CN109870456A - A kind of road surface health status rapid detection system and method - Google Patents
A kind of road surface health status rapid detection system and method Download PDFInfo
- Publication number
- CN109870456A CN109870456A CN201910105679.3A CN201910105679A CN109870456A CN 109870456 A CN109870456 A CN 109870456A CN 201910105679 A CN201910105679 A CN 201910105679A CN 109870456 A CN109870456 A CN 109870456A
- Authority
- CN
- China
- Prior art keywords
- data
- road surface
- car
- acquisition
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
- Road Repair (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of road surface health status rapid detection system and methods, including acquisition module: for obtaining interior vibration acceleration, pavement disease video and GPS positioning data；Car-mounted terminal: for receiving the data of each acquisition module, pre-processing collected data, and data are uploaded to server on cloud by treated；Server on cloud: for receiving, parsing and storing the data of car-mounted terminal upload；And visualization terminal: for issuing data and generating report, real-time, various dimensions is provided and customization shows testing result；It is connected between the acquisition module and car-mounted terminal by transmission module, is connected between server and visualization terminal by network on the car-mounted terminal, cloud.The present invention collects data and acquires, transmits, parses, is published on one, greatly reduces testing cost, can provide accurate, the pavement of road situation of high frequency, road safety information convenient for the public.
Description
Technical field
The present invention relates to a kind of pavement detection system and method more particularly to a kind of road surface health status rapid detection systems
And method.
Background technique
In recent years, Maintenance Decision making based on data-driven had become national policy requirement, but China still faces
Huge detection pressure, in the network of highways more than 4,500,000 kilometers, only 10% or so highway, high-grade highway are obtained
It has arrived effective detection, and suitable detection means is lacked for large-scale inferior grade road, farm-to-market road, only a small number of
Big city carries out routine testing maintenance to its urban road.
Currently, its price such as pavement detection method of mainstream such as laser detecting apparatus, three-dimensional radar detector is often in 100-
Between 12000000 etc., the multifunctional examining measuring car price of Australian ARRB group exploitation is more up to 24,000,000, it is difficult to a large amount of
It introduces and is used for road quality and quickly detect.And on the other hand, many traditional detection methods, such as three meter rulers, level, hand push
Formula profiler etc., although price is cheap, due to being the mode of operation of semi-artificial semi-machine, detection efficiency is low, generally only makees
For equipment calibration use, can not promote on a large scale.
In addition to this, domestic road management system haves the defects that at high cost, efficiency is relatively low.Road Detection data due to
The difference in area, data interaction degree is low, and excellent maintenance decision can not be widely applied.And in recent years, with " internet
+ " rapid rising of concept, the road administration department in country and place gradually opened many road administration data.These data storages are huge,
If can be carried out reasonable excavation and utilize, it will bring huge convenience and benefit to society.
Summary of the invention
Technical problem to be solved by the invention is to provide a kind of road surface health status rapid detection system and methods, collect number
According to acquisition, transmission, parse, be published on one, greatly reduce testing cost, can be provided convenient for the public it is accurate,
The pavement of road situation of high frequency, road safety information.
The present invention quickly examines the technical solution adopted is that providing a kind of road surface health status to solve above-mentioned technical problem
Examining system, including acquisition module: for obtaining interior vibration acceleration, pavement disease video and GPS positioning data；Vehicle-mounted end
End: for receiving the data of each acquisition module, pre-processing collected data, and data are uploaded to cloud by treated
Upper server；Server on cloud: for receiving, parsing and storing the data of car-mounted terminal upload；And visualization terminal: it is used for
It issues data and generates report, real-time, various dimensions are provided and customization shows testing result；The acquisition module and car-mounted terminal
Between by transmission module be connected, on the car-mounted terminal, cloud server and visualization terminal between by network be connected.
Further, the acquisition module includes interior vibration acceleration acquisition module, pavement disease video acquisition module
With GPS positioning acquisition module.
Further, the interior vibration acceleration acquisition module is two symmetrical 3 axis MEMS vibrating sensings
Device, two 3 axis MEMS vibrating sensors are fixed on vehicle trunk, and are located at rear-wheel top, so that vibrating sensor
X-axis is parallel with vehicle body direction, and z-axis is parallel with overall height direction.
Further, the pavement disease video acquisition module is industrial digital camera, and the industrial digital camera is differentiated
Rate >=2,000,000 pixels, maximum pixel≤7.5 μm, aperture >=F1.4.
The present invention also provides a kind of road surface health status rapid detection method, the interior vibration to solve above-mentioned technical problem
Dynamic acceleration acquisition module is two symmetrical 3 axis MEMS vibrating sensors, and the pavement disease video acquisition module is
Industrial digital camera, the car-mounted terminal by the local GPS data library of the data deposit after acquisition process, flatness data library and
Pavement condition index database；The detection method includes the following steps: S1) surface evenness acquisition: it is vibrated by two MEMS
Sensor acquires the vibration information of vehicle, and calculates road surface world flatness with power spectral density algorithm by car-mounted terminal and refer to
Number IRI；S2) pavement disease situation acquires: acquiring road surface picture by vehicle-mounted industrial digital camera, and passes through deep neural network
Algorithm identifies the pavement disease in picture, and calculates pavement condition index PCI according to pavement disease；S3) data upload:
During detection, car-mounted terminal constantly accesses local GPS data library, flatness data library, pavement condition index data
Library, when there is the record not uploaded in database, data are recalled and pass through transmission module and be uploaded to cloud and put down by car-mounted terminal
Platform；S4) visualize: on cloud server by pavement condition index PCI, surface evenness data and GPS data progress
Match, international roughness index is converted into Road surface quality index RQI and is matched with GPS data, while by road surface
Status score PCI, Road surface quality index RQI are further matched with the electronics section in GIS map, and then are visualized
Show the situation of surface evenness, road surface breakage.
Further, the step S1 includes: S11) location information of GPS positioning acquisition module continuous collecting vehicle, and
Constantly calculate the accumulation displacement that vehicle is assumed；Vehicle adds up since 0 from static starting, displacement；S12) two vehicle-mounted MEMS vibrations
The vibration data of dynamic sensor continuous collecting vehicle, and send data to car-mounted terminal；The frequency acquisition meeting of flatness data
It is adjusted according to speed: when speed is 0, frequency acquisition 0Hz；When speed is 3.6km/h, frequency acquisition 20Hz；Speed
When for 36km/h, frequency acquisition 200Hz；When speed is v km/h, frequency acquisition isS13) when accumulative position
When shifting meets or exceeds preset distance, car-mounted terminal saves the vibration data acquired always before at one section of pending data,
And the power spectral density algorithm process data are used, calculate the international roughness index in the sectioni, while according to positioning
The positional information calculation of sensor acquisition goes out the position of form center in the section, and by flatness calculated result and corresponding section
Position of form center will be stored in local flatness data library；S14) accumulation displacement is zeroed again, repeats step S12 and rapid S13,
Start the station acquisition in next section.
Further, the step S1 further includes periodically carrying out calibration test for detection vehicle, adjusts power spectra algorithm
Relevant parameter, the method for demarcating test are as follows: allow vehicle in a certain length, international roughness index0Known section
Upper traveling, vibrating sensor acquires vehicle vibration information, and calculates IRI by power spectral density algorithm1, and and IRI0It carries out
Comparison: if result meetsThen think that Vehicular vibration parameter calibration result is accurate；Conversely, then continuing to adjust vehicle
Vibration parameters, until meetCarry out calibration acquisition when, speed control respectively 20km/h,
40km/h, 60km/h drive at a constant speed, and at least acquire under each vehicle speed condition 2 times.
Further, the step S2 includes: S21) location information of positioning acquisition sensor continuous collecting vehicle, not
The disconnected accumulation displacement for calculating vehicle and assuming；Vehicle adds up since 0 from static starting, displacement；S22) industrial digital camera acquires
The frequency of road surface picture, acquisition road surface picture can be adjusted according to speed；When speed is 0, the frequency of picture collection is 0；
When speed is 3.6km/h, picture collection frequency is 1Hz；When speed is v km/h, the frequency acquisition of picture be (20 ×
v)/3.6Hz；S23) in detection process, the image of acquisition is stored in local file, the position letter of alignment sensor acquisition
Breath can be stored in local GPS data library, while acquisition image path corresponding with the GPS can also be written to the GPS data
In library；S24) when accumulative displacement meets or exceeds preset distance, car-mounted terminal is by all images collected in the section
It is input in neural network algorithm, the disease on the i-th class road surface is identified by neural network algorithm and calculates disease region
Area Ai, corresponding degree of disease wi, calculate the pavement damage ratio DR in the sectioni, and calculate the pavement behavior in the section
Indices P CIi, while the position of form center in the section is gone out according to the positional information calculation that alignment sensor acquires；Pavement condition index
PCI calculated result and corresponding section position of form center will be stored in local pavement condition index database.
Further, road surface picture collection is as follows in the step S3: S31) according in camera internal reference calibration process, photo
Visual angle, distortion carry out view transformation processing to photo, the effective coverage area after photo visual angle change to the transformation relation of photo
For A；S32) Damage Types in the effective coverage of the picture after view transformation are identified with trained neural network,
Identify the type A of the i-th class pavement disease in photoi, corresponding degree of disease wi, and road surface breakage is calculated according to the following formula
Rate:In formula, DR is pavement damage ratio, is the sum of entire impaired area caused by various damages and photograph
The percentage of effective coverage area in piece；wiFor the weight of the i-th class pavement damage；S33) car-mounted terminal is counted according to accumulative displacement
The PCI in section is calculated, specifically: assuming that vehicle, from static starting, displacement adds up since 0, when accumulative displacement is met or exceeded
When 20m, the Pavement distress PCI in this section of accumulative distance is calculated, calculated result is recorded in this with corresponding GPS data
The pci data library on ground, while the displacement that car-mounted terminal adds up adds up again from 0；PCI calculation formula is as follows: PCI=100-
a0DRa1；In formula, DR is pavement damage ratio, a0、a1Respectively road surface types coefficient；S34) accumulation displacement is zeroed again, repeats to walk
Rapid S33), start the pavement condition index for calculating next section.
Further, the step S3 further includes being corrected as follows to collected picture visual angle and distortion: S301)
Suitable position places gridiron pattern calibration cloth and shoots image in the middle part of picture；S302 X-comers) are found, and find most edge
Four angle points；S303) Automatic-searching and only consider the rectangular area vertical lines that aforementioned four angle point surrounds；S304) basis
The projection theory of camera shooting, each vertical lines will finally converge at a bit, find this point；It S305) will be on convergent point and image
Two angle points at edge are separately connected, and the extended line of each connecting line meets at a point, image with the extended line of image lower edge
Two angle points of top edge and two intersection points composition one on lower edge extended line are trapezoidal, and it includes whole picture and generation that this is trapezoidal
The projection view angles of the whole picture of table；S306) projection view angles are converted to and overlook visual angle, two trapezoidal bevel edges are converted in parallel
Two lines, and the distance of trapezoidal two parallel edges up and down is controlled, so that the ratio of gridiron pattern horizontal edge and vertical edge still maintains real
Border ratio；S307 tessellated angle point after converting visual angle) is found, calculates the horizontal pixel distance between two angle points, and sentence
Grid number therebetween, to obtain the lateral distance of a grid in top view/vertically apart from corresponding pixel number；Again and chessboard
The actual size of lattice is corresponding, obtains a horizontal pixel distance/corresponding actual size of vertical pixel distance in top view；
S308 it) by the corresponding relationship of the obtained pixel of step S307) and calibration gridiron pattern actual size, obtains with the viewing angles
Actual size corresponding to road surface breakage in picture or area, and the corresponding road surface of whole picture that can be shot in turn
Area.
The present invention comparison prior art has following the utility model has the advantages that health status quick detection system in road surface provided by the invention
System and method are collected data and are acquired, transmit, parse, are published on one using light-weighted framework mode；Pass through machine vision, depth
The technologies such as study, cloud computing are spent, it can be achieved that the road surfaces such as surface evenness, bumping at bridge-head, the apparent disease in road surface, road table construction depth
The quick detection of healthy key index will test by cloud platform, analyze result real-time exhibition.Lightweight detection system of the invention
The equipment price of system only has the 10%-30% of market same category of device price, greatly reduces testing cost.Detection data can be with
Multivariate data fusion, can check testing result in issue terminal and information platform in real time, and it is accurate, high frequency to provide for the public
Pavement of road situation, road safety information are formulated the maintenance plan of science for road maintenance enterprise, are provided for government finance decision
Data are supported.
Detailed description of the invention
Fig. 1 is that health status rapid detection system in road surface of the present invention forms frame diagram；
Fig. 2 is the shooting picture after the present invention is corrected using internal reference；
Fig. 3 is that the present invention finds vertical lines schematic diagram；
Fig. 4 is that gridiron pattern of the invention overlooks visual angle figure；
Fig. 5 is that the present invention carries out visual angle, distortion transform processing schematic to acquisition picture.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 1 is that health status rapid detection system in road surface of the present invention forms frame diagram.
Referring to Figure 1, health status rapid detection system in road surface provided by the invention, including acquisition module, transmission module,
Server, visualization terminal composition on car-mounted terminal, cloud, wherein acquisition module includes: interior vibration acceleration acquisition, road again
Face disease video acquisition, GPS positioning acquisition.
Health status rapid detection system in road surface provided by the invention, detection error is ± 10%, it is sufficient to meet road and support
Specified accuracy demand is protected, detection efficiency is high, and the bicycle odd-numbered day can realize the measurement more than 300 kilometers, in addition to vehicle-mounted power supply, sensor
Module use storage battery power supply, can continuous-stable work more than 72 hours.In addition, the present invention also have low cost, lightweight, can
The characteristics of on-demand customization, keyization operation, the pavement state all standing of road network is detected, realizes Transportation facilities situation
It is information-based；Testing result can carry out merging excavation with multi-source data simultaneously, can check inspection in issue terminal and information platform in real time
It surveys and is serviced as a result, conveniently providing customization for major highway administration unit, testing agency, provide Road planar for the public
Condition, road safety information provide data for government finance decision and support.
Health status rapid detection system in road surface provided by the invention, the selection of each main modular and function are as follows:
1 acquisition module
1.1 interior vibration acceleration acquisitions
By vehicle mounted portable data collector, the 3-axis acceleration of vehicle travel process is measured.Portable data acquisition
The associated specifications of device are as follows:
(1) portable data collector can measure 3-axis acceleration, and (g is acceleration of gravity, value to measuring range ± 5.0g
9.8m·s-2)；
(2) acceleration analysis precision≤0.1g；
(3) 0~1000Hz of acceleration analysis frequency is adjustable；
(4) collector passes through Power supply；
(5) collector can be reequiped according to different vehicle specification, embed intelligence MEMS module；
(6) collector be generally mounted to vehicle specify wheel shaft above, quantity be it is two or more, be fixedly connected with the vehicle body；
(7) collector will acquire data and be transmitted to car-mounted terminal by wired or wireless.
1.2 pavement disease video acquisitions
By high-speed industrial camera, road pavement video information carries out shooting, collecting.High-speed industrial camera associated specifications
It is as follows:
(1) used industrial camera resolution ratio >=2,000,000 pixels, maximum pixel≤7.5 μm, aperture >=F1.4；
(2) shooting frame rate of used camera is in 1~100 frame second-1Interior adjustable, actual photographed frame per second can be according to speed tune
It is whole, meet max. speed 80kmh-1, realize that road surface is continuously shot and clapped without leakage；
(3) camera used in has editability, there is sufficient I/O interface, allows secondary development；
(4) for camera there are two types of photo mode is acquired, continuous acquisition photo after being powered one is camera, another kind is that camera is logical
It crosses speed triggering to be acquired, frequency acquisition changes with speed.
(5) camera can pass storage in real time, be transmitted to car-mounted terminal by wired or wireless；Triggering is supported to deposit figure, triggering video recording,
Included caching simultaneously, supports breakpoint transmission.
(6) camera is generally mounted to vehicle top, and for camera lens towards vehicle back lower place ground, quantity is one or more.
1.3 positioning acquisition modules
Positioning acquisition module can acquire vehicle position information in real time.Its technical requirements is as follows: (1) using GPS, Beidou bimodulus
Positioning；(2) it is combined using inertial navigation and difference, realizes receiver positioning, position error≤1.0m；(3) data acquiring frequency is adjustable
It is whole, it is 1Hz or 5Hz；(4) receiver is typically mounted on test carriage, and quantity is generally one.
2 transmission modules
Transmission module is for realizing the data between different components, disparate modules, information transmission.Transmission used in system
Module includes wire transmission and wireless transmission.Its technical requirements difference is as follows: (1) wire transmission: efficiency of transmission >=gigabit ether
Net (GigE) transmission, high s/n ratio；(2) it is wirelessly transferred: data to be transmitted being packaged, 3/4/5G network transmission is passed through.
3 car-mounted terminals
Car-mounted terminal is industrial host, for receiving the data of each acquisition module acquisition, and the state of collecting test system
Information；The data of acquisition are cleared up, handled, are parsed；The data parsed are uploaded to server on cloud.Car-mounted terminal
Associated specifications are as follows: (1) for industrial host, (GPU) containing graphics processor, and multiple data-interfaces are had, with wired, nothing
Line coffret；(2) there is local storage function, it can storing data in no network environment；(3) car-mounted terminal is generally mounted to vehicle
Front stall, quantity are generally one；(4) car-mounted terminal is powered by the cigar lighter on test carriage, and is supported hot-swappable.
Server on 4 clouds
The function of server is to receive, parsing, store the data that car-mounted terminal uploads on cloud.The technology of server is wanted on cloud
Ask as follows: (1) can real-time reception upload data；(2) database is encrypted；(3) data of database can be in a variety of nets
Network terminal access；(4) cloud upper mounting plate has strange land calamity for data synchronization, platform dual-active no-harass switch mechanism, i.e., monitors bottom
Data sync storage guarantees the data of active and standby monitoring center in main central store system and the storage system of Disaster Preparation Center
Continuity and integrality, as far as possible reduction loss of data probability, double centers are synchronous duplication, real time data synchronization；Normal condition
Under, client accesses the application server at main center by looped network, and when disaster occurs, by network switching, client can be straight
The application server of Disaster Preparation Center is asked in receiving；(5), cloud upper mounting plate can be interacted with other multivariate datas, facilitate data
Further excavate.
5 visualization terminals
Using web develop visual query end, can on the multiple terminals platform such as computer, mobile phone, plate in real time, multidimensional
Degree, profound, customization show testing result, provide pavement of road situation, road safety information for the public, support for road
The maintenance plan that enterprise formulates science is protected, data is provided for government finance decision and supports.
The present invention is based on the detection of the quick surface evenness of distributed sensor network, the main interior vibration by acquisition multi-point
Dynamic acceleration information, bind profile density analysis algorithm, inverse surface evenness situation；Vehicle abnormality Vibration Condition is recorded, in conjunction with
Site and degree occur for GPS map data mining platform, locking bumping at bridge-head.Different from conventional laser detection method, measurement of the invention misses
Difference is maintained within ± 10%, and measurement efficiency is more than 300km/day, is substantially increased the efficiency of surface evenness detection and can be held
Continuous property.
The present invention efficiently solve traditional equipment time and effort consuming, it is complicated for operation and expensive the problems such as, can be realized more
Vehicle, it is a wide range of and when low consumption detect, filled up the blank of China's inferior grade road and township road flatness detection means, can
To effectively improve the technical level of China's road life-cycle management.
The present invention is based on the detections of the quick surface evenness of distributed sensor network mainly to be completed by four submodule cooperations:
(1) portable data collector: three shaft vibration acceleration in collecting vehicle；
(2) AI car-mounted terminal: data prediction, and matched with GPS data, cloud is uploaded later；
(3) server on cloud: data receiver, parsing, storage；
(4) terminal: data publication, report generation is visualized.
Health status rapid detection system in road surface provided by the invention, control process are as follows:
1, equipment is installed
The installation two intelligent 3 axis MEMS vibrating sensors above test vehicle trunk, rear-wheel, it is ensured that vibrating sensing
The x-axis of device is parallel with vehicle body direction, and z-axis is parallel with overall height direction, and two sensors are symmetrical.Car-mounted terminal, transmission mould
Block and locating module are also mounted to position.
2, vibration parameters are demarcated
In order to guarantee surface evenness calculated result effectively, reliably, needs periodically to carry out calibration test for detection vehicle, adjust
The relevant parameter of whole power spectra algorithm.The method for demarcating test are as follows: allow vehicle in a certain length, international roughness index
IRI0Test carriage is travelled on the test road being calibrated, and is opened system in driving process, is passed through two three axis of intelligence
MEMS vibrating sensor acquires vehicle body vibration data, passes through the speed and displacement data of GPS gathers vehicle.To surveyed road every
100m is segmented, according to speed, displacement and vibration data and just quasi- Vehicular vibration parameter, with power spectral density algorithm
Tentative calculation goes out the flatness IRI on road surface in each segmentation roadi, and with calibrated road evenness IRI0It compares, when each
The result of tentative calculation in section meetsThen think that Vehicular vibration parameter calibration result is accurate；Conversely, then continuing to adjust
The vibration parameters of vehicle, until meeting
In order to guarantee calibration result, when carrying out calibration acquisition, speed is controlled respectively in 20km/h, 40km/h, 60km/h,
It drives at a constant speed, is at least acquired under each vehicle speed condition 2 times.
3, vibration measurement and flatness calculate
When formally starting test, 3 axis MEMS vibrating sensor passes to collected three shaft vibration data of vehicle vehicle-mounted
Terminal, locating module is by the real-time position data of vehicle and speed data transmission to car-mounted terminal.Car-mounted terminal shakes according to vehicle
Dynamic parameter, Vehicular vibration data, vehicle position data and speed data, the state in section where being calculated with power spectral density algorithm
Border flatness index IRI.Specific steps are as follows:
(1) location information of positioning acquisition sensor continuous collecting vehicle, and constantly calculate the accumulation displacement that vehicle is assumed；
Vehicle vehicle adds up since 0 from static starting, displacement；
The vibration data of (2) two vehicle-mounted MEMS vibrating sensor continuous collecting vehicles, and send data to vehicle-mounted end
End；The frequency acquisition of flatness data can be adjusted according to speed: when speed is 0, frequency acquisition 0Hz；When speed is
When 3.6km/h, frequency acquisition 20Hz；When speed is 36km/h, frequency acquisition 200Hz；When speed is v km/h, acquisition
Frequency is
(3) when accumulative displacement meets or exceeds preset distance, vibration data that car-mounted terminal will acquire always before
One section of pending data is saved into, and uses the power spectral density algorithm process data, calculates the international flatness in the section
Index IRIi, while the position of form center in the section is gone out according to the positional information calculation that alignment sensor acquires.Flatness calculates knot
Fruit and corresponding section position of form center will be stored in local flatness data library.
(4) accumulation displacement is zeroed again, is repeated step (2), is started the station acquisition in next section.
4, Data Matching and upload
Data in flatness data library are written in SD card or the hard disk of car-mounted terminal local, while passing through car-mounted terminal
4G network, the data that will test are uploaded to server on cloud in real time.
5, data summarization and visual presentation
Server verifies terminal identity, if legal terminal, then after receiving the connection request of remote vehicular terminal on cloud
Data receiver thread is established for it, receives data；If illegal terminal, then link is closed.The international roughness index received
IRI data will be converted into Road surface quality index RQI, and imported into GIS figure layer, and be matched to corresponding electronics section
On, the distribution situation of road network riding quality index RQI is intuitively shown by system platform.
The present invention is innovative in surface evenness quickly detects to use power spectral density algorithm, and vehicle can in detection process
Speed change traveling, vibration data quickly can go out surface evenness by inverse, facilitate accurate, quick, all standing measurement surface evenness.
The present invention gives by surface evenness situation RQI in conjunction with GPS, and when detection can be uploaded to server on cloud in real time, realizes road surface
The fining of disease measures, while testing result can carry out merging with multi-sources big datas such as the volume of traffic, meteorology, garden distributions point
Analysis, it is intuitive to show the pavement disease regularity of distribution.
It is also possible to be detected automatically based on machine vision, artificial intelligence road pavement disease.Base of the present invention
It detects in the pavement disease of machine vision, artificial intelligence and is mainly completed by four submodule cooperations automatically:
(1) high-speed industrial digital camera: adaptive acquisition road table photo；
(2) car-mounted terminal: by acquiring picture intelligent recognition disease, calculating the pavement condition index PCI in section, and with
GPS data matching, uploads cloud later；
(3) server on cloud: data receiver, parsing, storage；
(4) terminal (data publication, report generation) is visualized.
Pavement disease video acquisition module operation control process of the invention is as follows:
1, equipment is installed
Camera is installed on vehicle top middle portion, camera lens is not any in the photo of camera acquisition towards vehicle back lower place ground
Object blocks, and picture is placed in the middle.Car-mounted terminal, transmission module, locating module are also mounted to position.
2, camera calibration
In order to guarantee the accuracy of Image Acquisition and calculating, need periodically according to camera lens internal reference, with gridiron pattern side
The visual angle for the picture that method acquires camera and distortion are modified.The program of calibration and usage is specific as follows:
(1) suitable position places gridiron pattern calibration cloth and shoots image in the middle part of picture, and Fig. 2 is the gridiron pattern of first test acquisition
Picture.
(2) X-comers are being found, and is finding most marginal four angle points (four of composition gridiron pattern outermost rectangle
Angle point).
(3) Automatic-searching and only consider rectangular area vertical lines that this four angle points surround (vertical lines are defined herein
For the straight line apart from the degree of direct north -45 to 45 degree of ranges), as shown in Figure 3.
(4) projection theory shot according to camera, each vertical lines will finally converge at a bit, find this point.
(5) convergent point and two angle points of image top edge are separately connected, the extended line of each connecting line will be with image
The extended line of lower edge meets at a point, and two angle points of image top edge and two intersection points on lower edge extended line will form
One trapezoidal, and it includes whole picture, and this trapezoidal projection view angles for representing whole picture that this is trapezoidal.
(6) visual angle of projection is converted to the visual angle of vertical view, is intuitively converted to two trapezoidal bevel edges parallel
Two lines.However, to ensure that the ratio of gridiron pattern horizontal edge and vertical edge still maintains actual ratio, trapezoidal two parallel edges up and down
Distance be also required to change.The size of image i.e. behind conversion visual angle, horizontal edge and vertical edge is changed compared with original image.
(7) tessellated angle point after converting visual angle is found, calculates the horizontal pixel distance between two angle points, and sentence therebetween
Grid number, the corresponding pixel number of lateral distance of a grid in top view can be obtained, similarly also available top view
In grid it is vertical apart from corresponding pixel number.It is corresponding with tessellated actual size again, just it can know that in top view,
One horizontal pixel is apart from corresponding actual size and a corresponding actual size of vertical pixel distance.
(8) corresponding relationship of the pixel and calibration gridiron pattern actual size obtained by step (7), so that it may know with this
Actual size corresponding to road surface breakage in the picture of a viewing angles or area, while also whole of available shooting
The corresponding road area of picture, as shown in Figure 4.
3, software starts
After camera calibration is good, start car-mounted terminal, the image capture software and transmitting software in car-mounted terminal start automatically.
4, Image Acquisition
(1) location information of positioning acquisition sensor continuous collecting vehicle, and constantly calculate the accumulation displacement that vehicle is assumed；
Vehicle adds up since 0 from static starting, displacement；
(2) industrial camera acquires road surface picture, and the frequency of acquisition road surface picture can be adjusted according to speed.When speed is
When 0, the frequency of picture collection is 0；When speed is 3.6km/h, picture collection frequency is 1Hz；When speed is v km/h, figure
The frequency acquisition of piece is (20 × v)/3.6Hz.
(3) in detection process, the image of acquisition can be stored in local file, the position letter of alignment sensor acquisition
Breath can be stored in local GPS data library, while can also be written to the GPS data to reply acquisition image path with the GPS
In library.
(4) when accumulative displacement meets or exceeds preset distance, car-mounted terminal is by all figures collected in the section
As being input in neural network algorithm, the disease on the i-th class road surface is identified by neural network algorithm and calculates disease region
Area Ai, corresponding degree of disease wi, and according to " highway technology status assessment standard ", calculate the road surface breakage in the section
Rate DRi, and calculate the pavement condition index PCI in the sectioni, while being gone out according to the positional information calculation that alignment sensor acquires
The position of form center in the section.Pavement condition index PCI calculated result and corresponding section position of form center will be stored in local
Pavement condition index database in.
5, pavement disease identifies
Disease recognition program in car-mounted terminal can connected reference local image data base, when existing in image data base
When photo that camera acquires, not handled by disease recognition, according to time series, calculation processing is carried out to photo.The mistake of processing
Journey is specific as shown in figure 5, including the following steps:
(1) is carried out by view transformation processing to photo, is shone for the transformation relation of photo according to photo visual angle, distortion in step 2
Effective coverage area after piece visual angle change is A.
(2) Damage Types in the effective coverage of the picture after view transformation are known with trained neural network
Not, the type A of the i-th class pavement disease in photo can be identifiedi, corresponding degree of disease wi, and road is calculated according to the following formula
Face breakage rate.
In formula, DR is pavement damage ratio, is the sum of this impaired area of various damages and effective coverage area in photo
Percentage (%)；wiFor the weight of the i-th class pavement damage, according to " highway technology status assessment standard " value.
(3) car-mounted terminal calculates the PCI in section according to accumulative displacement, specifically: assuming that vehicle is displaced from static starting
Add up since 0, when accumulative displacement meets or exceeds 20m, calculates the Pavement distress in this section of accumulative distance
(PCI), calculated result and corresponding GPS data are recorded in local pci data library, while the accumulative displacement of car-mounted terminal is from 0
Again add up.PCI calculation formula is as follows:
PCI=100-a0DRa1
In formula, DR is pavement damage ratio, a0、a1Respectively road surface types coefficient, according to " highway technology status assessment standard "
Value.
6, data upload
Data in pci data library are written in SD card or the hard disk of car-mounted terminal local, while during detection,
Vehicle-mounted terminal system can constantly access local GPS data library, flatness data library, pavement condition index database, work as database
In when having the record not uploaded, data can be recalled and pass through transmission module (3G/4G/5G) and are uploaded to by vehicle-mounted terminal system
Cloud platform.
7, data summarization and visual presentation
Cloud platform matches pavement condition index PCI with surface evenness data with GPS data, according to " highway
Condition state standard " international roughness index is converted into Road surface quality index RQI and is carried out with GPS data
Matching, while PCI, RQI will further match the electronics section in GIS map, and then visualize evenness of road surface
The situation of degree, road surface breakage.Server verifies terminal identity after receiving the connection request of remote vehicular terminal on cloud, if
Legal terminal then establishes data receiver thread for it, receives data；If illegal terminal, then link is closed.The data received
It imported into GIS figure layer, and is matched on corresponding section, road network PCI distribution situation is intuitively shown by system platform.
The present invention is innovative in pavement disease image recognition to use image aspects, distortion correction, facilitates accurate quantitative analysis
Count pavement disease.For the present invention by pavement distress PCI in conjunction with GPS, when detection, can be uploaded to server on cloud in real time, real
The fining measurement of pavement disease is showed, the connection established Damage Types, the data such as position, disease quantity occur is intuitive to show
The pavement disease regularity of distribution.The present invention use nerual network technique, rely on lightweight equipment, it can be achieved that pavement disease it is quick,
It accurately identifies.
Beneficial effects of the present invention are as follows:
1, present system relies on lightweight equipment, it can be achieved that all standing of road at different levels, high frequency time, fast inspection, institute
The Road surface quality index RQI measured is combined with GIS map, can angularly show surface evenness from time, space
The rule of development；Measured pavement of road damaged condition PCI is combined with GIS map, can angularly be shown from time, space
The rule of development of road disease, road health status.
2, after measured Road surface quality index RQI, pavement condition index PCI are imported into GIS map by the present invention,
Unit can be supported for road pipe, surface evenness, pavement distress visual presentation are provided, so that it is when formulating maintenance plan
It is referred to；And can with rainfall, temperature, the volume of traffic, garden distribution etc. polynary big data convergence analysis, facilitate to pavement of road
Situation is estimated, and then facilitates the analysis of road disease rule, can effectively be pushed the road maintenance decision of data-driven, be mentioned
Road network total quality is risen, provides reliable theoretical and data supporting for road maintenance decision, maintenance fund reasonable distribution etc..
3, the surface evenness data of road network grade of the invention are provided to road surface health platform or enterprise's digital map navigation is soft
Part, provides each path flatness situation in planning path for traveler, and path optimizing selection improves driver and passenger on way of driving
In comfort level.
Although the present invention is disclosed as above with preferred embodiment, however, it is not to limit the invention, any this field skill
Art personnel, without departing from the spirit and scope of the present invention, when can make a little modification and perfect therefore of the invention protection model
It encloses to work as and subject to the definition of the claims.
Claims (10)
1. a kind of road surface health status rapid detection system characterized by comprising
Acquisition module: for obtaining interior vibration acceleration, pavement disease video and GPS positioning data；
Car-mounted terminal: for receiving the data of each acquisition module, pre-processing collected data, and will treated number
According to being uploaded to server on cloud；
Server on cloud: for receiving, parsing and storing the data of car-mounted terminal upload；And
Visualization terminal: for issuing data and generating report, real-time, various dimensions is provided and customization shows testing result；
It is connected between the acquisition module and car-mounted terminal by transmission module, server and visual on the car-mounted terminal, cloud
Change and is connected between terminal by network.
2. health status rapid detection system in road surface as described in claim 1, which is characterized in that the acquisition module includes vehicle
Internal vibration acceleration acquisition module, pavement disease video acquisition module and GPS positioning acquisition module.
3. health status rapid detection system in road surface as claimed in claim 2, which is characterized in that the car vibration acceleration
Acquisition module is two symmetrical 3 axis MEMS vibrating sensors, after two 3 axis MEMS vibrating sensors are fixed on vehicle
On standby case, and it is located at rear-wheel top, so that the x-axis of vibrating sensor is parallel with vehicle body direction, z-axis is parallel with overall height direction.
4. health status rapid detection system in road surface as claimed in claim 2, which is characterized in that the pavement disease video is adopted
Integrate module as industrial digital camera, the industrial digital camera resolution >=2,000,000 pixels, maximum pixel≤7.5 μm, aperture >=
F1.4。
5. a kind of road surface health status rapid detection method is quickly detected using road surface health status as claimed in claim 2
System, which is characterized in that the car vibration acceleration acquisition module is two symmetrical 3 axis MEMS vibrating sensors,
The pavement disease video acquisition module is industrial digital camera, and the data after acquisition process are stored in local by the car-mounted terminal
GPS data library, flatness data library and pavement condition index database；The detection method includes the following steps:
S1) surface evenness acquires: by the vibration information of two MEMS vibrating sensor acquisition vehicles, and being used by car-mounted terminal
Power spectral density algorithm calculates road surface international roughness index；
S2) pavement disease situation acquires: acquiring road surface picture by vehicle-mounted industrial digital camera, and is calculated by deep neural network
Method identifies the pavement disease in picture, and calculates pavement condition index PCI according to pavement disease；
S3) data upload: during detection, car-mounted terminal constantly access local GPS data library, flatness data library,
Pavement condition index database, when there is the record not uploaded in database, data are recalled and pass through transmission by car-mounted terminal
Module is uploaded to cloud platform；
S4) visualize: on cloud server by pavement condition index PCI, surface evenness data and GPS data progress
Match, international roughness index is converted into Road surface quality index RQI and is matched with GPS data, while by road surface
Status score PCI, Road surface quality index RQI are further matched with the electronics section in GIS map, and then are visualized
Show the situation of surface evenness, road surface breakage.
6. health status rapid detection method in road surface as claimed in claim 5, which is characterized in that the step S1 includes:
S11) the location information of GPS positioning acquisition module continuous collecting vehicle, and constantly calculate the accumulation displacement that vehicle is assumed；Vehicle
From static starting, displacement adds up since 0；
S12) the vibration data of two vehicle-mounted MEMS vibrating sensor continuous collecting vehicles, and send data to car-mounted terminal；
The frequency acquisition of flatness data can be adjusted according to speed: when speed is 0, frequency acquisition 0Hz；When speed is 3.6km/h
When, frequency acquisition 20Hz；When speed is 36km/h, frequency acquisition 200Hz；When speed is v km/h, frequency acquisition is
S13) when accumulative displacement meets or exceeds preset distance, car-mounted terminal saves the vibration data acquired always before
At one section of pending data, and the power spectral density algorithm process data are used, calculates the international roughness index in the section
IRIi, while the position of form center in the section is gone out according to the positional information calculation that alignment sensor acquires, and flatness is calculated and is tied
Fruit and corresponding section position of form center will be stored in local flatness data library；
S14) accumulation displacement is zeroed again, is repeated step S12 and rapid S13, is started the station acquisition in next section.
7. health status rapid detection method in road surface as claimed in claim 6, which is characterized in that the step S1 further includes fixed
Phase is that detection vehicle carries out calibration test, adjusts the relevant parameter of power spectra algorithm, the method for demarcating test are as follows: allow vehicle one
Certain length, international roughness index0It being travelled on known section, vibrating sensor acquires vehicle vibration information, and
IRI is calculated by power spectral density algorithm1, and and IRI0It compares: if result meetsThen think vehicle
Vibration parameters calibration result is accurate；Conversely, then continuing the vibration parameters of adjustment vehicle, until meeting?
When carrying out calibration acquisition, speed is controlled respectively in 20km/h, 40km/h, 60km/h, is driven at a constant speed, under each vehicle speed condition at least
Acquisition 2 times.
8. health status rapid detection method in road surface as claimed in claim 5, which is characterized in that the step S2 includes:
S21) the location information of positioning acquisition sensor continuous collecting vehicle, and constantly calculate the accumulation displacement that vehicle is assumed；Vehicle
From static starting, displacement adds up since 0；
S22) industrial digital camera acquires road surface picture, and the frequency of acquisition road surface picture can be adjusted according to speed；Work as speed
When being 0, the frequency of picture collection is 0；When speed is 3.6km/h, picture collection frequency is 1Hz；When speed is v km/h,
The frequency acquisition of picture is (20 × v)/3.6Hz；
S23) in detection process, the image of acquisition is stored in local file, the location information meeting of alignment sensor acquisition
It is stored in local GPS data library, while acquisition image path corresponding with the GPS can be also written in the GPS data library；
S24) when accumulative displacement meets or exceeds preset distance, car-mounted terminal is defeated by all images collected in the section
Enter into neural network algorithm, the disease on the i-th class road surface is identified by neural network algorithm and calculates the face in disease region
Product Ai, corresponding degree of disease wi, calculate the pavement damage ratio DR in the sectioni, and calculate the pavement condition index in the section
PCIi, while the position of form center in the section is gone out according to the positional information calculation that alignment sensor acquires；Pavement condition index PCI meter
Calculating result and corresponding section position of form center will be stored in local pavement condition index database.
9. health status rapid detection method in road surface as claimed in claim 8, which is characterized in that road surface figure in the step S3
Piece acquisition is as follows:
S31) according in camera internal reference calibration process, photo visual angle, distortion carry out visual angle change to photo to the transformation relation of photo
Processing is changed, the effective coverage area after photo visual angle change is A；
S32) Damage Types in the effective coverage of the picture after view transformation are identified with trained neural network,
Identify the type A of the i-th class pavement disease in photoi, corresponding degree of disease wi, and road surface breakage is calculated according to the following formula
Rate:
In formula, DR is pavement damage ratio, is the sum of entire impaired area caused by various damages and effective coverage area in photo
Percentage；wiFor the weight of the i-th class pavement damage；
S33) car-mounted terminal calculates the PCI in section according to accumulative displacement, specifically: assuming that vehicle is displaced from static starting from 0
Start to add up, when accumulative displacement meets or exceeds 20m, calculate the Pavement distress PCI in this section of accumulative distance,
Calculated result is recorded in local pci data library with corresponding GPS data, while the displacement that car-mounted terminal adds up is tired out again from 0
Meter；PCI calculation formula is as follows:
PCI=100-a0DRa1
In formula, DR is pavement damage ratio, a0、a1Respectively road surface types coefficient；
S34) accumulation displacement is zeroed again, repeats step S33), start the pavement condition index for calculating next section.
10. health status rapid detection method in road surface as claimed in claim 9, which is characterized in that the step S3 further includes
Collected picture visual angle and distortion are corrected as follows:
S301) suitable position places gridiron pattern calibration cloth and shoots image in the middle part of picture；
S302 X-comers) are found, and find most marginal four angle points；
S303) Automatic-searching and only consider the rectangular area vertical lines that aforementioned four angle point surrounds；
S304) projection theory shot according to camera, each vertical lines will finally converge at a bit, find this point；
S305) convergent point and two angle points of image top edge are separately connected, the extended line of each connecting line is following with image
The extended line of edge meets at a point, and two angle points of image top edge and two intersection points on lower edge extended line form a ladder
Shape, it includes whole picture and the projection view angles for representing whole picture that this is trapezoidal；
S306) projection view angles are converted to and overlook visual angle, two trapezoidal bevel edges are converted to parallel two lines, and control ladder
The distance of two parallel edges above and below shape, so that the ratio of gridiron pattern horizontal edge and vertical edge still maintains actual ratio；
S307 tessellated angle point after converting visual angle) is found, calculates the horizontal pixel distance between two angle points, and sentence therebetween
Grid number, to obtain the lateral distance of a grid in top view/vertically apart from corresponding pixel number；Again with it is tessellated
Actual size is corresponding, obtains a horizontal pixel distance/corresponding actual size of vertical pixel distance in top view；
S308 it) by the corresponding relationship of the obtained pixel of step S307) and calibration gridiron pattern actual size, obtains with visual angle bat
Actual size or area corresponding to the road surface breakage in picture taken the photograph, and the whole picture that can be shot in turn is corresponding
Road area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910105679.3A CN109870456B (en) | 2019-02-01 | 2019-02-01 | Rapid detection system and method for road surface health condition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910105679.3A CN109870456B (en) | 2019-02-01 | 2019-02-01 | Rapid detection system and method for road surface health condition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109870456A true CN109870456A (en) | 2019-06-11 |
| CN109870456B CN109870456B (en) | 2022-01-28 |
Family
ID=66918601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910105679.3A Active CN109870456B (en) | 2019-02-01 | 2019-02-01 | Rapid detection system and method for road surface health condition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109870456B (en) |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930731A (en) * | 2019-10-08 | 2020-03-27 | 南京理工大学 | Intelligent transportation card and road surface detection system based on same |
| CN110942010A (en) * | 2019-11-22 | 2020-03-31 | 斑马网络技术有限公司 | Detection method and device for determining road surface undulation state based on vehicle-mounted camera |
| CN110969103A (en) * | 2019-11-21 | 2020-04-07 | 同济大学 | Method for measuring length of highway pavement disease based on PTZ camera |
| CN111160735A (en) * | 2019-12-16 | 2020-05-15 | 宁波市市政设施中心 | Bridgehead vehicle-jumping detection method based on LSTM recurrent neural network |
| CN111507233A (en) * | 2020-04-13 | 2020-08-07 | 吉林大学 | Multi-mode information fusion intelligent vehicle pavement type identification method |
| CN111610191A (en) * | 2020-04-20 | 2020-09-01 | 武汉理工大学 | Road detection and repair system |
| CN111638229A (en) * | 2019-10-08 | 2020-09-08 | 上海大学 | Web-based bidirectional positioning association method for airport pavement diseases and satellite maps |
| CN111785060A (en) * | 2020-06-18 | 2020-10-16 | 杭州恒领科技有限公司 | Special vehicle driving track information acquisition system based on 5G communication |
| CN111985494A (en) * | 2020-07-07 | 2020-11-24 | 深圳大学 | Road disease detection and classification method based on lightweight vehicle-mounted terminal |
| CN112067629A (en) * | 2020-09-09 | 2020-12-11 | 镇江千里路智能交通科技有限公司 | Vehicle-mounted lightweight pavement performance detection device |
| CN112505142A (en) * | 2020-10-27 | 2021-03-16 | 北京建筑大学 | Method for detecting damage of road structure, autonomous mobile device and storage medium |
| CN112726351A (en) * | 2020-12-30 | 2021-04-30 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112785867A (en) * | 2020-12-30 | 2021-05-11 | 上海智能交通有限公司 | Intelligent vehicle-mounted system for road health inspection |
| CN112800911A (en) * | 2021-01-20 | 2021-05-14 | 同济大学 | Pavement damage rapid detection and natural data set construction method |
| CN112907599A (en) * | 2021-02-22 | 2021-06-04 | 佳木斯大学 | Measuring device for indoor design |
| CN112985311A (en) * | 2021-02-09 | 2021-06-18 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN113012427A (en) * | 2021-02-09 | 2021-06-22 | 上海同陆云交通科技有限公司 | Improved vehicle-mounted lightweight inspection system and method |
| CN113155079A (en) * | 2021-03-01 | 2021-07-23 | 北京市市政工程研究院 | Method and device for judging road driving comfort |
| CN113191291A (en) * | 2021-05-10 | 2021-07-30 | 南京金智视讯技术有限公司 | Road flatness detection method based on motion camera |
| CN113191269A (en) * | 2021-04-30 | 2021-07-30 | 南京金智视讯技术有限公司 | Road surface road condition real-time monitoring method based on 5G + AI intelligent analysis |
| CN113295137A (en) * | 2021-05-21 | 2021-08-24 | 吉林大学 | Road unevenness identification method based on vehicle wheel speed fluctuation |
| CN113552138A (en) * | 2021-08-25 | 2021-10-26 | 浙江盘盘科技有限公司 | Cable drum quality detection system based on computer vision |
| CN113592784A (en) * | 2021-07-08 | 2021-11-02 | 浙江科技学院 | Method and device for detecting pavement diseases based on lightweight convolutional neural network |
| CN113588664A (en) * | 2021-08-02 | 2021-11-02 | 安徽省通途信息技术有限公司 | Vehicle-mounted road defect rapid inspection and analysis system |
| CN113638294A (en) * | 2021-08-17 | 2021-11-12 | 广东粤高智慧交通科技有限公司 | Intelligent detection system technology for road maintenance diseases |
| CN113847944A (en) * | 2021-09-14 | 2021-12-28 | 石家庄铁道大学 | Road disease detection device and method based on reinforcement learning memory control |
| CN113932758A (en) * | 2021-09-15 | 2022-01-14 | 同济大学 | Road surface flatness prediction method and device |
| CN113962301A (en) * | 2021-10-20 | 2022-01-21 | 北京理工大学 | Multi-source input signal fused pavement quality detection method and system |
| CN114518094A (en) * | 2020-11-16 | 2022-05-20 | 阿里巴巴集团控股有限公司 | Road detection method and system |
| CN114581856A (en) * | 2022-05-05 | 2022-06-03 | 广东邦盛北斗科技股份公司 | Agricultural unit motion state identification method and system based on Beidou system and cloud platform |
| CN114608512A (en) * | 2022-01-13 | 2022-06-10 | 云南省公路科学技术研究院 | Whole-process monitoring system for detecting technical condition of highway pavement |
| CN114996373A (en) * | 2022-03-31 | 2022-09-02 | 重庆市凤筑科技有限公司 | Public transportation big data system, method and storage medium based on geographic information system |
| WO2022183482A1 (en) * | 2021-03-05 | 2022-09-09 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and apparatus for road inspection |
| WO2022193008A1 (en) * | 2021-03-15 | 2022-09-22 | Iris R&D Group Inc. | System and method for automatic monitoring of pavement condition |
| CN115201218A (en) * | 2022-07-13 | 2022-10-18 | 鲁朗软件(北京)有限公司 | Vehicle-mounted pavement disease intelligent detection method and system |
| CN115713855A (en) * | 2022-10-14 | 2023-02-24 | 港珠澳大桥管理局 | Vehicle-mounted terminal system, data display method and device and computer equipment |
| CN115798194A (en) * | 2022-11-01 | 2023-03-14 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Road condition monitoring method and device based on vehicle vibration data |
| CN116087198A (en) * | 2022-12-02 | 2023-05-09 | 河南交通发展研究院有限公司 | Highway road surface situation data acquisition equipment and automatic rapid detection system thereof |
| CN116448773A (en) * | 2023-06-19 | 2023-07-18 | 河北工业大学 | Pavement disease detection method and system with image-vibration characteristics fused |
| CN116448016A (en) * | 2023-04-26 | 2023-07-18 | 成都智达万应科技有限公司 | Intelligent rapid detection system and detection vehicle with same |
| CN116972906A (en) * | 2023-06-21 | 2023-10-31 | 清华大学 | Highway state evaluation method, device, storage medium and collection box |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104790283A (en) * | 2015-04-10 | 2015-07-22 | 同济大学 | Quick road surface roughness detection system based on vehicle-mounted accelerometer |
| CN104864878A (en) * | 2015-05-22 | 2015-08-26 | 汪军 | Electronic map based road condition physical information drawing and inquiring method |
| CN106529593A (en) * | 2016-11-08 | 2017-03-22 | 广东诚泰交通科技发展有限公司 | Pavement disease detection method and system |
| DE102017001364A1 (en) * | 2017-02-14 | 2017-10-19 | Daimler Ag | Method for environment detection and visualization |
| CN108335002A (en) * | 2017-01-20 | 2018-07-27 | 亚信蓝涛（江苏）数据科技有限公司 | A kind of visual road maintenance big data analysis system |
-
2019
- 2019-02-01 CN CN201910105679.3A patent/CN109870456B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104790283A (en) * | 2015-04-10 | 2015-07-22 | 同济大学 | Quick road surface roughness detection system based on vehicle-mounted accelerometer |
| CN104864878A (en) * | 2015-05-22 | 2015-08-26 | 汪军 | Electronic map based road condition physical information drawing and inquiring method |
| CN106529593A (en) * | 2016-11-08 | 2017-03-22 | 广东诚泰交通科技发展有限公司 | Pavement disease detection method and system |
| CN108335002A (en) * | 2017-01-20 | 2018-07-27 | 亚信蓝涛（江苏）数据科技有限公司 | A kind of visual road maintenance big data analysis system |
| DE102017001364A1 (en) * | 2017-02-14 | 2017-10-19 | Daimler Ag | Method for environment detection and visualization |
Non-Patent Citations (2)
| Title |
|---|
| 王婷婷: "公路路面裂缝检测与识别技术研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 黄岩岩等: "鱼眼畸变棋盘格图像校正", 《计算机工程与应用》 * |
Cited By (57)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930731A (en) * | 2019-10-08 | 2020-03-27 | 南京理工大学 | Intelligent transportation card and road surface detection system based on same |
| CN111638229A (en) * | 2019-10-08 | 2020-09-08 | 上海大学 | Web-based bidirectional positioning association method for airport pavement diseases and satellite maps |
| CN111638229B (en) * | 2019-10-08 | 2023-07-18 | 上海大学 | Airport pavement disease and satellite map bidirectional positioning correlation method based on Web |
| CN110969103A (en) * | 2019-11-21 | 2020-04-07 | 同济大学 | Method for measuring length of highway pavement disease based on PTZ camera |
| CN110969103B (en) * | 2019-11-21 | 2021-05-11 | 同济大学 | Method for measuring length of highway pavement disease based on PTZ camera |
| CN110942010A (en) * | 2019-11-22 | 2020-03-31 | 斑马网络技术有限公司 | Detection method and device for determining road surface undulation state based on vehicle-mounted camera |
| CN110942010B (en) * | 2019-11-22 | 2023-06-02 | 斑马网络技术有限公司 | Detection method and device for determining road surface fluctuation state based on vehicle-mounted camera |
| CN111160735A (en) * | 2019-12-16 | 2020-05-15 | 宁波市市政设施中心 | Bridgehead vehicle-jumping detection method based on LSTM recurrent neural network |
| CN111507233A (en) * | 2020-04-13 | 2020-08-07 | 吉林大学 | Multi-mode information fusion intelligent vehicle pavement type identification method |
| CN111610191A (en) * | 2020-04-20 | 2020-09-01 | 武汉理工大学 | Road detection and repair system |
| CN111785060A (en) * | 2020-06-18 | 2020-10-16 | 杭州恒领科技有限公司 | Special vehicle driving track information acquisition system based on 5G communication |
| CN111985494A (en) * | 2020-07-07 | 2020-11-24 | 深圳大学 | Road disease detection and classification method based on lightweight vehicle-mounted terminal |
| CN111985494B (en) * | 2020-07-07 | 2023-12-22 | 深圳大学 | Road disease detection and classification method based on lightweight vehicle-mounted terminal |
| CN112067629A (en) * | 2020-09-09 | 2020-12-11 | 镇江千里路智能交通科技有限公司 | Vehicle-mounted lightweight pavement performance detection device |
| CN112505142A (en) * | 2020-10-27 | 2021-03-16 | 北京建筑大学 | Method for detecting damage of road structure, autonomous mobile device and storage medium |
| CN112505142B (en) * | 2020-10-27 | 2023-01-24 | 北京建筑大学 | Method for detecting damage of road structure, autonomous mobile device and storage medium |
| CN114518094A (en) * | 2020-11-16 | 2022-05-20 | 阿里巴巴集团控股有限公司 | Road detection method and system |
| CN112726351A (en) * | 2020-12-30 | 2021-04-30 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| NL2030322A (en) * | 2020-12-30 | 2022-07-21 | Shanghai Tonglu Cloud Transp Technology Co Ltd | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112726351B (en) * | 2020-12-30 | 2021-08-27 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112785867A (en) * | 2020-12-30 | 2021-05-11 | 上海智能交通有限公司 | Intelligent vehicle-mounted system for road health inspection |
| CN112800911A (en) * | 2021-01-20 | 2021-05-14 | 同济大学 | Pavement damage rapid detection and natural data set construction method |
| CN113012427A (en) * | 2021-02-09 | 2021-06-22 | 上海同陆云交通科技有限公司 | Improved vehicle-mounted lightweight inspection system and method |
| CN112985311A (en) * | 2021-02-09 | 2021-06-18 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN113012427B (en) * | 2021-02-09 | 2022-05-24 | 上海同陆云交通科技有限公司 | Improved vehicle-mounted lightweight inspection system and method |
| CN112907599B (en) * | 2021-02-22 | 2022-02-15 | 佳木斯大学 | Measuring device for indoor design |
| CN112907599A (en) * | 2021-02-22 | 2021-06-04 | 佳木斯大学 | Measuring device for indoor design |
| CN113155079A (en) * | 2021-03-01 | 2021-07-23 | 北京市市政工程研究院 | Method and device for judging road driving comfort |
| WO2022183482A1 (en) * | 2021-03-05 | 2022-09-09 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and apparatus for road inspection |
| WO2022193008A1 (en) * | 2021-03-15 | 2022-09-22 | Iris R&D Group Inc. | System and method for automatic monitoring of pavement condition |
| CN113191269B (en) * | 2021-04-30 | 2023-06-09 | 南京金智视讯技术有限公司 | Road surface road condition real-time monitoring method based on 5G+AI intelligent analysis |
| CN113191269A (en) * | 2021-04-30 | 2021-07-30 | 南京金智视讯技术有限公司 | Road surface road condition real-time monitoring method based on 5G + AI intelligent analysis |
| CN113191291A (en) * | 2021-05-10 | 2021-07-30 | 南京金智视讯技术有限公司 | Road flatness detection method based on motion camera |
| CN113295137A (en) * | 2021-05-21 | 2021-08-24 | 吉林大学 | Road unevenness identification method based on vehicle wheel speed fluctuation |
| CN113592784A (en) * | 2021-07-08 | 2021-11-02 | 浙江科技学院 | Method and device for detecting pavement diseases based on lightweight convolutional neural network |
| CN113588664A (en) * | 2021-08-02 | 2021-11-02 | 安徽省通途信息技术有限公司 | Vehicle-mounted road defect rapid inspection and analysis system |
| CN113638294A (en) * | 2021-08-17 | 2021-11-12 | 广东粤高智慧交通科技有限公司 | Intelligent detection system technology for road maintenance diseases |
| CN113552138A (en) * | 2021-08-25 | 2021-10-26 | 浙江盘盘科技有限公司 | Cable drum quality detection system based on computer vision |
| CN113847944B (en) * | 2021-09-14 | 2024-02-02 | 石家庄铁道大学 | Road disease detection device and method based on reinforced learning memory control |
| CN113847944A (en) * | 2021-09-14 | 2021-12-28 | 石家庄铁道大学 | Road disease detection device and method based on reinforcement learning memory control |
| CN113932758A (en) * | 2021-09-15 | 2022-01-14 | 同济大学 | Road surface flatness prediction method and device |
| CN113962301A (en) * | 2021-10-20 | 2022-01-21 | 北京理工大学 | Multi-source input signal fused pavement quality detection method and system |
| CN114608512A (en) * | 2022-01-13 | 2022-06-10 | 云南省公路科学技术研究院 | Whole-process monitoring system for detecting technical condition of highway pavement |
| CN114996373B (en) * | 2022-03-31 | 2023-08-08 | 重庆市凤筑科技有限公司 | Public transportation big data system and method based on geographic information system and storage medium |
| CN114996373A (en) * | 2022-03-31 | 2022-09-02 | 重庆市凤筑科技有限公司 | Public transportation big data system, method and storage medium based on geographic information system |
| CN114581856A (en) * | 2022-05-05 | 2022-06-03 | 广东邦盛北斗科技股份公司 | Agricultural unit motion state identification method and system based on Beidou system and cloud platform |
| CN115201218A (en) * | 2022-07-13 | 2022-10-18 | 鲁朗软件(北京)有限公司 | Vehicle-mounted pavement disease intelligent detection method and system |
| CN115713855A (en) * | 2022-10-14 | 2023-02-24 | 港珠澳大桥管理局 | Vehicle-mounted terminal system, data display method and device and computer equipment |
| CN115798194B (en) * | 2022-11-01 | 2024-01-19 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Road condition monitoring method and device based on vehicle vibration data |
| CN115798194A (en) * | 2022-11-01 | 2023-03-14 | 西部科学城智能网联汽车创新中心(重庆)有限公司 | Road condition monitoring method and device based on vehicle vibration data |
| CN116087198A (en) * | 2022-12-02 | 2023-05-09 | 河南交通发展研究院有限公司 | Highway road surface situation data acquisition equipment and automatic rapid detection system thereof |
| CN116087198B (en) * | 2022-12-02 | 2024-02-23 | 河南交通发展研究院有限公司 | Highway road surface situation data acquisition equipment and automatic rapid detection system thereof |
| CN116448016A (en) * | 2023-04-26 | 2023-07-18 | 成都智达万应科技有限公司 | Intelligent rapid detection system and detection vehicle with same |
| CN116448773A (en) * | 2023-06-19 | 2023-07-18 | 河北工业大学 | Pavement disease detection method and system with image-vibration characteristics fused |
| CN116448773B (en) * | 2023-06-19 | 2023-08-18 | 河北工业大学 | Pavement disease detection method and system with image-vibration characteristics fused |
| CN116972906A (en) * | 2023-06-21 | 2023-10-31 | 清华大学 | Highway state evaluation method, device, storage medium and collection box |
| CN116972906B (en) * | 2023-06-21 | 2024-02-13 | 清华大学 | Highway state evaluation method, device, storage medium and collection box |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109870456B (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109870456A (en) | A kind of road surface health status rapid detection system and method | |
| US11486548B2 (en) | System for detecting crack growth of asphalt pavement based on binocular image analysis | |
| CN104567708B (en) | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision | |
| US20210004363A1 (en) | Updating high definition maps based on age of maps | |
| WO2022141913A1 (en) | On-board positioning device-based roadside millimeter-wave radar calibration method | |
| CN205632521U (en) | Track state intelligence inspection device | |
| CN104005325B (en) | Based on pavement crack checkout gear and the method for the degree of depth and gray level image | |
| CN106049210A (en) | Intelligent rail state detection platform | |
| CN105905132A (en) | Intelligent rail state patrolling device and method | |
| CN106296814B (en) | Highway maintenance detection and virtual interactive interface method and system | |
| WO2018205123A1 (en) | Landslide mass dynamic monitoring method and system | |
| CN108107462A (en) | The traffic sign bar gesture monitoring device and method that RTK is combined with high speed camera | |
| CN101694084A (en) | Ground on-vehicle mobile detecting system | |
| CN103778681A (en) | Vehicle-mounted high-speed road inspection system and data acquisition and processing method | |
| CN102855659A (en) | Three-dimensional holographic visualization system and method for high-speed comprehensively detecting train | |
| CN112985311B (en) | Vehicle-mounted portable lightweight intelligent inspection method and system | |
| CN110362895B (en) | Land acquisition removal application management system based on BIM + GIS technology | |
| CN104410839A (en) | Mobile online monitoring system for mountain fire and landslide hazards in power transmission line pole and tower region and monitoring method | |
| CN104864909A (en) | Road surface pothole detection device based on vehicle-mounted binocular vision | |
| CN107316460A (en) | A kind of monitoring car system and method with exceeded candid photograph function | |
| CN114858214B (en) | Urban road performance monitoring system | |
| CN106156199A (en) | A kind of video monitoring image memory search method | |
| CN108388995A (en) | A kind of method for building up of road asset management system and establish system | |
| CN204240947U (en) | The contact net geometric parameter measurement instrument of view-based access control model measuring technique | |
| CN103810855A (en) | Multi-characteristic quantity comprehensive traffic detection system oriented to multi-user group |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211122 Address after: 200082 4th floor, block a, 1229 Zhoujiazui Road, Yangpu District, Shanghai Applicant after: SHANGHAI INTELLIGENT TRANSPORTATION Co.,Ltd. Applicant after: Shanghai urban construction digital industry group Co., Ltd Address before: 200000 room A107, first floor, building 64, No. 1436, Jungong Road, Yangpu District, Shanghai Applicant before: SHANGHAI INTELLIGENT TRANSPORTATION Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |