CN114971166A - Lightweight road pavement service quality inspection system - Google Patents
Lightweight road pavement service quality inspection system Download PDFInfo
- Publication number
- CN114971166A CN114971166A CN202210389240.XA CN202210389240A CN114971166A CN 114971166 A CN114971166 A CN 114971166A CN 202210389240 A CN202210389240 A CN 202210389240A CN 114971166 A CN114971166 A CN 114971166A
- Authority
- CN
- China
- Prior art keywords
- road
- data
- pavement
- service quality
- road surface
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
- E01C23/01—Devices 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention relates to the technical field of road quality detection, in particular to a lightweight road pavement service quality inspection system, which comprises: the vehicle-mounted AI road intelligent perception subsystem acquires original data through the inspection equipment and acquires pavement service quality data according to the original data; and the Internet of things big data platform is used for associating the road surface service quality data with the road surface map to obtain the road surface service quality evaluation data. The vehicle-mounted AI road intelligent perception subsystem acquires original data through the inspection equipment, acquires pavement service quality data according to the original data and sends the pavement service quality data to the Internet of things big data platform, and the Internet of things big data platform correlates the pavement service quality data with a pavement map to acquire pavement service quality evaluation data, so that automatic pavement quality inspection is realized, labor cost is reduced, and the efficiency and accuracy of the road pavement service quality inspection are improved.
Description
Technical Field
The invention relates to the technical field of road quality detection, in particular to a light road pavement service quality inspection system.
Background
With the explosive growth of the scale construction of the roads and the urban roads in China and the increasing maturity of road networking operation in recent years, the information-based construction management of the road infrastructure becomes an important strategic development direction of the nation, the digital and accurate management of the road infrastructure is a main work target of a management and maintenance unit, the road surface is used as an important structure for providing vehicle running in the road infrastructure, and the quality of the road surface directly influences the running safety and the driving comfort of the vehicle.
At present, there are two general ways of road quality monitoring, one of which is special detection and evaluation, a road test detection technician utilizes special road operation equipment to collect road surface disease data, and a road test detection technical expert performs manual analysis and processing on the collected road surface disease data and a stepping data record of field data collection technicians during field operation to obtain a detection result; and secondly, in daily patrol, road maintenance personnel use a mobile phone to shoot and record on site after finding out the road surface diseases in daily road patrol and maintenance work, and upload shot road surface disease images to a maintenance management software system for data management. However, the two road quality monitoring methods have high detection cost, low efficiency and poor accuracy, can not automatically perform pavement quality inspection, and can not meet the requirements of decision-making institutions of government road management departments and road maintenance management implementing units on real-time monitoring of the pavement quality of the road network level.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a light road pavement service quality inspection system, which can automatically inspect the pavement quality.
The invention adopts the technical scheme that a lightweight road pavement service quality inspection system
In a first implementable manner, a lightweight road pavement quality of service inspection system, comprising: the vehicle-mounted AI road intelligent perception subsystem acquires original data through inspection equipment; acquiring pavement service quality data according to the original data; and the Internet of things big data platform is used for associating the road surface service quality data with the road surface map to obtain the road surface service quality evaluation data.
With reference to the first implementable manner, in a second implementable manner, the inspection apparatus includes: the dynamic inspection equipment is used for measuring the change of the structure and the shape of the road surface to obtain dynamic monitoring data of the road surface; the 360-degree panoramic equipment is used for digitally collecting road surface diseases and facilities along the road to obtain road surface disease images and road implementation images; and the positioning equipment is used for acquiring positioning data.
With reference to the second implementable manner, in a third implementable manner, the vehicle-mounted AI road intelligent perception subsystem includes: the vehicle-mounted AI edge module is used for acquiring a pavement service quality evaluation result according to the pavement dynamic monitoring data, the pavement disease image and the implementation image along the road; acquiring pavement service quality data according to a pavement service quality evaluation result; the vehicle intelligent central control visualization module is respectively connected with the dynamic inspection equipment, the 360-degree panoramic equipment and the positioning equipment through a vehicle-mounted AI edge module; the vehicle intelligent central control visualization module is used for monitoring and controlling the running states of the dynamic inspection equipment, the 360-degree panorama and the positioning equipment in real time.
With reference to the second implementable manner, in a fourth implementable manner, the dynamic testing device includes: the road noise instrument is used for acquiring a road noise index; the road noise index is used for representing the road noise degree generated by the interaction between the tire and the road surface; the dynamic tire pressure monitor is used for acquiring a bump index; the jounce index is used to characterize the degree of jounce resulting from the interaction between the tire and the road surface; the rocking instrument is used for acquiring a rocking index; the roll index is used to characterize the lateral vehicle attitude change resulting from the geometric profile of the road cross section.
With reference to the second implementable manner, in a fifth implementable manner, the 360-degree panoramic apparatus includes: the road surface disease identification module is used for acquiring road surface images of a plurality of scenes; preprocessing a road surface image; establishing a pavement image disease expert resource library according to the preprocessed pavement image; constructing a pavement disease identification model according to a pavement image disease expert resource library; carrying out pavement disease identification by utilizing a pavement disease identification model; the pavement disease area measuring module acquires the disease length in the pavement image by a grid marking method; extracting a disease skeleton in the pavement image; acquiring the width of the disease according to the disease framework; acquiring the pavement damage area according to the damage length and the damage width; the road surface disease type classification module is used for acquiring a geometric characteristic set of the road surface diseases; pre-classifying the pavement viruses according to the geometric feature set; and finely classifying the pavement viruses according to a pavement disease classification model.
With reference to the second implementable manner, in a sixth implementable manner, the positioning device includes: the encoder is used for acquiring mileage information; the Beidou is used for acquiring spatial position information; and the real-time differential positioning measurement module is used for acquiring differential positioning information.
With reference to the first implementable manner, in a seventh implementable manner, the internet of things big data platform includes: the data processing subsystem is used for correlating the pavement service quality data with a pavement map to obtain a pavement service quality complete map, pavement service quality evaluation data and visual pavement image unstructured data; the road meta-universe subsystem is used for acquiring health state prediction data of a road surface according to the road surface service quality data; generating a road surface inspection task according to the health state prediction data, the road traffic operation data and the road weather environment monitoring data; and sending the road surface inspection task to the vehicle-mounted AI road intelligent perception subsystem, and triggering the vehicle-mounted AI road intelligent perception subsystem to execute the road surface inspection task.
According to the technical scheme, the beneficial technical effects of the invention are as follows: the data processing subsystem associates the pavement service quality data with the pavement map to obtain a complete pavement service quality map and pavement service quality evaluation data, so that the pavement service quality can be visually known, the traffic risk is reduced, and the comfort level of drivers and passengers is improved.
With reference to the seventh implementable manner, in an eighth implementable manner, the data processing subsystem implements associating the road surface quality of service data with the road surface map by: acquiring preset high-precision single-point longitude and latitude measurement data; forming a longitude and latitude data dictionary of the road surface according to the high-precision single-point longitude and latitude measurement data; importing the longitude and latitude data dictionary into a road surface map to obtain a high-precision road surface map; and associating the longitude and latitude information in the pavement service quality data with the longitude and latitude information of the high-precision road pavement map.
With reference to the seventh implementable manner, in a ninth implementable manner, the metasystem further includes: the road management module is used for carrying out digital management of the whole life cycle of the infrastructure important structures of the road; the road data storage module is used for storing road design data, construction data, historical maintenance data, pavement service quality data, future performance trend prediction data, road infrastructure digital information and road maintenance management pile number positioning data; and the road maintenance module is used for providing decision suggestions for road maintenance.
With reference to the ninth implementable manner, in a tenth implementable manner, the vehicle-mounted AI road intelligent perception subsystem further includes: the head-up display module is connected with the Internet of things big data platform and is used for synchronously displaying positioning data, road infrastructure digital information, pavement service quality evaluation data and a pavement service quality complete map which are collected by the inspection equipment.
According to the technical scheme, the beneficial technical effects of the invention are as follows: the vehicle-mounted AI road intelligent perception subsystem acquires original data through inspection equipment; the method comprises the steps of obtaining pavement service quality data according to original data, sending the pavement service quality data to an Internet of things big data platform, associating the pavement service quality data with a pavement map by the Internet of things big data platform, and obtaining pavement service quality evaluation data, so that automatic pavement quality inspection is realized, labor cost is reduced, and efficiency and accuracy of the pavement service quality inspection are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a schematic diagram of a lightweight road pavement service quality inspection system provided in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of inspection equipment according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another lightweight road pavement quality of service inspection system provided by an embodiment of the invention;
fig. 4 is a schematic view of a road segment according to an embodiment of the present invention.
Reference numerals:
the system comprises a 1-vehicle-mounted AI road intelligent sensing subsystem, a 2-Internet of things big data platform, a 3-inspection device, a 4-vehicle-mounted AI edge module, a 5-vehicle intelligent central control visualization module, a 6-head-up display module, a 7-RTK high-precision single-point positioning device, a 310-dynamic inspection device, a 311-road noise instrument, a 312-dynamic tire pressure monitor, a 313-swing instrument, a 320-sand-doped 360-degree panoramic device, a 321-sand-doped 360-degree panoramic camera, a 330-positioning device, a 331-encoder, 332-Beidou and 333-RTK.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Referring to fig. 1, the present embodiment provides a light road pavement service quality inspection system, including: the system comprises a vehicle-mounted AI road intelligent perception subsystem 1 and an Internet of things big data platform 2; the vehicle-mounted AI road intelligent perception subsystem acquires original data through inspection equipment; acquiring pavement service quality data according to the original data; and the Internet of things big data platform is used for associating the road surface service quality data with the road surface map to obtain the road surface service quality evaluation data.
In some embodiments, AI (Artificial Intelligence) is a new technical science to study, develop theories, methods, techniques, and applications for simulating, extending, and expanding human Intelligence. The Internet of Things (IoT, Internet of Things), namely, "Internet connected with everything", is an extended and expanded network on the basis of the Internet, combines various information sensing devices with the network to form a huge network, and realizes interconnection and intercommunication of people, machines and Things at any time and any place.
Referring to fig. 1, a sensing layer of the vehicle-mounted AI road intelligent sensing subsystem collects original data through inspection equipment. The original data comprises a tire road noise signal, a dynamic tire pressure signal, a running attitude measurement data of a swing instrument, 360-degree panoramic data and positioning data; the data layer of the vehicle-mounted AI road intelligent perception subsystem stores, calculates and transmits original data, realizes real-time perception and rapid analysis of pavement service quality, and synchronizes the pavement service quality data and positioning data to the Internet of things big data platform. The method comprises the following steps that an Internet of things big data platform is provided with a data processing subsystem based on a GIS (Geographic Information System) technology and a road meta-space subsystem based on a digital twin technology road, wherein the data processing subsystem associates road service quality data uploaded by an edge end vehicle-mounted AI road intelligent perception subsystem with a road map to obtain road service quality evaluation data; and the road meta-universe subsystem acquires a road inspection task according to the road surface service quality data, and performs intelligent analysis evaluation and digital twin visualization on the road surface service quality data.
In some embodiments, the road noise meter obtains a tire road noise signal, and performs signal processing on the tire road noise signal to obtain a road noise index. The dynamic tire pressure monitor obtains a dynamic tire pressure signal, and the dynamic tire pressure signal is subjected to signal processing to obtain a jolt index. The swaying instrument obtains swaying instrument driving attitude measurement data, and the swaying instrument driving attitude measurement data is analyzed and processed to obtain a swaying index. The 360-degree panoramic equipment obtains 360-degree panoramic data, and the 360-degree panoramic data comprises road surface disease images and road implementation images along the lines. The positioning device obtains positioning data.
In some embodiments, the positioning data is obtained by GNSS (Global Navigation Satellite System), RTK (Real-Time Kinematic), DMI (Distance Measuring Instrument), and the like.
As shown in fig. 2, optionally, the inspection equipment 3 includes: a motion detection device 310, a 360 degree panoramic device 320, and a positioning device 330; the dynamic inspection equipment is used for measuring the change of the structure and the shape of the road surface to obtain dynamic monitoring data of the road surface; the 360-degree panoramic equipment is used for digitally collecting road surface diseases and facilities along the road to obtain road surface disease images and road implementation images; and the positioning equipment is used for acquiring positioning data.
Optionally, the dynamic inspection equipment is a dynamic road surface detection instrument, and the dynamic inspection equipment measures the road surface structure and the shape change by using a vehicle-road coupling method based on an acoustic principle to obtain a dynamic signal; and extracting and processing the characteristic signals of the dynamic signals in a frequency domain and a time domain to obtain road noise indexes, bump indexes and swing indexes of the road.
In some embodiments, as shown in fig. 2, the 360-degree panoramic device 320 is a 360-degree panoramic camera 321, such as a 360-degree panoramic true color CCD camera, and the 360-degree panoramic camera captures road defects and road-line facilities digitally to form road defect images and road-line implementation images.
As shown in fig. 2, optionally, the motion detection device 310 includes: a road noise meter 311, a dynamic tire pressure monitor 312, and a wobble meter 313; the road noise instrument is used for acquiring a road noise index; the road noise index is used for representing the road noise degree generated by the interaction between the tire and the road surface; the dynamic tire pressure monitor is used for acquiring a bump index; the jounce index is used to characterize the degree of jounce resulting from the interaction between the tire and the road surface; the rocking instrument is used for acquiring a rocking index; the roll index is used to characterize the lateral vehicle attitude change resulting from the geometric profile of the road cross section.
Optionally, the road noise meter is used for measuring the road surface structure state to obtain a road noise index; the road noise Index (Pavement Acoustic Index) is used to evaluate changes in the quality of service of a Pavement resulting from a combination of Pavement damage, macrostructure, mix type, Pavement stiffness, and the like. In some embodiments, the road noise meter is formed by an IEPE type free field sound pressure working microphone, the sensitivity is 50mv/Pa, and the frequency response can reach 20 KHz.
Optionally, the dynamic tire pressure detector is used for measuring the deformation state of the structure to obtain a bump index; the jounce Index (road quality Index) is used to evaluate the change in road service quality caused by road surface deformation. In some embodiments, the dynamic tire pressure monitor is constructed with an IEPE type dynamic pressure sensor with a sensitivity of 800mv/kPa and a resolution of 0.001 kPa.
Optionally, the vehicle-mounted AI road intelligent perception subsystem is further configured to form a road Service quality Index (road quality Index) according to the road noise Index and the jounce Index, and the road Service quality Index (road quality Index) is used to comprehensively evaluate the road Service quality of damaged and deformed road surface structures.
Optionally, the swinging instrument is used for measuring the geometrical line type condition of the cross section of the road surface to obtain the swinging index. The sway Index (Pavement Rock Index) was obtained by a gyroscope and accelerometer. In some embodiments, the wobbler is formed of an IEPE-type gyroscope and accelerometer with a sensitivity of 10mV/g and a frequency response of 0.1Hz to 6 kHz.
As shown in connection with fig. 2, optionally, the positioning device 330 comprises: the encoder 331, the Beidou 332 and the real-time differential positioning measurement module; the encoder is used for acquiring mileage information; the Beidou is used for acquiring spatial position information; and the real-time differential positioning measurement module is used for acquiring differential positioning information.
In some embodiments, the Real-Time differential positioning measurement module is an RTK (Real-Time Kinematic) 333. The encoder 331 measures mileage information, the big dipper 332 measures spatial position information, the RTK333 carries out differential positioning, obtains differential positioning information, and positioning device fuses encoder, big dipper and real-time differential positioning measurement module, realizes carrying out millimeter-scale accurate positioning analysis to road surface quality, improves the accuracy of road surface quality of service data.
In some embodiments, it is prior art for the encoder to obtain the mileage information. The big dipper acquires spatial position information, includes: and acquiring spatial position information through a Beidou positioning chip in the Beidou satellite navigation and positioning system.
As shown in fig. 3, optionally, the vehicle-mounted AI road intelligent sensing subsystem includes: the vehicle-mounted AI edge module 4 and the vehicle intelligent central control visualization module 5; the vehicle-mounted AI edge module is used for acquiring a pavement service quality evaluation result according to the pavement dynamic monitoring data, the pavement disease image and the implementation image along the road; acquiring pavement service quality data according to a pavement service quality evaluation result; the vehicle intelligent central control visualization module 4 is respectively connected with the dynamic inspection equipment, the 360-degree panoramic equipment and the positioning equipment through a vehicle-mounted AI edge module; the vehicle intelligent central control visualization module is used for monitoring and controlling the running states of the dynamic inspection equipment, the 360-degree panorama and the positioning equipment in real time.
As shown in fig. 3, optionally, the vehicle-mounted AI edge module 4 is connected with a road noise meter 311, a dynamic tire pressure detector 312, a wobble meter 313, a 360-degree panorama device 321, an encoder 331, a beidou 332, and an RTK333, respectively. The vehicle-mounted AI edge module 4 is also connected with the vehicle intelligent central control visualization module 5 through a WIFI6 network; and the vehicle-mounted AI edge module 4 is connected with the Internet of things big data platform 2 through a 5G network. The vehicle intelligent central control visualization module 5 is connected with one end of a head-up display module (HUD) 6. The other end of the head-up display module 6 is connected with the Internet of things big data platform 2.
Optionally, the in-vehicle AI edge module includes an edge calculation processor and a digital image processor.
Optionally, obtaining a road service quality assessment result according to the road dynamic monitoring data, the road disease image and the road implementation image along the road includes: and carrying out automatic processing on the dynamic road monitoring data, the road surface disease images and the road along-line implementation images by using a high-performance edge calculation processor and a digital image processor to carry an artificial intelligence AI algorithm so as to obtain a road surface service quality evaluation result.
Optionally, the vehicle-mounted AI edge module is further configured to provide a resource scheduling management policy in cooperation with the internet of things big data platform. The resource scheduling management strategy comprises equipment management, resource management and network connection management of the edge node.
Optionally, obtaining the road service quality data according to the road service quality assessment result includes: receiving road infrastructure digital information and road maintenance management pile number positioning data which are sent by an Internet of things big data platform in real time; and simultaneously associating the digital information of the road infrastructure and the positioning data of the road maintenance management stake with the pavement service quality evaluation result to obtain pavement service quality data.
In some embodiments, the vehicle-mounted AI edge module builds a data transmission channel between the edge device and the internet of things big data platform through a 5G (5th Generation Mobile Communication Technology, fifth Generation Mobile Communication Technology) Mobile Communication network. The Internet of things big data platform sends the road infrastructure digital information and the road maintenance management pile number positioning data to the vehicle-mounted AI road intelligent perception subsystem through the data transmission channel in real time, the vehicle-mounted AI road intelligent perception subsystem associates the road infrastructure digital information and the road maintenance management pile number positioning data with a road service quality assessment result in the data processing process, the road service quality data with the road infrastructure digital information and the road maintenance management pile number positioning data are obtained, and the road service quality data are transmitted to the Internet of things big data platform through the data transmission channel in real time.
In some embodiments, the vehicle-mounted AI road intelligent perception subsystem carries a WIFI6 wireless network, a high-speed data communication local area network is established on a road inspection vehicle platform, and the vehicle intelligent central control visualization module monitors and controls the running states of the dynamic inspection equipment, the 360-degree panoramic equipment and the positioning equipment in real time by using the WIFI6 network.
Optionally, the 360 degree panoramic apparatus comprises: the system comprises a pavement disease identification module, a pavement disease area measurement module and a pavement disease type classification module; the road surface disease identification module is used for acquiring road surface images of a plurality of scenes; preprocessing a road surface image; establishing a pavement image disease expert resource library according to the preprocessed pavement image; constructing a pavement disease identification model according to a pavement image disease expert resource library; carrying out pavement disease identification by utilizing a pavement disease identification model; the pavement damage area measuring module acquires the damage length in the pavement image by a grid marking method; extracting a disease skeleton in the pavement image; acquiring the width of the disease according to the disease framework; acquiring the pavement damage area according to the damage length and the damage width; the road surface disease type classification module is used for acquiring a geometric characteristic set of the road surface diseases; pre-classifying the pavement viruses according to the geometric feature set; and finely classifying the pavement viruses according to a pavement disease classification model.
Optionally, acquiring road surface images of a plurality of scenes comprises: and under different illumination conditions, acquiring images of a plurality of different road sections. Because the background noise performance of the pavement diseases is different under different illumination conditions, the performance of the pavement disease identification model is also different. Therefore, by collecting a plurality of specific representative illumination and road surface images of road sections, the disease characteristics learned by the road surface disease identification model are wider, and the constructed image road surface disease identification model has stronger applicability.
Optionally, the preprocessing is performed on the road surface image, and includes: and carrying out filtering processing on the road surface image, and processing the road surface image by adopting a dodging image enhancement technology. The road surface image collected by the inspection equipment often has interference information such as shadows, traffic sign marks and the like. Therefore, in the pavement image preprocessing stage, a processing mode based on field filtering is adopted for image denoising; and the influence of uneven illumination and shadow is eliminated by adopting a uniform light image enhancement technology. Therefore, the interference information in the road surface image is preprocessed before the road surface image disease expert resource library is established, and the recognition accuracy of the road surface disease recognition model is improved.
In some embodiments, the performance and the reasoning speed of the pavement damage recognition model depend on the size of the pavement damage training set. Therefore, a massive disease expert identification resource library is built before the road disease identification model is trained, the data of the road disease training set are perfected, and the precision and the performance of the road disease identification model are improved.
Optionally, constructing a pavement disease identification model according to a pavement image disease expert resource library, including: selecting a training set and a verification set from a pavement image disease expert resource library; performing model training on a GPU (Graphics Processing Unit) server by using a TensorFlow deep learning framework according to a training set to obtain an initial pavement damage recognition model; and verifying the initial pavement disease identification model through a verification set to obtain the generalization ability and the technical index performance of the reflection model, and determining the initial pavement disease identification model as the pavement disease identification model under the condition that the generalization ability and the technical index performance meet preset conditions.
Optionally, the preset condition is that the accuracy of the initial pavement damage identification model is greater than a preset threshold.
Optionally, after determining the initial pavement damage identification model as the pavement damage identification model, the method further includes: the method comprises the steps of obtaining a real-time pavement image, testing the performance capability of a pavement disease recognition model through the real-time pavement image, determining a reasoning short plate of the pavement disease recognition model according to the performance capability, and adjusting a model structure, model training data or a model training strategy according to the reasoning short plate.
In some embodiments, the deep learning framework adopts a deep learning image processing technology, and the supervised deep learning image processing technology is used for understanding and learning a large amount of sample training data through a neural network model, extracting image features to be operated and road surface disease images in a training set, and performing attribute identification analysis.
In some embodiments, the establishment of the pavement damage recognition model includes selection, training, evaluation and optimization of the model. The selection of the model includes: selecting any model from an image sub-block classification model based on a full convolution neural network and an image segmentation model based on the convolution neural network; the image sub-block classification model is simple and reliable, the reasoning speed is high, the model generalization capability is strong, the image segmentation model is high in accuracy, the detected diseases are continuous, and the noise output is low. The training of the model comprises: and performing model training on the GPU server by using a TensorFlow deep learning framework according to the training set to obtain an initial pavement disease recognition model. The evaluation of the model includes: and verifying the initial pavement damage identification model through a verification set to obtain the generalization ability and the technical index performance of the reflection model, and determining the initial pavement damage identification model as the pavement damage identification model under the condition that the generalization ability and the technical index performance meet the preset conditions. The optimization of the model comprises: the method comprises the steps of obtaining a real-time pavement image, testing the performance capability of a pavement disease recognition model through the real-time pavement image, determining a reasoning short plate of the pavement disease recognition model according to the performance capability, and adjusting a model structure, model training data or a model training strategy according to the reasoning short plate.
In some embodiments, in the binary image of the pavement image, the diseases are marked by white pixel points, and the length of the diseases in the pavement image is solved by adopting a 32 × 32 grid marking method.
Optionally, acquiring a disease width according to the disease skeleton, including: matching the eight-connected region where each pixel point of the disease skeleton is located with a pre-designed direction template, and calculating the normal direction of each pixel point; intercepting the normal lines of the preset length in the normal line direction, returning each intercepted normal line to the corresponding position in the road surface image, and acquiring the pixel gray value of each corresponding position in the road surface image; counting a distribution function of the pixel gray values; and determining the width of the diseases in the pavement image according to the distribution function.
Optionally, obtaining the pavement damage area according to the damage length and the damage width, including: and multiplying the disease length by the disease width to obtain the pavement disease area.
In some embodiments, the pavement disease area measurement module performs sub-block separation on one or more pavement diseases in a pavement image by adopting a crack target separation method and vectorizes a disease profile, accurately finds out a minimum external matrix of the pavement diseases, finally extracts pixel points of a single pavement disease, and measures the length and the width of the pavement disease; and acquiring the area of the pavement damage according to the length and the width of the pavement damage so as to know the severity of the pavement damage.
Optionally, the road surface damage type classification module performs preliminary classification treatment by adopting a combined damage characteristic classification set, and then performs fine classification of the damage by adopting a supervised radial basis probability neural network, so that the damage degree of the road surface can be more accurately evaluated.
Optionally, the geometric feature set of the road surface disease includes: transverse length, longitudinal length, aspect ratio, area and density characteristics of the pavement defect.
Optionally, the fine classification of the pavement viruses according to the pavement disease classification model includes: and inputting the pavement viruses into a pavement virus classification model to obtain fine classification of the pavement viruses.
In some embodiments, a pavement disease expert classification database is established by using the existing pavement disease data; and selecting data from the pavement disease expert classification database by adopting a radial basis probability neural network model to perform model training, index evaluation and model regression so as to obtain a pavement disease classification model. And combining the pavement disease classification model with a TensorFlow open-source deep learning framework to perform fine classification on the pavement diseases.
Optionally, the internet of things big data platform includes: a data processing subsystem and a road meta-universe subsystem; the data processing subsystem is used for correlating the pavement service quality data with a pavement map to obtain a pavement service quality complete map, pavement service quality evaluation data and visual pavement image unstructured data; the road meta-universe subsystem is used for acquiring health state prediction data of a road surface according to the road surface service quality data; generating a road surface inspection task according to the health state prediction data, the road traffic operation data and the road weather environment monitoring data; and sending the road surface inspection task to the vehicle-mounted AI road intelligent perception subsystem, and triggering the vehicle-mounted AI road intelligent perception subsystem to execute the road surface inspection task.
In some embodiments, the internet of things big data platform comprises: the data processing subsystem is based on a GIS technology, associates pavement service quality data uploaded by an edge-end vehicle-mounted AI road intelligent perception subsystem with a pavement map by using a space coordinate intelligent matching method, automatically creates a high-precision GIS map layer of pavement service quality, fuses the high-precision digital map, forms a complete map service of pavement service quality by using a GIS data automatic processing tool, and simultaneously obtains pavement service quality evaluation data and visual pavement image unstructured data. The production structured pavement service quality evaluation data is stored in a MySQL database, and the visual pavement image unstructured data is stored in an NAS memory.
In some embodiments, the metauniverse (Metaverse) is a virtual world that is linked and created using technological means, mapped and interacted with the real world, and has a digital living space of a new social hierarchy. The meta universe is essentially a virtualization, digitization process for the real world.
Optionally, obtaining the health status prediction data of the road pavement according to the pavement service quality data includes: and inputting the pavement service quality data into a preset health state prediction data model to obtain the health state prediction data of the pavement.
In some embodiments, the road traffic operation data and the road weather environment monitoring data are downloaded from a traffic data platform over a 5G network.
Optionally, generating a road surface inspection task according to the health status prediction data, the road traffic operation data and the road weather environment monitoring data, including: the method comprises The steps of utilizing a road surface intelligent maintenance algorithm to conduct automatic analysis on road surface health state prediction data, road traffic operation data and road weather environment monitoring data, generating a road surface inspection task, and pushing The road surface inspection task to a vehicle-mounted AI road intelligent perception subsystem through an OTT (Over The Top, providing various application services for users through The Internet) function.
In some embodiments, the road inspection task includes: the vehicle-mounted AI road intelligent perception subsystem acquires original data through inspection equipment; the method comprises the steps of obtaining pavement service quality data according to original data, sending the pavement service quality data to an Internet of things big data platform, and enabling the Internet of things big data platform to correlate the pavement service quality data with a pavement map to obtain a pavement service quality complete map, pavement service quality evaluation data and visual pavement image unstructured data.
Optionally, the data processing subsystem associates the road surface service quality data with the road surface map by the following method, that is, the spatial coordinate intelligent matching method: acquiring preset high-precision single-point longitude and latitude measurement data; forming a longitude and latitude data dictionary of the road surface according to the high-precision single-point longitude and latitude measurement data; importing the longitude and latitude data dictionary into a road surface map to obtain a high-precision road surface map; and associating the longitude and latitude information in the pavement service quality data with the longitude and latitude information of the high-precision road pavement map. The high-precision road pavement map is formed through the high-precision single-point longitude and latitude measurement data, the association speed is improved, and the road inspection speed is further improved.
In some embodiments, as shown in fig. 4, the RTK high-precision single-point positioning device 7 obtains the preset high-precision single-point longitude and latitude measurement data, which are the longitude and latitude values of the points a1, a2, A3, B1, B2 and B3 in fig. 4. Optionally, the length of each section is divided into maintenance pile number mileage sections of the road, and when the curvature radius of the road is smaller, the length of each section is shorter, so that the formed section area is rectangular as much as possible. And importing the RTK high-precision single-point longitude and latitude measurement data into a data management system of the Internet of things big data platform to form a longitude and latitude data dictionary of the road surface, and importing the longitude and latitude data dictionary into a road surface map to form a high-precision road surface map.
Optionally, the internet of things big data platform automatically associates longitude and latitude information carried by the road service quality data uploaded by the vehicle-mounted AI road intelligent sensing subsystem with RTK high-precision single-point longitude and latitude information in a high-precision road map, and a complete map of the road service quality is formed through a GIS data automatic processing tool.
In some embodiments, in the data processing process, the vehicle-mounted AI road intelligent perception subsystem downloads the longitude and latitude data of the road from the database of the Internet of things big data platform through the 5G network, and performs data processing by taking the longitude and latitude data as a reference point.
Optionally, the metasystem further comprises: the system comprises a road management module, a road data storage module and a road maintenance module; the road management module is used for carrying out digital management of the whole life cycle of the infrastructure important structures of the road; the road data storage module is used for storing road design data, construction data, historical maintenance data, pavement service quality data, future performance trend prediction data, road infrastructure digital information and road maintenance management pile number positioning data; and the road maintenance module is used for providing decision suggestions for road maintenance.
In some embodiments, the GIS technology-based road meta-space subsystem is deployed on an Internet of things big data platform, and the road meta-space subsystem performs data analysis and business application on a road surface service quality complete map, road surface service quality evaluation data and visual road surface image unstructured data. The road meta-universe subsystem carries out digital management of the whole life cycle on the important structures of the road infrastructure through the road management module, and stores road design data, construction data, historical maintenance data, pavement service quality data, road infrastructure digital information, road maintenance management pile number positioning data and future performance trend prediction data through the road data storage module; and scientific decision suggestions are provided for road maintenance through the road maintenance module.
Optionally, inputting the pavement service quality data into a preset performance trend prediction model to obtain future performance trend prediction data; and inputting the pavement service quality data into a preset decision suggestion model to obtain a decision suggestion.
Optionally, the vehicle-mounted AI road intelligent perception subsystem further includes: the head-up display module is connected with the Internet of things big data platform and is used for synchronously displaying positioning data, road infrastructure digital information, pavement service quality evaluation data and a pavement service quality complete map which are collected by the inspection equipment.
In some embodiments, a head-up display module (HUD) is used to project current speed-of-time, navigation, etc. information onto an electro-optical display device on the windshield and form an image in front of the glass. Therefore, the driver can see navigation and vehicle speed information without turning the head or lowering the head, the operation is very convenient, and the driving risk is reduced.
Optionally, the road meta-universe subsystem sends positioning data, road infrastructure digital information, road service quality evaluation data and a road service quality integrity map collected by the inspection equipment to a head-up display module of the automatic driving automobile by using a GIS data sharing service software interface, so that road service quality information is provided for the automatic driving automobile, and driving comfort of drivers and passengers is improved.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. The utility model provides a lightweight road surface quality of service system of patrolling and examining, its characterized in that includes:
the vehicle-mounted AI road intelligent perception subsystem acquires original data through the inspection equipment; acquiring pavement service quality data according to the original data;
and the Internet of things big data platform is used for correlating the road surface service quality data with a road surface map to obtain road surface service quality evaluation data.
2. The system of claim 1, wherein the inspection device includes:
the dynamic inspection equipment is used for measuring the change of the structure and the shape of the road surface to obtain dynamic monitoring data of the road surface;
the 360-degree panoramic equipment is used for digitally collecting road surface diseases and facilities along the road to obtain road surface disease images and road implementation images;
and the positioning equipment is used for acquiring positioning data.
3. The system of claim 2, wherein the on-board AI road intelligence perception subsystem comprises:
the vehicle-mounted AI edge module is used for acquiring a pavement service quality evaluation result according to the pavement dynamic monitoring data, the pavement disease image and the implementation image along the road; acquiring pavement service quality data according to the pavement service quality evaluation result;
the vehicle intelligent central control visualization module is respectively connected with the dynamic inspection equipment, the 360-degree panoramic equipment and the positioning equipment through the vehicle-mounted AI edge module; the vehicle intelligent central control visualization module is used for monitoring and controlling the running states of the dynamic inspection equipment, the 360-degree panorama and the positioning equipment in real time.
4. The system of claim 2, wherein the motion detection device comprises:
the road noise instrument is used for acquiring a road noise index; the road noise index is used for representing the road noise degree generated by the interaction between the tire and the road surface;
the dynamic tire pressure monitor is used for acquiring a bump index; the jounce index is used for representing the degree of jounce generated by the interaction between the tire and the road surface;
the rocking instrument is used for acquiring a rocking index; the sway index is used for representing the change of the transverse driving attitude of the vehicle generated by the geometric linear form of the road cross section.
5. The system of claim 2, wherein the 360 degree panoramic apparatus comprises:
the road surface disease identification module is used for acquiring road surface images of a plurality of scenes; preprocessing the road surface image; establishing a pavement image disease expert resource library according to the preprocessed pavement image; constructing a pavement disease identification model according to the pavement image disease expert resource library; carrying out pavement disease identification by using the pavement disease identification model;
the pavement disease area measuring module acquires the disease length in the pavement image by a grid marking method; extracting a disease skeleton in the pavement image; acquiring the width of the disease according to the disease framework; acquiring the pavement damage area according to the damage length and the damage width;
the road surface disease type classification module is used for acquiring a geometric feature set of the road surface diseases; pre-classifying the pavement viruses according to the geometric feature set; and finely classifying the pavement viruses according to the pavement disease classification model.
6. The system of claim 2, wherein the positioning device comprises:
the encoder is used for acquiring mileage information;
the Beidou is used for acquiring spatial position information;
and the real-time differential positioning measurement module is used for acquiring differential positioning information.
7. The system of claim 1, wherein the internet of things big data platform comprises:
the data processing subsystem is used for correlating the pavement service quality data with a pavement map to obtain a pavement service quality complete map, pavement service quality evaluation data and visual pavement image unstructured data;
the road meta-universe subsystem is used for acquiring the health state prediction data of the road surface according to the road surface service quality data; generating a road surface inspection task according to the health state prediction data, the road traffic operation data and the road weather environment monitoring data; and sending the road surface inspection task to the vehicle-mounted AI road intelligent perception subsystem, and triggering the vehicle-mounted AI road intelligent perception subsystem to execute the road surface inspection task.
8. The system of claim 7, wherein the data processing subsystem effects the correlation of the quality of service data with a road map by:
acquiring preset high-precision single-point longitude and latitude measurement data;
forming a longitude and latitude data dictionary of the road surface according to the high-precision single-point longitude and latitude measurement data;
importing the longitude and latitude data dictionary into the road surface map to obtain a high-precision road surface map;
and associating the longitude and latitude information in the pavement service quality data with the longitude and latitude information of the high-precision road pavement map.
9. The system of claim 7, wherein the metasystem further comprises:
the road management module is used for carrying out digital management of the whole life cycle of the infrastructure important structures of the road;
the road data storage module is used for storing road design data, construction data, historical maintenance data, pavement service quality data, future performance trend prediction data, road infrastructure digital information and road maintenance management pile number positioning data;
and the road maintenance module is used for providing decision suggestions for road maintenance.
10. The system of claim 9, wherein the vehicle-mounted AI-road intelligent perception subsystem, further comprises:
the head-up display module is connected with the Internet of things big data platform, and is used for synchronously displaying the positioning data acquired by the inspection equipment, the road infrastructure digital information, the pavement service quality evaluation data and the pavement service quality complete map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210389240.XA CN114971166A (en) | 2022-04-13 | 2022-04-13 | Lightweight road pavement service quality inspection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210389240.XA CN114971166A (en) | 2022-04-13 | 2022-04-13 | Lightweight road pavement service quality inspection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114971166A true CN114971166A (en) | 2022-08-30 |
Family
ID=82977779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210389240.XA Pending CN114971166A (en) | 2022-04-13 | 2022-04-13 | Lightweight road pavement service quality inspection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971166A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116758757A (en) * | 2023-08-18 | 2023-09-15 | 福建智涵信息科技有限公司 | Highway maintenance inspection method, medium and equipment |
| CN117291583A (en) * | 2023-11-27 | 2023-12-26 | 贵州联广科技股份有限公司 | Internet of things data management method and system |
-
2022
- 2022-04-13 CN CN202210389240.XA patent/CN114971166A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116758757A (en) * | 2023-08-18 | 2023-09-15 | 福建智涵信息科技有限公司 | Highway maintenance inspection method, medium and equipment |
| CN116758757B (en) * | 2023-08-18 | 2023-11-14 | 福建智涵信息科技有限公司 | Highway maintenance inspection method, medium and equipment |
| CN117291583A (en) * | 2023-11-27 | 2023-12-26 | 贵州联广科技股份有限公司 | Internet of things data management method and system |
| CN117291583B (en) * | 2023-11-27 | 2024-02-23 | 贵州联广科技股份有限公司 | Internet of things data management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112816954B (en) | Road side perception system evaluation method and system based on true value | |
| CN109870456B (en) | Rapid detection system and method for road surface health condition | |
| CN112380317B (en) | High-precision map updating method and device, electronic equipment and storage medium | |
| Lekshmipathy et al. | Vibration vs. vision: Best approach for automated pavement distress detection | |
| CN114971166A (en) | Lightweight road pavement service quality inspection system | |
| Staniek | Road pavement condition diagnostics using smartphone-based data crowdsourcing in smart cities | |
| CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
| CN110427993B (en) | High-speed train navigation blind area positioning method based on meteorological parameters | |
| CN103837087B (en) | Pantograph automatic testing method based on active shape model | |
| JP2016217084A (en) | Road surface condition measurement system, road surface condition measurement method and road surface condition measurement program | |
| CN110021167A (en) | A kind of highway cloud inspection system and data processing method | |
| Benmhahe et al. | Automated pavement distress detection, classification and measurement: A review | |
| CN112070756A (en) | Three-dimensional road surface disease measuring method based on unmanned aerial vehicle oblique photography | |
| CN114627021A (en) | Point cloud and deep learning based defect detection method and system | |
| CN112488995A (en) | Intelligent injury judging method and system for automatic train maintenance | |
| CN115439643A (en) | Road disease size analysis and management method based on monocular measurement | |
| Camilleri et al. | Detecting road potholes using computer vision techniques | |
| Alrajhi et al. | Detection of road condition defects using multiple sensors and IoT technology: A review | |
| Shtayat et al. | Using supervised machine learning algorithms in pavement degradation monitoring | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| CN116448773B (en) | Pavement disease detection method and system with image-vibration characteristics fused | |
| CN111553500B (en) | Railway traffic contact net inspection method based on attention mechanism full convolution network | |
| CN117152617A (en) | Urban flood identification method and system | |
| CN111726535A (en) | Smart city CIM video big data image quality control method based on vehicle perception | |
| CN116796402A (en) | Highway environment recognition method and system based on BIM building information model |
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 |