CN116448016A - Intelligent rapid detection system and detection vehicle with same - Google Patents
Intelligent rapid detection system and detection vehicle with same Download PDFInfo
- Publication number
- CN116448016A CN116448016A CN202310470865.3A CN202310470865A CN116448016A CN 116448016 A CN116448016 A CN 116448016A CN 202310470865 A CN202310470865 A CN 202310470865A CN 116448016 A CN116448016 A CN 116448016A
- Authority
- CN
- China
- Prior art keywords
- crack
- detection
- vehicle
- detection algorithm
- algorithm
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 115
- 238000001914 filtration Methods 0.000 claims abstract description 18
- 201000010099 disease Diseases 0.000 claims abstract description 15
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 15
- 230000001133 acceleration Effects 0.000 claims abstract description 14
- 238000004891 communication Methods 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims abstract description 12
- 230000000295 complement effect Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000006073 displacement reaction Methods 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000003709 image segmentation Methods 0.000 claims description 13
- 238000003708 edge detection Methods 0.000 claims description 7
- 239000010426 asphalt Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims 2
- 238000001303 quality assessment method Methods 0.000 abstract description 3
- 238000012800 visualization Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D63/00—Motor vehicles or trailers not otherwise provided for
- B62D63/02—Motor vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/30—Measuring arrangements characterised by the use of optical techniques for measuring roughness or irregularity of surfaces
-
- 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
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses an intelligent rapid detection system and a detection vehicle with the same. The system comprises a data acquisition system and a detection algorithm system; the data acquisition system is in communication connection with the detection algorithm system. According to the embodiment of the invention, the high-definition camera and the six-suction sensor are respectively connected into the vehicle-mounted NVR for storing data, the tablet personal computer integrates the vehicle-mounted SDK and 808 protocols, the vehicle-mounted NVR is connected through the local area network, and the data acquisition system is used for actively acquiring data such as high-definition images, angular velocity, acceleration, GPS and the like. The tablet computer is uploaded to the detection algorithm system through 808 protocol. The image processing algorithm of the detection algorithm system is used for identifying the diseases of the image and calculating cracks, the complementary filtering and Kalman filtering fitting algorithm is combined for calculating the flatness, and then a detection result report is generated. And finally, road condition assessment and disease map visualization application are carried out through a data analysis system, so that the road quality assessment problems of high cost and low efficiency are solved.
Description
Technical Field
The invention relates to the technical field related to pavement detection, in particular to an intelligent rapid detection system and a detection vehicle with the same.
Background
Road surface flatness is an index of road surface evaluation involving three elements of people, vehicles, and roads, and affects four aspects of comfort, safety, economy, and road surface structure. Therefore, the method has very important significance in timely detecting the road surface flatness. Road breakage detection is one of the important contents of road maintenance management work. The traditional manual processing method has the disadvantages of low speed, danger, traffic influence and inaccuracy, and can not meet the requirements of pavement damage detection. With the rapid development of photoelectric technology and computer technology, the application of nondestructive detection technology to pavement damage detection is a necessary trend.
However, the prior detection technology has the following defects and shortcomings:
(1) In actual operation, the method has the characteristics of low efficiency, high cost and the like in manually collecting the data, and the road condition data is collected later and is financial.
(2) The application degree of high-end technologies such as dynamic digital image acquisition and analysis is still low, the information capability is not provided, and the accuracy of highway detection data is still to be improved.
(3) The 5G network has high flow cost and insufficient maintenance funds.
(4) The evaluation of the highway performance index is imperfect and not deep.
(5) The intelligent performance is insufficient, and the capability of actively finding out road pavement disease conditions is lacking. The detection speed is not fast and the frequency is not high.
Disclosure of Invention
In response to at least one of the deficiencies of the prior art, one aspect of the present invention discloses an intelligent rapid detection system.
The intelligent rapid detection system can comprise a data acquisition system and a detection algorithm system; the data acquisition system is in communication connection with the detection algorithm system.
According to a preferred embodiment of the invention, the data acquisition system comprises a plurality of high-definition cameras, a six-axis sensor and an intelligent terminal; the plurality of high-definition cameras and the six-axis sensor are respectively connected to the vehicle-mounted NVR; the vehicle-mounted NVR is in communication connection with the intelligent terminal; the intelligent terminal is integrated with a vehicle-mounted SDK and 808 protocols, so that the data acquisition system can actively acquire high-definition images, angular velocity, acceleration and/or GPS data through the SDK; and goes to the detection algorithm system via the 808 protocol.
According to a preferred embodiment of the invention, the intelligent terminal is a tablet computer.
According to a preferred embodiment of the present invention, the detection algorithm system includes a weighted neighborhood averaging algorithm module, an 8-direction Sober edge detection algorithm module, an Otsu image segmentation algorithm module, a complementary filtering algorithm module, and a kalman filtering algorithm module.
According to a preferred embodiment of the invention, the detection algorithm system judges the disease type through an image processing algorithm of a weighted neighborhood average algorithm module, an 8-direction Sober edge detection algorithm module and an Otsu image segmentation algorithm module;
the judging flow of the disease type is as follows:
(6) Reading an image acquired by the data acquisition system, and preprocessing the image, wherein the preprocessing comprises image restoration, image noise reduction and image enhancement;
(7) Image segmentation is carried out by using an Otsu image segmentation algorithm;
(8) Extracting characteristic analysis parameters, namely extracting characteristics by adopting a local binary pattern and a directional gradient histogram;
(9) Judging the number of connected domains of the linear cracks and the nonlinear cracks, setting a judging threshold T as 5, and if N is more than 5, judging the connected domains to belong to the nonlinear cracks, wherein the connected domains comprise netlike cracks and pit slots; then, the mesh cracks and pits are judged through size calculation;
(10) The projection of the linear crack in the vertical direction has obvious extreme points; and calculating projection values W and H of the linear crack on the x axis and the y axis, wherein if the horizontal projection value W is larger than the vertical projection value H, the linear crack is a transverse crack, otherwise, the linear crack is a longitudinal crack.
According to a preferred embodiment of the present invention, the detection algorithm calculates the length of the linear fracture by:
calculating a linear crack by a statistical pixel point number method, performing skeleton extraction on the linear crack to obtain a pixel width crack, and obtaining the total number of the crack pixels after skeleton extraction as LX after the actual representative length mu of each pixel, wherein the crack length is L=mu;
the detection algorithm system calculates the width of the linear crack by:
the width of the linear slit is calculated as follows:
(6) Making a vertical line of the crack, and setting two intersection points of the vertical line and the edge of the crack as；
(7) Calculating the width between two points:；
(8) Obtaining n pixel width samplesMaximum width->；
(9) Calculating the pixel number D of the original cracks:；
(10) Then the average width of the crack is:；
wherein mu is a calibration coefficient, L is the crack length, and D is the original crack pixel number.
According to a preferred embodiment of the present invention, the detection algorithm calculates the area of the nonlinear fracture by:
the area of the nonlinear fracture is calculated as follows:
the area calculating method comprises adopting minimum circumscribed rectangular area calculation, projecting nonlinear crack in X-axis and Y-axis directions, and obtaining maximum value of crack in X-axis directionAnd minimum->Obtaining maximum value +.about.of crack on Y-bar>And the lowest value->；
The area of the damaged road surface, i.e., the crack area, is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein μ is a calibration coefficient;
according to the road technical condition evaluation standard, the damage condition of the road is evaluated by adopting the road damage index PCI, wherein DR is the road damage rate which is the area of road damageArea of investigation->The ratio of (2) is:
；
the automatic detection calculation formula is as follows；
Wherein,,15 parts of asphalt pavement and 10.66 parts of cement-concrete pavement;
wherein,,asphalt pavement adopts 0.412 and cement-mixed soil pavement adopts 0.461.
According to a preferred embodiment of the invention, the detection algorithm system calculates an international flatness index IRI through a complementary filtering algorithm module and a kalman filtering algorithm module;
wherein, the international flatness index IRI is calculated as:
(1) The vertical vibration speed of the vehicle-mounted platform in the ith-1 longitudinal displacement is set asVertical vibration displacement +>Longitudinal spacingTime interval->Acceleration of +.>The vertical velocity in the ith longitudinal displacement is:
；
(2) The vertical vibration displacement in the ith longitudinal displacement is:
；
(3) Then the i-th longitudinal displacement inner displacement measurement valueThe corresponding corrected road surface elevation is:
；
(4) The road elevation average for i longitudinal displacements is:
；
(5) The flatness index delta sigma is:
(6) A linear conversion relation exists between the international flatness index IRI and the flatness standard deviation sigma, and the relation formula is as follows:
i.e. +.>。
According to a preferred embodiment of the present invention, the system further comprises a data analysis system; the data analysis system is in communication connection with the detection algorithm system; and the data analysis system generates a detection report according to the calculation result of the detection algorithm system, and carries out road condition assessment and GPS map visual display.
One aspect of the invention discloses an intelligent rapid detection vehicle.
The intelligent rapid detection vehicle comprises the intelligent rapid detection system as described in any one of the above.
The intelligent rapid detection system and the one or more technical schemes in the detection vehicle with the system provided by the embodiment of the invention have at least one of the following technical effects:
the intelligent rapid detection system and the detection vehicle with the system realize the judgment of road surface diseases by adopting the road surface image recognition technology, so that the labor intensity of workers can be reduced, and the working efficiency is improved. Through adopting six sensor technique of taking out, can realize automated inspection road surface roughness, promote the detection efficiency of road greatly, the financial expenditure of saving that can be great guarantees the safety of driving people.
Additional features of the invention will be set forth in part in the description which follows. Additional features of part of the invention will be readily apparent to those skilled in the art from a examination of the following description and the corresponding figures or a study of the manufacture or operation of the embodiments. The features of the present disclosure may be implemented and realized in the practice or use of the various methods, instrumentalities and combinations of the specific embodiments described below.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. Like reference symbols in the various drawings indicate like elements. Wherein,,
FIG. 1 is a schematic diagram of a system architecture of an intelligent rapid detection system according to some embodiments of the present invention;
FIG. 2 is a general flow diagram of an intelligent rapid detection system according to some embodiments of the invention;
FIG. 3 is a schematic view of camera calibration of the intelligent rapid detection system according to some embodiments of the present invention;
FIG. 4 is a schematic diagram of a disease type determination flow for an intelligent rapid detection system according to some embodiments of the present invention;
fig. 5 is a schematic diagram of an IRI calculation flow for an intelligent rapid detection system according to some embodiments of the invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that if the terms "first," "second," and the like are referred to in the description of the present invention and the claims and the above figures, they are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the invention herein. Furthermore, if the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present invention, if the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like are referred to, the indicated azimuth or positional relationship is based on that shown in the drawings. These terms are only used to better describe the present invention and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present invention will be understood by those of ordinary skill in the art according to the specific circumstances.
Further, in the present invention, the terms "mounted," "configured," "provided," "connected," "sleeved," and the like are to be construed broadly if they relate to. For example, it may be a fixed connection, a removable connection, or a unitary construction; may be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements, or components. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
An embodiment of one aspect of the invention discloses an intelligent rapid detection system.
As shown in fig. 1 to 5, the intelligent rapid detection system may include a data acquisition system and a detection algorithm system; the data acquisition system is in communication connection with the detection algorithm system.
The data acquisition system comprises a plurality of high-definition cameras, six-axis sensors and an intelligent terminal; the plurality of high-definition cameras and the six-axis sensor are respectively connected to the vehicle-mounted NVR; the vehicle-mounted NVR is in communication connection with the intelligent terminal; the intelligent terminal is integrated with a vehicle-mounted SDK and 808 protocols, so that the data acquisition system can actively acquire high-definition images, angular velocity, acceleration and/or GPS data through the SDK; and goes to the detection algorithm system via the 808 protocol. Preferably, the intelligent terminal is a tablet computer.
The detection algorithm system comprises a weighted neighborhood average algorithm module, an 8-direction Sober edge detection algorithm module, an Otsu image segmentation algorithm module, a complementary filtering algorithm module and a Kalman filtering algorithm module.
In this embodiment, the vehicle-mounted NVR, six-axis sensor, and three cameras may be installed in a general automobile. The camera and the six-axis sensor are respectively connected into the vehicle-mounted NVR. The six-axis sensor and the onboard NVR are placed in the trunk. The camera is installed at the back side of the car roof through the installation mechanism, and the installation mechanism has the function of lifting and rotating the camera. For example, the mounting mechanism may employ an existing camera pan-tilt mechanism. The camera may be a high definition camera. And fixing the camera, and acquiring the ratio of the actual width to the width of the image pixels, namely marking the calibration coefficient as mu by adopting a technology of detecting two circular centers. As shown in fig. 3, the road surface is captured by using a camera with two white circles with a diameter of 100mm and a fixed distance d=500 mm between the two centers of circles. After image processing is carried out by a detection algorithm system to obtain a binarized picture, two white circles and coordinates of centers of the two circles are identified. The calibration coefficients are: />Calibration systemThe number is used to calculate the specific dimensions of the crack length, width and area.
In this embodiment, the data acquisition system may be integrated with a vehicle-mounted SDK and 808 protocols, and the SDK may actively acquire data such as a high-definition image, an angular velocity, an acceleration, and a GPS. Capturing a real-time video stream of a camera, decoding the real-time video stream into a YV12 format, converting the YV12 format into RGB images, and controlling the camera through an SDK, wherein the control comprises starting and stopping snapshot, fixed-distance snapshot, real-time image data acquisition, parameter configuration and the like. The real-time video flow of the high-definition camera is adopted, the real-time video flow is decoded into a YV12 format, the YV format is converted into RGB images, and the control of the camera is realized through the SDK, including the acquisition of real-time image data, the parameter configuration, the subsequent processing of the images and the like. And finally, transferring to a detection algorithm system through 808 protocols. The detection algorithm system judges the disease type through a weighted neighborhood average algorithm, an 8-direction Sober edge detection algorithm and an image processing algorithm of an Otsu image segmentation algorithm.
Specifically, the disease type judging flow is as follows:
(1) The method comprises the steps of reading an image, preprocessing the image, including image restoration, image noise reduction, image enhancement and the like.
(2) Image segmentation was performed using the Otsu image segmentation algorithm.
(3) And extracting characteristic analysis parameters, and extracting the characteristics by adopting a local binary pattern and a directional gradient histogram.
(4) The number of connected domains of the linear cracks and the nonlinear cracks is determined, a determination threshold T is set to be 5, and if N >5, the non-linear cracks comprise netlike cracks and pits. And then the mesh cracks and pits are judged through size calculation.
(5) The linear crack has obvious extreme points projected in the vertical direction. And calculating projection values W and H of the linear crack on the x axis and the y axis, wherein if the horizontal projection value W is larger than the vertical projection value H, the linear crack is a transverse crack, otherwise, the linear crack is a longitudinal crack.
The length of the linear crack is calculated by a detection algorithm system.
Specifically, calculating a linear crack by a statistical pixel point number method, performing skeleton extraction on the linear crack to obtain a pixel width crack, and obtaining the total number of the crack pixels after skeleton extraction as LX through the actual representative length μ of each pixel, wherein the crack length is l=μ;
the width of the linear crack is calculated by a detection algorithm system.
Specifically, the width of the linear crack is calculated as follows:
(1) Making a vertical line of the crack, and setting two intersection points of the vertical line and the edge of the crack as；
(2) Calculating the width between two points:；
(3) Obtaining n pixel width samplesMaximum width->；
(4) Calculating the pixel number D of the original cracks:；
(5) Then the average width of the crack is:；
wherein mu is a calibration coefficient, L is the crack length, and D is the original crack pixel number.
And calculating the area of the nonlinear crack through a detection algorithm system.
Specifically, the area of the nonlinear crack is calculated as follows:
the area calculating method comprises adopting minimum circumscribed rectangular area calculation, projecting nonlinear crack in X-axis and Y-axis directions, and obtaining maximum value of crack in X-axis directionAnd minimum->Obtaining maximum value +.about.of crack on Y-bar>And the lowest value->；
The area of the damaged road surface, i.e., the crack area, is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein μ is a calibration coefficient;
according to the road technical condition evaluation standard, the damage condition of the road is evaluated by adopting the road damage index PCI, wherein DR is the road damage rate which is the area of road damageArea of investigation->The ratio of (2) is:
；
the automatic detection calculation formula is as follows；
Wherein,,15 parts of asphalt pavement and 10.66 parts of cement-concrete pavement;
wherein,,asphalt pavement adopts 0.412 and cement-mixed soil pavement adopts 0.461.
Through the detection algorithm system, DR and PCI are calculated based on the images, and diseases are positioned through GPS positioning data, so that the application of visually displaying the disease map on the map can be realized.
And calculating IRI through a detection algorithm system. The algorithm combining the complementary filtering and the Kalman filtering is adopted, so that data such as acceleration, angular velocity and the like are fitted, and the accuracy of calculating the elevation value of the road surface is improved, and therefore the automatic, high-speed and high-quality modern road surface detection is realized. The acceleration data is subjected to secondary integration to obtain displacement information, and the vertical vibration process of the vehicle-mounted platform between two adjacent data sampling points can be processed in an approximate uniform speed process because the sampling time of the two adjacent data points is short.
Specifically, the international flatness index IRI is calculated as:
(1) The vertical vibration speed of the vehicle-mounted platform in the ith-1 longitudinal displacement is set asVertical vibration displacement +>Longitudinal spacingTime interval->Acceleration of +.>The vertical velocity in the ith longitudinal displacement is:
；
(2) The vertical vibration displacement in the ith longitudinal displacement is:
；
(3) Then the i-th longitudinal displacement inner displacement measurement valueThe corresponding corrected road surface elevation is:
；
(4) The road elevation average for i longitudinal displacements is:
；
(5) The flatness index delta sigma is:
(6) A linear conversion relation exists between the international flatness index IRI and the flatness standard deviation sigma, and the relation formula is as follows:
i.e. +.>。
According to the intelligent rapid detection system, the vehicle-mounted NVR, the six-axis sensor and the three high-definition cameras are installed on a common automobile, the high-definition cameras and the six-axis sensor are respectively connected with the vehicle-mounted NVR to store data, the tablet personal computer integrates the vehicle-mounted SDK and 808 protocols, the vehicle-mounted NVR is connected through the local area network, the data acquisition system is used for actively acquiring data such as high-definition images, angular velocity, acceleration and GPS, and meanwhile the monitoring and control cameras are used for achieving start-stop snapshot and fixed-distance snapshot. The tablet computer is uploaded to the detection algorithm system through 808 protocol. The detection algorithm system comprises a weighted neighborhood average algorithm, an 8-direction Sober edge detection algorithm, an Otsu image segmentation algorithm, a complementary filtering algorithm and a Kalman filtering algorithm. The image processing algorithm of the detection algorithm system is used for identifying the diseases of the image and calculating cracks, the complementary filtering and Kalman filtering fitting algorithm is combined for calculating flatness, and then the detection result report is generated to comprise information data such as picture data, vehicle speed, longitude, latitude, IRI, RQI, DR, PCI and the like. And finally, carrying out road condition assessment and disease map visualization application through a data analysis system. The road quality assessment method and device solve the road quality assessment problems of high cost and low efficiency.
The detection algorithm system is a Kalman filter through data preprocessing, image recognition and the like. The generated detection result report includes information data such as vehicle speed, longitude, latitude, IRI, RQI, PCI, and the like. Absolute size data (mm) of pits, cracks and the like of the road surface are automatically calculated through image recognition, DR and PCI data with longitude and latitude are generated, and the recall rate of image recognition and the accuracy rate of image recognition reach 90%. And automatically calculating the running index of the road surface and the flatness RQI data with longitude and latitude according to the road surface data. The pavement detection accuracy reaches 90%. The data acquisition system integrates the vehicle-mounted SDK and 808 protocols, actively acquires high-definition images through the SDK, and simultaneously acquires data such as angular velocity, acceleration, GPS and the like.
The six-axis sensor is detection equipment with the characteristics of intelligence, microminiaturization, systemization, networking and the like, and is also the first step for realizing automatic detection and control. The six-axis sensor senses information and converts the information into a required information form according to rules so as to meet a series of requirements of information transmission, processing, control and the like. Compared with the common sensor, the six-axis sensor of the embodiment has a more accurate function, and the measured data can be decomposed into forces of X, Y, Z three directions axes in a space coordinate system, so that the six-axis sensor is often called a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer. The six-axis sensor basically consists of a three-axis accelerometer for detecting transverse acceleration and a three-axis gyroscope for detecting angular rotation and balancing. Acceleration and angular velocity are mainly collected as basic data for calculating the road surface flatness.
The tablet personal computer uses a USB3.0 communication protocol, an interface is usually connected with a local area network of the vehicle-mounted NVR by using a type-c, data are automatically acquired through a data acquisition system, and then the data are forwarded to a detection algorithm system through 808 protocols by the data acquisition system. The adoption of flat plate acquisition data transmission is regarded as solving the problem of high flow cost. The data transmission adopts 5G network transmission, so that the transmission efficiency is high, road condition data is automatically generated, and manual operation is reduced.
In this embodiment, three high-definition cameras are installed behind the roof of the inspection vehicle, the acquisition speed is 12 frames per second, and the speed of the inspection vehicle is 20 km to 80 km. By adopting the linear array camera technology, the detection width of 3.75 meters in the transverse direction can be achieved, and the highest detection precision can reach 1mm (millimeter). Every three meters a high definition photo, the road detection is guaranteed to be omitted.
Further, the system also comprises a data analysis system.
The data analysis system is in communication connection with the detection algorithm system; and the data analysis system generates a detection report according to the calculation result of the detection algorithm system, and carries out road condition assessment and GPS map visual display.
Specifically, a data analysis system is used for generating a detection report according to the result, wherein the detection report comprises information data such as picture data, vehicle speed, longitude, latitude, road surface performance index PCI, international flatness index IRI, road surface comprehensive breakage rate DR, road surface running quality index RQI and the like, and road condition assessment and GPS map visual display are carried out.
The invention also discloses an intelligent rapid detection vehicle. The intelligent rapid detection vehicle comprises the intelligent rapid detection system as described in any one of the above.
The inspection vehicle of the embodiment can transform the conventional maintenance vehicle of the road into a lightweight road detection vehicle, greatly improves the detection efficiency of the road, greatly saves financial expenditure and ensures the safety of driving people; can adopt integrated design, easy to assemble.
The intelligent rapid detection system and the detection vehicle with the system provided by the embodiment of the invention have the following advantages:
(1) By adopting a vehicle-mounted ultra-high definition dynamic snapshot technology, high-precision positioning triggering fixed-distance snapshot, one high-definition photo is obtained every three meters, and road detection is guaranteed to be omitted.
(2) By adopting an 800-ten-thousand-resolution camera, a crack with the width of 2mm on a road can be detected.
(3) The tablet personal computer can monitor and control the camera, start and stop snapshot, fixed-distance snapshot and the like.
(4) And the road condition data is transmitted and collected through a tablet personal computer USB3.0 transmission protocol, so that 5G flow expense is saved.
(5) The road condition map visualizes road condition assessment data, and the map visualizes display, so that timeliness and authenticity of the data are ensured.
(6) By adopting the high-precision six-pump sensor, the road surface flatness detection with automation, high speed and high quality is realized.
It should be noted that all of the features disclosed in this specification, or all of the steps in a method or process disclosed, may be combined in any combination, except mutually exclusive features and/or steps.
In addition, the foregoing detailed description is exemplary, and those skilled in the art, having the benefit of this disclosure, may devise various arrangements that, although not explicitly described herein, are within the scope of the present disclosure. It should be understood by those skilled in the art that the present description and drawings are illustrative and not limiting to the claims. The scope of the invention is defined by the claims and their equivalents.
Claims (10)
1. The intelligent rapid detection system is characterized by comprising a data acquisition system and a detection algorithm system; the data acquisition system is in communication connection with the detection algorithm system.
2. The intelligent rapid detection system of claim 1, wherein the data acquisition system comprises a plurality of high definition cameras, a six-axis sensor and an intelligent terminal;
the plurality of high-definition cameras and the six-axis sensor are respectively connected to the vehicle-mounted NVR;
the vehicle-mounted NVR is in communication connection with the intelligent terminal;
the intelligent terminal is integrated with a vehicle-mounted SDK and 808 protocols, so that the data acquisition system can actively acquire high-definition images, angular velocity, acceleration and/or GPS data through the SDK; and goes to the detection algorithm system via the 808 protocol.
3. The intelligent rapid detection system of claim 2, wherein the intelligent terminal is a tablet computer.
4. The intelligent rapid detection system of claim 1, wherein the detection algorithm system comprises a weighted neighborhood averaging algorithm module, an 8-direction Sober edge detection algorithm module, an Otsu image segmentation algorithm module, a complementary filtering algorithm module, and a kalman filtering algorithm module.
5. The intelligent rapid detection system according to claim 4, wherein the detection algorithm system judges the disease type through an image processing algorithm of a weighted neighborhood average algorithm module, an 8-direction Sober edge detection algorithm module and an Otsu image segmentation algorithm module;
the judging flow of the disease type is as follows:
(1) Reading an image acquired by the data acquisition system, and preprocessing the image, wherein the preprocessing comprises image restoration, image noise reduction and image enhancement;
(2) Image segmentation is carried out by using an Otsu image segmentation algorithm;
(3) Extracting characteristic analysis parameters, namely extracting characteristics by adopting a local binary pattern and a directional gradient histogram;
(4) Judging the number of connected domains of the linear cracks and the nonlinear cracks, setting a judging threshold T as 5, and if N is more than 5, judging the connected domains to belong to the nonlinear cracks, wherein the connected domains comprise netlike cracks and pit slots; then, the mesh cracks and pits are judged through size calculation;
(5) The projection of the linear crack in the vertical direction has obvious extreme points; and calculating projection values W and H of the linear crack on the x axis and the y axis, wherein if the horizontal projection value W is larger than the vertical projection value H, the linear crack is a transverse crack, otherwise, the linear crack is a longitudinal crack.
6. The intelligent rapid detection system of claim 5, wherein the detection algorithm system calculates the length of the linear fracture by:
calculating a linear crack by a statistical pixel point number method, performing skeleton extraction on the linear crack to obtain a pixel width crack, and obtaining the total number of the crack pixels after skeleton extraction as LX after the actual representative length mu of each pixel, wherein the crack length is L=mu;
the detection algorithm system calculates the width of the linear crack by:
the width of the linear slit is calculated as follows:
(1) Making a vertical line of the crack, and setting two intersection points of the vertical line and the edge of the crack as；
(2) Calculating the width between two points:；
(3) Obtaining n pixel width samplesMaximum width->；
(4) Calculating the pixel number D of the original cracks:；
(5) Then the average width of the crack is:；
wherein mu is a calibration coefficient, L is the crack length, and D is the original crack pixel number.
7. The intelligent rapid detection system of claim 6, wherein the detection algorithm system calculates the area of the nonlinear fracture by:
the area of the nonlinear fracture is calculated as follows:
the area calculating method adopts minimum external rectangular area calculation, and is specific to non-traditionalThe linear crack is projected in the X-axis and Y-axis directions, and then the maximum value of the crack in the X-axis direction is obtainedAnd minimum->Obtaining maximum value +.about.of crack on Y-bar>And the lowest value->；
The area of the damaged road surface, i.e., the crack area, is:the method comprises the steps of carrying out a first treatment on the surface of the Wherein μ is a calibration coefficient;
according to the road technical condition evaluation standard, the damage condition of the road is evaluated by adopting the road damage index PCI, wherein DR is the road damage rate which is the area of road damageArea of investigation->The ratio of (2) is:
；
the automatic detection calculation formula is as follows；
Wherein,,15 parts of asphalt pavement and 10.66 parts of cement-concrete pavement;
wherein the method comprises the steps of，Asphalt pavement adopts 0.412 and cement-mixed soil pavement adopts 0.461.
8. The intelligent rapid detection system according to claim 7, wherein the detection algorithm calculates an international flatness index IRI by means of a complementary filtering algorithm module and a kalman filtering algorithm module;
wherein, the international flatness index IRI is calculated as:
(1) The vertical vibration speed of the vehicle-mounted platform in the ith-1 longitudinal displacement is set asVertical vibration displacement +>Longitudinal spacingTime interval->Acceleration of +.>The vertical velocity in the ith longitudinal displacement is:
；
(2) The vertical vibration displacement in the ith longitudinal displacement is:
；
(3) Then the i-th longitudinal displacement inner displacement measurement valueThe corresponding corrected road surface elevation is:
；
(4) The road elevation average for i longitudinal displacements is:
；
(5) The flatness index delta sigma is:
(6) A linear conversion relation exists between the international flatness index IRI and the flatness standard deviation sigma, and the relation formula is as follows:
i.e. +.>。
9. The intelligent rapid detection system of one of claims 1 to 8, further comprising a data analysis system;
the data analysis system is in communication connection with the detection algorithm system; and the data analysis system generates a detection report according to the calculation result of the detection algorithm system, and carries out road condition assessment and GPS map visual display.
10. An intelligent rapid test vehicle, characterized in that it comprises an intelligent rapid test system according to one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310470865.3A CN116448016A (en) | 2023-04-26 | 2023-04-26 | Intelligent rapid detection system and detection vehicle with same |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310470865.3A CN116448016A (en) | 2023-04-26 | 2023-04-26 | Intelligent rapid detection system and detection vehicle with same |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116448016A true CN116448016A (en) | 2023-07-18 |
Family
ID=87133580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310470865.3A Pending CN116448016A (en) | 2023-04-26 | 2023-04-26 | Intelligent rapid detection system and detection vehicle with same |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116448016A (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1563891A (en) * | 2004-04-20 | 2005-01-12 | 长安大学 | System and method for discriminating road gap |
| CN101246000A (en) * | 2008-03-21 | 2008-08-20 | 哈尔滨工业大学 | Pavement planeness automatic detection device and detecting method |
| CN101319485A (en) * | 2008-07-16 | 2008-12-10 | 张小虎 | Photographing measurement method for detecting highroad pavement planeness |
| CN106087677A (en) * | 2016-06-02 | 2016-11-09 | 上海华城工程建设管理有限公司 | Asphalt pavement crack type automatic identifying method |
| 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 |
| CN111145161A (en) * | 2019-12-28 | 2020-05-12 | 北京工业大学 | Method for processing and identifying pavement crack digital image |
| CN111275363A (en) * | 2020-03-27 | 2020-06-12 | 山东智路信息科技有限公司 | Road network flatness evaluation system and method based on vehicle vibration data |
| CN112726351A (en) * | 2020-12-30 | 2021-04-30 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112985311A (en) * | 2021-02-09 | 2021-06-18 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN113532362A (en) * | 2021-07-15 | 2021-10-22 | 特路（北京）科技有限公司 | Intelligent automatic mapping and analyzing system for road safety adaptability |
| CN113638294A (en) * | 2021-08-17 | 2021-11-12 | 广东粤高智慧交通科技有限公司 | Intelligent detection system technology for road maintenance diseases |
| CN114118241A (en) * | 2021-11-17 | 2022-03-01 | 同济大学 | Road information detection system based on vehicle-mounted radar |
| CN114596551A (en) * | 2022-03-03 | 2022-06-07 | 湘潭大学 | Vehicle-mounted forward-looking image crack detection method |
| CN115201218A (en) * | 2022-07-13 | 2022-10-18 | 鲁朗软件(北京)有限公司 | Vehicle-mounted pavement disease intelligent detection method and system |
| CN115457277A (en) * | 2022-09-23 | 2022-12-09 | 东南大学 | Intelligent pavement disease identification and detection method and system |
| CN218059821U (en) * | 2022-04-06 | 2022-12-16 | 湖南省首华工程检测鉴定有限公司 | Highway quality detection device |
| CN115506216A (en) * | 2022-10-21 | 2022-12-23 | 浙江海康智联科技有限公司 | Pavement evenness analysis method and maintenance inspection system |
| CN115797338A (en) * | 2023-02-02 | 2023-03-14 | 河北工业大学 | Panoramic road surface multi-performance index calculation method and system based on binocular vision |
-
2023
- 2023-04-26 CN CN202310470865.3A patent/CN116448016A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1563891A (en) * | 2004-04-20 | 2005-01-12 | 长安大学 | System and method for discriminating road gap |
| CN101246000A (en) * | 2008-03-21 | 2008-08-20 | 哈尔滨工业大学 | Pavement planeness automatic detection device and detecting method |
| CN101319485A (en) * | 2008-07-16 | 2008-12-10 | 张小虎 | Photographing measurement method for detecting highroad pavement planeness |
| CN106087677A (en) * | 2016-06-02 | 2016-11-09 | 上海华城工程建设管理有限公司 | Asphalt pavement crack type automatic identifying method |
| 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 |
| CN111145161A (en) * | 2019-12-28 | 2020-05-12 | 北京工业大学 | Method for processing and identifying pavement crack digital image |
| CN111275363A (en) * | 2020-03-27 | 2020-06-12 | 山东智路信息科技有限公司 | Road network flatness evaluation system and method based on vehicle vibration data |
| CN112726351A (en) * | 2020-12-30 | 2021-04-30 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN112985311A (en) * | 2021-02-09 | 2021-06-18 | 上海同陆云交通科技有限公司 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| CN113532362A (en) * | 2021-07-15 | 2021-10-22 | 特路（北京）科技有限公司 | Intelligent automatic mapping and analyzing system for road safety adaptability |
| CN113638294A (en) * | 2021-08-17 | 2021-11-12 | 广东粤高智慧交通科技有限公司 | Intelligent detection system technology for road maintenance diseases |
| CN114118241A (en) * | 2021-11-17 | 2022-03-01 | 同济大学 | Road information detection system based on vehicle-mounted radar |
| CN114596551A (en) * | 2022-03-03 | 2022-06-07 | 湘潭大学 | Vehicle-mounted forward-looking image crack detection method |
| CN218059821U (en) * | 2022-04-06 | 2022-12-16 | 湖南省首华工程检测鉴定有限公司 | Highway quality detection device |
| CN115201218A (en) * | 2022-07-13 | 2022-10-18 | 鲁朗软件(北京)有限公司 | Vehicle-mounted pavement disease intelligent detection method and system |
| CN115457277A (en) * | 2022-09-23 | 2022-12-09 | 东南大学 | Intelligent pavement disease identification and detection method and system |
| CN115506216A (en) * | 2022-10-21 | 2022-12-23 | 浙江海康智联科技有限公司 | Pavement evenness analysis method and maintenance inspection system |
| CN115797338A (en) * | 2023-02-02 | 2023-03-14 | 河北工业大学 | Panoramic road surface multi-performance index calculation method and system based on binocular vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463918B (en) | Lane line extraction method based on fusion of laser point cloud and image data | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN108759973B (en) | Water level measuring method | |
| CN109658397A (en) | A kind of rail polling method and system | |
| CN113011283B (en) | Non-contact type rail sleeper relative displacement real-time measurement method based on video | |
| CN114627021A (en) | Point cloud and deep learning based defect detection method and system | |
| CN113781537A (en) | Track elastic strip fastener defect identification method and device and computer equipment | |
| CN113554667A (en) | Three-dimensional displacement detection method and device based on image recognition | |
| CN115439643A (en) | Road disease size analysis and management method based on monocular measurement | |
| CN114971166A (en) | Lightweight road pavement service quality inspection system | |
| CN116342598A (en) | Steel strand quality detection method based on machine vision | |
| CN114494845A (en) | Artificial intelligence hidden danger troubleshooting system and method for construction project site | |
| JP2009052907A (en) | Foreign matter detecting system | |
| CN116448016A (en) | Intelligent rapid detection system and detection vehicle with same | |
| CN111784785B (en) | Bridge dynamic displacement identification method | |
| CN113343849A (en) | Fusion sensing equipment based on radar and video | |
| CN117197019A (en) | Vehicle three-dimensional point cloud image fusion method and system | |
| CN112284509A (en) | Bridge structure vibration mode measuring method based on mobile phone video | |
| CN111709905A (en) | Analysis method for detecting cracks based on images | |
| CN116091456A (en) | Road visibility detection method | |
| CN106934356B (en) | Bus stop night passenger flow statistical method and system based on thermal imaging | |
| CN115578695A (en) | Water gauge water level machine vision detection method and device with free shooting visual angle | |
| CN115409691A (en) | Bimodal learning slope risk detection method integrating laser ranging and monitoring image | |
| CN113963230A (en) | Parking space detection method based on deep learning | |
| CN112883778A (en) | Road well lid height difference identification method and device based on computer vision |
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 |