CN115272930A - Ground penetrating radar-based road surface state evaluation method - Google Patents
Ground penetrating radar-based road surface state evaluation method Download PDFInfo
- Publication number
- CN115272930A CN115272930A CN202210896306.4A CN202210896306A CN115272930A CN 115272930 A CN115272930 A CN 115272930A CN 202210896306 A CN202210896306 A CN 202210896306A CN 115272930 A CN115272930 A CN 115272930A
- Authority
- CN
- China
- Prior art keywords
- road surface
- vehicle
- road
- ground penetrating
- penetrating radar
- 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
- 230000000149 penetrating effect Effects 0.000 title claims abstract description 27
- 238000011156 evaluation Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 63
- 201000010099 disease Diseases 0.000 claims abstract description 61
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 61
- 239000002344 surface layer Substances 0.000 claims abstract description 4
- 230000001133 acceleration Effects 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000004441 surface measurement Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000009432 framing Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 239000010426 asphalt Substances 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/44—Event detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/885—Radar or analogous systems specially adapted for specific applications for ground probing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a ground penetrating radar-based road surface state evaluation method, which comprises the following steps: acquiring a road video and road basic data based on a vehicle-mounted camera and a ground penetrating radar, wherein the road basic data comprises roadbed and road surface layer data, road surface deflection and flatness parameters; calculating a vehicle state characteristic quantity according to the road basic data and vehicle information acquired by a vehicle-mounted sensing device, inputting the vehicle state characteristic quantity into a road surface state judgment device to judge the road surface state of a detected road section, and outputting a judgment result; constructing a pavement disease detection model, inputting the pavement video into the pavement disease detection model for detection, and obtaining a detection result; and comprehensively evaluating the road surface state of the detected road section according to the detection result and the judgment result. The invention can realize the detection of specific types of road surface diseases and the evaluation of road surface states, and greatly improves the accuracy.
Description
Technical Field
The invention relates to the technical field of pavement layer detection, in particular to a ground penetrating radar-based pavement state evaluation method.
Background
In recent years, with the rapid development of socioeconomic, the construction of highway engineering continues to increase, and due to the unique climate, hydrogeological and landform conditions in the interior, early-built highways (particularly highways with lower grades) have a lot of serious early diseases, wherein pavement cracks are a lot due to the uneven settlement of a roadbed, the lower strength of the roadbed and the like. The continuous development of cracks seriously influences the integrity of the pavement and reduces the service life of the pavement, and some areas have large rainfall capacity, so that the cracks of the pavement are easy to generate water seepage, and the water seepage makes the pavement slippery, thereby reducing the adhesive force between tires and the pavement, causing the deterioration of the driving environment and seriously threatening the driving safety. The road surface internal structure diseases are difficult to accurately detect and measure, so that the road surface internal structure diseases are difficult to timely repair and treat, various damages are caused, the structural safety and the service life of the road surface are seriously endangered, the difficulty of road surface management and maintenance is greatly improved, higher maintenance and maintenance cost becomes a great burden of a traffic management department, and great negative effects are brought to managers and builders.
The composite asphalt pavement is a typical road tunnel pavement form, fatigue cracks and reflection cracks are the most typical and widely-occurring tunnel asphalt pavement diseases, and the occurrence of the cracks greatly reduces the integrity of the pavement, has great influence on the bearing capacity of the pavement and seriously threatens the driving safety. At present, the traditional detection or perception technology for the cracks of the asphalt pavement mainly comprises the following steps: manual inspection, rapid inspection vehicles and various pre-embedded sensors. Most areas still rely on manual inspection, but manual inspection is inefficient and has large errors. With the rapid development of image processing technology, laser scanning technology and the like, the rapid detection system for the road surface is rapidly developed, the application of the rapid detection system obviously improves the single detection speed, but the existing identification precision is low, and the requirements on the fine management and maintenance of the road surface cannot be met. Therefore, how to improve the detection precision of the pavement crack diseases based on the computer vision has great significance to the pavement management and maintenance.
The defects of cavities, water damage and the like in the pavement structure are typical defect types in the pavement structure, driving safety and the service life of roads are directly and seriously damaged, the pavement structure and the defects in the pavement structure are strong in trapping and shielding performance and high in detection difficulty, an effective detection means is absent at present, the defects of serious crack settlement, pit and the like can be found and treated only after the defects are developed, the water damage is difficult to eradicate, the defects are caused to be stubborn diseases of the asphalt pavement, the treatment area and the maintenance cost are increased, and adverse social influence is caused. Therefore, early detection and early disposal of cavities and water damage areas inside the pavement become main problems for maintenance management, and a rapid and accurate nondestructive detection method is urgently needed.
Disclosure of Invention
The invention aims to provide a ground penetrating radar-based road surface state evaluation method to solve the defects in the prior art.
In order to achieve the purpose, the invention provides the following scheme:
a ground penetrating radar-based road surface state evaluation method comprises the following steps:
acquiring a road video and road basic data based on a vehicle-mounted camera and a ground penetrating radar, wherein the road basic data comprises roadbed and road surface layer data, road surface deflection and flatness parameters;
acquiring vehicle information according to the road basic data and the vehicle-mounted sensing device, calculating a vehicle state characteristic quantity, inputting the vehicle state characteristic quantity into a road surface state judgment device to judge the road surface state of the detected road section, and outputting a judgment result;
constructing a pavement disease detection model, inputting the pavement video into the pavement disease detection model for detection, and obtaining a detection result;
and comprehensively evaluating the road surface state of the detected road section according to the detection result and the judgment result.
Preferably, the ground penetrating radar is a road ground penetrating radar, the road ground penetrating radar comprises a host, and a transmitting antenna and a receiving antenna which are respectively connected with the host, an output end of the transmitting antenna is used for transmitting signals to a detected road surface, an input end of the receiving antenna is used for receiving radar signals of the detected road surface, and an output end of the receiving antenna is connected with the road surface state judging device through an amplifier.
Preferably, the vehicle-mounted sensing device is mounted on a vehicle, and includes an acceleration sensor for acquiring an acceleration and a driving speed of the vehicle, a GPS receiver for acquiring spatial position information of the vehicle to associate road surface state information of a detected road section with GIS information, and a wheel speed sensor for detecting a rotational speed of a wheel.
Preferably, calculating the vehicle state characteristic amount includes:
the vehicle state characteristic amount is obtained by performing calculation based on vehicle characteristic information obtained by the on-vehicle sensor device, wherein the vehicle characteristic information includes a time-series waveform of acceleration detected by an acceleration sensor provided on a wheel, a band value of a fluctuation spectrum of air pressure in a tire detected by an internal pressure sensor provided on the wheel, a band power value of tire noise, a tire circumferential direction vibration value, and a tire radial direction vibration value.
Preferably, in the road surface determination device, each road surface recognition function is set in advance for different road surface states, the calculated values of the vehicle state feature amounts are input to the road surface recognition functions respectively to obtain feature amount recognition values, and the road surface state detection result is output based on the feature amount recognition values.
Preferably, obtaining the feature quantity identification value includes:
the road surface determination device obtains the feature amount identification value by correcting the road surface identification function, or the distribution state of the identification function value for each road surface state, or the distribution state of the feature amount for each road surface state, using the obtained vehicle state feature information.
Preferably, the constructing of the pavement disease detection model comprises:
and dividing the pavement video into a training set and a testing set, inputting the training set into the pavement disease detection model, and performing iterative training on the model by using a gradient descent method to obtain a trained pavement disease detection model.
Preferably, inputting the test set into the trained pavement disease detection model for detection, including: the method comprises the steps of obtaining a video marked with road surface disease types and confidence coefficient information by adopting frame-by-frame and pixel-by-pixel comparison, framing the video to obtain a video image set of each frame, and determining the disease types of the same position in each frame of video image.
Preferably, the same disease in the continuous frame images is subjected to duplicate removal and counting treatment, and the disease position is tracked by using a Kalman filtering algorithm to obtain a detection result.
The invention has the beneficial effects that:
the invention simultaneously uses the pavement state judgment device and the pavement disease detection model to detect the pavement to be evaluated, thereby not only not influencing the traffic efficiency of highway traffic, but also realizing the detection of specific types of pavement diseases and the evaluation of pavement states and greatly improving the accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a flowchart of a ground penetrating radar-based road surface condition evaluation method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
A ground penetrating radar-based road surface state evaluation method (as shown in figure 1) comprises the following steps:
acquiring a road video and road basic data based on a vehicle-mounted camera and a ground penetrating radar, wherein the road basic data comprises roadbed and road surface layer data, road surface deflection and flatness parameters;
calculating a vehicle state characteristic quantity according to the road basic data and vehicle information acquired by the vehicle-mounted sensing device, inputting the vehicle state characteristic quantity into a road surface state judgment device to judge the road surface state of the detected road section, and outputting a judgment result;
constructing a pavement disease detection model, inputting the pavement video into the pavement disease detection model for detection, and obtaining a detection result;
and comprehensively evaluating the road surface state of the detected road section according to the detection result and the judgment result.
According to the further optimization scheme, the vehicle-mounted camera device is a linear array camera, the linear array camera stably scans along the road direction to acquire road surface images, the line frequency during acquisition can reach 10000 lines/second, the images are continuously stored in a memory of an industrial computer through a high-speed acquisition card, and the current mileage position is recorded. In the acquisition process, in order to prevent frame loss caused by processing and storage overtime and avoid time-consuming processing such as data compression, image conversion and the like, the video data is stored into a continuous non-compressed large file format. Then, a certain compression format is exported according to application requirements in the video exporting process, so that the video data can be stored without lost frames to the maximum extent, and the storage space is effectively reduced.
The ground penetrating radar is a road ground penetrating radar which comprises a host, a transmitting antenna and a receiving antenna, wherein the transmitting antenna and the receiving antenna are respectively connected with the host, the output end of the transmitting antenna is used for transmitting signals to a detection road surface, the input end of the receiving antenna receives radar signals of the detection road surface, and the output end of the receiving antenna is connected with the road surface state judging device through an amplifier.
In a further preferred embodiment, the vehicle-mounted sensing device is mounted on a vehicle and comprises an acceleration sensor, a GPS receiver and a wheel speed sensor, wherein the acceleration sensor is used for acquiring acceleration and driving speed of the vehicle, the GPS receiver is used for acquiring spatial position information of the vehicle and realizing association between road surface state information of a detected road section and GIS information, and the wheel speed sensor is used for detecting rotation speed of a wheel.
And the GPS position is used for realizing the association of the pavement damage information and the GIS information. And acquiring the current position of the system at the same time of image acquisition through a mileage encoder and a GPS receiver.
In a further optimization scheme, the calculating the vehicle state characteristic quantity comprises:
the vehicle state characteristic amount is obtained by performing calculation based on characteristic information obtained by the on-vehicle sensor device, wherein the characteristic information includes a frequency spectrum of a time-series waveform of acceleration detected by an acceleration sensor provided on a tire or a wheel, a band value of a fluctuation spectrum of air pressure in the tire, a band power value of tire noise, and a tire circumferential direction vibration value and a tire radial direction vibration value.
The acceleration sensor is disposed substantially at the center of the inner liner of the tire on the tire air chamber side. The acceleration sensor detects vibration (tire vibration) input from a road surface to a tread of the tire.
The feature amount calculation includes a vibration waveform detection section, a region signal extraction section, and a feature amount calculation section. The feature amount calculation means calculates a feature amount for estimating a state of a road surface (road surface state) on which the vehicle is running, from a time-series waveform of tire vibration detected by the acceleration sensor. The vibration waveform detecting means detects an acceleration waveform for one rotation of the tire using the wheel speed detected by the wheel speed sensor.
The characteristic quantities of the vehicle include vibration levels of a plurality of frequency bands that change with a road surface state obtained from a frequency spectrum of a time-series waveform of acceleration detected by an acceleration sensor provided in a tire or a wheel or a knuckle, a band value of a fluctuation spectrum of air pressure detected by a pressure sensor provided in a tire air chamber, and a band power value of tire noise acquired by a microphone provided in a tire or a frame in front of a rear wheel. A bidirectional vibration sensor provided as an in-vehicle sensor is also included to detect tire circumferential vibration and tire radial vibration, and specific frequency components of these vibration waveforms are used as characteristic quantities of the vehicle.
In a further preferred embodiment, the road surface determination device includes road surface identification functions preset for different road surface states, and the vehicle state feature amount calculated values are input to the road surface identification functions to obtain feature amount identification values, and the road surface state detection results are output based on the feature amount identification values. The road surface determination device corrects the road surface recognition function, or the distribution state of the recognition function value for each road surface state, or the distribution state of the feature amount for each road surface state, by using the acquired vehicle state feature information. The time-series waveform of the tire vibration detected by the acceleration sensor is used in the present embodiment to estimate the road surface under the running vehicle as any one of a dry road surface, a wet road surface, a snow road surface, and an icy road surface.
The road surface condition estimation device may calculate each of feature vectors having vibration levels of a plurality of specific frequency bands as components from time-series waveforms of time windows extracted by windowing time-series waveforms of tire vibrations for a predetermined time width, calculate a kernel function from the feature vectors and the feature vectors for each of road surface conditions determined in advance, and estimate the road surface condition as any one of a dry road surface, a wet road surface, a snow road surface, and an icy road surface from a value of a recognition (discrimination) function using the kernel function. It should be noted that the feature vector for each road surface state is a feature vector having a plurality of specific frequency bands as components determined by running the test vehicle on a dry road surface, a wet road surface, a snow road surface, and an icy road surface, respectively.
Further optimizing the scheme, constructing a pavement disease detection model comprises:
and dividing the pavement video into a training set and a testing set, inputting the training set into the pavement disease detection model, and performing iterative training on the model by using a gradient descent method to obtain a trained pavement disease detection model. Inputting the test set into the trained pavement disease detection model for detection, obtaining a video marked with pavement disease categories and confidence information by adopting frame-by-frame and pixel-by-pixel comparison, framing the video to obtain a video image frame set, and determining the disease categories at the same position in the video image frame. And selecting a yolov5 network as a pavement disease detection model.
Further optimizing the scheme, carrying out duplicate removal and counting treatment on the same disease in continuous frame images, and respectively allocating a tracker for predicting the movement position of the disease in the next frame for the target disease appearing in the video by using a Kalman filtering algorithm, wherein each tracker corresponds to a disease tracking number m; correcting the predicted position according to the detection result of the road surface disease position in the next frame to obtain the optimal position estimation value of the disease tracked in the frame; comparing the disease at the optimal position in the current frame with the disease tracked in the previous frame: if the two diseases are the same disease, the disease is subjected to duplicate removal counting in two frames before and after; if the two are not the same disease, counting the tracked diseases to obtain the real-time tracking counting and detection result of the same disease in the continuous frames. And marking the pavement diseases including transverse cracks, longitudinal cracks, crazing and ruts in each video frame image.
According to the method, the disease detection results of the pavement diseases in the single-frame images are combined by adopting a disease processing method of spatial position combination to realize the de-duplication processing of the diseases at the same position, the de-duplication processing of the diseases at the same position in the continuous multi-frame images is realized by adopting a Kalman filtering algorithm, the real-time accurate tracking and counting of the pavement diseases can be obtained, and the pavement state at the position within a preset time period and a preset range can be judged; the state of the road surface of the detected road section is judged through the road surface state judging device, then the road surface damage of the same road section is detected through the road surface damage detection model, the road surface state is comprehensively evaluated through the comprehensive judgment result and the detection result, the detection of specific types of road surface damage and the evaluation of the road surface state are realized, and the accuracy is greatly improved.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.
Claims (9)
1. A ground penetrating radar-based road surface state evaluation method is characterized by comprising the following steps:
acquiring a road video and road basic data based on a vehicle-mounted camera and a ground penetrating radar, wherein the road basic data comprises roadbed and road surface layer data, road surface deflection and flatness parameters;
acquiring vehicle information according to the road basic data and the vehicle-mounted sensing device, calculating a vehicle state characteristic quantity, inputting the vehicle state characteristic quantity into a road surface state judgment device to judge the road surface state of the detected road section, and outputting a judgment result;
constructing a pavement disease detection model, inputting the pavement video into the pavement disease detection model for detection, and obtaining a detection result;
and comprehensively evaluating the road surface state of the detected road section according to the detection result and the judgment result.
2. The method according to claim 1, wherein the ground penetrating radar is a ground penetrating radar for road use, the ground penetrating radar for road use comprises a host machine, a transmitting antenna and a receiving antenna, the transmitting antenna and the receiving antenna are respectively connected with the host machine, an output end of the transmitting antenna is used for transmitting signals to a detected road surface, an input end of the receiving antenna is used for receiving radar signals of the detected road surface, and an output end of the receiving antenna is connected with the road surface state judging device through an amplifier.
3. The method according to claim 1, wherein the on-vehicle sensor device is mounted on a vehicle, and comprises an acceleration sensor for acquiring acceleration and driving speed of the vehicle, a GPS receiver for acquiring spatial position information of the vehicle and associating road surface state information of a detected road section with GIS information, and a wheel speed sensor for detecting a rotational speed of a wheel.
4. The ground penetrating radar-based road surface condition evaluation method according to claim 3, wherein calculating the vehicle condition characteristic amount includes:
the vehicle state characteristic amount is obtained by performing calculation based on vehicle characteristic information obtained by the on-vehicle sensor device, wherein the vehicle characteristic information includes a time-series waveform of acceleration detected by an acceleration sensor provided on a wheel, a band value of a fluctuation spectrum of air pressure in a tire detected by an internal pressure sensor provided on the wheel, a band power value of tire noise, a tire circumferential direction vibration value, and a tire radial direction vibration value.
5. The ground penetrating radar-based road surface condition evaluation method according to claim 4, wherein each road surface recognition function is preset in the road surface determination device for each road surface condition, the calculated vehicle condition feature amount values are input to the road surface recognition functions to obtain feature amount recognition values, respectively, and the road surface condition detection result is output based on the feature amount recognition values.
6. The ground penetrating radar-based road surface condition evaluation method according to claim 5, wherein obtaining the feature quantity identification value includes:
the road surface determination device obtains the feature amount identification value by correcting the road surface identification function, or the distribution state of the identification function value for each road surface state, or the distribution state of the feature amount for each road surface state, using the obtained vehicle state feature information.
7. The ground penetrating radar-based road surface condition evaluation method according to claim 1, wherein constructing a road surface disease detection model comprises:
dividing the pavement video into a training set and a testing set, inputting the training set into the pavement disease detection model, and performing iterative training on the model by using a gradient descent method to obtain a trained pavement disease detection model.
8. The ground penetrating radar-based road surface condition evaluation method according to claim 7, wherein the step of inputting the test set into the trained road surface disease detection model for detection comprises: the method comprises the steps of obtaining a video marked with road surface disease types and confidence coefficient information by adopting frame-by-frame and pixel-by-pixel comparison, framing the video to obtain a video image set of each frame, and determining the disease types of the same position in each frame of video image.
9. The ground penetrating radar-based road surface condition evaluation method according to claim 8, wherein the same disease in the continuous frame images is subjected to de-weighting and counting, and a Kalman filtering algorithm is used for tracking the position of the disease to obtain a detection result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210896306.4A CN115272930A (en) | 2022-07-28 | 2022-07-28 | Ground penetrating radar-based road surface state evaluation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210896306.4A CN115272930A (en) | 2022-07-28 | 2022-07-28 | Ground penetrating radar-based road surface state evaluation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115272930A true CN115272930A (en) | 2022-11-01 |
Family
ID=83771648
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210896306.4A Pending CN115272930A (en) | 2022-07-28 | 2022-07-28 | Ground penetrating radar-based road surface state evaluation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115272930A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117077452A (en) * | 2023-10-17 | 2023-11-17 | 深圳市城市交通规划设计研究中心股份有限公司 | Comprehensive evaluation method for service life of road, electronic equipment and storage medium |
CN118226457A (en) * | 2024-05-27 | 2024-06-21 | 同济大学 | Pavement disease amount accurate statistical method based on single-point laser ranging radar |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107003429A (en) * | 2014-10-06 | 2017-08-01 | 株式会社普利司通 | Pavement state judges system |
CN113962960A (en) * | 2021-10-22 | 2022-01-21 | 西安电子科技大学 | Pavement disease detection method based on deep learning |
CN114118241A (en) * | 2021-11-17 | 2022-03-01 | 同济大学 | Road information detection system based on vehicle-mounted radar |
-
2022
- 2022-07-28 CN CN202210896306.4A patent/CN115272930A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107003429A (en) * | 2014-10-06 | 2017-08-01 | 株式会社普利司通 | Pavement state judges system |
CN113962960A (en) * | 2021-10-22 | 2022-01-21 | 西安电子科技大学 | Pavement disease detection method based on deep learning |
CN114118241A (en) * | 2021-11-17 | 2022-03-01 | 同济大学 | Road information detection system based on vehicle-mounted radar |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117077452A (en) * | 2023-10-17 | 2023-11-17 | 深圳市城市交通规划设计研究中心股份有限公司 | Comprehensive evaluation method for service life of road, electronic equipment and storage medium |
CN117077452B (en) * | 2023-10-17 | 2024-02-27 | 深圳市城市交通规划设计研究中心股份有限公司 | Comprehensive evaluation method for service life of road, electronic equipment and storage medium |
CN118226457A (en) * | 2024-05-27 | 2024-06-21 | 同济大学 | Pavement disease amount accurate statistical method based on single-point laser ranging radar |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN115272930A (en) | Ground penetrating radar-based road surface state evaluation method | |
US10365248B2 (en) | Method for acoustic detection of the condition of the road and the tire | |
JP7172619B2 (en) | Road surface condition estimation device and road surface condition estimation method | |
US6807473B1 (en) | Road recognition system | |
CN103927870B (en) | A kind of vehicle detection apparatus based on multiple vibration detection sensors | |
US20190003852A1 (en) | Method for mapping data relating to road conditions | |
CN111783638B (en) | System and method for detecting number of wheel axles of vehicle and identifying vehicle type | |
US20220274599A1 (en) | Method and System for the Recognition of the Irregularities of a Road Pavement | |
CN104334375B (en) | Tire uneven wear detection method and tire uneven wear testing equipment | |
CN112304633B (en) | Method for identifying automobile braking safety risk in wet and slippery road surface state | |
CN110532657B (en) | Pier structure state evaluation method based on variable speed vehicle excitation and wavelet packet analysis | |
CN109671077B (en) | Method and system for detecting anti-skid performance of asphalt pavement | |
CN103486971B (en) | A kind of subway tunnel fracture width detection and correcting algorithm | |
WO2019080380A1 (en) | Wheelmark transverse distribution measuring system and method | |
Yu et al. | Pavement roughness index estimation and anomaly detection using smartphones | |
CN107798293A (en) | A kind of crack on road detection means | |
Nagayama et al. | Road condition evaluation using the vibration response of ordinary vehicles and synchronously recorded movies | |
CN106960581A (en) | Speed measurer for motor vehicle based on voice signal | |
JP2002243535A (en) | Road surface condition detecting device | |
CN115797338B (en) | Panoramic pavement multi-performance index calculation method and system based on binocular vision | |
CN113795415B (en) | Method and system for detecting irregularities of a road surface | |
CN113008985A (en) | Method for evaluating road pavement structure by utilizing tire/pavement noise | |
CN114264597B (en) | Low-cost road adhesion coefficient determination method and system | |
CN110399664B (en) | Driving speed determining method and device | |
CN112816043B (en) | Method and system for determining vehicle type of vehicle |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221101 |