CN112726351B - Vehicle-mounted portable lightweight intelligent inspection method and system - Google Patents
Vehicle-mounted portable lightweight intelligent inspection method and system Download PDFInfo
- Publication number
- CN112726351B CN112726351B CN202011601294.5A CN202011601294A CN112726351B CN 112726351 B CN112726351 B CN 112726351B CN 202011601294 A CN202011601294 A CN 202011601294A CN 112726351 B CN112726351 B CN 112726351B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- data
- detection
- equipment
- road
- 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.)
- Active
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
- E01C23/01—Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/30—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring roughness or irregularity of surfaces
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/10—Information sensed or collected by the things relating to the environment, e.g. temperature; relating to location
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
Abstract
The invention belongs to the technical field of road detection, in particular to a vehicle-mounted portable lightweight intelligent inspection method and a system, and provides the following scheme, which comprises the following equipment: the intelligent vehicle-mounted edge computing box mainly comprises computer hardware equipment such as a CPU (central processing unit), a GPU (graphic processing unit) and the like meeting the running requirements of related algorithms for road detection, and the outer wall of the intelligent vehicle-mounted edge computing box is provided with a hardware interface used for receiving and transmitting various data signals. The project development equipment has the advantages of simple instrument, simple installation and operation, economy and reasonability, and low requirement on measurement environment. Only simple calibration work is required to be carried out regularly, and the precision of the measurement result is high. And because the measurement mode is vehicle-mounted measurement, the measurement speed is high, the efficiency is high, the method is suitable for measuring the road flatness in a large range, and the flatness detection period can be greatly shortened.
Description
Technical Field
The invention relates to the technical field of road detection, in particular to a vehicle-mounted portable lightweight intelligent inspection method and system.
Background
Road transportation is at the beginning of five transportation modes such as highway, railway, aviation, pipeline, water transportation and the like with the advantages of rapidness, convenience and direct door-to-door effect, and occupies an extremely important position in national economic development. By the end of 2019, the total mileage of the existing traffic roads in China exceeds 501 kilometers, and the original roads must be maintained and maintained while the roads are newly built, so that the driving safety is ensured and the operation cost is reduced.
On one hand, the traditional road detection method has many defects, for example, the hand-push type section instrument method and other human working methods have the problems of time and labor consumption and troublesome operation, and the laser detection vehicle and other professional detection equipment are expensive and easily influenced by the environment, so that the large-range high-frequency popularization and use are difficult. On the other hand, the road quality management tasks are respectively shared by departments such as provincial and urban highway administration, road and government offices, local maintenance companies, and traffic department basic construction quality supervision central stations. The problems of complex flow, obvious obstruction and the like exist in data interaction of each link, so that a plurality of detection works are repeatedly performed, and a large amount of manpower and material resource investment is wasted. Therefore, the necessary measures of improving the road service level and ensuring the driving safety are to carry out the normalized daily inspection by using the expressway detection equipment and carry out the unified deployment management on the road quality detection data.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides a vehicle-mounted portable lightweight intelligent inspection method and a vehicle-mounted portable lightweight intelligent inspection system.
The invention provides a vehicle-mounted portable lightweight intelligent inspection system, which comprises the following equipment: the intelligent vehicle-mounted edge computing box mainly comprises computer hardware equipment such as a CPU (central processing unit), a GPU (graphic processing unit) and the like meeting the running requirements of related algorithms for road detection, and the outer wall of the intelligent vehicle-mounted edge computing box is provided with a hardware interface used for receiving and transmitting various data signals.
A vehicle-mounted portable lightweight intelligent inspection method comprises the following steps:
s1: equipment installation: the equipment required by the system is arranged at each part of the vehicle body according to the requirement and the power supply is ensured;
s2: equipment calibration: calibrating a rear high-definition industrial camera, a front 360-degree pan-tilt camera and an acceleration sensor according to requirements, wherein equipment calibration is required to be carried out when the equipment is used for the first time and after the equipment is re-installed; s3: daily detection: after the system is ensured to work normally, the target road section is detected according to a road detection plan, and the detection content can comprise road surface flatness detection, road surface disease detection and accessory facility integrity detection; s4: and (3) data uploading: and uploading the collected road detection data to a back-end database in an online or offline manner in a unified manner to serve as a data source for big data analysis or visual display.
Preferably, the step S1 is to install: at first place vehicle-mounted edge calculation intelligence box inside the vehicle, should ensure that the vehicle goes in-process intelligence box and can not take place to remove on a large scale and the wiring can not drop or break, places and supplies power through the power in the car after accomplishing.
Preferably, the high-definition industrial camera arranged at the rear of the vehicle tail in the step S1 is arranged at the tail of the vehicle body through a suction cup device, the installation position of the camera is not too low, the view field is ensured to cover at least one lane, and the aperture and the focal length of the camera are adjusted; the vehicle-mounted front 360-degree pan-tilt camera is mounted at the front part of a vehicle body and is generally positioned at the front end of a vehicle roof, at least one lane needs to be covered within a view angle range, and an aperture and a camera focal length are adjusted; the acceleration sensor is disposed above the rear axle of the vehicle, it should be ensured that the acceleration sensor is respectively close to two tires, and the installation position thereof should be fixed by means of a bolt or an adhesive tape or the like.
Preferably, the high-precision RTK positioning device in step S1 is placed on the top of the vehicle, and it is required to ensure that the position above the high-precision RTK positioning device is not shielded by other objects so as not to affect the positioning precision; after the equipment is installed, the equipment is required to be connected with a signal transmission line between each equipment and the vehicle-mounted edge computing intelligent box, and whether data flow is smooth and whether the equipment can normally operate is checked.
Preferably, the step S2 is to calibrate: carry out camera calibration to rearmounted high definition industrial camera of rear of a vehicle and on-vehicle leading 360 cloud platform cameras: manufacturing a checkerboard plane plate, wherein the size of each checkerboard is required to be ensured to be not less than 10cm x 10cm, the shape of each checkerboard is required to be a standard square, the edge of each checkerboard is clearly distinguishable, and the number of rows and columns of each checkerboard is required to be not less than 5; placing the checkerboards at different positions within the visual angle range of the camera respectively, taking pictures as calibration data, and ensuring that the calibration data at least comprises one picture of the checkerboards at the upper left corner, the upper right corner, the middle, the lower left corner and the lower right corner of the image respectively, wherein the total number of the calibration data is not less than 10; detecting feature points in all calibration data, namely the corner points of each checkerboard by using an algorithm tool, and solving internal parameters, external parameters and distortion coefficients of the camera under an ideal distortion-free condition by using known checkerboard data; and obtaining an optimal internal parameter, external parameter and distortion parameter matrix by combining the internal parameters, external parameters and distortion coefficients of the cameras of the multiple pictures and using the maximum likelihood estimation optimization result.
Preferably, the step S2 is to calibrate: calibrating the acceleration sensor: selecting 5-10 sections of road sections with known road surface evenness, wherein the international evenness index IRI distribution meets the requirement of uniform distribution between 1-5 as much as possible; fixing an acceleration sensor device right above left and right rear axle wheels in a vehicle trunk; connecting a vehicle-mounted edge computing intelligent box, starting equipment, recording the starting and ending time of a road section, and intercepting calibration data; testing for 2 times in the same direction on the same test road section at the same specified speed (30-80km/h), calculating the power spectral density curve integral of the test road section, and if the difference of the measurement results on the two sides exceeds 10%, continuing to perform spectral density integral calibration until the accuracy requirement is met; respectively measuring the test road sections with uniformly distributed predetermined 5-10 IRI sections, and calculating the integral mean value of the two spectral densities; model fitting is carried out through the known IRI and spectral density integral system to obtain fitting parameters, in order to guarantee accuracy of a test result, the same test speed is recommended to be kept, if the test speed is changed, the test result is corrected according to a speed correction coefficient, the default calculation distance of the system is 500 meters, and flatness calculation is carried out once every 500 meters.
Preferably, in the daily detection in step S3, the detection content corresponding to each sub-device is: the vehicle tail rear high-definition industrial camera is used for detecting the distribution condition of pavement diseases, the detected pavement diseases comprise cracks, pit slots, net cracks, repair, well cover height frame difference, expansion joint damage and the like, the detection principle is that a pavement disease identification model with high detection precision is obtained through an early-stage training image target detection algorithm, and the pavement diseases are quickly identified based on the model; the detection principle is that an affiliated facility identification model with high detection precision is obtained through a pre-training image semantic segmentation algorithm, affiliated facilities in an image are separated based on the model, and then the integrity of the affiliated facilities is judged by detecting the appearance line shape of the affiliated facilities through Hough transform; the acceleration sensor is used for detecting the road surface evenness, the detection principle is that the system response change of the sprung mass and the unsprung mass of the motor vehicle under the influence of the elevation difference is simplified by utilizing a quarter vehicle model, the acceleration change is distributed to wave bands of different frequencies by combining the road surface wave theory and a power spectral density method, and then the international evenness index is effectively estimated by utilizing the acceleration root mean square value.
Preferably, the step S4 data uploading: the data transmission and background processing environment mainly comprises: the system comprises a data receiving module, a WebService module, a JavaScript webpage module, a data calculation module, a database module, a standard module and a report generation module.
Preferably, the data receiving module receives data sent by the acquisition device to a designated folder by using an FTPserver; the WebService module realizes the conversion of a coordinate system by utilizing a Baidu map API; the data calculation module is used for processing the original data and generating detection result data; the database module adopts an Oracle database as background data storage; the report generation module is used for outputting a summarized result to the system, and the summarized result comprises detection road section information, engineering names, detection results and the like; the webpage module is used as a foreground display part, a hundred-degree webpage API is called, calculation results of driving tracks, flatness and disease indexes of collected vehicles are displayed on a foreground hundred-degree map, a background data processing flow is used for receiving data transmitted by various collection equipment, road surface flatness calculation, road surface disease identification and accessory facility integrity detection are carried out by using a processing algorithm, display based on the hundred-degree map API is realized, storage is carried out by using an oracle database, and finally, historical data is combined, and road section maintenance suggestions are given according to relevant specifications.
The beneficial effects of the invention are as follows:
compared with the traditional detection, the vehicle-mounted portable lightweight intelligent inspection method and system have the advantages that the project development equipment is simple and convenient in instrument, simple in installation and operation, economical and reasonable, and low in requirement on the measurement environment. Only simple calibration work is required to be carried out regularly, and the precision of the measurement result is high. And because the measurement mode is vehicle-mounted measurement, the measurement speed is high, the efficiency is high, the method is suitable for measuring the road flatness in a large range, and the flatness detection period can be greatly shortened. In addition, in the system, various wireless sensor network technologies are adopted, so that data acquisition and transmission are more reliable, matched geographic information can be acquired by utilizing GPS equipment, and the GPS equipment can be combined with an electronic map to acquire and display real-time data of an urban road network.
The parts of the device not involved are the same as or can be implemented using prior art.
Drawings
FIG. 1 is a schematic structural diagram of a vehicle-mounted portable lightweight intelligent inspection method and system provided by the invention;
fig. 2 is a schematic structural diagram of a high-definition industrial camera arranged behind a vehicle tail of the vehicle-mounted portable lightweight intelligent inspection method and system provided by the invention;
fig. 3 is a schematic structural diagram of a vehicle-mounted portable lightweight intelligent inspection method provided by the invention.
In the figure: the system comprises a vehicle-mounted front 360-degree tripod head camera, a 2-mounted high-precision RTK positioning device, a 3-mounted edge calculation intelligent box, a 4GPU, a 5CPU, a 6 hardware interface, a 7-vehicle rear high-definition industrial camera, an 8-acceleration sensor and a vehicle-mounted rear high-definition industrial camera.
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.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific aspect
Referring to fig. 2, a vehicle-mounted portable lightweight intelligent inspection system comprises the following devices: the intelligent vehicle edge computing box 3 mainly comprises computer hardware equipment such as a CPU5 and a GPU4 which meet the running requirements of related algorithms for road detection, and the outer wall of the intelligent vehicle edge computing box 3 is provided with a hardware interface 6 used for receiving and transmitting various data signals.
Referring to fig. 1 and 3, a vehicle-mounted portable lightweight intelligent inspection method is based on the vehicle-mounted portable lightweight intelligent inspection system, and is characterized by comprising the following steps:
s1: equipment installation: the equipment required by the system is arranged at each part of the vehicle body according to the requirement and the power supply is ensured;
s2: equipment calibration: calibrating a rear high-definition industrial camera, a front 360-degree pan-tilt camera and an acceleration sensor according to requirements, wherein equipment calibration is required to be carried out when the equipment is used for the first time and after the equipment is re-installed;
s3: daily detection: after the system is ensured to work normally, the target road section is detected according to a road detection plan, and the detection content can comprise road surface flatness detection, road surface disease detection and accessory facility integrity detection;
s4: and (3) data uploading: and uploading the collected road detection data to a back-end database in an online or offline manner in a unified manner to serve as a data source for big data analysis or visual display.
In the present invention, step S1 is the equipment installation: at first place vehicle-mounted edge calculation intelligent box 3 inside the vehicle, should ensure that the vehicle goes in-process intelligent box can not take place to remove on a large scale and the wiring can not drop or break, places and supplies power through the power in the car after accomplishing.
In the invention, the high-definition industrial camera 7 arranged at the rear of the vehicle tail in the step S1 is arranged at the tail of the vehicle body through a sucker device, the installation position of the camera is not too low, the visual field is ensured to cover at least one lane, and the aperture and the camera focal length are adjusted; the vehicle-mounted front 360-degree pan-tilt camera 1 is mounted at the front part of a vehicle body, is generally positioned at the front end of a vehicle roof, at least one lane needs to be covered within a view angle range, and an aperture and a camera focal length are adjusted; the acceleration sensor 8 is disposed above the rear axle of the vehicle, the acceleration sensor 8 should be secured near the two tires, respectively, and its mounting position should be fixed by means of a tool such as a bolt or an adhesive tape.
In the invention, the high-precision RTK positioning device 2 of the step S1 is placed at the top of the vehicle, and the upper part of the high-precision RTK positioning device is required to be protected from being shielded by other objects so as not to influence the positioning precision; after the equipment is installed, the signal transmission lines between the equipment and the vehicle-mounted edge computing intelligent box 3 need to be connected, and whether data flow is smooth and whether the equipment can normally run is checked.
In the invention, step S2 is equipment calibration: the camera calibration is carried out on the rear high-definition industrial camera 7 of the vehicle tail and the vehicle-mounted front 360-degree tripod head camera 1: manufacturing a checkerboard plane plate, wherein the size of each checkerboard is required to be ensured to be not less than 10cm x 10cm, the shape of each checkerboard is required to be a standard square, the edge of each checkerboard is clearly distinguishable, and the number of rows and columns of each checkerboard is required to be not less than 5; placing the checkerboards at different positions within the visual angle range of the camera respectively, taking pictures as calibration data, and ensuring that the calibration data at least comprises one picture of the checkerboards at the upper left corner, the upper right corner, the middle, the lower left corner and the lower right corner of the image respectively, wherein the total number of the calibration data is not less than 10; detecting feature points in all calibration data, namely the corner points of each checkerboard by using an algorithm tool, and solving internal parameters, external parameters and distortion coefficients of the camera under an ideal distortion-free condition by using known checkerboard data; and obtaining an optimal internal parameter, external parameter and distortion parameter matrix by combining the internal parameters, external parameters and distortion coefficients of the cameras of the multiple pictures and using the maximum likelihood estimation optimization result.
In the invention, step S2 is equipment calibration: the acceleration sensor 8 is calibrated: selecting 5-10 sections of road sections with known road surface evenness, wherein the international evenness index IRI distribution meets the requirement of uniform distribution between 1-5 as much as possible; fixing an acceleration sensor 8 device right above left and right rear axle wheels in a vehicle trunk; connecting the vehicle-mounted edge computing intelligent box 3, starting equipment, recording the starting and ending time of a road section, and intercepting calibration data; testing for 2 times along the same direction on the same testing road section at the same specified speed of 30-80km/h, calculating the power spectral density curve integral of the road section, and if the difference of the measurement results on the two sides exceeds 10%, continuing to calibrate the spectral density integral until the accuracy requirement is met; respectively measuring the test road sections with uniformly distributed predetermined 5-10 IRI sections, and calculating the integral mean value of the two spectral densities; model fitting is carried out through the known IRI and spectral density integral system to obtain fitting parameters, in order to guarantee accuracy of a test result, the same test speed is recommended to be kept, if the test speed is changed, the test result is corrected according to a speed correction coefficient, the default calculation distance of the system is 500 meters, and flatness calculation is carried out once every 500 meters.
In the present invention, in the step S3, the detection contents corresponding to each sub-device in the daily detection: the vehicle tail rear high-definition industrial camera 7 is used for detecting the distribution condition of pavement diseases, the detected pavement diseases comprise cracks, pit slots, net cracks, repair, well cover height frame difference, expansion joint damage and the like, the detection principle is that a pavement disease identification model with high detection precision is obtained through an early-stage training image target detection algorithm, and rapid identification of the pavement diseases is carried out on the basis of the model; the detection principle is that an affiliated facility identification model with high detection precision is obtained through a pre-training image semantic segmentation algorithm, affiliated facilities in an image are separated based on the model, and then the integrity of the affiliated facilities is judged by detecting the appearance line shape of the affiliated facilities through Hough transform; the acceleration sensor 8 is used for detecting the road surface evenness, the detection principle is that the quarter car model is used for simplifying the system response change of the sprung mass and the unsprung mass of the motor vehicle under the influence of the elevation difference, the acceleration change is distributed to wave bands with different frequencies by combining the road surface wave theory and the power spectral density method, and then the international evenness index is effectively estimated by using the acceleration root mean square value.
In the invention, step S4 data uploading: the data transmission and background processing environment mainly comprises: the system comprises a data receiving module, a WebService module, a JavaScript webpage module, a data calculation module, a database module, a standard module and a report generation module.
In the invention, a data receiving module adopts FTPserver to receive data sent by acquisition equipment into a specified folder; the WebService module realizes the conversion of a coordinate system by utilizing a Baidu map API; the data calculation module is used for processing the original data and generating detection result data; the database module adopts an Oracle database as background data storage; the report generation module is used for outputting a summarized result to the system, and the summarized result comprises detection road section information, engineering names, detection results and the like; the webpage module is used as a foreground display part, a hundred-degree webpage API is called, calculation results of driving tracks, flatness and disease indexes of collected vehicles are displayed on a foreground hundred-degree map, a background data processing flow is used for receiving data transmitted by various collection equipment, road surface flatness calculation, road surface disease identification and accessory facility integrity detection are carried out by using a processing algorithm, display based on the hundred-degree map API is realized, storage is carried out by using an oracle database, and finally, historical data is combined, and road section maintenance suggestions are given according to relevant specifications.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (7)
1. The utility model provides a system is patrolled and examined to on-vehicle portable lightweight intelligence which characterized in that: the device comprises the following equipment: the intelligent vehicle-mounted edge computing box comprises a rear high-definition industrial camera (7) at the tail of a vehicle, a front 360-degree vehicle-mounted pan-tilt camera (1), an acceleration sensor (8), a high-precision RTK positioning device (2) and a vehicle-mounted edge computing intelligent box (3), wherein the vehicle-mounted edge computing intelligent box (3) mainly comprises a CPU (5) and a GPU (4) which meet the operation requirements of related algorithms for road detection, and a hardware interface (6) used for receiving and transmitting various data signals is arranged on the outer wall of the vehicle-mounted edge computing intelligent box (3);
the intelligent inspection method of the vehicle-mounted portable lightweight intelligent inspection system comprises the following steps:
s1: equipment installation: the equipment required by the system is arranged at each part of the vehicle body according to the requirement and the power supply is ensured;
s2: equipment calibration: calibrating a rear high-definition industrial camera (7) at the tail of the vehicle, a front 360-degree holder camera (1) and an acceleration sensor (8) according to requirements, wherein equipment calibration is required to be performed generally when the vehicle is used for the first time and after the equipment is re-installed;
s3: daily detection: after the system is ensured to work normally, the target road section is detected according to a road detection plan, and the detection content comprises road surface evenness detection, road surface disease detection and accessory facility integrity detection;
s4: and (3) data uploading: uniformly uploading the collected road detection data to a back-end database in an online or offline mode to serve as a data source for big data analysis or visual display;
step S2, calibrating the equipment: carry out camera calibration to rearmounted high definition industry camera of rear of a vehicle (7) and on-vehicle leading 360 cloud platform cameras (1): manufacturing a checkerboard plane plate, wherein the size of each checkerboard is required to be ensured to be not less than 10cm x 10cm, the checkerboard is in a standard square shape, the edge of each checkerboard is clearly distinguishable, and the number of rows and columns of each checkerboard is not required to be less than 5; respectively placing the checkerboards at different positions within the visual angle range of the camera and taking pictures as calibration data, wherein the calibration data at least comprises one picture of the checkerboards positioned at the upper left corner, the upper right corner, the middle, the lower left corner and the lower right corner of the image, and the total number of the calibration data is not less than 10; detecting feature points in all calibration data, namely the corner points of each checkerboard by using an algorithm tool, and solving internal parameters, external parameters and distortion coefficients of the camera under an ideal distortion-free condition by using known checkerboard data; combining the internal parameters, the external parameters and the distortion coefficients of the cameras of the multiple pictures, and obtaining an optimal internal parameter, external parameter and distortion parameter matrix by using a maximum likelihood estimation optimization result;
step S2, calibrating the equipment: the acceleration sensor (8) is calibrated: selecting 5-10 sections of road sections with known road surface evenness, wherein the international evenness index IRI distribution meets the uniform distribution between 1-5; fixing an acceleration sensor (8) device right above left and right rear axle wheels in a vehicle trunk; connecting a vehicle-mounted edge computing intelligent box (3), starting equipment, recording the starting and ending time of a road section, and intercepting calibration data; testing for 2 times along the same direction on the same testing road section at the same specified speed, calculating the power spectral density curve integral of the road section, and if the difference between the two measurement results exceeds 10%, continuing to calibrate the spectral density integral until the precision requirement is met; respectively measuring the test road sections with uniformly distributed predetermined 5-10 IRI sections, and calculating the integral mean value of the two spectral densities; model fitting is carried out through the known IRI and spectral density integral system to obtain fitting parameters, the same testing speed is kept during testing, if the testing speed is changed, the testing result is corrected according to a speed correction coefficient, the default calculation distance of the system is 500 meters, and flatness calculation is carried out once every 500 meters.
2. The vehicle-mounted portable lightweight intelligent inspection system according to claim 1, wherein the step S1 equipment installation: at first place vehicle-mounted edge calculation intelligence box (3) inside the vehicle, should ensure that the vehicle goes in-process intelligence box and can not take place to remove on a large scale and the wiring can not drop or break, places and supplies power through the power in the car after accomplishing.
3. The vehicle-mounted portable lightweight intelligent inspection system according to claim 2, wherein the high-definition industrial camera (7) arranged behind the vehicle tail in the step S1 is arranged at the tail of the vehicle body through a sucker device, the installation position of the camera is not too low, the view field is ensured to cover at least one lane, and the aperture and the camera focal length are adjusted; the vehicle-mounted front 360-degree pan-tilt camera (1) is arranged at the front part of a vehicle body and is generally positioned at the front end of a vehicle roof, at least one lane needs to be covered within a view angle range, and an aperture and a camera focal length are adjusted; the acceleration sensor (8) is arranged above the rear axle of the vehicle, the acceleration sensor (8) is respectively close to the two tires, and the installation position of the acceleration sensor is fixed by using a bolt or an adhesive tape tool.
4. The vehicle-mounted portable lightweight intelligent inspection system according to claim 3, wherein the high-precision RTK positioning device (2) of the step S1 is placed on the top of the vehicle, and the position above the high-precision RTK positioning device is protected from being shielded by other objects so as not to affect the positioning precision; after the equipment is installed, the signal transmission lines between the equipment and the vehicle-mounted edge computing intelligent box (3) need to be connected, and whether data flow is smooth and whether the equipment can normally run or not is checked.
5. The vehicle-mounted portable lightweight intelligent inspection system according to claim 1, wherein the detection contents corresponding to the sub-devices in the daily detection in the step S3 are as follows: the vehicle tail rear high-definition industrial camera (7) is used for detecting the distribution condition of pavement diseases, the detected pavement diseases comprise cracks, pit slots, net cracks, repair, high frame difference of a well cover and damage of an expansion joint, the detection principle is that a pavement disease identification model with high detection precision is obtained through an early-stage training image target detection algorithm, and rapid identification of the pavement diseases is carried out based on the model; the detection principle is that an accessory facility identification model with high detection precision is obtained through a pre-training image semantic segmentation algorithm, the accessory facilities in an image are separated based on the model, and the integrity of the accessory facilities is judged by detecting the appearance line shape of the accessory facilities through Hough transform; the acceleration sensor (8) is used for detecting the road surface evenness, the detection principle is that the system response change of the sprung mass and the unsprung mass of the motor vehicle under the influence of the elevation difference is simplified by utilizing a quarter vehicle model, the acceleration change is distributed to wave bands with different frequencies by combining the road surface wave theory and the power spectral density method, and then the international evenness index is effectively estimated by utilizing the acceleration root mean square value.
6. The vehicle-mounted portable lightweight intelligent inspection system according to claim 5, wherein the step S4 data uploading: the data transmission and background processing environment mainly comprises: the system comprises a data receiving module, a WebService module, a JavaScript webpage module, a data calculation module, a database module, a standard module and a report generation module.
7. The vehicle-mounted portable lightweight intelligent inspection system according to claim 6, wherein the data receiving module receives data sent by the acquisition device to a designated folder by using FTPserver; the WebService module realizes the conversion of a coordinate system by utilizing a Baidu map API; the data calculation module is used for processing the original data and generating detection result data; the database module adopts an Oracle database as background data storage; the report generation module is used for outputting a summarized result to the system, and the summarized result comprises detection road section information, engineering names and detection results; the webpage module is used as a foreground display part, a hundred-degree webpage API is called, calculation results of driving tracks, flatness and disease indexes of collected vehicles are displayed on a foreground hundred-degree map, a background data processing flow is used for receiving data transmitted by various collection equipment, road flatness calculation, road surface disease identification and accessory facility integrity detection are carried out by using a processing algorithm, display based on the hundred-degree map API is realized, an Oracle database is used for storage, and finally, historical data is combined, and road section maintenance suggestions are given according to relevant specifications.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011601294.5A CN112726351B (en) | 2020-12-30 | 2020-12-30 | Vehicle-mounted portable lightweight intelligent inspection method and system |
| NL2030322A NL2030322B1 (en) | 2020-12-30 | 2021-12-28 | Vehicle-mounted portable lightweight intelligent inspection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011601294.5A CN112726351B (en) | 2020-12-30 | 2020-12-30 | Vehicle-mounted portable lightweight intelligent inspection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112726351A CN112726351A (en) | 2021-04-30 |
| CN112726351B true CN112726351B (en) | 2021-08-27 |
Family
ID=75610059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011601294.5A Active CN112726351B (en) | 2020-12-30 | 2020-12-30 | Vehicle-mounted portable lightweight intelligent inspection method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112726351B (en) |
| NL (1) | NL2030322B1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114592411B (en) * | 2022-03-29 | 2023-05-23 | 中国矿业大学 | Carrier parasitic type intelligent inspection method for highway damage |
| CN116448016A (en) * | 2023-04-26 | 2023-07-18 | 成都智达万应科技有限公司 | Intelligent rapid detection system and detection vehicle with same |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5323647A (en) * | 1993-01-05 | 1994-06-28 | Pave Tech Inc. | Apparatus and method for measuring height variations in a surface |
| CN104695311A (en) * | 2014-12-31 | 2015-06-10 | 广东光阵光电科技有限公司 | On-board monitoring method and system for road condition |
| CN105019344A (en) * | 2015-07-21 | 2015-11-04 | 中山市拓维电子科技有限公司 | Road surface roughness monitor |
| 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 |
| CN110490940A (en) * | 2019-08-15 | 2019-11-22 | 北京迈格威科技有限公司 | Camera calibration method and apparatus based on gridiron pattern single image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN211734978U (en) * | 2019-12-02 | 2020-10-23 | 浙江交通职业技术学院 | Unmanned rapid comprehensive road detection vehicle system |
-
2020
- 2020-12-30 CN CN202011601294.5A patent/CN112726351B/en active Active
-
2021
- 2021-12-28 NL NL2030322A patent/NL2030322B1/en active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5323647A (en) * | 1993-01-05 | 1994-06-28 | Pave Tech Inc. | Apparatus and method for measuring height variations in a surface |
| CN104695311A (en) * | 2014-12-31 | 2015-06-10 | 广东光阵光电科技有限公司 | On-board monitoring method and system for road condition |
| CN105019344A (en) * | 2015-07-21 | 2015-11-04 | 中山市拓维电子科技有限公司 | Road surface roughness monitor |
| 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 |
| CN110490940A (en) * | 2019-08-15 | 2019-11-22 | 北京迈格威科技有限公司 | Camera calibration method and apparatus based on gridiron pattern single image |
Also Published As
| Publication number | Publication date |
|---|---|
| NL2030322B1 (en) | 2022-10-31 |
| NL2030322A (en) | 2022-07-21 |
| CN112726351A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109716108B (en) | Bituminous paving disease detecting system based on two mesh image analysis | |
| CN109870456B (en) | Rapid detection system and method for road surface health condition | |
| CN104567708B (en) | Full section of tunnel high speed dynamical health detection means and method based on active panoramic vision | |
| CN112985311B (en) | Vehicle-mounted portable lightweight intelligent inspection method and system | |
| WO2022206978A1 (en) | Roadside millimeter-wave radar calibration method based on vehicle-mounted positioning apparatus | |
| CN103743383B (en) | A kind of Automatic extraction method for road information based on a cloud | |
| CN103778681A (en) | Vehicle-mounted high-speed road inspection system and data acquisition and processing method | |
| CN103499343B (en) | Automatic classifying and identifying method for road line point cloud based on three-dimensional laser reflection strength | |
| CN112965077B (en) | Road inspection system and method based on vehicle-mounted laser radar | |
| CN112726351B (en) | Vehicle-mounted portable lightweight intelligent inspection method and system | |
| CN107944018A (en) | A kind of automatic quality detecting method of map vector positional precision based on laser point cloud data | |
| CN103714603B (en) | Based on the bus passenger flow statistical system of infrared distance sensor | |
| CN103499337B (en) | Vehicle-mounted monocular camera distance and height measuring device based on vertical target | |
| CN111272139B (en) | Monocular vision-based vehicle length measuring method | |
| WO2019080380A1 (en) | Wheelmark transverse distribution measuring system and method | |
| CN202853580U (en) | Apparatus for dynamic measurement of vehicle outer contour dimension and weight | |
| CN114118241A (en) | Road information detection system based on vehicle-mounted radar | |
| CN103810855A (en) | Multi-characteristic quantity comprehensive traffic detection system oriented to multi-user group | |
| CN108681337A (en) | A kind of culvert or the special inspection unmanned plane of bridge and unmanned plane visiting method | |
| CN208027170U (en) | A kind of power-line patrolling unmanned plane and system | |
| CN104732870A (en) | Measurement method and system for manufacturing large-scale map | |
| CN113012427B (en) | Improved vehicle-mounted lightweight inspection system and method | |
| CN203966335U (en) | Many characteristic quantities comprehensive traffic detection system of facing multiple users group | |
| CN116635739A (en) | Road side millimeter wave radar calibration method based on vehicle-mounted positioning device | |
| CN113567764A (en) | Highway ETC intelligent detection vehicle and calibration method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |