CN115201218A - Vehicle-mounted pavement disease intelligent detection method and system - Google Patents
Vehicle-mounted pavement disease intelligent detection method and system Download PDFInfo
- Publication number
- CN115201218A CN115201218A CN202210826470.8A CN202210826470A CN115201218A CN 115201218 A CN115201218 A CN 115201218A CN 202210826470 A CN202210826470 A CN 202210826470A CN 115201218 A CN115201218 A CN 115201218A
- Authority
- CN
- China
- Prior art keywords
- module
- vehicle
- disease
- data
- image
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- 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
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G06N3/08—Learning methods
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
- G01N2021/9518—Objects of complex shape, e.g. examined with use of a surface follower device using a surface follower, e.g. robot
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Biochemistry (AREA)
- Biomedical Technology (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Structural Engineering (AREA)
- Signal Processing (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Road Repair (AREA)
Abstract
The invention provides a vehicle-mounted pavement disease intelligent detection method and a system, comprising a starting detection system; after the vehicle is patrolled and examined, the image acquisition module acquires road surface data, and the acceleration module and the high-precision positioning module synchronously acquire acceleration data and vehicle positioning data in the vertical direction; a deep learning algorithm module of the edge calculation module performs reasoning to determine whether a disease exists in each frame of image, the type of the disease and the position information of the disease in the image; the edge calculation module superimposes the inference result on the road surface image after frame extraction and pushes the flow outwards by an RTSP (real time streaming protocol); the vehicle-mounted display module analyzes the video stream; the edge calculation module uploads the road surface image, the acceleration data and the high-precision positioning data to a remote server application module through a wireless communication module; the remote server application module receives and stores the road surface image, the acceleration data and the high-precision positioning data; and the remote server application module combines the positioning data to remove the defects and the duplication, and carries out the quantitative evaluation of the flatness according to the acceleration data.
Description
Technical Field
The invention relates to the technical field of road traffic detection, in particular to an intelligent detection method and system for vehicle-mounted pavement diseases.
Background
In recent thirty years, the infrastructure construction of China has been rapidly developed, the total mileage of roads is more and more, and the task pressure of inspecting road surface diseases is more and more. In order to solve the problem, a professional patrol vehicle is used for regular inspection or manual driving is used for daily inspection in most of the past. The regular inspection period is long, professional equipment is relied on, and the cost is high; the manual investigation efficiency is low, the data is inaccurate, and the investigation effect varies from person to person. With the rapid development of artificial intelligence, particularly deep learning, automatic analysis of road surface diseases by using road surface image data is also applied, but the road surface inspection real-time performance is poor due to the fact that multi-source data cannot be synchronously acquired and analyzed in real time through edge equipment, the overall condition of the road surface cannot be reflected, and the intelligent analysis capability of the edge equipment cannot be rapidly upgraded.
Reference is made to patent "CN 111767874A" a road surface disease detection method based on deep learning, which discloses a road surface disease detection method based on deep learning. The method comprises the following steps: collecting normal road data through a camera arranged on a vehicle, and labeling the collected data to classify the data as normal; respectively building two neural networks; training a neural network and judging the neural network; the characteristic vector of a normal road surface is obtained through training the neural network, the input image is calculated through distinguishing the neural network, a difference threshold value is calculated with the characteristic vector of the normal road surface, and whether the road has a disease risk or not is judged. The patent also discloses a detection system of the road surface disease detection method based on deep learning, which comprises a road data acquisition module, a model training module, a model reading module, a data model reasoning module and an abnormal area image output module.
Although the patent also uses a deep learning method to detect the road surface, the detection method only establishes a training library of the normal road surface, and the images different from the normal road surface are wrongly judged as the road diseases, so that the accuracy of the road disease analysis cannot be ensured. Secondly, inertial navigation data such as the acceleration of the inspection vehicle and the like are not combined, and the road flatness cannot be analyzed only according to two-dimensional image data. Thirdly, the patent does not provide an algorithm for removing the weight of the pavement damage, and the probability of repeated calculation of the pavement damage exists, so that the comprehensive evaluation of the pavement condition is distorted.
Refer to patent "CN 112817006A" - "a vehicle-mounted intelligent road disease detection method and system", this patent discloses a vehicle-mounted intelligent road disease detection method. The method comprises the following steps: starting a vehicle-mounted intelligent road disease detection system; the method comprises the following steps that a camera and a laser radar acquire road data; judging whether a suspected disease road exists by using a laser radar; storing the suspected disease road data into a data cache region; the deep learning algorithm module cuts out an image of a corresponding area of the suspected road and confirms whether the road is a diseased road or not; the disease road management module identifies and confirms data information of the disease road, stores the data information and sends the data information to the cloud server; the system displays the data information of the damaged road on a man-machine interaction interface and sends the data information to road management personnel.
The method for detecting the road surface by combining the laser radar and the deep learning is used, but inertial navigation data such as the acceleration of an inspection vehicle and the like are not combined in the detection method, and the road flatness cannot be analyzed. Thirdly, the patent does not provide an algorithm for removing the weight of the pavement damage, and the probability of repeated calculation of the pavement damage exists, so that the comprehensive evaluation of the pavement condition is distorted.
Disclosure of Invention
In order to solve the problem that the existing pavement disease detection system and method cannot accurately, effectively and quickly detect the disease condition, the invention provides the vehicle-mounted pavement disease intelligent detection method and system, wherein a deep learning convolutional neural network is utilized, and a deep learning algorithm module is constructed by a positive and negative sample balance construction method to solve the problem of misjudgment of the pavement disease; checking a disease analysis result in real time through an on-board display module; the acceleration acquisition module is added to acquire acceleration data in the vertical direction so as to more accurately evaluate the evenness of the road surface; accurate position information of the vehicle is obtained by adding a high-precision positioning module, and accurate redundant images are removed to realize disease duplication elimination; the remote server application module provides an automatic screening and manual auditing mechanism for pavement diseases, and automatic detection for pavement diseases and accurate evaluation for pavement comprehensive conditions are realized.
The invention adopts the following technical means:
an intelligent detection method for vehicle-mounted pavement diseases comprises the following steps:
step 1: starting a vehicle-mounted intelligent pavement disease detection system;
step 2: after the vehicle starts to patrol, the image acquisition module acquires road surface data, and the acceleration module and the high-precision positioning module synchronously acquire acceleration data and vehicle positioning data in the vertical direction;
and step 3: the edge calculation module performs frame extraction according to a specified frame interval and stores data in the storage module;
and 4, step 4: a deep learning algorithm module of the edge calculation module performs reasoning to determine whether a disease exists in each frame of image, the type of the disease and the position information of the disease in the image;
and 5: the edge calculation module superimposes the inference result on the road surface image after frame extraction and pushes the flow outwards by an RTSP (real time streaming protocol);
step 6: the vehicle-mounted display module displays the disease analysis video stream in real time through a Wi-Fi hotspot of the edge computing device;
and 7: the edge calculation module uploads the road surface image, the acceleration data and the high-precision positioning data to the remote server application module through the wireless communication module;
and 8: the remote server application module receives and stores the road surface image, the acceleration data and the high-precision positioning data;
and step 9: the remote server application module performs disease duplicate removal by combining high-precision positioning data according to the effective picture distance of the image acquisition module;
step 10: and the remote server application module carries out flatness quantitative evaluation on the patrol road according to the acceleration data in a segmented mode according to the specified length, and outputs an evaluation report.
Preferably, the first and second liquid crystal materials are,
in the step 4, the deep learning algorithm module performs reasoning to determine whether a disease exists in each frame of image, the type of the disease and the position information of the disease in the image, and the method comprises the following steps:
step 401: the deep learning algorithm module is provided with a threshold value X;
step 402: the deep learning algorithm module firstly identifies the position of a suspected disease by using a target detection technology and cuts an image of a disease area;
step 403: and the deep learning algorithm module identifies the cut suspected diseased pavement images by using a classification model, and takes the first candidate with the classification result confidence coefficient > = X as a final inference result.
Preferably, the first and second liquid crystal materials are,
in the step 5, in order to ensure that no disease omission occurs, the frame number A of the edge calculation module is calculated according to the maximum inspection vehicle speed S (unit: kilometer/hour) and the effective image detection distance D (unit: meter), and the formula is as follows:
a > = (S1000/3600/D) (round up).
Preferably, the first and second liquid crystal materials are,
in the step 10, the remote server application module performs quantitative evaluation of the flatness of the patrol road according to the acceleration data in a segmented manner according to the specified length, and the method includes the following steps:
step 1001: the remote server application module is provided with a road section evaluation granularity parameter B (unit: meter), wherein the value of B is an integral multiple of 50 and is not more than 1000;
step 1002: and the remote server application module calculates the total quantity, the total area and the average value of the vertical direction acceleration and the reference PQI value of the pavement diseases of each section B from the inspection starting point according to the position information.
Preferably, the first and second liquid crystal materials are,
the road surface PQI calculation formula of the invention is as follows:
PQI = α PCI + β RQI + γ RDI (α, β, γ are weighting coefficients).
The invention also provides a vehicle-mounted pavement damage intelligent detection system applied to the method, and the system comprises an intelligent module, wherein the intelligent module comprises:
the image acquisition module is used for acquiring continuous RGB image information behind the vehicle;
the edge computing module drives each module to perform tasks such as data acquisition, storage, reasoning, result sending and the like;
the deep learning algorithm module is used for detecting and reasoning the road surface image, detecting diseases, cutting, classifying and calculating the area;
the storage module is used for storing the road surface image, acceleration and positioned time flow data;
the vehicle-mounted display module is used for displaying the inference result of the edge calculation module;
the wireless communication module is used for connecting and communicating with the remote server module;
the acceleration acquisition module is used for acquiring position data of the inspection vehicle;
the high-precision positioning module is used for acquiring the acceleration data of the inspection vehicle in the vertical direction;
and the remote server application module is used for receiving, storing and analyzing various data uploaded by the edge calculation module and forming a detection report.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the pavement disease detection method based on deep learning, the problem of misjudgment of pavement diseases can be solved by using a target detection model and a disease classification model constructed by positive and negative samples in a balanced manner in a cascading manner.
2. While the edge computing module carries out reasoning, the reasoning result is pushed to the vehicle-mounted display module in real time, and the disease analysis result can be checked in real time.
3. The acceleration acquisition module is added to acquire acceleration data in the vertical direction so as to more accurately evaluate the evenness of the road surface; accurate position information of the vehicle is obtained by adding a high-precision positioning module, and accurate redundant images are removed to realize disease duplication removal; data fusion is carried out through a remote server application module, an automatic screening and manual checking mechanism for pavement diseases is provided, and automatic detection of the pavement diseases and accurate evaluation of comprehensive conditions of the pavement are achieved.
Drawings
FIG. 1 is a schematic diagram of the overall structure of the vehicle-mounted pavement damage intelligent detection method and system of the invention;
FIG. 2 is a schematic block diagram of the vehicle-mounted pavement damage intelligent detection method and system of the invention;
FIG. 3 is a schematic diagram illustrating the implementation details of the vehicle-mounted road surface damage intelligent detection method and system of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case to those of ordinary skill in the art.
As shown in fig. 1, the vehicle-mounted road surface disease intelligent detection method of the present invention includes the following steps:
step 1: starting a vehicle-mounted intelligent pavement disease detection system;
and 2, step: after the vehicle starts to patrol, the image acquisition module starts to acquire the road surface image video stream, and meanwhile, the acceleration module and the high-precision positioning module synchronously acquire acceleration data and vehicle positioning data in the vertical direction. The pavement diseases detected in the embodiment mainly comprise four diseases of transverse and longitudinal cracks, cracks and pot holes. Adopt 60fps frame rate high definition digtal camera, install on patrolling and examining car afterbody intermediate line to firm support is fixed, and the field of vision is towards the front lower place, ensures that the lower half of image picture is 3 meters distances (like fig. 3). An acceleration acquisition module and a high-precision positioning module of 10Hz equipment are adopted.
And 3, step 3: the edge calculation module collects images according to 60fps, and calculates necessary frame extraction intervals according to the maximum inspection vehicle speed S (unit: kilometer/hour) and the image effective detection distance D (unit: meter). The formula is as follows:
a > = (S1000/3600/D) (round up).
The edge calculation module extracts images at intervals of reserving A frames in seconds and stores the images in the storage module. Correspondingly, the acceleration data and the high-precision positioning data are also saved in the storage module.
And 4, step 4: and a deep learning algorithm module of the edge calculation module performs disease target detection on the extracted images, confirms whether a disease area exists in each frame of image, intercepts the disease area, forms a disease image and calls a classification model, the classification inference model is provided with a threshold value X, and when the confidence coefficient > = X of the inference result, the first candidate is the final inference result.
The training samples of the deep learning algorithm model of the embodiment are derived from 20 or more than ten thousand pre-collected disease pictures, and the original picture sizes are all reset to 640 × 360 as training samples although the original picture sizes are different.
And 5: and the edge computing module is used for superposing the reasoning result on the road surface image after the frame is extracted and outwards pushing the stream by an RTSP (real time streaming protocol).
In the embodiment, a logic switch F is provided, and when F is turned ON, the flow pushing is performed, and when F is turned OFF, the flow pushing is stopped to reduce the CPU load of the edge calculation module.
And 6: the vehicle-mounted display module is directly connected with a Wi-Fi hotspot of the edge computing device through a Wi-Fi communication protocol, the Wi-Fi hotspot of the edge device is named according to a naming rule in advance, and a video stream of a disease analysis result is automatically displayed after direct connection.
If the logic switch of the edge calculation module is turned OFF, displaying that the video stream does not have the real-time disease analysis result.
And 7: the edge calculation module uploads the road surface image, the acceleration data and the high-precision positioning data to the remote server application module through the 4G/5G wireless communication module.
In this embodiment, data is uploaded by using MQTT protocol.
And 8: the remote server application module receives and stores the road surface image, the acceleration data and the high-precision positioning data.
The embodiment stores the image data in a file mode, and stores the image URL, the acceleration data and the high-precision positioning data into a relational database for storage.
And step 9: and the remote server application module performs disease duplicate removal by combining high-precision positioning data according to the effective picture distance of the image acquisition module.
The effective distance of the embodiment is 3m, the remote server application module calculates the distance between the detected disease images in pairs from the near to the far according to the distance from the departure point, and deletes the disease images with the distance less than 3m and the monitoring result.
Step 10: and the remote server application module carries out flatness quantitative evaluation on the patrol road according to the acceleration data in a segmentation mode according to the specified length and outputs an evaluation report. The present embodiment sets a link evaluation granularity parameter B =100 (unit: meter), and calculates the total number of road surface defects, the total area, and the average value of vertical direction accelerations and the reference PQI value every 100 meters from the starting point of the patrol.
Wherein PQI = α PCI + β RQI + γ RDI (α, β, γ take values of 0.5,0.4 and 0.1, respectively).
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An intelligent detection method for vehicle-mounted pavement diseases is characterized by comprising the following steps:
step 1: starting a vehicle-mounted intelligent pavement disease detection system;
step 2: after the vehicle starts to patrol, the image acquisition module acquires road surface data, and the acceleration module and the high-precision positioning module synchronously acquire acceleration data and vehicle positioning data in the vertical direction;
and 3, step 3: the edge calculation module performs frame extraction according to a specified frame interval and stores data in the storage module;
and 4, step 4: a deep learning algorithm module of the edge calculation module performs reasoning to determine whether a disease exists in each frame of image, the type of the disease and the position information of the disease in the image;
and 5: the edge calculation module superimposes the inference result on the road surface image after frame extraction and pushes the flow outwards by an RTSP (real time streaming protocol);
and 6: the vehicle-mounted display module displays the disease analysis video stream in real time through the Wi-Fi hot spot of the edge computing device;
and 7: the edge calculation module uploads the road surface image, the acceleration data and the high-precision positioning data to a remote server application module through a wireless communication module;
and 8: the remote server application module receives and stores the road surface image, the acceleration data and the high-precision positioning data;
and step 9: the remote server application module combines high-precision positioning data to remove the disease duplicate according to the effective picture distance of the image acquisition module;
step 10: and the remote server application module carries out flatness quantitative evaluation on the patrol road according to the acceleration data in a segmented mode according to the specified length, and outputs an evaluation report.
2. The intelligent vehicle-mounted pavement damage detection method according to claim 1, wherein the vehicle-mounted pavement damage detection method comprises the steps of,
in the step 4, the deep learning algorithm module performs reasoning to determine whether a disease exists in each frame of image, the type of the disease and the position information of the disease in the image, and the method comprises the following steps:
step 401: the deep learning algorithm module is provided with a threshold value X;
step 402: the deep learning algorithm module firstly identifies the position of a suspected disease by using a target detection technology and cuts an image of a disease area;
step 403: and the deep learning algorithm module identifies the cut suspected diseased pavement images by using a classification model, and takes the first candidate with the classification result confidence coefficient > = X as a final inference result.
3. The intelligent detection method for the vehicle-mounted pavement diseases according to claim 1, characterized in that,
in the step 5, in order to ensure that no disease omission occurs, the frame extraction quantity A of the edge calculation module is calculated according to the maximum inspection vehicle speed S (unit: kilometer/hour) and the effective image detection distance D (unit: meter), and the formula is as follows:
a > = (S1000/3600/D) (round up).
4. The intelligent vehicle-mounted pavement damage detection method according to claim 1, wherein the vehicle-mounted pavement damage detection method comprises the steps of,
in the step 10, the remote server application module performs the quantitative evaluation of the flatness on the patrol road according to the acceleration data in a segmentation mode according to the specified length, and the method comprises the following steps:
step 1001: the remote server application module is provided with a road section evaluation granularity parameter B (unit: meter), wherein the value of B is an integral multiple of 50 and is not more than 1000;
step 1002: and the remote server application module calculates the total quantity, the total area and the average value of the vertical direction acceleration and the reference PQI value of the pavement diseases of each section B from the inspection starting point according to the position information.
5. The intelligent vehicle-mounted pavement damage detection method according to claim 4, wherein the vehicle-mounted pavement damage detection method comprises the steps of,
the PQI calculation formula is as follows:
PQI = α PCI + β RQI + γ RDI (α, β, γ are weighting coefficients).
6. An intelligent detection system for vehicle-mounted pavement diseases, which is applied to the intelligent detection method for vehicle-mounted pavement diseases according to any one of claims 1 to 5, and is characterized by comprising an intelligent module, wherein the intelligent module comprises:
the image acquisition module is used for acquiring continuous RGB image information behind the vehicle;
the edge calculation module drives each module to perform tasks such as data acquisition, storage, reasoning, result sending and the like;
the deep learning algorithm module is used for detecting and reasoning the road surface image, detecting diseases, cutting, classifying and calculating the area;
the storage module is used for storing the road surface image, the acceleration and the positioned time flow data;
the vehicle-mounted display module is used for displaying the inference result of the edge calculation module;
the wireless communication module is used for connecting and communicating with the remote server module;
the acceleration acquisition module is used for acquiring the position data of the inspection vehicle;
the high-precision positioning module is used for acquiring acceleration data of the inspection vehicle in the vertical direction;
and the remote server application module is used for receiving, storing and analyzing various data uploaded by the edge calculation module and forming a detection report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210826470.8A CN115201218A (en) | 2022-07-13 | 2022-07-13 | Vehicle-mounted pavement disease intelligent detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210826470.8A CN115201218A (en) | 2022-07-13 | 2022-07-13 | Vehicle-mounted pavement disease intelligent detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115201218A true CN115201218A (en) | 2022-10-18 |
Family
ID=83580295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210826470.8A Pending CN115201218A (en) | 2022-07-13 | 2022-07-13 | Vehicle-mounted pavement disease intelligent detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115201218A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN116304583A (en) * | 2023-05-17 | 2023-06-23 | 中铁大桥局集团有限公司 | Road surface smoothness detection and evaluation method and device |
| 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 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180141561A1 (en) * | 2015-05-06 | 2018-05-24 | Continental Teves Ag & Co. Ohg | Method and Apparatus for Detecting and Assessing Road Reflections |
| US20190154442A1 (en) * | 2016-01-15 | 2019-05-23 | Fugro Roadware Inc. | High speed stereoscopic pavement surface scanning system and method |
| CN109870456A (en) * | 2019-02-01 | 2019-06-11 | 上海智能交通有限公司 | A kind of road surface health status rapid detection system and method |
| CN113177611A (en) * | 2021-05-24 | 2021-07-27 | 河北工业大学 | Pavement disease rapid inspection method based on mechanical index and artificial neural network |
| US20210319561A1 (en) * | 2020-11-02 | 2021-10-14 | BeSTDR Infrastructure Hospital(Pingyu) | Image segmentation method and system for pavement disease based on deep learning |
| 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 |
-
2022
- 2022-07-13 CN CN202210826470.8A patent/CN115201218A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180141561A1 (en) * | 2015-05-06 | 2018-05-24 | Continental Teves Ag & Co. Ohg | Method and Apparatus for Detecting and Assessing Road Reflections |
| US20190154442A1 (en) * | 2016-01-15 | 2019-05-23 | Fugro Roadware Inc. | High speed stereoscopic pavement surface scanning system and method |
| CN109870456A (en) * | 2019-02-01 | 2019-06-11 | 上海智能交通有限公司 | A kind of road surface health status rapid detection system and method |
| US20210319561A1 (en) * | 2020-11-02 | 2021-10-14 | BeSTDR Infrastructure Hospital(Pingyu) | Image segmentation method and system for pavement disease based on deep learning |
| 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 |
| CN113177611A (en) * | 2021-05-24 | 2021-07-27 | 河北工业大学 | Pavement disease rapid inspection method based on mechanical index and artificial neural network |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN116304583A (en) * | 2023-05-17 | 2023-06-23 | 中铁大桥局集团有限公司 | Road surface smoothness detection and evaluation method and device |
| CN116304583B (en) * | 2023-05-17 | 2023-08-11 | 中铁大桥局集团有限公司 | Road surface smoothness detection and evaluation method and device |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115201218A (en) | Vehicle-mounted pavement disease intelligent detection method and system | |
| CN109870456B (en) | Rapid detection system and method for road surface health condition | |
| CN108765894B (en) | Bridge health condition monitoring and alarming system | |
| CN109285376A (en) | A kind of bus passenger flow statistical analysis system based on deep learning | |
| CN111833598B (en) | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway | |
| CN110991466A (en) | Highway road surface condition detecting system based on novel vision sensing equipment | |
| CN109935080B (en) | Monitoring system and method for real-time calculation of traffic flow on traffic line | |
| CN105608431A (en) | Vehicle number and traffic flow speed based highway congestion detection method | |
| US20240167962A1 (en) | System and method for automatic monitoring of pavement condition | |
| CN113588664A (en) | Vehicle-mounted road defect rapid inspection and analysis system | |
| KR101461184B1 (en) | Wether condition data extraction system using cctv image | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| Mertz et al. | City-wide road distress monitoring with smartphones | |
| CN111275957A (en) | Traffic accident information acquisition method, system and camera | |
| CN115220479A (en) | Dynamic and static cooperative power transmission line refined inspection method and system | |
| CN111626261A (en) | Intelligent inspection analysis early warning system for hydraulic buildings | |
| CN112769877A (en) | Group fog early warning method, cloud server, vehicle and medium | |
| CN115600124A (en) | Subway tunnel inspection system and inspection method | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN114971166A (en) | Lightweight road pavement service quality inspection system | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| CN113033443B (en) | Unmanned aerial vehicle-based automatic pedestrian crossing facility whole road network checking method | |
| CN111598885B (en) | Automatic visibility grade marking method for highway foggy pictures | |
| CN111553500B (en) | Railway traffic contact net inspection method based on attention mechanism full convolution network | |
| CN117037449A (en) | Group fog monitoring method and system based on edge calculation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |