CN113362284B - Method for measuring difference of road well frame - Google Patents
Method for measuring difference of road well frame Download PDFInfo
- Publication number
- CN113362284B CN113362284B CN202110554307.6A CN202110554307A CN113362284B CN 113362284 B CN113362284 B CN 113362284B CN 202110554307 A CN202110554307 A CN 202110554307A CN 113362284 B CN113362284 B CN 113362284B
- Authority
- CN
- China
- Prior art keywords
- well lid
- rms
- well
- image
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000000007 visual effect Effects 0.000 claims description 18
- 230000009466 transformation Effects 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 9
- 238000003702 image correction Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000009432 framing Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 abstract 1
- 238000007689 inspection Methods 0.000 description 21
- 238000001514 detection method Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000011083 cement mortar Substances 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- 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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
- G06T3/608—Rotation of whole images or parts thereof by skew deformation, e.g. two-pass or three-pass rotation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a method for measuring the frame difference of a road, which comprises the following steps: acquiring effective well lid data and vibration data corresponding to the effective well lid data according to image data and vibration data acquired by a vehicle; and calculating the rms index of the Z-axis component of the vibration data of the effective well lid, and correcting the speed to obtain an equivalent rms value. Compared with the prior art, the method has the advantages of high algorithm efficiency, multiple data dimensions, strong anti-interference capability, labor cost saving and the like, and is beneficial to improving the effect of maintaining and managing the frame difference of the pavement well.
Description
Technical Field
The invention relates to the technical field of road performance detection, in particular to a road well frame difference measuring method.
Background
The flatness of the municipal road engineering pavement is closely related to the elevation of the difference of various along-street pipeline inspection well frames, and the well frame difference refers to the relative height difference between the well frame of the inspection well cover on the road pavement and the road surface. Unevenness on the road surface directly influences the service function of road, can influence the travelling comfort of people's trip on the one hand, more can influence driving safety when on the other hand is serious. The stubborn disease exists on the road for a long time and becomes a common quality disease of urban pavement engineering. Therefore, in the road engineering quality inspection, the height difference between the well frame and the road surface (referred to as well frame difference for short) is listed as a project to be inspected.
As is known, when the connection between the inspection well and the road surface is not smooth, the phenomenon of vehicle jumping can be caused, the vehicle speed is often influenced, meanwhile, the impact of the vehicle on the surrounding road surface is increased, the road surface around the inspection well is damaged or pits appear too early, then the high projection or low depression of the inspection well forms the obstacle of the road surface, and the condition of traffic accidents caused by the fact that the inspection well is hidden in the driving can often appear. The disease condition that the formed well frame difference exceeds the allowable deviation is shown on the asphalt pavement, and the reason is not limited to several aspects:
(1) The backfill around the inspection well is not solid, and the density of each structural layer of the pavement is not enough, so that the pavement around the inspection well sinks.
(2) When the inspection well is lifted in construction, the inspection well frame is not matched with the elevation of the road surface and the transverse and longitudinal slopes of the road surface.
(3) The inspection well frame is lack of sufficient cement mortar and the cement concrete is firm in consolidation, and moves after the vehicle is subjected to pressure, so that the pavement structure around the well is broken and continues to develop.
(4) Due to defects of foundation and masonry quality of the inspection well, after the pavement is used for a long time, the periphery of the inspection well can generate settlement of different degrees.
At present, the municipal road pavement maintenance department mainly adopts a manual patrol mode to solve the problem of poor well frame. The inspection specialist regularly drives vehicles to pass through roads in the jurisdiction area, observes the well frame difference conditions on the roads, records the street positions corresponding to the well cover regions with serious degrees, photographs and reports the pictures to the highway management department, and the pavement maintenance is completed. However, the manual inspection-based troubleshooting method is time-consuming and labor-consuming, and due to dynamic detection, the visual strength is low, the scene interference is serious, the screening efficiency is low, the coverage rate is insufficient, and the time period is long; meanwhile, the regular local road section inspection mode is poor in overall monitoring strength, the inspection result of the road surface condition is a manual record, and time is needed for subsequently packaging structured data, so that the uploading instantaneity is low, and the maintenance intensity of a traffic management department is influenced.
Disclosure of Invention
The invention aims to provide a method for measuring the difference of the road well frame so as to overcome the defects of the prior art.
The purpose of the invention can be realized by the following technical scheme:
a method for measuring the difference between the frames of a road and a manhole cover on the road surface is disclosed, wherein the difference between the frames is the relative height difference between the frame of the manhole cover and the road surface, and the manhole cover is the manhole cover, and the method comprises the following steps:
acquiring effective well lid data and vibration data corresponding to the effective well lid according to image data and vibration data acquired by a vehicle;
and calculating the rms index of the Z-axis component of the vibration data of the effective well lid, and correcting the speed to obtain an equivalent rms value.
Preferably, the step of calculating the rms index of the Z-axis component of the vibration data comprises:
extracting t second vibration data in a collection time period corresponding to the effective well lid in the vibration data, calculating the root mean square value of the Z-axis component of each second vibration data, and taking the maximum value as an rms index:
rms_max＝max(Z 1 ，Z 2 ，…，Z t-1 ，Z t )
wherein rms _ max is the rms index, Z t Is the root mean square value of the Z-axis component of time t.
Preferably, Z is t The calculation formula of (2) is as follows:
wherein z is tn Is the nth Z-axis component of time t, and n is the number of components per second.
Preferably, the step of performing speed correction on the rms index comprises:
converting the rms index calculated under all vehicle speed conditions into an equivalent rms value under the equivalent speed, wherein the calculation formula is as follows
Wherein rms _ max revised Is an equivalent rms value, rms max Is an rms index, v e And v is the current speed corresponding to the rms index.
Preferably, the specific step of acquiring effective well lid data and vibration data corresponding to the effective well lid data includes:
acquiring image data and vibration data acquired by a vehicle;
converting the image data into a overlooking visual angle, identifying the well lid in the image data, and acquiring the size and the position of the well lid;
and (4) judging the validity of the well lid, matching the image acquisition timestamp corresponding to the effective well lid with the vibration data, and acquiring the vibration data of the effective well lid.
Preferably, the specific step of converting the image data into a top view includes:
the image data collected by the vehicle is an oblique visual angle, the image data is processed by using an image correction algorithm, the original image is projected to a new visual plane through a perspective transformation matrix, a perspective transformation matrix with a unique angle is set for the same vehicle and the same camera, perspective transformation is completed on pixel point coordinates on the image, and the image data of an overlooking visual angle is output.
Preferably, the specific step of identifying the manhole cover in the image data includes:
identifying the well lid in the image data by adopting a computer vision algorithm, inputting the image data of the overlooking visual angle into the computer vision algorithm, detecting the image with the well lid, framing out a circumscribed rectangle of the well lid on the image with the well lid, outputting the length a and the width b of the circumscribed rectangle as the size of the well lid, and outputting a distance d between the center of the circumscribed rectangle and two pixels of a left lane line and a right lane line of the image 1 ，d 2 As relative position information.
Preferably, when validity judgment is carried out on the well lid, a virtual wheel track belt is established, and the well lid with the position intersected with the virtual wheel track belt is an effective well lid.
Preferably, the virtual wheel track is as follows:
the pixel distance between the left lane line and the right lane line in the image data of the overlooking visual angle is l, an area within the distance of l/3 pixel from the left lane line and the distance of l/3 pixel from the right lane line is taken as a virtual wheel track,
the judgment standard of the effective well lid is as follows:
well lid position satisfies d 1 < l/3+a/2 or d 2 The well cover of < l/3+a/2 is an effective well cover, wherein d 1 For the pixel distance of the external rectangle of the well lid from the left lane line, d 2 The well lid is externally connected with the pixel distance of the rectangle distance from the right lane line.
Preferably, the measuring method further comprises the following steps:
and (5) carrying out well frame difference degree grading, giving an rms index after speed correction according to the fitting relation between the sample well frame difference degree and the rms index of the vibration data, and outputting the well frame difference degree grading.
Compared with the prior art, the invention has the following advantages:
1. the well lid image acquisition system can process the acquired well lid image and vibration data, can effectively use rms indexes to express the height of the well frame difference, visually reflect the vibration condition of vehicles passing through the well lid area, reflect the degree grade of the well frame difference on the side surface, greatly improve the acquisition efficiency of the road well frame difference, can be quickly deployed and applied to the domestic municipal road inspection business, realize efficient and stable well lid detection, and reduce the labor cost of inspection and measurement of the well frame difference.
2. The invention adopts image processing and computer methods to analyze the image data of the front view and the back view acquired by the industrial camera, thereby improving the efficiency of image processing, greatly reducing manual operation, quickly identifying the well lid in the image, outputting the size and the relative position information of the well lid, and further combining vibration data to acquire the well frame difference, thereby improving the detection efficiency and the accuracy of the well frame difference;
3. according to the invention, by a data fusion method, the image data and the vibration data are fully utilized, and the omnibearing and multi-angle data support is provided for the well frame difference measurement and the degree grading, so that the reexamination and the continuous tracking at any time are facilitated, and the timeliness and the reliability of the well frame difference measurement are improved while the accuracy is met.
4. The vibration data acquired by the triaxial acceleration sensor is utilized to visually reflect the vibration condition of the vehicle passing through the manhole cover area, the side surface reflects the degree grade of the well frame difference, errors of manual judgment of inspection specialists are avoided, and the vibration data acquisition method has more persuasion and practical value.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a schematic layout diagram of a data acquisition device according to the present invention;
FIG. 3 is a schematic diagram of an image correction algorithm according to the present invention;
FIG. 4 is a schematic view of a computer vision algorithm recognition of the present invention;
FIG. 5 is a schematic diagram illustrating virtual track determination according to the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. Note that the following description of the embodiments is merely a substantial example, and the present invention is not intended to be limited to the application or the use thereof, and is not limited to the following embodiments.
Examples
A method for measuring the difference between a road well frame and a road surface is disclosed, wherein the well frame difference refers to the relative height difference between the well frame of a well cover on the road surface and the road surface, the well cover in the invention refers to the well cover, and as shown in figure 1, the method specifically comprises the following steps:
s1: and acquiring data.
As shown in FIG. 2, the invention utilizes light-weight acquisition equipment which can be deployed on any vehicle to acquire data, and comprises an on-vehicle industrial camera for acquiring front view image data and rear view image data, a triaxial acceleration sensor for acquiring vibration data and necessary fixed components, wherein the data acquired at the same time are ensured to have the same timestamp label.
In this embodiment, the forward-looking image data is used to identify and acquire the well frame difference.
Step S2: and carrying out well lid identification and positioning, converting the image data into an overlooking visual angle, identifying the well lid in the image data, and acquiring the size and the position of the well lid.
The method comprises the steps of acquiring image data of an oblique view angle by a vehicle, processing the image data by using an image correction algorithm, projecting an original image to a new view plane through a transformation matrix, setting a perspective transformation matrix with a unique angle for erecting the same camera of the same vehicle, completing perspective transformation on pixel point coordinates on the image, and outputting the image data of the overlooking view angle. As shown in fig. 3, the left side is the original front view image, and the right side is the front view image of the top view angle corrected by the image correction algorithm.
Because the acquisition equipment on the vehicle is obliquely erected, the acquired image data is an oblique visual angle, the image data is processed and subjected to perspective transformation by using an image correction algorithm, the original image is projected to a new visual plane through a 3 x 3 transformation matrix, the perspective distortion of distance or inclination caused by the inclination assumption of a camera is eliminated, the same camera erection angle of the same vehicle has a unique transformation matrix, the perspective transformation matrix is given, the perspective transformation can be completed on the pixel point coordinates on the image, and the overlooking visual angle is output, and the specific transformation formula is as follows:
wherein u and v are original image pixel coordinates, w is homogeneous coordinates, w ' is transformed homogeneous coordinates, x ' and y ' are transformed image physical coordinates, a ii For the transform coefficients, x, y are the physical coordinates of the finally acquired image with the relationship x = x '/w', y = y '/w', a ii Are transform coefficients, homogeneous coordinates.
After the image data is converted into the overlooking visual angle, the identification of the well lid in the image can be carried out.
In this embodiment, a computer vision algorithm is used to identify a well lid in image data, the corrected image data of the overlooking view angle is input, an image with the well lid is detected, an external rectangle of the well lid is framed on the image with the well lid, the length a and the width b of the external rectangle are output as the size of the well lid, and the distance d between the center of the external rectangle and two pixels of the left lane line and the right lane line of the image is output 1 ，d 2 As relative position information. The computer vision algorithm includes: YOLOv1, YOLOv2, YOLOv3, SSD, and the like. As shown in fig. 4, the left side is a front view image of the overlooking view angle corrected by using the image correction algorithm, and a solid frame of the edge of the manhole cover in the right side image is a circumscribed rectangle of the manhole cover.
In this embodiment, the YOLOv3 algorithm identifies the manhole cover.
And step S3: carry out the validity judgement of well lid, when carrying out validity judgement to the well lid, establish virtual wheel track area, the crossing well lid in position and virtual wheel track area is effective well lid, matches the image acquisition timestamp that effective well lid corresponds with vibration data, acquires the vibration data of effective well lid.
Specifically, the virtual wheel track is: and taking an area within a distance of l/3 pixel from the left lane line and a distance of l/3 pixel from the right lane line as a virtual wheel track. As shown in fig. 5, the left side is a front view image of the top view angle corrected by the image correction algorithm, and the dashed frame in the right side image is a virtual circular trace band.
The judgment standard of the effective well lid is as follows: well lid position satisfies d 1 < l/3+a/2 or d 2 The well cover of < l/3+a/2 is an effective well cover, wherein d 1 For the pixel distance of the external rectangle of well lid apart from the left lane line, d 2 The well lid is externally connected with the pixel distance of the rectangle distance from the right lane line.
In step S3 of this embodiment, only the forward-looking image data is judged to be an effective manhole cover, the image acquisition timestamps corresponding to the effective manhole cover are matched, then the vibration data is segmented according to the timestamps, the image acquisition time corresponding to the effective manhole cover and c seconds before and after the image acquisition time are obtained as the acquisition time period of the effective manhole cover, and vibration data of 11 seconds is adopted in this embodiment for 5 seconds before and after the image acquisition time period. For each second, a component of the Z-axis is segmented from the vibration data acquired by the three-axis acceleration sensor.
And step S4: and performing well frame difference measurement. And calculating the rms index of the Z-axis component of the vibration data, and correcting the speed to obtain the equivalent rms index.
In the method, the rms index of the Z-axis component of the vibration data of the effective well lid is used for representing the magnitude degree of the well frame difference of the effective well lid, and the equivalent rms index is obtained. The rms index of the vehicle vibration data can be used for evaluating the bumping degree of the vehicle from the road surface, generally, the rms index passing through a flat road surface is basically consistent and can be ignored in a lower degree, but the rms index passing through an effective well cover has larger difference and has positive correlation with the size of the well frame difference, meanwhile, the bumping degree can be uniformized to the same standard by the equivalent rms index, and therefore the equivalent rms index can uniformly represent the size of the well frame difference.
The step of calculating the rms index of the Z-axis component of the vibration data includes:
extracting t second vibration data in a collection time period corresponding to the effective well lid in the vibration data, calculating the root mean square value of the Z-axis component of each second vibration data, and taking the maximum value as an rms index:
rms_max＝max(Z 1 ，Z 2 ，…，Z t-1 ，Z t )
wherein rms _ max is the rms index, Z t Is the root mean square value of the Z-axis component of time t, in this embodiment, t =11.
And wherein, in the above-mentioned method,
wherein z is tn Is the nth Z-axis component of time t, and n is the number of components per second.
And (3) carrying out speed correction on the obtained rms index to obtain an equivalent rms value:
the rms index calculated under all vehicle speed conditions is converted into an equivalent rms value under the equivalent speed, and the calculation formula is as follows
Wherein rms _ max revised Is the equivalent rms value, rms max Is an rms index, v e And v is the current speed corresponding to the rms index.
In this embodiment, so far, the equivalent rms value corresponding to the effective well lid is obtained and used as a measurement standard of the well frame difference, further, in order to facilitate classification of the well frame difference of the well lid and obtain the grade of the well frame difference corresponding to the well lid, step S5 is introduced: and (5) carrying out well frame difference degree grading, giving an rms index after speed correction according to the fitting relation between the sample well frame difference degree and the rms index of the vibration data, and outputting the well frame difference degree grading.
In the embodiment, a plurality of well frame differences with different heights are collected as samples, the levels of the well frame differences are marked in a grading mode, the standard score is 1-10, the larger the number is, the larger the well frame difference is, the more serious the well frame difference is, and the precision is 0.1. And obtaining the equivalent rms values of the well lids calculated through the step S2-4. And fitting by taking the equivalent rms value after the speed correction as an independent variable and well frame differential degree grading as a dependent variable to obtain:
d is the well frame difference grade and m and n are calculation parameters as a well frame difference grade grading function. And then, inputting the equivalent rms value of any effective well lid after speed correction, and acquiring the difference range grade of the well frame according to the grading function D.
In addition, in the embodiment, in order to improve the detection accuracy and ensure the well lid image identification accuracy, the artificial well frame difference degree is rechecked. Matching the image acquisition time stamps corresponding to the effective well lids, extracting the back view image data in the area near the time stamps of-2 to +3 seconds by using time dislocation, acquiring the overlook images of the section of back view image data, and performing artificial well frame difference degree recheck, wherein the recheck content comprises whether a well frame exists in the image and whether the actual size of the well frame difference is consistent with the predicted size.
The above embodiments are merely examples and do not limit the scope of the present invention. These embodiments may be implemented in other various manners, and various omissions, substitutions, and changes may be made without departing from the technical spirit of the present invention.
Claims (4)
1. A road well frame difference measuring method is characterized by comprising the following steps:
acquiring effective well lid data and vibration data corresponding to the effective well lid according to image data and vibration data acquired by a vehicle;
calculating the rms index of the Z-axis component of the vibration data of the effective well lid, and performing speed correction to obtain an equivalent rms value;
specifically, the concrete steps of obtaining effective well lid data and vibration data corresponding to the effective well lid data include:
acquiring image data and vibration data acquired by a vehicle;
converting the image data into a overlooking visual angle, identifying the well lid in the image data, and acquiring the size and the position of the well lid;
judging the validity of the well lid, matching the image acquisition timestamp corresponding to the valid well lid with the vibration data, and acquiring the vibration data of the valid well lid;
when the effectiveness of the well lid is judged, a virtual wheel track belt is established, and the well lid with the position crossed with the virtual wheel track belt is the effective well lid;
the virtual wheel track belt is as follows:
the pixel distance between the left lane line and the right lane line in the image data of the overlooking visual angle is l, an area within the distance of l/3 pixel from the left lane line and the distance of l/3 pixel from the right lane line is taken as a virtual wheel track,
the judgment standard of the effective well lid is as follows:
well lid position satisfies d 1 < l/3+a/2 or d 2 The well cover less than l/3+a/2 is an effective well cover, wherein a is the length of a well cover external rectangle, and d 1 For the pixel distance of the external rectangle of well lid apart from the left lane line, d 2 The pixel distance from the external rectangle of the well lid to the right lane line is obtained;
the step of calculating the rms index of the Z-axis component of the vibration data includes:
extracting t second vibration data in a collection time period corresponding to the effective well lid in the vibration data, calculating the root mean square value of the Z-axis component of each second vibration data, and taking the maximum value as an rms index:
rms_max＝max(Z 1 ，Z 2 ，…，Z t-1 ，Z t )
wherein rms _ max is the rms index, Z t Is the root mean square value of the Z-axis component of time t,
z is t The calculation formula of (2) is as follows:
wherein z is tn Is the nth Z-axis component of time t, n is the number of components per second,
the step of performing speed correction on the rms index comprises the following steps:
the rms index calculated under all vehicle speed conditions is converted into an equivalent rms value under the equivalent speed, and the calculation formula is as follows
Wherein, rms _ max revised Is an equivalent rms value, rms max Is an rms index, v e And v is the current speed corresponding to the rms index.
2. The method as claimed in claim 1, wherein the step of converting the image data into a top view comprises:
the image data collected by the vehicle is an oblique visual angle, the image data is processed by using an image correction algorithm, the original image is projected to a new visual plane through a perspective transformation moment, a perspective transformation matrix with a unique angle is set for the same camera of the same vehicle, the perspective transformation is completed on the pixel point coordinates of the image, and the image data of the overlooking visual angle is output.
3. The method of claim 1, wherein the step of identifying the manhole cover in the image data comprises:
identifying the well lid in the image data by adopting a computer vision algorithm, inputting the image data of the overlooking visual angle into the computer vision algorithm, detecting the image with the well lid, framing out a circumscribed rectangle of the well lid on the image with the well lid, outputting the length a and the width b of the circumscribed rectangle as the size of the well lid, and outputting a distance d between the center of the circumscribed rectangle and two pixels of a left lane line and a right lane line of the image 1 ，d 2 As relative position information.
4. The method for measuring the difference between the well frames of the road according to claim 1, wherein the method for measuring the difference between the well frames of the road further comprises the following steps:
and (5) carrying out well frame difference degree grading, giving an rms index after speed correction according to the fitting relation between the sample well frame difference degree and the rms index of the vibration data, and outputting the well frame difference degree grading.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110554307.6A CN113362284B (en) | 2021-05-20 | 2021-05-20 | Method for measuring difference of road well frame |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110554307.6A CN113362284B (en) | 2021-05-20 | 2021-05-20 | Method for measuring difference of road well frame |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113362284A CN113362284A (en) | 2021-09-07 |
| CN113362284B true CN113362284B (en) | 2023-04-07 |
Family
ID=77527110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110554307.6A Active CN113362284B (en) | 2021-05-20 | 2021-05-20 | Method for measuring difference of road well frame |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113362284B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107905073A (en) * | 2017-11-09 | 2018-04-13 | 南京中高知识产权股份有限公司 | The method knead dough smoothness measuring equipment of straight line laser profile scanning surface evenness |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106840049B (en) * | 2016-12-16 | 2019-02-05 | 东南大学 | Pavement quality ranking method based on built-in three axis acceleration sensor smart phone |
| CN208149168U (en) * | 2018-03-14 | 2018-11-27 | 北京汽车股份有限公司 | Vehicle crosses well lid DAS (Driver Assistant System) and vehicle |
| CN109934452A (en) * | 2019-01-21 | 2019-06-25 | 上海同济检测技术有限公司 | Road Comfort Evaluation method based on multi-source data |
| CN110728650B (en) * | 2019-08-27 | 2023-04-18 | 深圳大学 | Well lid depression detection method based on intelligent terminal and related equipment |
| CN111339905B (en) * | 2020-02-22 | 2022-07-08 | 郑州铁路职业技术学院 | CIM well lid state visual detection system based on deep learning and multiple visual angles |
-
2021
- 2021-05-20 CN CN202110554307.6A patent/CN113362284B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107905073A (en) * | 2017-11-09 | 2018-04-13 | 南京中高知识产权股份有限公司 | The method knead dough smoothness measuring equipment of straight line laser profile scanning surface evenness |
Non-Patent Citations (1)
| Title |
|---|
| 乔瑞萍 ; 孙贺 ; 董员臣 ; 王方 ; .基于多特征融合的井盖检测系统实现.电子技术应用.2018,(第6期),第50-53页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113362284A (en) | 2021-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103778681B (en) | A kind of vehicle-mounted highway cruising inspection system and data acquisition and disposal route | |
| KR101926561B1 (en) | Road crack detection apparatus of patch unit and method thereof, and computer program for executing the same | |
| Koch et al. | Pothole detection in asphalt pavement images | |
| JP6713505B2 (en) | Pavement information collection and inspection system, pavement information collection and inspection method, and program | |
| WO2022089194A1 (en) | Millimeter-wave radar data-based lane line detection method | |
| CN109064495A (en) | A kind of bridge floor vehicle space time information acquisition methods based on Faster R-CNN and video technique | |
| US11593952B2 (en) | Structural vibration monitoring method based on computer vision and motion compensation | |
| CN110929676A (en) | Deep learning-based real-time detection method for illegal turning around | |
| CN112070756B (en) | Three-dimensional road surface disease measuring method based on unmanned aerial vehicle oblique photography | |
| WO2019080380A1 (en) | Wheelmark transverse distribution measuring system and method | |
| CN103310459A (en) | Three-dimensional information based detection algorithm for cement concrete pavement structure depth | |
| KR20200007165A (en) | Pot-hole detection system using vision sensor mounted on unmanned air vehicle, and method for the same | |
| JP4025161B2 (en) | Flow velocity distribution measurement system, flow velocity distribution measurement method, flow velocity distribution measurement program, flow rate measurement system, flow rate measurement method, and flow rate measurement program | |
| CN113362284B (en) | Method for measuring difference of road well frame | |
| CN116631187B (en) | Intelligent acquisition and analysis system for case on-site investigation information | |
| CN116399302B (en) | Method for monitoring dynamic compaction settlement in real time based on binocular vision and neural network model | |
| CN112254701B (en) | Vehicle-mounted bridge head vehicle jump detection and analysis system and method thereof | |
| CN110969103B (en) | Method for measuring length of highway pavement disease based on PTZ camera | |
| CN113761264A (en) | Infrastructure construction mobile intelligent patrol equipment and intelligent management method | |
| Fakhri et al. | Application of UAV photogrammetry in obtaining qualitative road pavement information | |
| CN111595859A (en) | Bridge and culvert damage detection method and damage detection and management system | |
| JAMES | THE AUTOMATED DISTRESS DETECTION IN PAVEMENTS-A LITERATURE REVIEW ON THE INNOVATION METHOD | |
| Jahanshahi et al. | A novel system for road surface monitoring using an inexpensive infrared laser sensor | |
| Meinderts et al. | Clearance measurement validation for highway infrastructure with use of lidar point clouds | |
| CN117490577B (en) | Method for measuring railway ballasted track ballasted particle migration |
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 |