CN106758715A - A kind of measuring method of the pavement current repair quantities based on image recognition result - Google Patents

A kind of measuring method of the pavement current repair quantities based on image recognition result Download PDF

Info

Publication number
CN106758715A
CN106758715A CN201710050204.XA CN201710050204A CN106758715A CN 106758715 A CN106758715 A CN 106758715A CN 201710050204 A CN201710050204 A CN 201710050204A CN 106758715 A CN106758715 A CN 106758715A
Authority
CN
China
Prior art keywords
crack
road surface
computing
pavement
detection
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
Application number
CN201710050204.XA
Other languages
Chinese (zh)
Other versions
CN106758715B (en
Inventor
赵延东
潘宗俊
高鑫
邓捷
王浩仰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZHONGGONG HI-TECH CONSERVATION TECHNOLOGY CO LTD
Original Assignee
ZHONGGONG HI-TECH CONSERVATION TECHNOLOGY CO LTD
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ZHONGGONG HI-TECH CONSERVATION TECHNOLOGY CO LTD filed Critical ZHONGGONG HI-TECH CONSERVATION TECHNOLOGY CO LTD
Priority to CN201710050204.XA priority Critical patent/CN106758715B/en
Publication of CN106758715A publication Critical patent/CN106758715A/en
Application granted granted Critical
Publication of CN106758715B publication Critical patent/CN106758715B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • EFIXED CONSTRUCTIONS
    • E01CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
    • E01CCONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
    • E01C23/00Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
    • E01C23/01Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs

Abstract

The invention discloses a kind of measuring method of the pavement current repair quantities based on image recognition result of offer, including:By IMAQ and identification equipment, in recognizing and distinguish computing individual pavement image according to damaged boundary curve, the various types of damaged quantity in crack class road surface;It is determined that detecting section start, end pile No. scope, computing detects the quantity summation of crack class road surface breakage in all pavement images in road section scope;By the detection section crack class road surface breakage quantity summation of the calculating, computing, the computing detection section full width various types of road surface breakage quantity summations of width internal fissure class are carried out with full width conversion coefficient K;By in the detection section full width width of the calculating, the various types of damaged quantity summations in crack class road surface, the matching pavement current repair quantities of computing.Relative to prior art, the survey engineering amount degree of accuracy is greatly improved, the aspect such as manpower, material, workload and duration progress in the later stage, and distribution is accurate, it is to avoid waste.

Description

A kind of measuring method of the pavement current repair quantities based on image recognition result
Technical field
The invention belongs to road maintenance technical field, a kind of pavement current repair engineering based on image recognition result is particularly related to The measuring method of amount.
Background technology
Pavement current repair engineering refers to that the laterally or longitudinally crack that occurs of road pavement, block the road surface breakage such as split, are cracked and supported Protect treatment engineering measure, will not included during pavement maintenance generally overhaul, in repair road surface breakage maintenance, list light maintenance in Engineering.By accurate measuring and calculating pavement current repair quantities, rationally budget and pavement current repair engineering cost can be distributed, be routine servicing Management provides effective decision references.
The measuring and calculating of pavement current repair quantities is typically with manual site's investigation measuring method, and statistic mixed-state section full width is wide The quantity of road surface breakage in degree.Because highway mileage is more long, using artificial walking investigate inefficiency, and road surface breakage type compared with Many, the subjective judgement gap of investigator is larger, causes investigation measurement result subjectivity larger, therefore conventional method is present accurately Property difference and the low problem of efficiency.
The content of the invention
In view of this, the invention reside in a kind of measuring and calculating side of the pavement current repair quantities based on image recognition result of offer Method is low to solve the problems, such as the above-mentioned accuracy difference existed based on manual research measuring method and efficiency.
To solve the above problems, the present invention provides a kind of measuring and calculating side of the pavement current repair quantities based on image recognition result Method, including:
By IMAQ and identification equipment, in recognizing and distinguish computing individual pavement image according to damaged boundary curve, crack The various types of damaged quantity in class road surface;
It is determined that detection section start, end pile No. scope, crack class road in all pavement images in computing detection road section scope The damaged quantity summation in face;
By the detection section crack class road surface breakage quantity summation of the calculating, computing is carried out with full width conversion coefficient K, Computing detects the section full width various types of road surface breakage quantity summations of width internal fissure class;
By the way that in the detection section full width width of the calculating, the various types of damaged quantity summations in crack class road surface are transported Matching pavement current repair quantities.
Preferably, the crack class road surface breakage type is:Strip crack and block crack.
Preferably, the various types of damaged processes in crack class road surface include in recognizing individual pavement image:
Pavement image is divided into the grid of 0.1m × 0.1m, by automatic identification technology, by comprising damaged road surface net Lattice are identified;
For any independent crack or joint set, any part of its mark mesh shape cannot cover 0.3m × The square area of 0.3m, is identified as strip crack;
For any independent crack or joint set, any part of its mark mesh shape covers at least one 0.3m The square area of × 0.3m, is identified as block crack.
Preferably, full width conversion coefficient K is obtained by the computing of below equation:
K=α × β;
Wherein, α is detection width conversion coefficient, w1It is half range width of roadway, w0It is the detection width of pavement image, β is inspection Direction conversion coefficient is surveyed, two direction of traffics of detection up-downgoing are 1, detect that single direction of traffic is 2.
Preferably, the pavement current repair quantities of computing matching includes:
The length summation in strip crack is defined as cementation of fissures quantities;The area summation in block crack is defined as digging work Cheng Liang.
The present invention arbitrarily sets the technical scheme of criterion of identification relative in the prior art, with the accurate effect of identification. The criterion of identification of determination, introduces accuracy of identification and working area the two parameters, so as to obtain the measurement result in later stage relative to Prior art, the degree of accuracy is greatly improved, the light maintenance quantities for obtaining, and the manpower, material, workload and duration in the later stage enter The aspects such as degree, distribution is accurate, it is to avoid waste.
Brief description of the drawings
Fig. 1 is the flow chart of embodiment;
Fig. 2 is the image after the image shot in embodiment and identification;
Fig. 3 is two way dual lane highway, the schematic diagram of unidirectional detection in embodiment;
Fig. 4 is two way dual lane highway, the schematic diagram of two-way detection in embodiment;
Fig. 5 is two-way many two-lane highways, the schematic diagram of unidirectional detection in embodiment;
Fig. 6 is two-way many two-lane highways, the schematic diagram of two-way detection in embodiment.
Specific embodiment
It is the scheme in the clear explanation present invention, preferred embodiment is given below and is described with reference to the accompanying drawings.
Referring to Fig. 1, Fig. 1 is the flow chart of the embodiment of the present invention one, is comprised the following steps:
Step S11:By IMAQ and identification equipment, computing individual pavement image is recognized and distinguished according to damaged boundary curve In, the various types of multiple breakage quantity S in crack class road surfacei
Wherein crack class road surface breakage type includes strip crack and block crack;
During i=1, S1Equal to the length in strip crack, during i=2, S2Equal to the area in block crack;
Recognizing the process of crack class road surface breakage in individual pavement image includes:
Pavement image is divided into the grid of 0.1m × 0.1m, by automatic identification technology, by comprising damaged road surface net Lattice are identified.
For any independent crack or joint set, any part of its mark mesh shape cannot cover 0.3m × The square area of 0.3m, is identified as strip crack;
For any independent crack or joint set, any part of its mark mesh shape can cover at least one The square area of 0.3m × 0.3m, is identified as block crack;
Typical strip crack and block crack example are referring to Fig. 2;Left side is pavement image in figure, and right side is identification in figure Image afterwards, wherein, the grid on right side is mesh shape mark;
Crack class road surface breakage quantity S in the corresponding pavement images of Fig. 2iIt is shown in Table 1;Table 1 is the S after being recognized in image right1 And S2
Table 1
Pavement image Strip fracture length S1(m) Block flaw area S2(m2)
Strip crack example one 2.3 0
Strip crack example two 6.8 0
Block crack example one 0 0.09
Block crack example two 5.0 0.24
The purpose for distinguishing strip crack and block crack is the adaptable light maintenance engineering measure of selection, and usual strip crack is adopted Cementation of fissures measure is used, block crack uses digging measure, and its criterion of identification determines the accuracy rate of light maintenance quantities measuring and calculating.
Traditional method is measured by manual site, so that count convenient, counted when road surface breakage reaches certain scale Enter block crack, accordingly it will usually be desirable to which the crack of repairing arbitrarily sets area, for example, it is in the majority using 0.5m × 0.5m marks, so Simple to count the corresponding workload in crack, extremely inaccurate, easily causing needs the small-sized block slit gauge for carrying out digging to enter filling Seam measures engineering amount.
0.3m × 0.3m criterion of identification that the present invention is used, digs according to the precision based on image recognition result and block crack The mechanical work minimum area for mending technique determines.For example, cell --- industry mark of the image recognition precision for 0.1m × 0.1m Accurate requirement, the suitable cutting area based on pavement cutting machine, area is too small to be awkward.
Table 2 gives the recognition result of typical case (Fig. 2) under different criterion of identification, as a result shows, reduces this identification mark Standard, will cause part strip crack to be mistakenly identified as block crack, and the too small digging operation inconvenience of area is implemented;Expand this identification mark Standard, will make part bulk crack identification be strip crack, cause the inaccurate of light maintenance quantities measuring and calculating.
Table 2
By upper table as can be seen that selection 0.3m × 0.3m after, the correct highest of recognition result.Made using 0.3m × 0.3m It is criterion of identification, relative in the prior art, arbitrarily sets the technical scheme of criterion of identification, with the accurate effect of identification.Really Fixed criterion of identification, introduces accuracy of identification and working area the two parameters, so as to obtain the measurement result in later stage relative to existing There is technology, the degree of accuracy is greatly improved, the light maintenance quantities for obtaining, manpower, material, workload and duration progress in the later stage Etc. aspect, distribution is accurate, it is to avoid waste.
Step S12:It is determined that detection section start, end pile No. scope, in computing detection road section scope in all pavement images The quantity summation of crack class road surface breakage;
By detection section terminus pile No. scope [a, b] being input into, all pavement images in computing detection road section scope The quantity summation of middle crack class road surface breakage
For example G101 terminus pile No. scope [110+000,121+065], computing crack class road surface breakage quantity is total And STiIt is shown in Table 3;
Table 3
Step S13:By the detection section crack class road surface breakage quantity summation of the calculating, with full width conversion coefficient K Carry out computing, the computing detection section full width various types of road surface breakage quantity summations of width internal fissure class;
By detecting section crack class road surface breakage quantity summation STi, computing, computing detection are carried out with full width conversion coefficient K Section full width width internal fissure class road surface breakage quantity summation SWi=KSTi
Full width conversion coefficient K is obtained by the computing of below equation:
K=α β;
Wherein, α is detection width conversion coefficient, w1It is half range width of roadway, w0It is the detection width of pavement image, β is inspection Survey direction conversion coefficient;
Fig. 3 provides the calculated examples one of full width conversion coefficient K:
Two way dual lane highway, unidirectional detection, α=w1/w0, β=2;
Fig. 4 provides the calculated examples two of full width conversion coefficient K:
Two way dual lane highway, two-way detection, α=w1/w0, β=1;
Fig. 5 provides the calculated examples three of full width conversion coefficient K:
Two-way multilane highway, unidirectional detection, α=w1/w0, β=2;
Fig. 6 provides the calculated examples four of full width conversion coefficient K:
Two-way multilane highway, two-way detection, α=w1/w0, β=1;
Step S14:
By the way that in the detection section full width width of the calculating, the various types of damaged quantity summations in crack class road surface are transported Matching pavement current repair quantities.
By detecting section full width width internal fissure class road surface breakage quantity summation SWi, the matching pavement current repair of computing Quantities, i.e. SMi=SWi
Pavement current repair quantities includes cementation of fissures quantities and digging quantities, and matching process is:
Cementation of fissures quantities SM1Equal to the length summation S in strip crackW1, i.e. SM1=SW1
Digging quantities SM2Equal to the area summation S in block crackW2, i.e. SM2=SW2
By the method for the present invention, the corresponding various types of highways for being capable of achieving accurately to calculate damaged road surface break Damage amount, such that it is able to accurately determine corresponding light maintenance quantities, is easy to distribute corresponding material.
For the scheme illustrated in each embodiment of the invention, it is all within the spirit and principles in the present invention, made Any modification, equivalent substitution and improvements etc., should be included within the scope of the present invention.

Claims (5)

1. a kind of measuring method of the pavement current repair quantities based on image recognition result, it is characterised in that including:
By IMAQ and identification equipment, in recognizing and distinguish computing individual pavement image according to damaged boundary curve, crack class road The various types of damaged quantity in face;
It is determined that detection section start, end pile No. scope, crack class road surface is broken in all pavement images in computing detection road section scope The quantity summation of damage;
By the detection section crack class road surface breakage quantity summation of the calculating, computing, computing are carried out with full width conversion coefficient K The detection section full width various types of road surface breakage quantity summations of width internal fissure class;
By in the detection section full width width of the calculating, the various types of damaged quantity summations in crack class road surface, computing with Matching pavement current repair quantities.
2. method according to claim 1, it is characterised in that the crack class road surface breakage type is:Strip crack and Block crack.
3. method according to claim 2, it is characterised in that recognize crack class road surface all kinds in individual pavement image Damaged process include:
Pavement image is divided into the grid of 0.1m × 0.1m, by automatic identification technology, by comprising damaged road surface grid mark Know out;
For any independent crack or joint set, any part of its mark mesh shape cannot cover 0.3m × 0.3m's Square area, is identified as strip crack;
For any independent crack or joint set, any part of its mark mesh shape cover at least one 0.3m × The square area of 0.3m, is identified as block crack.
4. method according to claim 1, it is characterised in that full width conversion coefficient K is obtained by the computing of below equation:
K=α × β;
α=w1/wo
Wherein, α is detection width conversion coefficient, w1It is half range width of roadway, woIt is the detection width of pavement image, β is detection side To conversion coefficient, two direction of traffics of detection up-downgoing are 1, detect that single direction of traffic is 2.
5. method according to claim 3, it is characterised in that the pavement current repair quantities of computing matching includes:
The length summation in strip crack is defined as cementation of fissures quantities;The area summation in block crack is defined as digging engineering Amount.
CN201710050204.XA 2017-01-23 2017-01-23 A kind of measuring method of the pavement current repair project amount based on image recognition result Active CN106758715B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710050204.XA CN106758715B (en) 2017-01-23 2017-01-23 A kind of measuring method of the pavement current repair project amount based on image recognition result

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710050204.XA CN106758715B (en) 2017-01-23 2017-01-23 A kind of measuring method of the pavement current repair project amount based on image recognition result

Publications (2)

Publication Number Publication Date
CN106758715A true CN106758715A (en) 2017-05-31
CN106758715B CN106758715B (en) 2019-01-11

Family

ID=58941595

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710050204.XA Active CN106758715B (en) 2017-01-23 2017-01-23 A kind of measuring method of the pavement current repair project amount based on image recognition result

Country Status (1)

Country Link
CN (1) CN106758715B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113780196A (en) * 2021-09-15 2021-12-10 江阴市浩华新型复合材料有限公司 Abnormal data real-time reporting system
WO2022007120A1 (en) * 2020-07-08 2022-01-13 谢超奇 Road patching quantitative positioning data sending platform and method

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6028948A (en) * 1997-12-29 2000-02-22 Lockheed Martin Corporation Surface anomaly-detection and analysis method
CN1563891A (en) * 2004-04-20 2005-01-12 长安大学 System and method for discriminating road gap
CN101929125A (en) * 2009-08-21 2010-12-29 中公高科(北京)养护科技有限公司 Road rut detection method
CN104463458A (en) * 2014-12-04 2015-03-25 广东能达高等级公路维护有限公司 Expressway daily maintenance information management system
CN106087677A (en) * 2016-06-02 2016-11-09 上海华城工程建设管理有限公司 Asphalt pavement crack type automatic identifying method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6028948A (en) * 1997-12-29 2000-02-22 Lockheed Martin Corporation Surface anomaly-detection and analysis method
CN1563891A (en) * 2004-04-20 2005-01-12 长安大学 System and method for discriminating road gap
CN101929125A (en) * 2009-08-21 2010-12-29 中公高科(北京)养护科技有限公司 Road rut detection method
CN104463458A (en) * 2014-12-04 2015-03-25 广东能达高等级公路维护有限公司 Expressway daily maintenance information management system
CN106087677A (en) * 2016-06-02 2016-11-09 上海华城工程建设管理有限公司 Asphalt pavement crack type automatic identifying method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022007120A1 (en) * 2020-07-08 2022-01-13 谢超奇 Road patching quantitative positioning data sending platform and method
CN113780196A (en) * 2021-09-15 2021-12-10 江阴市浩华新型复合材料有限公司 Abnormal data real-time reporting system
CN113780196B (en) * 2021-09-15 2022-05-31 江阴市浩华新型复合材料有限公司 Abnormal data real-time reporting system

Also Published As

Publication number Publication date
CN106758715B (en) 2019-01-11

Similar Documents

Publication Publication Date Title
Selezneva et al. Characterization of transverse cracking spatial variability: use of long-term pavement performance data for continuously reinforced concrete pavement design
CN104483330A (en) Concrete surface crack real-time monitoring system and cracking risk dynamic assessment method
CN104330023A (en) Acquisition system and identification method of concrete surface initial crack information
CN102359056B (en) Detection method of bituminous pavement data
CN109298419B (en) Ground penetrating radar and coring-based pavement crack development state detection method
CN105911256B (en) Quantify the method for testing of country rock grade
CN103675920A (en) Nondestructive test method for depth and horizontal position of hidden crack of road base
CN106758715B (en) A kind of measuring method of the pavement current repair project amount based on image recognition result
CN116894610B (en) Pavement leveling quality analysis management system based on concrete laser leveling machine
CN104975556B (en) The loose identification of a kind of flexible pavement based on three-dimensional laser technology and computational methods
CN104655639A (en) Pavement crack detection method capable of accurately acquiring crack characteristics and pavement crack detection system capable of accurately acquiring crack characteristics
CN107091085B (en) Multi-parameter discrimination method for stratum stability of shallow-buried and underground-excavated tunnel
CN114387328A (en) RQD calculation method based on deep learning model and core image
Kargah-Ostadi et al. Evaluation framework for automated pavement distress identification and quantification applications
CN116990310B (en) Wall concrete crack monitoring and early warning system based on data analysis
CN101923651A (en) Calibration method of automatic recognition accuracy of corrupted data based on pavement images
Serigos et al. Evaluation of rut-depth accuracy and precision using different automated measurement systems
CN105987834A (en) Integrated sampling method used for coal sample detection and integrated sampling system
CN104911982A (en) Pavement disease detection method based on magnetic analysis technology
McRobbie et al. Developing new methods for the automatic measurement of raveling a traffic-speed
Wright et al. New methods for network level automated assessment of surface condition in the UK
Chang et al. Practical implementation of automated fault measurement based on pavement profiles
CN112982184A (en) Road and bridge disease analysis and maintenance decision method based on big data
CN113808124B (en) Bridgehead vehicle jump judging method based on point cloud technology
CN103258059A (en) Transverse crack information processing method and system for expressway bituminous pavement

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