CN116486269A - Bridge crack identification method and system based on image analysis - Google Patents
Bridge crack identification method and system based on image analysis Download PDFInfo
- Publication number
- CN116486269A CN116486269A CN202310506075.6A CN202310506075A CN116486269A CN 116486269 A CN116486269 A CN 116486269A CN 202310506075 A CN202310506075 A CN 202310506075A CN 116486269 A CN116486269 A CN 116486269A
- Authority
- CN
- China
- Prior art keywords
- target
- real
- bridge
- time
- crack
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000010191 image analysis Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 86
- 238000000605 extraction Methods 0.000 claims abstract description 77
- 238000001514 detection method Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 230000004048 modification Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 7
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241000579895 Chlorostilbon Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000018044 dehydration Effects 0.000 description 1
- 238000006297 dehydration reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000010976 emerald Substances 0.000 description 1
- 229910052876 emerald Inorganic materials 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- ZLIBICFPKPWGIZ-UHFFFAOYSA-N pyrimethanil Chemical compound CC1=CC(C)=NC(NC=2C=CC=CC=2)=N1 ZLIBICFPKPWGIZ-UHFFFAOYSA-N 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (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
According to the bridge crack identification method and the system based on image analysis, the target analysis results are identified according to the configured target bridge crack identification threads, so that the target bridge crack positioning information corresponding to the bridge detection image to be processed is obtained according to the event content according to the target analysis results of the identification processing according to the target bridge crack identification threads when the bridge detection image is extracted from the event, description vector extraction is carried out by using the description vector characteristics when the description vector extraction is carried out by using the threads, the description vector extraction dimension is the same as the distribution condition of the target classification characteristics in the target analysis results, the distribution condition of the event and the accuracy of the classification results in the event are considered, and therefore the obtained target bridge crack positioning information is accurate and reliable, and the accuracy and reliability of identifying the target bridge crack positioning information from the bridge detection image are improved.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a bridge crack identification method and system based on image analysis.
Background
Image analysis or image analysis is the extraction of meaningful information from an image; mainly extracted from the digital image by digital image processing technology. The image analysis task may be as simple as reading a bar code label or as complex as identifying a person from a person's face. For analyzing large amounts of data, a computer is indispensable for tasks requiring complex computation or for extraction of quantitative information.
At present, the technical field of image analysis technique application is more extensive, and the bridge crack discernment needs a large amount of manual work to survey at actual operation in-process, and not only extravagant manpower still extravagant a large amount of time like this is difficult to the position of reconnaissance in the manual work, is difficult to confirm the accurate position of crack, consequently, this application can discern the bridge crack through image analysis technique, so, can overcome above-mentioned technical problem.
Disclosure of Invention
In order to improve the technical problems in the related art, the application provides a bridge crack identification method and system based on image analysis.
In a first aspect, a method for identifying a bridge crack based on image analysis is provided, the method comprising: acquiring a real-time bridge state data set of a bridge detection image to be processed; classifying the real-time bridge state data set to obtain a target classification result corresponding to the real-time bridge state data set; obtaining each target class feature corresponding to the target classification result, and analyzing and processing the corresponding each target class feature according to the distribution condition of the target classification result in the real-time bridge state data set to obtain a target analysis result; performing recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed, wherein the target bridge crack recognition thread performs description vector extraction according to the target class feature, and the description vector extraction dimension of the target bridge crack recognition thread is identical to the distribution condition of the target class feature in the target analysis result; and extracting a target classification result corresponding to the target bridge crack positioning information from the real-time bridge state data set, and determining the target classification result as a bridge detection image.
In an independent embodiment, the analyzing the corresponding each target class feature according to the distribution of the target classification result in the real-time bridge status data set to obtain a target analysis result includes: respectively determining target feature items in the analysis result by each target category feature; and sequentially arranging each target feature item according to the distribution condition of the target classification result in the real-time bridge state data set to obtain the target analysis result.
In an independent embodiment, the target bridge crack recognition thread is an artificial intelligent recognition thread, and the step of performing recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed includes: obtaining a real-time input image queue and a real-time description vector extraction image queue corresponding to a real-time description vector extraction unit of the target bridge crack identification thread, wherein when the real-time description vector extraction unit is a first unit, the real-time input image queue is the target analysis result, and when the real-time description vector extraction unit is not the first unit, the real-time input image queue is an output image queue of a previous description vector extraction unit of the real-time description vector extraction unit; when the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, performing recognition processing on the real-time input image queue to obtain a target input image queue, wherein the preset dimension corresponding to the target input image queue is the same as the preset dimension corresponding to the real-time description vector extraction image queue, and the preset dimension corresponding to the preset dimension is the dimension corresponding to the constraint range of the target category characteristic in the target analysis result; extracting the description vector of the target input image queue according to the real-time description vector extraction image queue to obtain a real-time output image queue; and obtaining target bridge crack positioning information corresponding to the bridge detection image to be processed according to the real-time output image queue.
In an independent embodiment, when the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, performing recognition processing on the real-time input image queue to obtain a target input image queue includes: when the preset dimension corresponding to the real-time input image queue is smaller than the preset dimension corresponding to the real-time description vector extraction image queue, adding secondary feature items before the first feature item and/or after the last feature item on the preset dimension of the real-time input image queue to obtain the target input image queue; or when the preset dimension corresponding to the real-time input image queue is larger than the preset dimension corresponding to the real-time description vector extraction image queue, compressing the real-time input image queue to obtain the target input image queue, wherein the target class feature is sampled during compressing, and the dimension of compressing is the same as the distribution condition of the target class feature in the target analysis result.
In an independently implemented embodiment, the method further comprises: obtaining example data, wherein the example data comprises configuration classification results corresponding to configuration events and corresponding information extraction bridge crack positioning information; each configuration category characteristic corresponding to the configuration classification result is obtained, and the corresponding configuration category characteristic is analyzed and processed according to the distribution condition of the configuration classification result in the configuration event, so that a configuration analysis result is obtained; and carrying out thread configuration on the configuration analysis result and the corresponding information extraction bridge crack positioning information determination configuration example to obtain the target bridge crack identification thread, wherein the description vector extraction is carried out according to the configuration class characteristics when the thread configuration is carried out, and the description vector extraction dimension of the thread configuration is the same as the distribution condition of the configuration class characteristics in the configuration analysis result.
In an independently implemented embodiment, the method further comprises: obtaining bridge crack sizes corresponding to the real-time bridge state data sets, and obtaining target crack positions of a plurality of bridge detection images to be processed, wherein the target crack positions correspond to the bridge crack sizes; obtaining target bridge crack identification threads corresponding to each target crack position; the step of carrying out recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed comprises the following steps: and carrying out recognition processing on the target analysis result according to each configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to each target crack position.
In an independent embodiment, the classifying the real-time bridge status data set to obtain the target classification result corresponding to the real-time bridge status data set includes: acquiring real-time crack data of preset crack conditions in the real-time bridge state data set; matching the real-time fracture data with the preset fracture conditions to obtain a target fracture event; and classifying the target crack event to obtain a target classification result corresponding to the real-time bridge state data set.
In an independent embodiment, the identifying the target analysis result according to the configured target bridge crack identifying thread, and obtaining the target bridge crack positioning information corresponding to the bridge detection image to be processed includes: performing recognition processing on the target analysis results according to the configured target bridge crack recognition threads to obtain crack occurrence areas corresponding to each target analysis result in the real-time bridge state data set; and determining the target bridge crack positioning information according to each target analysis result in the crack occurrence area corresponding to the target classification result.
In a second aspect, a bridge crack recognition system based on image analysis is provided, comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the method described above.
According to the bridge crack identification method and system based on image analysis, a real-time bridge state data set of a bridge detection image to be processed is obtained, classification processing is conducted on the real-time bridge state data set to obtain a target classification result corresponding to the real-time bridge state data set, each target class feature corresponding to the target classification result is obtained, analysis processing is conducted on each corresponding target class feature according to the distribution condition of the target classification result in the real-time bridge state data set to obtain a target analysis result, identification processing is conducted on the target analysis result according to a configured target bridge crack identification thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed, description vector extraction is conducted on the target bridge crack identification thread by the target class feature, the description vector extraction dimension of the target bridge crack identification thread is identical to the distribution condition of the target class feature in the target analysis result, and the target classification result corresponding to the target bridge crack positioning information is extracted from the real-time bridge state data set to be determined to be the bridge detection image. The method comprises the steps that when an event is extracted from a bridge detection image, a target analysis result which is obtained according to the content of the event and is subjected to identification processing according to a target bridge crack identification thread is obtained, when the thread is used for carrying out description vector extraction, description vector extraction is carried out according to target category characteristics, the description vector extraction dimension is the same as the distribution condition of the target category characteristics in the target analysis result, and the distribution condition of the event and the accuracy of the classification result in the event are considered, so that the obtained target bridge crack positioning information is accurate and reliable, and the accuracy and the reliability of identifying the target bridge crack positioning information from the bridge detection image are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a bridge crack recognition method based on image analysis according to an embodiment of the present application.
Fig. 2 is a block diagram of a bridge crack recognition device based on image analysis according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, a method for identifying a bridge crack based on image analysis is shown, which may include the following steps 110-140.
Step 110, obtaining a real-time bridge state data set of the bridge detection image to be processed.
For example, the bridge detection image to be processed may be photographed by an unmanned aerial vehicle to obtain image data. The real-time bridge state data set can be understood as a data set consisting of the current states of the respective positions of the bridge. The method can be used for surveying places which cannot be reached by some people, so that the accuracy of crack identification can be improved.
And 120, classifying the real-time bridge state data set to obtain a target classification result corresponding to the real-time bridge state data set.
For example, the specific implementation of the classification processing may include dividing the real-time bridge status data set according to a set requirement, where the set requirement may be used as a standard for division according to occurrence of a crack or a suspected crack.
And 130, obtaining each target class feature corresponding to the target classification result, and analyzing and processing each corresponding target class feature according to the distribution condition of the target classification result in the real-time bridge state data set to obtain a target analysis result.
By way of example, the target class feature may be understood as an important feature in the target classification result regarding crack information.
And 140, carrying out recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed.
The target bridge crack identification thread performs description vector extraction according to the target category characteristics, and the description vector extraction dimension of the target bridge crack identification thread is the same as the distribution condition of the target category characteristics in the target analysis result; and extracting a target classification result corresponding to the target bridge crack positioning information from the real-time bridge state data set, and determining the target classification result as a bridge detection image.
For example, the target bridge fracture identification thread may be an artificial intelligence thread that functions to identify fracture information and determine where the fracture occurs.
It can be understood that a real-time bridge state data set of the bridge detection image to be processed is obtained, the real-time bridge state data set is subjected to classification processing to obtain a target classification result corresponding to the real-time bridge state data set, each target class feature corresponding to the target classification result is obtained, each corresponding target class feature is analyzed and processed according to the distribution condition of the target classification result in the real-time bridge state data set to obtain a target analysis result, the target analysis result is identified and processed according to the configured target bridge crack identification thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed, wherein the target bridge crack identification thread performs description vector extraction according to the target class feature, the description vector extraction dimension of the target bridge crack identification thread is identical to the distribution condition of the target class feature in the target analysis result, and the target classification result corresponding to the target bridge crack positioning information is extracted from the real-time bridge state data set to be determined as the bridge detection image. The method comprises the steps that when an event is extracted from a bridge detection image, a target analysis result which is obtained according to the content of the event and is subjected to identification processing according to a target bridge crack identification thread is obtained, when the thread is used for carrying out description vector extraction, description vector extraction is carried out according to target category characteristics, the description vector extraction dimension is the same as the distribution condition of the target category characteristics in the target analysis result, and the distribution condition of the event and the accuracy of the classification result in the event are considered, so that the obtained target bridge crack positioning information is accurate and reliable, and the accuracy and the reliability of identifying the target bridge crack positioning information from the bridge detection image are improved.
In an independent embodiment, when the corresponding each target class feature is analyzed and processed according to the distribution condition of the real-time bridge status data set according to the target classification result, there is a problem that analysis is inaccurate, so that it is difficult to accurately obtain the target analysis result including the content described in step a and step b.
And a step a of respectively determining the target characteristic matters in the analysis result by using each target category characteristic.
By way of example, the feature may be understood as a crack feature point corresponding to the kind of the crack, and may be a length of the crack or a width of the crack during the actual operation.
And b, sequentially arranging each target feature item according to the distribution condition of the target classification result in the real-time bridge state data set to obtain the target analysis result.
Illustratively, the specific implementation of the arranging includes ordering according to the importance level of the target feature.
It can be understood that when the corresponding target class features are analyzed and processed according to the distribution condition of the real-time bridge state data set according to the target classification result, the problem of inaccurate analysis is solved, so that the importance level of target feature matters of the target analysis result can be accurately obtained for sorting and the like.
In a possible implementation embodiment, the target bridge crack identification thread is an artificial intelligent identification thread, and when the target analysis result is identified according to the configured target bridge crack identification thread, there may be a problem of inaccurate identification, so that it is difficult to accurately obtain the target bridge crack positioning information corresponding to the bridge detection image to be processed, which is described in steps 10-30.
And step 10, obtaining a real-time input image queue and a real-time description vector extraction image queue corresponding to the real-time description vector extraction unit of the target bridge crack identification thread, wherein when the real-time description vector extraction unit is a first unit, the real-time input image queue is the target analysis result, and when the real-time description vector extraction unit is not the first unit, the real-time input image queue is an output image queue of a previous description vector extraction unit of the real-time description vector extraction unit.
And step 20, when the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, performing recognition processing on the real-time input image queue to obtain a target input image queue, wherein the preset dimension corresponding to the target input image queue is the same as the preset dimension corresponding to the real-time description vector extraction image queue, and the preset dimension corresponding to the preset dimension is the dimension corresponding to the constraint range of the target category feature in the target analysis result.
Illustratively, the preset dimension may be understood as the angle of the shot.
Step 30, extracting the description vector of the target input image queue according to the real-time description vector extraction image queue to obtain a real-time output image queue; and obtaining target bridge crack positioning information corresponding to the bridge detection image to be processed according to the real-time output image queue.
By way of example, the target bridge crack locating information may be understood as the specific location where the crack occurs on the bridge.
It can be understood that when the target analysis result is identified according to the configured target bridge crack identification thread, the problem of inaccurate identification is solved, so that the target bridge crack positioning information corresponding to the bridge detection image to be processed can be accurately obtained.
In a possible embodiment, when the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, a problem of recognition error may exist when the real-time input image queue is subjected to recognition processing, so that it is difficult to accurately obtain the target input image queue, which is described in step q1 and step q 2.
And q1, when the preset dimension corresponding to the real-time input image queue is smaller than the preset dimension corresponding to the real-time description vector extraction image queue, adding secondary feature items before the first feature item and/or after the last feature item on the preset dimension of the real-time input image queue to obtain the target input image queue.
And q2, or when the preset dimension corresponding to the real-time input image queue is larger than the preset dimension corresponding to the real-time description vector extraction image queue, performing compression processing on the real-time input image queue to obtain the target input image queue, wherein the target class features are sampled during compression processing, and the dimension of the compression processing is identical with the distribution condition of the target class features in the target analysis result.
It can be understood that when the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, the problem of recognition errors is solved when the real-time input image queue is subjected to recognition processing, so that the target input image queue can be accurately obtained.
In an alternative embodiment, the method further comprises: obtaining example data, wherein the example data comprises configuration classification results corresponding to configuration events and corresponding information extraction bridge crack positioning information; each configuration category characteristic corresponding to the configuration classification result is obtained, and the corresponding configuration category characteristic is analyzed and processed according to the distribution condition of the configuration classification result in the configuration event, so that a configuration analysis result is obtained; and carrying out thread configuration on the configuration analysis result and the corresponding information extraction bridge crack positioning information determination configuration example to obtain the target bridge crack identification thread, wherein the description vector extraction is carried out according to the configuration class characteristics when the thread configuration is carried out, and the description vector extraction dimension of the thread configuration is the same as the distribution condition of the configuration class characteristics in the configuration analysis result.
It will be appreciated that configuration analysis results can be more accurately obtained by processing with artificial intelligence.
In an alternative embodiment, the method further comprises: and obtaining the bridge crack size corresponding to the real-time bridge state data set, and obtaining target crack positions of a plurality of bridge detection images to be processed corresponding to the bridge crack size.
It will be appreciated that the size of the crack can be determined more accurately.
In an alternative embodiment, a target bridge fracture identification thread corresponding to each target fracture location is obtained; the step of carrying out recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed comprises the following steps: and carrying out recognition processing on the target analysis result according to each configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to each target crack position.
It can be appreciated that the accuracy and reliability of obtaining the target bridge fracture positioning information can be improved.
In a possible embodiment, the step of classifying the real-time bridge status data set includes the step of describing the step w 1-step w3, where the step of classifying the real-time bridge status data set includes a problem of classification errors, so that it is difficult to accurately obtain the target classification result corresponding to the real-time bridge status data set.
And step w1, obtaining real-time crack data of preset crack conditions in the real-time bridge state data set.
And step w2, matching the real-time fracture data with the preset fracture conditions to obtain a target fracture event.
Further, setting the crack condition in advance can be understood as setting a condition according to the size of the crack to match with real-time data, wherein the crack is generated due to shrinkage caused by dehydration of the concrete or uneven expansion caused by temperature difference in temperature in the hardening process of the concrete.
And step w3, classifying the target crack event to obtain a target classification result corresponding to the real-time bridge state data set.
It can be understood that when the real-time bridge state data set is classified, the problem of classification errors is solved, so that a target classification result corresponding to the real-time bridge state data set can be accurately obtained.
In a possible embodiment, when the target analysis result is identified according to the configured target bridge crack identification thread, there is a problem of abnormal data identification, so that it is difficult to accurately obtain the target bridge crack positioning information corresponding to the bridge detection image to be processed, where the steps include the descriptions in step e1 and step e 2.
And e1, carrying out recognition processing on the target analysis results according to the configured target bridge crack recognition threads to obtain crack occurrence areas corresponding to each target analysis result in the real-time bridge state data set.
By way of example, the crack occurrence region may be understood as a range in which a crack occurs.
And e2, determining the target bridge crack positioning information according to each target analysis result in the crack occurrence area corresponding to the target classification result.
It can be understood that when the target analysis result is identified and processed according to the configured target bridge crack identification thread, the problem of abnormal data identification is solved, so that the target bridge crack positioning information corresponding to the bridge detection image to be processed can be accurately obtained.
On the basis of the above, referring to fig. 2, there is provided a bridge crack recognition device 200 based on image analysis, the device comprising:
the data obtaining module 210 is configured to obtain a real-time bridge status data set of the bridge detection image to be processed;
the result classification module 220 is configured to perform classification processing on the real-time bridge status data set, so as to obtain a target classification result corresponding to the real-time bridge status data set;
The result analysis module 230 is configured to obtain each target class feature corresponding to the target classification result, and analyze and process the corresponding each target class feature according to the distribution condition of the target classification result in the real-time bridge state data set, so as to obtain a target analysis result;
the positioning determining module 240 is configured to perform recognition processing on the target analysis result according to a configured target bridge crack recognition thread, so as to obtain target bridge crack positioning information corresponding to a bridge detection image to be processed, where the target bridge crack recognition thread performs description vector extraction with the target class feature, and the description vector extraction dimension of the target bridge crack recognition thread is the same as the distribution condition of the target class feature in the target analysis result; and extracting a target classification result corresponding to the target bridge crack positioning information from the real-time bridge state data set, and determining the target classification result as a bridge detection image.
On the basis of the above, a bridge crack recognition system 300 based on image analysis is shown, comprising a processor 310 and a memory 320 in communication with each other, the processor 310 being adapted to read a computer program from the memory 320 and execute it to implement the method described above.
On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.
In summary, based on the above scheme, a real-time bridge state data set of a bridge detection image to be processed is obtained, the real-time bridge state data set is subjected to classification processing to obtain a target classification result corresponding to the real-time bridge state data set, each target class feature corresponding to the target classification result is obtained, each corresponding target class feature is analyzed and processed according to the distribution condition of the target classification result in the real-time bridge state data set to obtain a target analysis result, the target analysis result is identified and processed according to a configured target bridge crack identification thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed, wherein the target bridge crack identification thread performs description vector extraction according to the target class feature, the description vector extraction dimension of the target bridge crack identification thread is identical to the distribution condition of the target class feature in the target analysis result, and the target classification result corresponding to the target bridge crack positioning information is extracted from the real-time bridge state data set to be determined as the bridge detection image. The method comprises the steps that when an event is extracted from a bridge detection image, a target analysis result which is obtained according to the content of the event and is subjected to identification processing according to a target bridge crack identification thread is obtained, when the thread is used for carrying out description vector extraction, description vector extraction is carried out according to target category characteristics, the description vector extraction dimension is the same as the distribution condition of the target category characteristics in the target analysis result, and the distribution condition of the event and the accuracy of the classification result in the event are considered, so that the obtained target bridge crack positioning information is accurate and reliable, and the accuracy and the reliability of identifying the target bridge crack positioning information from the bridge detection image are improved.
It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations of the present application may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.
Meanwhile, the present application uses specific words to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer storage medium may be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.
The computer program code necessary for operation of portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., a conventional programming language such as C language, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, ruby and Groovy, or other programming languages, etc. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.
Furthermore, the order in which the elements and sequences are presented, the use of numerical letters, or other designations are used in the application and are not intended to limit the order in which the processes and methods of the application are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Likewise, it should be noted that in order to simplify the presentation disclosed herein and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the numbers allow for adaptive variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this application is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the present application, documents that are currently or later attached to this application for which the broadest scope of the claims to the present application is limited. It is noted that the descriptions, definitions, and/or terms used in the subject matter of this application are subject to such descriptions, definitions, and/or terms if they are inconsistent or conflicting with such descriptions, definitions, and/or terms.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of this application. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present application may be considered in keeping with the teachings of the present application. Accordingly, embodiments of the present application are not limited to only the embodiments explicitly described and depicted herein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (9)
1. The bridge crack identification method based on image analysis is characterized by comprising the following steps:
acquiring a real-time bridge state data set of a bridge detection image to be processed;
classifying the real-time bridge state data set to obtain a target classification result corresponding to the real-time bridge state data set;
obtaining each target class feature corresponding to the target classification result, and analyzing and processing the corresponding each target class feature according to the distribution condition of the target classification result in the real-time bridge state data set to obtain a target analysis result;
performing recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed, wherein the target bridge crack recognition thread performs description vector extraction according to the target class feature, and the description vector extraction dimension of the target bridge crack recognition thread is identical to the distribution condition of the target class feature in the target analysis result; and extracting a target classification result corresponding to the target bridge crack positioning information from the real-time bridge state data set, and determining the target classification result as a bridge detection image.
2. The method according to claim 1, wherein analyzing the corresponding each target class feature according to the distribution of the target classification result in the real-time bridge status data set to obtain a target analysis result comprises:
respectively determining target feature items in the analysis result by each target category feature;
and sequentially arranging each target feature item according to the distribution condition of the target classification result in the real-time bridge state data set to obtain the target analysis result.
3. The method according to claim 1 or 2, wherein the target bridge crack recognition thread is an artificial intelligent recognition thread, and the step of performing recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed includes:
obtaining a real-time input image queue and a real-time description vector extraction image queue corresponding to a real-time description vector extraction unit of the target bridge crack identification thread, wherein when the real-time description vector extraction unit is a first unit, the real-time input image queue is the target analysis result, and when the real-time description vector extraction unit is not the first unit, the real-time input image queue is an output image queue of a previous description vector extraction unit of the real-time description vector extraction unit;
When the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, performing recognition processing on the real-time input image queue to obtain a target input image queue, wherein the preset dimension corresponding to the target input image queue is the same as the preset dimension corresponding to the real-time description vector extraction image queue, and the preset dimension corresponding to the preset dimension is the dimension corresponding to the constraint range of the target category characteristic in the target analysis result;
extracting the description vector of the target input image queue according to the real-time description vector extraction image queue to obtain a real-time output image queue; and obtaining target bridge crack positioning information corresponding to the bridge detection image to be processed according to the real-time output image queue.
4. The method of claim 3, wherein when the preset dimension corresponding to the real-time input image queue is different from the preset dimension corresponding to the real-time description vector extraction image queue, performing recognition processing on the real-time input image queue to obtain a target input image queue includes:
When the preset dimension corresponding to the real-time input image queue is smaller than the preset dimension corresponding to the real-time description vector extraction image queue, adding secondary feature items before the first feature item and/or after the last feature item on the preset dimension of the real-time input image queue to obtain the target input image queue;
or when the preset dimension corresponding to the real-time input image queue is larger than the preset dimension corresponding to the real-time description vector extraction image queue, compressing the real-time input image queue to obtain the target input image queue, wherein the target class feature is sampled during compressing, and the dimension of compressing is the same as the distribution condition of the target class feature in the target analysis result.
5. The method according to claim 1, wherein the method further comprises:
obtaining example data, wherein the example data comprises configuration classification results corresponding to configuration events and corresponding information extraction bridge crack positioning information; each configuration category characteristic corresponding to the configuration classification result is obtained, and the corresponding configuration category characteristic is analyzed and processed according to the distribution condition of the configuration classification result in the configuration event, so that a configuration analysis result is obtained;
And carrying out thread configuration on the configuration analysis result and the corresponding information extraction bridge crack positioning information determination configuration example to obtain the target bridge crack identification thread, wherein the description vector extraction is carried out according to the configuration class characteristics when the thread configuration is carried out, and the description vector extraction dimension of the thread configuration is the same as the distribution condition of the configuration class characteristics in the configuration analysis result.
6. The method according to claim 1, wherein the method further comprises: obtaining bridge crack sizes corresponding to the real-time bridge state data sets, and obtaining target crack positions of a plurality of bridge detection images to be processed, wherein the target crack positions correspond to the bridge crack sizes;
obtaining target bridge crack identification threads corresponding to each target crack position; the step of carrying out recognition processing on the target analysis result according to the configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to the bridge detection image to be processed comprises the following steps: and carrying out recognition processing on the target analysis result according to each configured target bridge crack recognition thread to obtain target bridge crack positioning information corresponding to each target crack position.
7. The method of claim 1, wherein the classifying the real-time bridge status data set to obtain the target classification result corresponding to the real-time bridge status data set comprises:
acquiring real-time crack data of preset crack conditions in the real-time bridge state data set;
matching the real-time fracture data with the preset fracture conditions to obtain a target fracture event;
and classifying the target crack event to obtain a target classification result corresponding to the real-time bridge state data set.
8. The method according to claim 1, wherein the identifying the target analysis result according to the configured target bridge crack identifying thread, to obtain target bridge crack positioning information corresponding to the bridge inspection image to be processed includes:
performing recognition processing on the target analysis results according to the configured target bridge crack recognition threads to obtain crack occurrence areas corresponding to each target analysis result in the real-time bridge state data set;
and determining the target bridge crack positioning information according to each target analysis result in the crack occurrence area corresponding to the target classification result.
9. A bridge fracture identification system based on image analysis, comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute it to implement the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506075.6A CN116486269A (en) | 2023-05-05 | 2023-05-05 | Bridge crack identification method and system based on image analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310506075.6A CN116486269A (en) | 2023-05-05 | 2023-05-05 | Bridge crack identification method and system based on image analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116486269A true CN116486269A (en) | 2023-07-25 |
Family
ID=87221301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310506075.6A Pending CN116486269A (en) | 2023-05-05 | 2023-05-05 | Bridge crack identification method and system based on image analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116486269A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118211169A (en) * | 2024-05-21 | 2024-06-18 | 中铁西南科学研究院有限公司 | Intelligent bridge health state monitoring method and system based on deep learning |
-
2023
- 2023-05-05 CN CN202310506075.6A patent/CN116486269A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118211169A (en) * | 2024-05-21 | 2024-06-18 | 中铁西南科学研究院有限公司 | Intelligent bridge health state monitoring method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112286906B (en) | Information security processing method based on block chain and cloud computing center | |
| CN113378554B (en) | Intelligent interaction method and system for medical information | |
| CN116486269A (en) | Bridge crack identification method and system based on image analysis | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN115641176A (en) | Data analysis method and AI system | |
| CN117370767B (en) | User information evaluation method and system based on big data | |
| CN116204681A (en) | Short video release information detection method, system and cloud platform | |
| CN116468534A (en) | Credit information level analysis method and system for collective economic organization | |
| CN115514570B (en) | Network diagnosis processing method, system and cloud platform | |
| US11187992B2 (en) | Predictive modeling of metrology in semiconductor processes | |
| CN115373688B (en) | Optimization method and system of software development thread and cloud platform | |
| CN113626538B (en) | Medical information intelligent classification method and system based on big data | |
| CN115687618A (en) | User intention analysis method and system based on artificial intelligence | |
| CN114721943A (en) | Method and device for determining test range | |
| CN113610117B (en) | Underwater sensing data processing method and system based on depth data | |
| CN113645063B (en) | Intelligent data integration method and system based on edge calculation | |
| CN114842573B (en) | Vehicle test data processing method, system and cloud platform | |
| CN115756576B (en) | Translation method of software development kit and software development system | |
| US20180137270A1 (en) | Method and apparatus for non-intrusive program tracing for embedded computing systems | |
| CN114329209B (en) | Portrayal analysis method and system combined with innovation resource data | |
| CN113626559B (en) | Semantic-based intelligent network document retrieval method and system | |
| CN112286724B (en) | Data recovery processing method based on block chain and cloud computing center | |
| CN115409510B (en) | Online transaction security system and method | |
| CN113610123B (en) | Multi-source heterogeneous data fusion method and system based on Internet of things | |
| CN113608689B (en) | Data caching method and system based on edge calculation |
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 |