CN115271114A - Method and equipment for maintaining road surface in tunnel - Google Patents
Method and equipment for maintaining road surface in tunnel Download PDFInfo
- Publication number
- CN115271114A CN115271114A CN202210809441.0A CN202210809441A CN115271114A CN 115271114 A CN115271114 A CN 115271114A CN 202210809441 A CN202210809441 A CN 202210809441A CN 115271114 A CN115271114 A CN 115271114A
- Authority
- CN
- China
- Prior art keywords
- road surface
- tunnel
- damage
- traffic flow
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 58
- 238000012423 maintenance Methods 0.000 claims abstract description 51
- 230000008439 repair process Effects 0.000 claims description 39
- 238000012549 training Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 238000005336 cracking Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2471—Distributed queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- 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
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Computer Security & Cryptography (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a method and equipment for maintaining a road surface in a tunnel, and belongs to the technical field of road maintenance. The method comprises the steps of obtaining a plurality of real-time road surface monitoring images and corresponding collecting information from image collecting equipment, inputting each road surface monitoring image into a damaged road surface identification model, and determining whether a monitored road surface corresponding to the road surface monitoring images is a road surface to be maintained. If so, determining the corresponding tunnel position and the corresponding road surface damage time according to the acquired information. And determining a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel. Wherein the reachable destination of the alternative path is the downlink and/or uplink of the tunnel location or the reachable extension of the downlink and/or uplink of the tunnel. And determining the road surface maintenance information of the tunnel based on the road surface monitoring image, the road surface damage time and the traffic flow weight set, and sending the road surface maintenance information to a maintenance terminal.
Description
Technical Field
The application relates to the technical field of pavement maintenance, in particular to a method and equipment for maintaining a pavement in a tunnel.
Background
With the continuous development of the traffic industry, roads are all around, and in the past, most roads are laid on the ground to bypass complex terrains such as hills and ravines as much as possible. Nowadays, the development of road construction technology, in order to shorten the interval between two places, people begin to dig mountains and repair roads, and construct a tunnel penetrating through mountains.
The appearance in tunnel has reduced people's trip time, gives people the convenience of bringing. Under the perennial high strength in tunnel used, the road surface in tunnel will take place to damage, and the environment of traveling in tunnel is very complicated, if can not carry out reasonable arrangement to the tunnel and restore, not only can influence the current efficiency in tunnel, also can threaten navigating mate's life safety.
Disclosure of Invention
In order to solve the above problems, embodiments of the present application provide a method and an apparatus for maintaining a road surface in a tunnel, which are used to provide maintenance information for reasonably repairing the tunnel, and ensure tunnel passing efficiency and life safety of drivers.
In one aspect, an embodiment of the present application provides a method for maintaining a pavement in a tunnel, where the method includes:
and acquiring a plurality of real-time road surface monitoring images and corresponding acquisition information from image acquisition equipment. And inputting each road surface monitoring image into a preset damaged road surface identification model so as to determine whether the monitored road surface corresponding to the road surface monitoring image is the road surface to be maintained. And under the condition that the monitored pavement corresponding to the pavement monitoring image is determined to be the pavement to be maintained, determining the tunnel position and the pavement damage time corresponding to the pavement to be maintained according to the acquired information of the pavement monitoring image. And determining a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel. Wherein the reachable destination of the alternative path is the downlink and/or uplink of the tunnel location or the reachable extension of the downlink and/or uplink of the tunnel. And determining the road maintenance information of the tunnel based on the road monitoring image, the road damage time and the traffic flow weight set, and sending the road maintenance information to a maintenance terminal.
In one implementation manner of the application, a damaged image frame corresponding to a damaged road surface in each road surface monitoring image is determined through a damaged road surface identification model. And identifying a damage label corresponding to each damaged image frame. Wherein the damage label comprises at least one or more of: subsidence, rutting, cracking, shrinkage cracking, and water seepage. And determining whether the damage degree of the monitored road surface is greater than a preset threshold value or not based on each damaged label. And under the condition that the damage degree of the monitored road surface is determined to be larger than a preset threshold value, taking the monitored road surface as the road surface to be maintained.
In one implementation of the present application, a damage level comparison image corresponding to each damaged label is determined. Wherein, one damaged label has at least two damaged degree comparison images. The preset threshold value is in the damage degree value corresponding interval corresponding to the two damage degree comparison images. And matching the damaged image frames corresponding to the damaged labels with the damaged degree comparison images so as to determine the corresponding damage degree values of the damaged labels according to the matching results. And determining the damage degree value according to the matched damage degree comparison image. And determining whether the damage degree of the monitored road surface is greater than a preset threshold value or not according to the damage weight corresponding to each damaged label and the corresponding damage degree value.
In one implementation of the present application, a first average traffic flow of a tunnel is determined according to historical driving data of the tunnel. And determining a second average traffic flow corresponding to each replaceable path according to the historical driving data of each replaceable path. And determining corresponding first traffic flow weight based on the first average traffic flow and each second average traffic flow. And determining a third average traffic flow of a plurality of preset time periods of the tunnel based on the historical driving data of the tunnel, so as to determine a plurality of second traffic flow weights of the tunnel according to the third average traffic flow. And determining a traffic flow weight set according to the first traffic flow weight and each second traffic flow weight of the tunnel.
In one implementation of the present application, a traffic flow average of the first average traffic flow and each of the second average traffic flows is determined. And determining first traffic flow weights corresponding to the first average traffic flow and each second average traffic flow according to the traffic flow average value, the first average traffic flow and each second average traffic flow.
In one implementation of the present application, the road surface damage type of the road surface monitoring image is determined through a preset damage type identification model. And determining the repairing time of the tunnel according to the pavement damage type. And determining a plurality of third traffic flow weight sequences within first preset time according to the road surface damage time, the traffic flow weight set and the traffic flow weight set of each replaceable path. And determining a time period in which the third traffic flow weight of the tunnel in each third traffic flow weight sequence meets the minimum weight value, wherein the time period is a period to be repaired. And determining whether the first traffic flow weight of the replaceable path is greater than the first traffic flow weight of the tunnel or not in the period to be repaired. And under the condition that the first traffic flow weight of the replaceable path is greater than the first traffic flow weight of the tunnel, taking the period to be repaired as a repair period. Otherwise, eliminating the minimum weight value, and determining the time period corresponding to the minimum weight value in the eliminated third traffic flow weight sequence, which is the repair time period to be determined, until the repair time period is determined. And under the condition that the repairing time period is shorter than the repairing time period, determining the repairing time periods within M Mth preset time until the sum value of each repairing time period is longer than the repairing time period, and determining each repairing time period as pavement maintenance information. Wherein M is a natural number.
In one implementation of the present application, a plurality of road surface damage images in a block chain platform and corresponding road surface damage types thereof are obtained. And (3) taking each road damage image as a training sample, taking the corresponding road damage type as a training label of the training sample, and inputting the training label into a preset neural network recognition model. And under the condition that the loss function of the neural network recognition model is smaller than a preset value, determining the trained neural network recognition model as a damage type recognition model.
In one implementation of the present application, a plurality of sample data images are obtained, and each sample data image and the corresponding damage degree comparison image are input to a preset classifier to train the classifier. The classifier divides the sample data into at least a plurality of image combinations which are consistent with the number of the damage degree comparison images. And matching the damage degree value in the image combination with the damage degree comparison image. And matching the image combination corresponding to the damaged image frame through the classifier so as to determine the damage degree value corresponding to the damaged image frame according to the matched image combination.
In one implementation manner of the application, under the condition that the damage degree of the monitored road surface is determined to be smaller than or equal to the preset threshold value, the damaged image frame in the monitored road surface is sent to the maintenance terminal.
On the other hand, the embodiment of the present application provides a road surface maintenance equipment in tunnel, and this equipment includes:
at least one processor; and a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
and acquiring a plurality of real-time road surface monitoring images and corresponding acquisition information from the image acquisition equipment. And inputting each road surface monitoring image into a preset damaged road surface identification model to determine whether the monitored road surface corresponding to the road surface monitoring image is the road surface to be maintained. And under the condition that the monitored pavement corresponding to the pavement monitoring image is determined to be the pavement to be maintained, determining the tunnel position and the pavement damage time corresponding to the pavement to be maintained according to the acquired information of the pavement monitoring image. And determining a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel. Wherein the reachable destination of the alternative path is the downlink and/or uplink of the tunnel location or the reachable extension of the downlink and/or uplink of the tunnel. And determining the road surface maintenance information of the tunnel based on the road surface monitoring image, the road surface damage time and the traffic flow weight set, and sending the road surface maintenance information to a maintenance terminal.
By the scheme, whether the tunnel pavement needs to be maintained or not is determined by utilizing the pavement monitoring image and the collected information of the tunnel, and then the traffic flow weight set of the tunnel and the alternative path thereof is determined according to historical driving data and position related information of the tunnel. And then through image recognition technology, length when confirming road surface restoration to confirm the restoration period of restoring this tunnel road surface, avoid carrying out unreasonable restoration to the tunnel, influence tunnel traffic efficiency. Meanwhile, the timely repair can guarantee the life safety of the driver, and the experience of the driver in driving the tunnel is also improved. A plurality of replaceable paths of the tunnel are considered, the traffic pressure of the road surface maintenance tunnel can be carried out through the environment, and the maintenance and repair efficiency of the tunnel is further improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flow chart of a method for maintaining a pavement in a tunnel according to an embodiment of the present disclosure;
FIG. 2 is a schematic view of a method for maintaining a road surface in a tunnel according to an embodiment of the present disclosure;
FIG. 3 is another schematic view of a method for maintaining a pavement in a tunnel according to an embodiment of the present disclosure;
FIG. 4 is a schematic view of a method for maintaining a road surface in a tunnel according to an embodiment of the present disclosure;
FIG. 5 is a schematic flow chart illustrating a method for maintaining a pavement in a tunnel according to an embodiment of the present disclosure;
fig. 6 is a schematic structural view of a road surface maintenance device in a tunnel according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The embodiment of the application provides a method and equipment for maintaining a road surface in a tunnel, which are used for providing maintenance information for reasonably repairing the tunnel and ensuring tunnel passing efficiency and life safety of drivers.
Various embodiments of the present application are described in detail below with reference to the accompanying drawings.
An embodiment of the present application provides a method for maintaining a pavement in a tunnel, as shown in fig. 1, the method may include steps S101 to S105:
s101, a server acquires a plurality of real-time road surface monitoring images and corresponding acquisition information from image acquisition equipment.
The image acquisition equipment can be a camera arranged in a tunnel or handheld image acquisition equipment of tunnel inspection personnel, the real-time pavement monitoring image refers to an image of a pavement image sending server acquired by the image acquisition equipment in real time, and the acquisition information refers to the acquisition time and the acquisition place of the real-time pavement monitoring image.
The server is only an exemplary execution subject of the road surface maintenance method in the tunnel, and the execution subject is not limited to the server, and the present application is not particularly limited thereto.
And S102, the server inputs each road surface monitoring image into a preset damaged road surface identification model so as to determine whether the monitored road surface corresponding to the road surface monitoring image is the road surface to be maintained.
The damaged road surface identification model may be a neural network model such as: alexNet, ZFNET, VGG, etc.
In this embodiment of the present application, the server inputs each road surface monitoring image into a preset damaged road surface identification model to determine whether a monitored road surface corresponding to the road surface monitoring image is a road surface to be maintained, which specifically includes:
firstly, the server determines a damaged image frame corresponding to the damaged road surface in each road surface monitoring image through the damaged road surface identification model.
The damaged road surface recognition model can be trained through a plurality of road surface damaged image samples, and after multiple times of training, the damaged road surface recognition model can recognize damaged image frames corresponding to the damaged road surface in the road surface monitoring image. In the embodiment of the present application, since the number of the image capturing devices is not limited, for the same road surface, there may be a plurality of image capturing devices that capture road surface images from different directions, so that there are a plurality of road surface monitoring images, and the road surface monitoring image is an image including a plurality of image frames.
Then, the server determines a damaged label corresponding to each damaged image frame through the identification operation of the damaged road surface identification model.
Wherein the damage label comprises at least one or more of: subsidence, rutting, cracking, shrinkage cracking, and water seepage.
The damaged labels are determined for labels corresponding to the road surface damaged image samples used for training the damaged road surface identification model, and different damaged labels correspond to a plurality of road surface damaged image samples, so that the identification accuracy of the damaged road surface identification model is guaranteed.
Then, the server determines whether the damage degree of the monitored road surface is greater than a preset threshold value based on each damaged label.
Specifically, the server determines whether the damage degree of the monitored road surface is greater than a preset threshold value or not based on each damaged label, and the method comprises the following steps:
firstly, the server determines the damage degree corresponding to each damaged label and compares the damaged labels with the images.
Wherein, one damaged label has at least two damaged degree comparison images. The preset threshold value is in the damage degree value corresponding interval corresponding to the two damage degree comparison images.
As shown in FIG. 2, the damaged image is 201,202,203 and 204 compared with the image, and the damaged image frame corresponding to the damaged label is 205.
And secondly, the server compares the damaged image frames corresponding to the damaged labels with the damaged images to match the damaged images so as to determine the corresponding damaged degree values of the damaged labels according to the matching results.
And determining the damage degree value according to the matched damage degree comparison image.
Each damage degree comparison image has a unique damage degree value, for example, the damage degree value of 201 is a, the damage degree value of 202 is b, the damage degree value of 203 is c, and the damage degree value of 204 is d. And the server compares the damaged image frame of the damaged label with each damaged degree comparison image to match, so as to obtain the damaged degree value of the damaged label.
In some embodiments of the present application, the server compares the damaged image frame corresponding to the damaged label with each damaged degree to match the image, so as to determine the damaged degree value corresponding to the damaged label according to the matching result, which specifically includes:
the server acquires a plurality of sample data images, compares each sample data image with the corresponding damage degree, and inputs the sample data images and the corresponding damage degree to a preset classifier so as to train the classifier.
The classifier divides the sample data into at least a plurality of image combinations which are consistent with the number of the damage degree comparison images. And matching the damage degree value in the image combination with the damage degree comparison image.
The classifier can use a classification algorithm of a support vector machine to take the sample data image and each damage degree comparison image as input, take the sample data image and the classification of each damage degree comparison image as output, thereby classifying the sample data image into image combinations, and the number of the classified image combinations is at least equal to the number of the damage degree comparison images. For example, the damage degree comparison image with different input damage degree values is 4, the classifier divides the sample data image into at least 4 image combinations to distinguish the sample data image, so that the images with different damage degrees can be classified according to characteristics.
The classification algorithm of the support vector machine can realize the classification of the nonlinear model, a two-classifier is established between every two classes, and the sample data image is accurately classified. Different sample data images will match the damage levels of different damage level values compared to the image. And determining that the training of the classifier is finished until the accuracy of the training of the classifier is higher than a preset accuracy, for example, the accuracy of the classified image combination reaches 99%.
Then, the server matches the image combination corresponding to the damaged image frame through the classifier, so as to determine the damage degree value corresponding to the damaged image frame according to the matched image combination.
And after the damaged image frame is classified by the classifier, the server combines the images divided by the damaged image frame to obtain the damage degree value of the damaged image frame.
And thirdly, the server determines whether the damage degree of the monitored road surface is greater than a preset threshold value according to the damage weight corresponding to each damaged label and the corresponding damage degree value.
In the embodiment of the application, the damage weight is obtained according to the damage label, the damage weight can be preset according to a user, and different damage weights represent the severity of different damage labels, for example, the damage weight of a sunken track is 0.2, the damage weight of a rut is 0.15 \8230;. And the server calculates the product of the damage weight and the damage degree value and compares the product value with a preset threshold value so as to determine whether the damage degree of the monitored road surface is greater than the preset threshold value.
For example, the damage weight is a, the damage degree value is B, the size relationship between a × B and the preset threshold C is compared, and the server may determine the damage degree of the monitored road surface.
And finally, under the condition that the damage degree of the monitored road surface is determined to be larger than a preset threshold value by the server, taking the monitored road surface as the road surface to be maintained.
In the embodiment of the application, the preset threshold is set according to actual use of a user, the preset threshold represents that the damage degree reaches the degree to be maintained and repaired or approaches the degree to be maintained and repaired, and specific values of the preset threshold are not specifically limited in the application.
In one embodiment of the application, the server sends a damaged image frame in the monitored road surface to the maintenance terminal under the condition that the damage degree of the monitored road surface is determined to be less than or equal to the preset threshold value.
In the road surface maintenance method in the tunnel in-service use process, the maintenance terminal can watch the actual conditions of the monitored road surface in real time, and even if the monitored road surface has the condition that the image frame is damaged, the maintenance terminal does not need to carry out maintenance immediately, the judgment can also be carried out by a corresponding expert of the maintenance terminal, so that the problem that the road surface maintenance with small damage degree is untimely is avoided, the damage degree of the road surface is increased, and the road surface is seriously damaged. Meanwhile, the phenomenon that subsequent damage is aggravated to influence the tunnel communication efficiency and threaten the life safety of drivers can be avoided to a certain extent.
S103, under the condition that the monitored road surface corresponding to the road surface monitoring image is determined to be the road surface to be maintained by the server, the tunnel position and the road surface damage time corresponding to the road surface to be maintained are determined according to the collected information of the road surface monitoring image.
In other words, after the server determines the monitored road surface as the road surface to be maintained, the server may determine, according to the collected information, a tunnel position where the road surface to be maintained is located, and find a first time when the road surface of the road surface to be maintained is damaged, that is, a road surface damage time.
And S104, the server determines a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel.
Wherein the reachable destination of the alternative path is a downlink and/or uplink of the tunnel location or a reachable extension of the downlink and/or uplink of the tunnel.
As shown in fig. 3 (bidirectional lane) and fig. 4 (unidirectional lane), when the tunnel is a bidirectional lane, another route identical to the start point and the destination of the tunnel exists in the driving direction of the current tunnel, the other route is a route not including the current tunnel, and the other route may include a tunnel, a highway, an aisle, and the like. Or in the driving direction of the current tunnel, an reachable destination which is the current tunnel on an extension line of a certain route exists.
In this embodiment of the application, the server determines a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the alternative path of the tunnel, and specifically includes:
first, the server determines a first average traffic flow of the tunnel according to historical driving data of the tunnel.
The historical driving data may be vehicle driving data of the tunnel collected in the past month or year of the tunnel, for example, in the past month, the average traffic flow of the tunnel is N, and N is taken as the first average traffic flow.
And secondly, the server determines a second average traffic flow corresponding to each alternative path according to the historical driving data of each alternative path.
The second average traffic flow is an average traffic flow of the alternative path for the same time period as the first average traffic flow.
And thirdly, the server determines corresponding first traffic flow weight based on the first average traffic flow and each second average traffic flow.
Specifically, the step of determining, by the server, the corresponding first traffic flow weight based on the first average traffic flow and each of the second average traffic flows includes:
first, the server determines a traffic flow average of the first average traffic flow and each of the second average traffic flows.
For example, the first average vehicle flow rate is N, and each of the second evaluation vehicle flow rates includes:
m1, M2, M3.. Mn, the traffic flow average is:
v = (N + M1+ M2+ \8230; + Mn)/(N + 1). Wherein n is a natural number.
And secondly, determining first traffic flow weights corresponding to the first average traffic flow and each second average traffic flow according to the traffic flow average value, the first average traffic flow and each second average traffic flow.
In the embodiment of the present application, the formula for determining the weight of the first vehicle flow rate according to the average vehicle flow rate, the first average vehicle flow rate and each second average vehicle flow rate is as follows:
wherein β is a first vehicle flow weight, and X is a first average vehicle flow or a second average vehicle flow.
Then, the server determines a third average traffic flow of the tunnel for a plurality of preset time periods based on the historical driving data of the tunnel, so as to determine a plurality of second traffic flow weights of the tunnel according to the third average traffic flow.
The server can determine a third average traffic flow of the tunnel in each time period such as a working day and a holiday, for example, 1 point-2 points on a certain day, according to the historical driving data of the tunnel, wherein the third average traffic flow is q1;2 to 3, and the third average traffic flow is q1; 3-4 points, and the third average traffic flow is q2;4 points to 5 points, and the third average vehicle flow rate is q2 \8230;, 8230;. The preset time period may be divided according to the third average traffic flow, for example, the third average traffic flow of the 1 point-2 point and the 2 point-3 point are the same, and the time is adjacent, and may be a preset time period; according to the scheme, 3-4 points and 4-5 points are also a preset time period. And determining the weight of the second vehicle flow according to the proportion of each third average vehicle flow in the total vehicle flow of each preset time period in a certain day, wherein if the third average vehicle flow is Y1 and the total vehicle flow is Y0, the weight is Y1/Y0.
And then, the server determines a traffic flow weight set according to the first traffic flow weight and each second traffic flow weight of the tunnel.
The traffic weight set is a weight set comprising a first traffic weight and each second traffic weight.
And S105, the server determines the road maintenance information of the tunnel based on the road monitoring image, the road damage time and the traffic flow weight set, and sends the road maintenance information to the maintenance terminal.
The maintenance terminal may be a handheld terminal of a maintenance worker, such as a mobile phone, an ipad, or a notebook computer, which is not specifically limited in this application.
In the embodiment of the present application, the server determines the road maintenance information of the tunnel based on the road monitoring image, the road damage time, and the traffic flow weight, as shown in fig. 5, specifically includes the following steps:
s501, the server determines the road surface damage type of the road surface monitoring image through a preset damage type identification model.
In the embodiment of the application, the method for maintaining the road surface in the tunnel is applied to a pre-built block chain platform, the block chain platform comprises a plurality of sub-nodes, and the sub-nodes are used for uploading road surface damage images and corresponding road surface damage types. Before determining the road surface damage type of the road surface monitoring image through a preset damage type identification model, the method further comprises the following steps:
firstly, a server acquires a plurality of road surface damage images in a block chain platform and corresponding road surface damage types.
Each child node in the block chain platform can upload a road surface damage image and a road surface damage type of the road surface damage image, and the child node can be a mobile phone of a user, for example, when the user finds that the road surface is damaged in the driving process, the user can take a picture and send the picture and the road surface damage type corresponding to the recruitment to the block chain platform.
Then, the server takes each road surface damage image as a training sample, takes the corresponding road surface damage type as a training label of the training sample, and inputs the training sample into a preset neural network recognition model.
The neural network recognition model may be the same as or different from the neural network model used in the damaged road surface recognition model, and this is not specifically limited in this application.
And under the condition that the loss function of the neural network recognition model is smaller than a preset value, the server determines the trained neural network recognition model as a damage type recognition model.
And when the loss function of the neural network recognition model is smaller than a preset value, namely the accuracy of the neural network recognition model meets the requirement, the server takes the trained neural network recognition model as a damage type recognition model.
And S502, the server determines the repair duration of the tunnel according to the road surface damage type.
In the embodiment of the application, the road surface damage type may have a damage type comparison table, the damage type comparison table includes a correspondence between the road surface damage type and the repair duration thereof, and the damage type comparison table may be generated in advance by a user.
S503, the server determines a third traffic flow weight sequence within the first preset time according to the road surface damage time, the traffic flow weight set and the traffic flow weight set of the replaceable path.
The third traffic flow weight sequence in the first preset time refers to that in a time period after the road surface damage time, if the time period comprises three sub-time periods of S1, S2 and S3, the first traffic flow weight of the tunnel is multiplied by the second traffic flow weight respectively to obtain a third traffic flow weight, and the third traffic flow weight sequence is generated according to the time sequence. And after the first vehicle flow weight of each replaceable path is multiplied by the second vehicle flow weight of the replaceable path (the acquisition mode of the second vehicle flow weight of the replaceable path can refer to the acquisition mode of the second vehicle flow weight of the tunnel), obtaining a third vehicle flow weight of the replaceable path, and generating a second weight sequence according to the time sequence.
According to the time sequence, the server obtains the weights in the first weight sequence of the tunnel and the second weight sequences of the replaceable paths corresponding to the same time period, such as S1, and arranges the weights according to the weight sequence to obtain a third traffic flow weight sequence.
And S504, the server determines a time period in which the third traffic flow weight of the tunnel in the third traffic flow weight sequence meets the minimum weight value, and the time period is a to-be-determined repair time period.
That is, when the minimum value of the third traffic flow weight sequence is the third traffic flow weight of the tunnel in the same time period, then the time period is the pending repair period.
And S505, the server determines whether the first traffic flow weight of the alternative path is greater than the first traffic flow weight of the tunnel in the period to be repaired.
And the server compares the first traffic flow weight of the replaceable path with the first traffic flow weight of the tunnel after determining the period of pending restoration.
S506, under the condition that the first traffic flow weight of the replaceable path is larger than that of the tunnel, the server takes the period to be repaired as the repair period.
That is to say, in the time period when the number of running vehicles on the alternative path is greater than that of running vehicles on the tunnel, as the repair time period, the comparison effect can be better through comparison of the weight, the weight can refer to the importance degree of the path, and if the importance degree of the tunnel in the repair waiting time period is higher than that of the alternative path, the tunnel maintenance will affect the running of normal vehicles.
And S507, otherwise, the server rejects the minimum weight value, and determines a time period corresponding to the minimum weight value in the third traffic flow weight sequence after rejection, which is a repair time period to be determined, until the repair time period is determined.
That is, in the case that the first traffic weight of the alternative route is smaller than the first traffic weight of the tunnel, the server will remove the sub-period of time with the smallest weight and continue to execute the step of S504.
And S508, under the condition that the repair time period is shorter than the repair time period, the server determines the repair time periods within M preset times until the sum of the repair time periods is longer than the repair time period, and determines that the repair time periods are the pavement maintenance information.
Wherein M is a natural number. That is, the repair time period may be 2-3 points on the first day, 3-4 points on the second day \8230, the repair time period is 10 hours, then the maintenance of the tunnel can be completed only when the sum of the repair time periods obtained by the server is greater than the repair time period, and each repair time period is used as the pavement maintenance information.
By the scheme, whether the tunnel pavement needs to be maintained or not is determined by utilizing the pavement monitoring image and the collected information of the tunnel, and then the traffic flow weight set of the tunnel and the alternative path thereof is determined according to historical driving data and position related information of the tunnel. And then through image recognition technology, length when confirming road surface restoration to confirm the restoration period of restoring this tunnel road surface, avoid carrying out unreasonable restoration to the tunnel, influence tunnel traffic efficiency. Meanwhile, the timely repair can guarantee the life safety of the driver, and the experience of the driver in driving the tunnel is also improved.
Fig. 6 is a road maintenance device in a tunnel according to an embodiment of the present application, where the device includes:
at least one processor; and a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to:
and acquiring a plurality of real-time road surface monitoring images and corresponding acquisition information from the image acquisition equipment. And inputting each road surface monitoring image into a preset damaged road surface identification model to determine whether the monitored road surface corresponding to the road surface monitoring image is the road surface to be maintained. If so, determining the tunnel position and the road surface damage time corresponding to the road surface to be maintained according to the collected information of the road surface monitoring image. And determining a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel. Wherein the reachable destination of the alternative path is the downlink and/or uplink of the tunnel location or the reachable extension of the downlink and/or uplink of the tunnel. And determining the road maintenance information of the tunnel based on the road monitoring image, the road damage time and the traffic flow weight set, and sending the road maintenance information to a maintenance terminal.
The embodiments in the present application are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The device and the method provided by the embodiment of the application are in one-to-one correspondence, so the device also has the beneficial technical effects similar to the corresponding method, and the beneficial technical effects of the method are explained in detail above, so the beneficial technical effects of the device are not described in detail here.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus comprising the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.
Claims (10)
1. A method of maintaining a pavement in a tunnel, the method comprising:
acquiring a plurality of real-time pavement monitoring images and corresponding acquisition information from image acquisition equipment;
inputting each road surface monitoring image into a preset damaged road surface identification model to determine whether the monitored road surface corresponding to the road surface monitoring image is a road surface to be maintained;
if so, determining the tunnel position and the road surface damage time corresponding to the road surface to be maintained according to the acquired information of the road surface monitoring image;
determining a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel; wherein the reachable destination of the alternative path is at the downlink and/or uplink of the tunnel location or at a reachable extension of the downlink and/or uplink of the tunnel;
and determining the road surface maintenance information of the tunnel based on the road surface monitoring image, the road surface damage time and the traffic flow weight set, and sending the road surface maintenance information to a maintenance terminal.
2. The method according to claim 1, wherein the step of inputting each road surface monitoring image into a preset damaged road surface identification model to determine whether the monitored road surface corresponding to the road surface monitoring image is a road surface to be maintained includes:
determining a damaged image frame corresponding to the damaged road surface in each road surface monitoring image through the damaged road surface identification model;
identifying a damage label corresponding to each damaged image frame; wherein the damage label comprises at least one or more of: sinking, rutting, cracking, shrinkage cracking and water seepage;
determining whether the damage degree of the monitored road surface is greater than a preset threshold value or not based on each damaged label;
and if so, taking the monitored pavement as the pavement to be maintained.
3. The method according to claim 2, wherein the determining whether the degree of damage of the monitored road surface is greater than a preset threshold value based on each damaged label specifically comprises:
determining a damage degree comparison image corresponding to each damaged label; wherein, at least two damage degree comparison images exist in one damage label; the preset threshold is positioned in a damage degree value corresponding interval corresponding to the two damage degree comparison images;
matching the damaged image frame corresponding to the damaged label with each damaged degree comparison image so as to determine a damaged degree value corresponding to the damaged label according to a matching result; wherein the damage degree value is determined according to the matched damage degree comparison image;
and determining whether the damage degree of the monitored road surface is greater than the preset threshold value or not according to the damage weight corresponding to each damaged label and the corresponding damage degree value.
4. The method according to claim 1, wherein the determining a traffic flow weight set of the tunnel based on the historical driving data of the tunnel corresponding to the road surface to be maintained and the historical driving data of the alternative path of the tunnel specifically comprises:
determining a first average traffic flow of the tunnel according to the historical driving data of the tunnel;
determining a second average traffic flow corresponding to each replaceable path according to the historical driving data of each replaceable path;
determining corresponding first vehicle flow weight based on the first average vehicle flow and each second average vehicle flow;
determining a third average traffic flow of a plurality of preset time periods of the tunnel based on the historical driving data of the tunnel, and determining a plurality of second traffic flow weights of the tunnel according to the third average traffic flow;
and determining the traffic flow weight set according to the first traffic flow weight and each second traffic flow weight of the tunnel.
5. The method of claim 4, wherein determining a corresponding first vehicle flow weight based on the first average vehicle flow and each of the second average vehicle flows comprises:
determining the traffic flow average value of the first average traffic flow and each second average traffic flow;
and determining first traffic flow weights corresponding to the first average traffic flow and each second average traffic flow according to the average traffic flow, the first average traffic flow and each second average traffic flow.
6. The method according to claim 5, wherein the determining the road maintenance information of the tunnel based on the road monitoring image, the road damage time and the traffic flow weight specifically comprises:
determining the road surface damage type of the road surface monitoring image through a preset damage type identification model;
determining the repair duration of the tunnel according to the pavement damage type;
determining a plurality of third traffic flow weight sequences within first preset time according to the road surface damage time, the traffic flow weight set and the traffic flow weight set of each replaceable path;
determining a time period in which the third traffic flow weight of the tunnel in each third traffic flow weight sequence meets the minimum weight value as a period to be repaired;
determining whether a first traffic weight of the alternative path is greater than a first traffic weight of the tunnel for the pending repair period;
taking the pending repair time period as a repair time period when the first traffic weight of the replaceable path is greater than the first traffic weight of the tunnel;
otherwise, eliminating the weight minimum value, and determining a time period corresponding to the weight minimum value in the eliminated third traffic flow weight sequence as a repair time period to be determined until the repair time period is determined;
determining M repair time periods within Mth preset time under the condition that the repair time period is shorter than the repair time period until the sum of the repair time periods is longer than the repair time period, and determining each repair time period as the pavement maintenance information; wherein M is a natural number.
7. The method according to claim 6, wherein the method is applied to a pre-built blockchain platform, the blockchain platform comprises a plurality of sub-nodes, and the sub-nodes are used for uploading road surface damage images and corresponding road surface damage types; before determining the road surface damage type of the road surface monitoring image through a preset damage type identification model, the method further comprises the following steps:
acquiring a plurality of road surface damage images in the block chain platform and corresponding road surface damage types;
taking each road surface damage image as a training sample, taking the corresponding road surface damage type as a training label of the training sample, and inputting the training label into a preset neural network recognition model;
and under the condition that the loss function of the neural network recognition model is smaller than a preset value, determining the trained neural network recognition model as the damage type recognition model.
8. The method according to claim 3, wherein the matching the damaged image frame corresponding to the damaged label with each damaged degree comparison image to determine a damaged degree value corresponding to the damaged label according to the matching result comprises:
acquiring a plurality of sample data images, comparing each sample data image with the corresponding damage degree, and inputting the sample data images and the corresponding damage degree to a preset classifier so as to train the classifier; wherein the classifier divides the sample data into at least a plurality of image combinations consistent with the number of damage degree comparison images; the damage degree value in the image combination is matched with the damage degree value of the corresponding damage degree comparison image;
and matching the image combination corresponding to the damaged image frame through the classifier so as to determine the damage degree value corresponding to the damaged image frame according to the matched image combination.
9. The method of claim 2, further comprising:
and under the condition that the damage degree of the monitored road surface is determined to be smaller than or equal to a preset threshold value, sending the damaged image frame in the monitored road surface to the maintenance terminal.
10. An in-tunnel roadway maintenance device, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,
the memory stores instructions executable by the at least one processor to cause the at least one processor to:
acquiring a plurality of real-time pavement monitoring images and corresponding acquisition information from image acquisition equipment;
inputting each road surface monitoring image into a preset damaged road surface identification model to determine whether the monitored road surface corresponding to the road surface monitoring image is a road surface to be maintained;
if so, determining the tunnel position and the road surface damage time corresponding to the road surface to be maintained according to the acquired information of the road surface monitoring image;
determining a traffic flow weight set of the tunnel based on historical driving data of the tunnel corresponding to the road surface to be maintained and historical driving data of the replaceable path of the tunnel; wherein the reachable destination of the alternative path is at the downlink and/or uplink of the tunnel location or at a reachable extension of the downlink and/or uplink of the tunnel;
and determining the road maintenance information of the tunnel based on the road monitoring image, the road damage time and the traffic flow weight set, and sending the road maintenance information to a maintenance terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210809441.0A CN115271114A (en) | 2022-07-11 | 2022-07-11 | Method and equipment for maintaining road surface in tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210809441.0A CN115271114A (en) | 2022-07-11 | 2022-07-11 | Method and equipment for maintaining road surface in tunnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115271114A true CN115271114A (en) | 2022-11-01 |
Family
ID=83766522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210809441.0A Pending CN115271114A (en) | 2022-07-11 | 2022-07-11 | Method and equipment for maintaining road surface in tunnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115271114A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601663A (en) * | 2022-12-16 | 2023-01-13 | 陕西交通电子工程科技有限公司（Cn） | Information classification method for highway pavement maintenance |
| CN115762155A (en) * | 2022-11-14 | 2023-03-07 | 东南大学 | Highway pavement abnormity monitoring method and system |
| CN116884226A (en) * | 2023-09-07 | 2023-10-13 | 山东金宇信息科技集团有限公司 | Ecological monitoring and early warning method, equipment and medium for road maintenance |
-
2022
- 2022-07-11 CN CN202210809441.0A patent/CN115271114A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115762155A (en) * | 2022-11-14 | 2023-03-07 | 东南大学 | Highway pavement abnormity monitoring method and system |
| CN115762155B (en) * | 2022-11-14 | 2024-03-22 | 东南大学 | Expressway pavement abnormality monitoring method and system |
| CN115601663A (en) * | 2022-12-16 | 2023-01-13 | 陕西交通电子工程科技有限公司（Cn） | Information classification method for highway pavement maintenance |
| CN116884226A (en) * | 2023-09-07 | 2023-10-13 | 山东金宇信息科技集团有限公司 | Ecological monitoring and early warning method, equipment and medium for road maintenance |
| CN116884226B (en) * | 2023-09-07 | 2023-11-21 | 山东金宇信息科技集团有限公司 | Ecological monitoring and early warning method, equipment and medium for road maintenance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115271114A (en) | Method and equipment for maintaining road surface in tunnel | |
| CN108765404A (en) | A kind of road damage testing method and device based on deep learning image classification | |
| CN111667101B (en) | Personalized electric power field operation path planning method and system integrating high-resolution remote sensing image and terrain | |
| CN105956268A (en) | Construction method and device applied to test scene of pilotless automobile | |
| CN110991466A (en) | Highway road surface condition detecting system based on novel vision sensing equipment | |
| Bello-Salau et al. | Image processing techniques for automated road defect detection: A survey | |
| Alzraiee et al. | Detecting of pavement marking defects using faster R-CNN | |
| CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
| CN115239219B (en) | Smart city muck vehicle management method and system based on Internet of things | |
| Hascoet et al. | Fasterrcnn monitoring of road damages: Competition and deployment | |
| CN110705452A (en) | Intelligent management and control method and system for facilities of expressway unattended toll station | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| WO2021076573A1 (en) | Systems and methods for assessing infrastructure | |
| CN107146025A (en) | A kind of road management decision system | |
| Silva et al. | Automated road damage detection using UAV images and deep learning techniques | |
| CN109902730B (en) | Power transmission line broken strand detection method based on deep learning | |
| CN103605960A (en) | Traffic state identification method based on fusion of video images with different focal lengths | |
| CN112308066A (en) | License plate recognition system | |
| CN112765392B (en) | High-speed rail train control positioning method and system based on image matching | |
| CN116206148A (en) | Intelligent detection, identification and classification method for decoration waste | |
| CN114592411A (en) | Carrier parasitic type intelligent road damage inspection method | |
| CN107423908B (en) | Road surface damage information acquisition method and road surface damage information acquisition system | |
| Chen et al. | A 5G Cloud Platform and Machine Learning-Based Mobile Automatic Recognition of Transportation Infrastructure Objects | |
| Tristan et al. | Fasterrcnn monitoring of road damages: Competition and deployment | |
| Van Cuong et al. | AI-Driven Vehicle Recognition for Enhanced Traffic Management: Implications and Strategies |
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 |