray level image and a 2 nd frame bridge gray level image in each minute of bridge image.
It should be noted that during bridge construction, abnormal vibration of the bridge may cause some potential safety hazards, and the vibration detector is limited by the effective range and sensitivity, so that the vibration of the bridge cannot be well detected in a global vibration manner.Algorithms can be used to match different views in a bridge construction scene, in BIM, suchThe matching can be used to detect changes in the structure, to perform safety monitoring, or to perform three-dimensional reconstruction from embodied data, so that bridge vibration changes and displacement differences can be more easily identified and tracked.
Specifically, in order to implement the bridge construction safety monitoring method based on BIM provided in this embodiment, firstly, a 1 st frame bridge gray image and a 2 nd frame bridge gray image in each minute in a bridge image need to be collected, and the specific process is as follows:
and erecting an industrial camera at the side position of the construction bridge, capturing the side image of the bridge at the position, and after the position is selected, arranging a camera frame at the position to shoot the bridge in construction. In the shot bridge image, only the first minute is cutFrame and->And (3) carrying out graying operation on the 1 st frame and the 2 nd frame bridge images in each minute in the bridge image, so as to obtain the 1 st frame bridge gray image and the 2 nd frame bridge gray image in each minute in the bridge image.
So far, the 1 st frame bridge gray level image and the 2 nd frame bridge gray level image in each minute of bridge image are obtained through the method.
Step S002: and acquiring the target surrounding neighborhood of each feature point according to the gray complexity in the initial surrounding neighborhood of each feature point in the 1 st frame of bridge gray image in the bridge image per minute.
1. And acquiring all characteristic points of the 1 st frame bridge gray level image in each minute in the bridge image and the position of each characteristic point.
It should be noted that, searching for characteristic points in the 1 st frame bridge gray level image of each minute in the bridge image, screening the found characteristic points, adjusting the size of a neighborhood window according to the distribution condition of pixel points around the characteristic points for the screened characteristic points, then completing the screening of noise points around the characteristic points, and carrying out the screening of the characteristic pointsAnd (5) constructing codes of the feature descriptors, and comparing the code results to finish feature point matching.
Specifically, inputting a 1 st frame bridge gray image per minute in the bridge imageThe feature point detection algorithm obtains all feature points of the 1 st frame bridge gray image in the bridge image every minute and the position of each feature point, wherein,the feature point detection algorithm is an existing algorithm, and the embodiment is not described in detail here.
So far, all the characteristic points of the 1 st frame bridge gray level image in each minute and the positions of each characteristic point are obtained.
2. And acquiring the target surrounding neighborhood of each characteristic point in the 1 st frame bridge gray level image in each minute in the bridge image.
The method includes the steps that characteristic points to be obtained are screened, the size of a neighborhood window is adjusted to the screened characteristic points according to the distribution condition of pixel points around the characteristic points, then screening of noise points in areas around the characteristic points is completed, encoding construction of BRIEF characteristic descriptors is conducted to the characteristic points, and encoding results are compared to complete characteristic point matching; each feature point corresponds to its position coordinates in the image,the algorithm needs to select a neighborhood window with a certain size around the pixel point corresponding to each feature point, then encodes the neighborhood window of each feature point, and then uses the neighborhood window as a basis for feature point comparison.
Further, the minimum requirement of the BRIEF algorithm is 256 bits, so that the code of the BRIEF feature descriptor is not required to use repeated pixels for coding during construction, the number of pixels in the neighborhood window is at least greater than 256, the result is 16 after 256 root marks, the pixels of the feature point are center points in the window, the side length of the initial surrounding neighborhood window is required to be odd, the odd number which is closest to and greater than 16 is 17, and 17×17 is selected as the size of the initial surrounding neighborhood.
Presetting a parameterWherein the present embodiment is +.>To describe the example, the present embodiment is not particularly limited, wherein +.>Depending on the particular implementation.
Specifically, for any one feature point in a 1 st frame bridge gray level image of any one minute in a bridge image, the feature point is taken as a central pixel point of a window, and the size of the acquired window isWindow of->And representing a preset neighborhood side length, and taking all pixel points in the window as an initial surrounding neighborhood of the feature point, wherein the initial surrounding neighborhood of the feature point comprises the feature point.
So far, the initial surrounding neighborhood of each characteristic point in the 1 st frame bridge gray image in each minute in the bridge image is obtained.
The smaller the complexity of the initial surrounding neighborhood of the feature point, the less obvious the pixel point change in the initial surrounding neighborhood of the feature point is, and the more the pixel point change is performedThe variation of the coding will not be obvious when the feature descriptors are coded, but if the complexity of the pixel points in the initial surrounding neighborhood of the feature points is larger, the variable of the coding result obtained when the coding is performed is more obvious, and the expanded initial surrounding neighborhood of the feature points will further generate the potential variable of the coding resultThe codes obtained in this way are more strict when the feature points are matched, and the probability of the obtained feature points being mismatched is reduced.
Specifically, in the bridge imageThe 1 st frame of bridge gray image in minutes +.>The calculation mode of gray complexity in the initial surrounding neighborhood of each feature point comprises the following steps:
in the method, in the process of the invention,representing the%>The 1 st frame of bridge gray image in minutes +.>Gray scale complexity in the initial surrounding neighborhood of each feature point; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Standard deviation of gray values of all pixel points in the initial surrounding neighborhood of each feature point; />Representing the%>Mark of gray value of all pixel points of 1 st frame bridge gray image in minuteAnd (5) accuracy difference.
By the way, by the method ofAdd->Taking the logarithm later and combining with +.>The initial surrounding neighborhood size may be adjusted based on the gray level complexity of all pixels within the initial surrounding neighborhood of the feature point. When the complexity of the gray value in the initial surrounding neighborhood of the feature point is larger, the size of the initial surrounding neighborhood of the feature point is increased faster, otherwise, the size of the initial surrounding neighborhood of the feature point is increased slowly, but at least the initial size is kept, so that the dynamic adjustment of the size of the initial surrounding neighborhood of the feature point is ensured to be neither too aggressive nor unresponsive.
Further, the edge length of the neighborhood is presetAnd the first part in the bridge image>The 1 st frame of bridge gray image in minutes +.>Gray complexity product in the initial surrounding neighborhood of each feature point, denoted as +.>A first product of the feature points; will be->The result value of the first product of the feature points rounded up is recorded as +.>The edge length of the neighborhood around the object of each feature point>The method comprises the steps of carrying out a first treatment on the surface of the By->The feature points are used as the central pixel points of the window, and the size of the window is acquired as +.>Is the window of (1), all pixel points in the window are taken as the +.>A target surrounding neighborhood of the feature points; further obtaining the target surrounding neighborhood of each characteristic point in the 1 st frame bridge gray level image per minute in the bridge image, wherein +.>The target surrounding neighborhood of the feature points includes +.>And feature points.
So far, the method is used for obtaining the target surrounding neighborhood of each characteristic point in the 1 st frame bridge gray level image in each minute in the bridge image.
Step S003: according to the possibility that each pixel point in the vicinity of the target of each characteristic point in the 1 st frame bridge gray level image in each minute in the bridge image is a noise pixel point, the vicinity of the target after updating of each characteristic point is obtained, and then all matching characteristic point pairs of the 1 st frame bridge gray level image in each two adjacent minutes in the bridge image are obtained.
1. And acquiring the target surrounding neighborhood updated by each characteristic point in the 1 st frame bridge gray image in each minute in the bridge image.
It should be noted that, after obtaining the neighborhood around the target of each feature point in the 1 st frame bridge gray image per minute in the bridge image, the following is due toIs sensitive mainly to noise in the neighborhood around the object of the feature point, so that the neighborhood around the object of each feature point needs to be treated firstScreening the noise points in the neighborhood; and comparing the 1 st frame and the 2 nd frame Liang Huidu images in the bridge image, and screening noise pixel points in the neighborhood around the target of each characteristic point in the 1 st frame bridge gray image in the bridge image.
Specifically, in the bridge imageThe 1 st frame of bridge gray image in minutes +.>The +.>The calculation method for the possibility that each pixel point is a noise pixel point comprises the following steps:
in the method, in the process of the invention,representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>The pixel points are noise pixel point possibility; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Gray values of the individual pixels; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>The pixel points are corresponding to the first pixel point in the bridge image>Gray values of pixel points at the same position in the 2 nd frame bridge gray image in minutes; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Eighth +.>Gray values of the individual pixels; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Eighth +.>The pixel points are corresponding to the first pixel point in the bridge image>Gray values of pixel points at the same position in the 2 nd frame bridge gray image in minutes; />The representation takes absolute value; />An exponential function based on a natural constant is represented.
It should be noted that, the feature points in the two adjacent frames and the pixels in the surrounding vicinity can be regarded as one-to-one correspondence between the two frames, because the bridge itself is not significantly displaced, and the movement of the person and the machine operation during the bridge construction can be regarded as almost unchanged between the two frames, and when one pixel is combined with the characteristics of the noise pixelsPixel point corresponding to position +.>The larger the difference in gray values is, while at the same time the pixel is +>Is adjacent to the pixel point around the target and the corresponding position>Is of the order of (2)The pixel point can be considered as +.>Is a noise point.
Specifically, if the first bridge imageThe 1 st frame of bridge gray image in minutes +.>The +.>The probability that each pixel point is a noise pixel point is greater than or equal to the +.>All pixels in the neighborhood around the target of each feature point are the average value of the possibility of noise pixels, and the +.>The pixel points are marked as noise pixel points, and the +.>The 1 st frame of bridge gray image in minutes +.>The +.>A pixel point corresponding to the +.>Gray values of pixel points at the same position in the 2 nd frame bridge gray image of minutes are taken as +.>Gray values of the individual pixels; and then for each characteristic point in the 1 st frame bridge gray scale image of each minute in the bridge imageAnd (3) screening and updating all noise pixel points in the target surrounding neighborhood, and obtaining the target surrounding neighborhood updated by each characteristic point in the 1 st frame bridge gray level image per minute in the bridge image.
So far, the neighborhood around the target after updating each characteristic point in the 1 st frame bridge gray image in each minute in the bridge image is obtained.
2. And acquiring all matched characteristic point pairs of the 1 st frame bridge gray level image every two adjacent minutes in the bridge image.
Specifically, inputting the neighborhood around the target after updating each characteristic point in the 1 st frame bridge gray image in each minute in the bridge imageThe algorithm encodes the feature descriptors to obtain feature descriptor codes of each feature point in the 1 st frame bridge gray image of each minute in the bridge image, wherein +.>The algorithm is an existing algorithm, and the description of this embodiment is not repeated here.
For the first of bridge imagesThe 1 st frame of bridge gray image in minutes +.>Characteristic points, obtain->Feature descriptor coding of feature points and the first +.>The Hamming distance between feature descriptor codes of all feature points in the 1 st frame bridge gray level image of minute, and the feature point with the minimum Hamming distance is taken as the +.>Feature points to be matched of the feature points are to be +.>Characteristic points and->And marking the feature points to be matched of the feature points as matched feature point pairs, and further obtaining all matched feature point pairs of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image.
So far, all matching characteristic point pairs of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image are obtained through the method.
Step S004: and acquiring the bridge displacement length of the 1 st frame bridge gray level image every two adjacent minutes according to all target matching characteristic point pairs of the 1 st frame bridge gray level image every two adjacent minutes in the bridge image, so as to evaluate the structural health condition of the bridge.
1. And acquiring all target matching characteristic point pairs of the 1 st frame bridge gray level image every two adjacent minutes in the bridge image.
It should be noted that, since the comparison frequency is once per minute, the firstMinute and->The first frame image in the minute carries out characteristic point matching, the matched characteristic points in the two frame images are in pairs, and the matched characteristic points possibly have wrong matched characteristic points and need to be screened; since the feature points with the wrong matching are only occupied, the angle average value obtained through all the feature points matched in pairs is definitely larger than the average value if the angles of the feature points with the wrong matching are the same.
Specifically, the first image of the bridge isThe 1 st frame of bridge gray image in minutes +.>Characteristic points and->Matching characteristic point pair consisting of characteristic points to be matched of the characteristic points is marked as +.>The matching feature point pairs are the first ∈of the bridge image>Minute and->No. 1 bridge gray image of frame 1 of minutes>The calculation method of the feature matching direction of the matching feature point pairs comprises the following steps:
in the method, in the process of the invention,representing the%>Minute and->No. 1 bridge gray image of frame 1 of minutes>Feature matching directions of the feature point pairs; />Representing the%>The 1 st frame of bridge gray image in minuteImage position ordinate values of the feature points; />Representing the%>The 1 st frame of bridge gray image in minuteThe ordinate values of the image positions of the feature points to be matched of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Image position abscissa values of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The image position abscissa value of the feature points to be matched of the feature points; />The representation takes absolute value.
Further, in the bridge imageMinute and->Bridge gray image of 1 st frame in minutesIs>The feature matching direction of the matching feature point pairs is smaller than or equal to the +.>Minute and->The average value of the characteristic matching directions of all the matching characteristic point pairs of the 1 st frame bridge gray level image in the minute is +.>The matching characteristic point pairs are marked as target characteristic points to be matched; and further obtaining all target matching characteristic point pairs of the 1 st frame bridge gray level image every two adjacent minutes in the bridge image.
So far, all target matching characteristic point pairs of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image are obtained.
2. And acquiring the bridge displacement length of the 1 st frame bridge gray level image every two adjacent minutes in the bridge image.
Specifically, through the first bridge imageMinute and->Feature point matching is carried out on all target matching feature point pairs of the bridge gray level image of the 1 st frame in minutes, displacement of each target matching feature point pair is obtained, and the displacement average value of all target matching feature point pairs is used as the +.>Minute and->Bridge displacement length of 1 st frame bridge gray level image in each minute, and further bridge displacement length of 1 st frame bridge gray level image in every two adjacent minutes in bridge image is obtainedDegree.
Presetting a parameterWherein the present embodiment is +.>To describe the example, the present embodiment is not particularly limited, wherein +.>Depending on the particular implementation.
Further, the bridge displacement length of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image is formed into a bridge displacement length sequence, the bridge displacement length sequence is used as vibration data of the bridge, the variance of the vibration data of the bridge is subjected to linear normalization and used as a bridge risk index, and if the bridge risk index is larger than or equal to a preset threshold valueThen at +.>And displaying a prompt in the environment: "risk exists in structural health status of bridge", if bridge risk index is smaller than preset threshold +.>Then at +.>And displaying a prompt in the environment: "structural health of bridge is good".
Through the steps, the bridge construction safety monitoring method based on BIM is completed.
The invention also provides a bridge construction safety monitoring system based on BIM, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any bridge construction safety monitoring method based on BIM when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The bridge construction safety monitoring method based on BIM is characterized by comprising the following steps of:
acquiring a 1 st frame bridge gray level image and a 2 nd frame bridge gray level image in each minute in the bridge image;
acquiring all characteristic points of a 1 st frame bridge gray level image in each minute; acquiring an initial surrounding neighborhood of each feature point by presetting a neighborhood side length; acquiring gray complexity in the initial surrounding neighborhood of each feature point according to gray value distribution of pixel points in the initial surrounding neighborhood of each feature point; acquiring the target surrounding neighborhood side length of each feature point according to the gray complexity in the initial surrounding neighborhood of each feature point and the preset neighborhood side length; acquiring the target surrounding neighborhood of each feature point according to the target surrounding neighborhood side length of each feature point;
according to the gray difference of each pixel point in the vicinity of the target of each feature point of the 1 st frame of bridge gray image per minute and the pixel point at the same position of the 2 nd frame of bridge gray image per minute, the possibility that each pixel point in the vicinity of the target of each feature point is a noise pixel point is obtained; screening noise pixel points according to the possibility that each pixel point in the target surrounding neighborhood of each feature point is a noise pixel point, updating the gray value of the noise pixel point, and obtaining the updated target surrounding neighborhood of each feature point; according to the updated target surrounding neighborhood of each feature point, matching the feature points in the 1 st frame bridge gray level image of every two adjacent minutes to obtain all matching feature point pairs; acquiring a feature matching direction of each matching feature point pair according to the position difference of each matching feature point pair; according to the feature matching direction of each matching feature point pair, acquiring all target matching feature point pairs of the 1 st frame bridge gray level image of every two adjacent minutes;
according to all target matching characteristic point pairs of the 1 st frame bridge gray level image of every two adjacent minutes, obtaining bridge displacement length of the 1 st frame bridge gray level image of every two adjacent minutes; and acquiring vibration data of the bridge according to the bridge displacement length of the 1 st frame of bridge gray level image every two adjacent minutes, and evaluating the structural health condition of the bridge according to the vibration data of the bridge.
2. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the obtaining the initial surrounding neighborhood of each feature point by presetting the neighborhood side length comprises the following specific steps:
for any one feature point in a 1 st frame bridge gray level image of any one minute in a bridge image, taking the feature point as a central pixel point of a window, and acquiring the window with the size ofWindow of->And representing the side length of a preset neighborhood, and taking all pixel points in the window as the initial surrounding neighborhood of the characteristic point.
3. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the specific formula for obtaining the gray complexity in the initial surrounding neighborhood of each feature point according to the gray value distribution of the pixel points in the initial surrounding neighborhood of each feature point is:
in the method, in the process of the invention,representing the%>Bridge frame 1 in minutesThe (th) in gray scale image>Gray scale complexity in the initial surrounding neighborhood of each feature point; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Standard deviation of gray values of all pixel points in the initial surrounding neighborhood of each feature point; />Representing the%>Standard deviation of gray values of all pixels of the 1 st frame bridge gray image in minutes.
4. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the specific method for obtaining the target surrounding neighborhood side length of each feature point according to the gray level complexity and the preset neighborhood side length in the initial surrounding neighborhood of each feature point includes:
will preset the neighborhood side lengthAnd the first part in the bridge image>The 1 st frame of bridge gray image in minutes +.>The gray complexity product in the initial surrounding neighborhood of each feature point is recorded as the first/>A first product of the feature points; will be->The result value of the first product of the feature points rounded up is recorded as +.>The edge length of the neighborhood around the object of each feature point>。
5. The bridge construction safety monitoring method based on BIM according to claim 4, wherein the specific formula for obtaining the possibility that each pixel point in the vicinity of the target of each feature point is a noise pixel point according to the gray scale difference between each pixel point in the vicinity of the target of each feature point in the 1 st frame of bridge gray scale image per minute and the pixel point in the same position in the 2 nd frame of bridge gray scale image per minute is:
in the method, in the process of the invention,representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>The pixel points are noise pixelsPoint likelihood; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Gray values of the individual pixels; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>The pixel points are corresponding to the first pixel point in the bridge image>Gray values of pixel points at the same position in the 2 nd frame bridge gray image in minutes; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Eighth +.>Gray values of the individual pixels; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The +.>Eighth +.>The pixel points are corresponding to the first pixel point in the bridge image>Gray values of pixel points at the same position in the 2 nd frame bridge gray image in minutes; />The representation takes absolute value;an exponential function based on a natural constant is represented.
6. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the specific method for screening noise pixels according to the possibility that each pixel in the vicinity around the target of each feature point is a noise pixel, updating the gray value of the noise pixel, and obtaining the vicinity around the target after updating each feature point includes the following steps:
if the first image of the bridgeThe 1 st frame of bridge gray image in minutes +.>The +.>The probability that each pixel point is a noise pixel point is greater than or equal to the +.>All pixels in the neighborhood around the target of each feature point are the average value of the possibility of noise pixels, and the +.>The pixel points are marked as noise pixel points, and the +.>The 1 st frame of bridge gray image in minutes +.>The +.>A pixel point corresponding to the +.>Gray values of pixel points at the same position in the 2 nd frame bridge gray image of minutes are taken as +.>Gray values of the individual pixels; and then divide each part in the bridge imageAnd screening and updating all noise pixel points in the target surrounding neighborhood of each characteristic point in the 1 st frame bridge gray image of the clock to obtain the target surrounding neighborhood updated by each characteristic point in the 1 st frame bridge gray image of each minute in the bridge image.
7. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the method for matching the feature points in the 1 st frame of bridge gray level image every two adjacent minutes according to the updated target surrounding neighborhood of each feature point to obtain all matching feature point pairs comprises the following specific steps:
for the first of bridge imagesThe 1 st frame of bridge gray image in minutes +.>Characteristic points, obtain->Feature descriptor coding of feature points and the first +.>The Hamming distance between feature descriptor codes of all feature points in the 1 st frame bridge gray level image of minute, and the feature point with the minimum Hamming distance is taken as the +.>Feature points to be matched of the feature points are to be +.>Characteristic points and->Marking the feature points to be matched of the feature points as matched feature point pairs, and further obtaining 1 st frame bridge gray of every two adjacent minutes in the bridge imageAll pairs of matching feature points of the degree image.
8. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the characteristic matching direction of each matching characteristic point pair is obtained according to the position difference of each matching characteristic point pair; according to the feature matching direction of each matching feature point pair, all target matching feature point pairs of the 1 st frame bridge gray level image of every two adjacent minutes are obtained, and the specific method comprises the following steps:
image the first bridgeThe 1 st frame of bridge gray image in minutes +.>Characteristic points and->Matching characteristic point pair consisting of characteristic points to be matched of the characteristic points is marked as +.>The matching feature point pairs are the first ∈of the bridge image>Minute and->No. 1 bridge gray image of frame 1 of minutes>The calculation method of the feature matching direction of the matching feature point pairs comprises the following steps:
in the method, in the process of the invention,representing the%>Minute and->No. 1 bridge gray image of frame 1 of minutes>Feature matching directions of the feature point pairs; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Image position ordinate values of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The ordinate values of the image positions of the feature points to be matched of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>Image position abscissa values of the feature points; />Representing the%>The 1 st frame of bridge gray image in minutes +.>The image position abscissa value of the feature points to be matched of the feature points; />The representation takes absolute value;
the first of bridge imagesMinute and->No. 1 bridge gray image of frame 1 of minutes>The feature matching direction of the matching feature point pairs is smaller than or equal to the +.>Minute and->The average value of the characteristic matching directions of all the matching characteristic point pairs of the 1 st frame bridge gray level image in the minute is +.>And marking the matched characteristic point pairs as target characteristic points to be matched.
9. The bridge construction safety monitoring method based on BIM according to claim 1, wherein the bridge vibration data is obtained according to the bridge displacement length of the 1 st frame of bridge gray level image every two adjacent minutes, and the bridge structural health condition is estimated according to the bridge vibration data, comprising the following specific steps:
the bridge displacement length of the 1 st frame bridge gray level image of every two adjacent minutes in the bridge image is formed into a bridge displacement length sequence, the bridge displacement length sequence is used as vibration data of the bridge, the variance of the vibration data of the bridge is subjected to linear normalization and used as a bridge risk index, and if the bridge risk index is larger than or equal to a preset threshold valueThen at +.>And displaying a prompt in the environment: "risk exists in structural health status of bridge", if bridge risk index is smaller than preset threshold +.>Then at +.>And displaying a prompt in the environment: "structural health of bridge is good".
10. A BIM-based bridge construction safety monitoring system comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor, when executing the computer program, realizes the steps of the BIM-based bridge construction safety monitoring method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311628136.2A CN117333824B (en) | 2023-12-01 | 2023-12-01 | BIM-based bridge construction safety monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311628136.2A CN117333824B (en) | 2023-12-01 | 2023-12-01 | BIM-based bridge construction safety monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117333824A true CN117333824A (en) | 2024-01-02 |
| CN117333824B CN117333824B (en) | 2024-02-13 |
Family
ID=89279646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311628136.2A Active CN117333824B (en) | 2023-12-01 | 2023-12-01 | BIM-based bridge construction safety monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117333824B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953036A (en) * | 2024-03-22 | 2024-04-30 | 河南敦喏建筑工程有限公司 | Road and bridge foundation settlement displacement monitoring system and method |
| CN118052733A (en) * | 2024-03-06 | 2024-05-17 | 昆山市交通工程发展中心 | Bridge state monitoring method based on AR live-action enhancement |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825009A (en) * | 2016-03-15 | 2016-08-03 | 东南大学 | Bridge vertical deformation property early warning method based on building information modeling |
| CN109559348A (en) * | 2018-11-30 | 2019-04-02 | 东南大学 | A kind of contactless deformation measurement method of bridge based on tracing characteristic points |
| CN110232387A (en) * | 2019-05-24 | 2019-09-13 | 河海大学 | A kind of heterologous image matching method based on KAZE-HOG algorithm |
| CN110634137A (en) * | 2019-09-26 | 2019-12-31 | 杭州鲁尔物联科技有限公司 | Bridge deformation monitoring method, device and equipment based on visual perception |
| CN112508071A (en) * | 2020-11-30 | 2021-03-16 | 中国公路工程咨询集团有限公司 | BIM-based bridge disease marking method and device |
| CN115456868A (en) * | 2022-11-14 | 2022-12-09 | 南京金易众和信息科技有限公司 | Data management method for fire drill system |
| CN116993725A (en) * | 2023-09-26 | 2023-11-03 | 深圳市普能达电子有限公司 | Intelligent patch information processing system of flexible circuit board |
-
2023
- 2023-12-01 CN CN202311628136.2A patent/CN117333824B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105825009A (en) * | 2016-03-15 | 2016-08-03 | 东南大学 | Bridge vertical deformation property early warning method based on building information modeling |
| CN109559348A (en) * | 2018-11-30 | 2019-04-02 | 东南大学 | A kind of contactless deformation measurement method of bridge based on tracing characteristic points |
| CN110232387A (en) * | 2019-05-24 | 2019-09-13 | 河海大学 | A kind of heterologous image matching method based on KAZE-HOG algorithm |
| CN110634137A (en) * | 2019-09-26 | 2019-12-31 | 杭州鲁尔物联科技有限公司 | Bridge deformation monitoring method, device and equipment based on visual perception |
| CN112508071A (en) * | 2020-11-30 | 2021-03-16 | 中国公路工程咨询集团有限公司 | BIM-based bridge disease marking method and device |
| CN115456868A (en) * | 2022-11-14 | 2022-12-09 | 南京金易众和信息科技有限公司 | Data management method for fire drill system |
| CN116993725A (en) * | 2023-09-26 | 2023-11-03 | 深圳市普能达电子有限公司 | Intelligent patch information processing system of flexible circuit board |
Non-Patent Citations (2)
| Title |
|---|
| 刘欢蝶;龚涛;章庆伟;苏时玲;: "基于FAST和BRIEF的密度聚类图像匹配算法改进", 测绘与空间地理信息, no. 03 * |
| 陈昌川;李奎;乔飞;姜宏伟;赵曼淇;公茂盛;王海宁;张天骐;: "基于图像处理的建筑物振动位移测量算法", 电子与信息学报, no. 10 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118052733A (en) * | 2024-03-06 | 2024-05-17 | 昆山市交通工程发展中心 | Bridge state monitoring method based on AR live-action enhancement |
| CN117953036A (en) * | 2024-03-22 | 2024-04-30 | 河南敦喏建筑工程有限公司 | Road and bridge foundation settlement displacement monitoring system and method |
| CN117953036B (en) * | 2024-03-22 | 2024-06-11 | 河南敦喏建筑工程有限公司 | Road and bridge foundation settlement displacement monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117333824B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117333824B (en) | BIM-based bridge construction safety monitoring method and system | |
| WO2018006834A1 (en) | Systems, processes and devices for occlusion detection for video-based object tracking | |
| CN104933389B (en) | Identity recognition method and device based on finger veins | |
| CN108986094B (en) | Automatic data updating method for training image library for face recognition | |
| CN105426827A (en) | Living body verification method, device and system | |
| CN110555875A (en) | Pupil radius detection method and device, computer equipment and storage medium | |
| CN107958441B (en) | Image splicing method and device, computer equipment and storage medium | |
| WO2022022551A1 (en) | Method and device for analyzing video for evaluating movement disorder having privacy protection function | |
| CN113705426B (en) | Face verification method, device, server and readable storage medium | |
| WO2021036634A1 (en) | Fault detection method and related product | |
| US20220309635A1 (en) | Computer vision-based anomaly detection method, device and electronic apparatus | |
| CN116385472B (en) | Hardware stamping part deburring effect evaluation method | |
| CN113752086A (en) | Method and device for detecting state of numerical control machine tool cutter | |
| CN112633221A (en) | Face direction detection method and related device | |
| CN117372917A (en) | Security abnormal behavior identification method based on multidimensional feature fusion | |
| CN117523235B (en) | A patient wound intelligent identification system for surgical nursing | |
| CN117475502B (en) | Iris and face fusion recognition method and system based on mine | |
| CN114503168A (en) | Object detection | |
| JP6799325B2 (en) | Image correction device, image correction method, attention point recognition device, attention point recognition method and abnormality detection system | |
| CN116092198B (en) | Mining safety helmet identification detection method, device, equipment and medium | |
| CN109447942A (en) | Image blur determines method, apparatus, computer equipment and storage medium | |
| CN117132947A (en) | Dangerous area personnel identification method based on monitoring video | |
| Saxena et al. | Video inpainting detection and localization using inconsistencies in optical flow | |
| CN114972354B (en) | Image processing-based autoclaved aerated concrete block production control method and system | |
| CN112487903B (en) | Gait data generation method and device based on countermeasure network |
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 |