CN109255288A - A kind of road surface breakage detection method, device and terminal device - Google Patents
A kind of road surface breakage detection method, device and terminal device Download PDFInfo
- Publication number
- CN109255288A CN109255288A CN201810813069.4A CN201810813069A CN109255288A CN 109255288 A CN109255288 A CN 109255288A CN 201810813069 A CN201810813069 A CN 201810813069A CN 109255288 A CN109255288 A CN 109255288A
- Authority
- CN
- China
- Prior art keywords
- road surface
- learning model
- deep learning
- accuracy rate
- pavement
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention is suitable for image identification technical field, provides a kind of road surface breakage detection method, device and terminal device, which comprises the present invention obtains the collected pavement image of acquisition device first；Then pavement image is inputted into the first deep learning model, obtains road surface abnormality detection result；Road surface abnormality detection result is finally sent to monitoring center, so that monitoring center is alerted according to road surface abnormality detection result.The present invention acquires pavement image by acquisition device, and pavement image is inputted in the first deep learning model by the method for image recognition and is calculated, obtain road surface abnormality detection result, improve the precision of road surface breakage detection, simultaneously, first deep learning model is preset in terminal device, it can be the detection for completing pavement image in terminal device, to disperse pavement detection task, the detection efficiency of road surface breakage is improved, and further provides efficient, high-quality data for maintenance of surface work and supports.
Description
Technical field
The invention belongs to image identification technical fields more particularly to a kind of road surface breakage detection method, device and terminal to set
It is standby.
Background technique
The increase of the volume of traffic and vehicle enlargement, phenomena such as serious of overloading lead to the appearance of road surface breakage, seriously affect
The safety of road traffic and comfort.Maintenance of surface is the emphasis of highway maintenance, and pavement distress is as maintenance of surface
The foundation of management work, stands highly important status in Decision making for pavement maintenance, and road surface breakage type has slight crack, longitudinal direction to split
The multiple types such as trace, lateral slight crack, cracking.
Currently, road surface breakage detects the method for relying primarily on artificial detection, i.e. surfaceman has found road surface in road surface inspection
It takes pictures after breakage upload, then relevant department is handled further according to the image of shooting.But the processing method of artificial detection is past
The phenomenon that slow toward treatment effeciency, and there are missing inspections, false retrieval, thus the problem for causing road surface breakage detection accuracy low.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of road surface breakage detection method, device and terminal device, to solve
The low problem of road surface breakage detection accuracy in the prior art.
The first aspect of the embodiment of the present invention provides a kind of road surface breakage detection method, comprising:
Obtain the collected pavement image of acquisition device；
Pavement image is inputted to the first deep learning model being preset in terminal device, obtains road surface abnormality detection knot
Fruit；
Road surface abnormality detection result is sent to monitoring center, so that monitoring center is carried out according to road surface abnormality detection result
Alarm.
The second aspect of the embodiment of the present invention provides a kind of road surface breakage detection device, comprising:
Image capture module, for obtaining the collected pavement image of acquisition device；
Testing result obtains module, for pavement image to be inputted the first deep learning mould being preset in terminal device
Type obtains road surface abnormality detection result；
Testing result sending module, for road surface abnormality detection result to be sent to monitoring center, so that monitoring center root
It is alerted according to road surface abnormality detection result.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
The step of realizing road surface breakage detection method as described above.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program realizes road surface breakage detection method as described above when being executed by processor
The step of.
Existing beneficial effect is the embodiment of the present invention compared with prior art: the embodiment of the present invention obtains acquisition dress first
Set collected pavement image；Then pavement image is inputted to the first deep learning model being preset in terminal device, obtained
Road surface abnormality detection result；Road surface abnormality detection result is finally sent to monitoring center, so that monitoring center is different according to road surface
Normal testing result is alerted.The embodiment of the present invention acquires pavement image, and the method for passing through image recognition by acquisition device
Pavement image is inputted in the first deep learning model and is calculated, road surface abnormality detection result is obtained, improves road surface breakage
The precision of detection, meanwhile, the first deep learning model is preset in terminal device, can be to complete road surface in terminal device
The detection of image improves the detection efficiency of road surface breakage to disperse the task of pavement detection, is further maintenance of surface work
Efficient, high-quality data are provided to support.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is a kind of implementation process schematic diagram of road surface breakage detection method provided in an embodiment of the present invention；
Fig. 2 is a kind of implementation process schematic diagram of road surface breakage detection method provided in an embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of road surface breakage detection device provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of road surface breakage detection device provided in an embodiment of the present invention；
Fig. 5 is the schematic diagram of terminal device provided in an embodiment of the present invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
Description and claims of this specification and term " includes " and their any deformations in above-mentioned attached drawing, meaning
Figure, which is to cover, non-exclusive includes.Such as process, method or system comprising a series of steps or units, product or equipment do not have
It is defined in listed step or unit, but optionally further comprising the step of not listing or unit, or optionally also wrap
Include the other step or units intrinsic for these process, methods, product or equipment.In addition, term " first ", " second " and
" third " etc. is for distinguishing different objects, not for description particular order.
In order to illustrate technical solution of the present invention, the following is a description of specific embodiments.
Embodiment 1:
Fig. 1 shows a kind of implementation process of road surface breakage detection method of one embodiment of the present of invention offer, mistake
Details are as follows for journey:
In S101, the collected pavement image of acquisition device is obtained.
In the present embodiment, acquisition device may include vehicle-mounted camera, unmanned plane camera and monitoring camera.Its
In, the bottom in vehicle or the front end of vehicle can be set in vehicle-mounted camera, thus dynamic during vehicle driving
Shoot the pavement image on advance road surface；Monitoring camera can be set in the both sides of traffic route, be obtained by monitoring camera
The pavement image on fixed road surface；Unmanned plane camera shoots dynamic pavement image in flight course.
In the present embodiment, pavement image may include video and picture.
In S102, pavement image is inputted to the first deep learning model being preset in terminal device, it is different to obtain road surface
Normal testing result.
In the present embodiment, terminal device may include car-mounted terminal, Airborne Terminal and monitor terminal, deposit in terminal device
The first deep learning model is contained, pavement image is inputted into the first deep learning model, obtains road surface abnormality detection result.
In the present embodiment, damaged sample is also preserved in terminal equipment database, damaged sample is for judging that road surface is broken
The type of damage, damaged type include but is not limited to crack and other types of damage, and wherein crack includes linear fractures and road surface tortoise
Split, linear fractures include longitudinal crack and transverse crack, longitudinal crack and transverse crack include respectively again irregular cracks and
Pattern cracking two types, road surface cracking are divided into entire road surface cracking and part road surface cracking two types, other types of damage
Can include but is not limited to white line is fuzzy, sidewalk line is fuzzy, one in track, concave-convex road surface, pit-hole and division or more
It is a.
Table 1
In the present embodiment, each damaged type, which mark, number, will number, damaged type and number and
The corresponding relationship of damaged type saves in the database.
By taking a specific application scenarios as an example, table 1 shows a kind of number provided in an embodiment of the present invention and damaged class
The correspondence table of type.
In the present embodiment, the damaged type marked in the abnormality detection result of road surface is type number, for example, working as certain section of road
When pit-hole occurs in face, then D40 is shown in the road surface abnormality detection result.
It in the present embodiment, can be first picture one by one by Video segmentation when pavement image is video, then
Picture is sequentially input into the first deep learning model, by the characteristic information in the first deep learning model extraction picture, according to
The characteristic information of picture judges picture with the presence or absence of type that is damaged, and judging damaged.
In the present embodiment, the first deep learning model can be convolutional neural networks model.
In the present embodiment, terminal device can also be the edge calculations gateway communicated with multiple acquisition devices, edge meter
Calculating gateway is in the network edge side close to terminal or data source header, and converged network, calculating, storage, application core ability are opened
It is laid flat platform.Vehicle-mounted camera, unmanned plane camera or monitoring camera acquire pavement image, and pavement image is then sent to side
Edge calculates gateway, and edge calculations gateway carries out damage testing according to the pavement image that acquisition device is sent, and show that road surface is examined extremely
It surveys as a result, road surface abnormality detection result is then sent to monitoring center.
In S103, road surface abnormality detection result is sent to monitoring center, so that monitoring center is examined extremely according to road surface
Result is surveyed to be alerted.
In embodiments of the present invention, monitoring center can be server, and monitoring center is examined extremely according to the road surface received
Survey the position for making the related personnel of maintenance of surface department timely road pavement exception as a result, notify relevant maintenance of surface department
Carry out maintenance.
From above-described embodiment it is found that the embodiment of the present invention obtains the collected pavement image of acquisition device first；Then will
Pavement image inputs the first deep learning model being preset in terminal device, obtains road surface abnormality detection result；Finally by road
Face abnormality detection result is sent to monitoring center, so that monitoring center is alerted according to road surface abnormality detection result.The present invention
Embodiment acquires pavement image by acquisition device, and pavement image is inputted the first deep learning by the method for image recognition
It is calculated in model, obtains road surface abnormality detection result, improve the precision of road surface breakage detection, meanwhile, by the first depth
Learning model is preset in terminal device, can be the detection for completing pavement image in terminal device, to disperse road surface inspection
The task of survey improves the detection efficiency of road surface breakage, further provides efficient, high-quality data for maintenance of surface work and supports.
In one embodiment of the invention, in Fig. 1 after step S101, method provided in an embodiment of the present invention is also wrapped
It includes:
In one embodiment, pavement image is sent to monitoring center, so that monitoring center is by pavement image input the
Two deep learning models are trained the second deep learning model.
In the present embodiment, monitoring center is provided with the second deep learning model, and acquisition device sends the road surface figure of acquisition
As to monitoring center, monitoring center inputs the second deep learning model for the pavement image received as training sample, is used for
The second deep learning model of training.Make since monitoring center receives all pavement images with the acquisition device of monitoring center communication
For training sample, a large amount of training sample is inputted into the second deep learning model, can constantly promote the second deep learning mould
The accuracy rate of type, it is possible to periodically newest second deep learning model is issued to terminal device, to improve pavement image
Road surface breakage detection accuracy.
In the present embodiment, center road surface testing result can also be obtained by the second deep learning model, then compared
The road surface abnormality detection result and center road surface testing result that same pavement image obtains, when road surface abnormality detection result and center
When pavement detection result is inconsistent, using center road surface testing result as final road surface abnormality detection result.
From above-described embodiment it is found that constantly training the second depth by the pavement image for acquiring a large amount of terminal device
Model is practised, the second deep learning model can be constantly optimized, the accuracy rate of the second deep learning model is improved, to improve road
The accuracy rate of face damage testing.
As shown in Fig. 2, in one embodiment of the invention, it is above-mentioned after pavement image is sent to monitoring center
Method further include:
In S201, the accuracy rate and the second deep learning model of the first deep learning model are obtained according to predetermined period
Accuracy rate.
In the present embodiment, maintenance department is according to on-the-spot investigation, obtains practical surface conditions, and by practical surface conditions with
Road surface abnormality detection result compares, and whether consistent judges the above two, if unanimously, it is determined that its be it is accurate, if inconsistent,
It is judged for inaccuracy, by accurate road surface abnormality detection results all in predetermined period divided by whole road surface abnormality detection knots
Fruit, obtains the accuracy rate of the first deep learning model, this step method is applied to terminal device.
Similarly, by accurate center road surface testing results all in predetermined period divided by all center pavement detection knots
Fruit, obtains the accuracy rate of the second deep learning model, and the method for this step is applied to monitoring center.
In the present embodiment, terminal device is stored with the accuracy rate of the first deep learning model, can be according to predetermined period
Regularly obtain the accuracy rate of local the first preset deep learning model；Meanwhile terminal device sends accuracy rate acquisition request
To monitoring center, monitoring center sends the accuracy rate of the second deep learning model to terminal device according to accuracy rate acquisition request；
In the present embodiment, the method that terminal device obtains the accuracy rate of the second deep learning model can also include: monitoring center by
More new information is sent to terminal device according to predetermined period, the accuracy rate of the second depth model is carried in more new information.
In S202, the accuracy rate of accuracy rate and the second deep learning model to the first deep learning model compares
Compared with.
In S203, if the accuracy rate of the second deep learning model is greater than the accuracy rate of the first deep learning model, from
Monitoring center obtains the second deep learning model.
In the present embodiment, the accuracy rate for comparing the first deep learning model and the second deep learning model, when the second depth
When spending the accuracy rate of learning model and being greater than the accuracy rate of the first deep learning model, terminal device is under monitoring center transmission pattern
Request is carried, after monitoring center receives model downloading request, sends the second deep learning model to terminal device, terminal device will
First deep learning model replaces with the second deep learning model, makes the second deep learning model as updated first depth
Learning model carries out subsequent pavement detection task.
In S204, the first deep learning model is replaced with into the second deep learning model.
In one embodiment of the invention, the first deep learning model is compared with the accuracy rate of the second deep learning model
Process can also be completed in monitoring center, details are as follows for detailed process:
1) accuracy rate for the first deep learning model that receiving terminal apparatus is sent；
2) compare the size of the accuracy rate of the first deep learning model and the second deep learning model；
3) if the accuracy rate of the second deep learning model is greater than the accuracy rate of the first deep learning model, it is deep to send second
Learning model is spent to terminal device, so that terminal device updates the first deep learning model.
In the present embodiment, by carrying out the comparison of accuracy rate in monitoring center, multiple first depth can be carried out simultaneously
Learning model can reduce the calculating task of terminal device compared with the second deep learning model, improve terminal device
The detection efficiency of road surface breakage task.
From above-described embodiment it is found that although the accuracy rate of the first deep learning model is also promoted by constantly training,
But monitoring center is available to arrive more training samples, therefore the accuracy rate of the second deep learning model is often higher than the
The accuracy rate of one deep learning model, therefore by regularly updating the first deep learning model in terminal device, Neng Gouti
The accuracy of high pavement detection keeps road surface abnormality detection result more accurate.It is more accurate to be provided for maintenance of surface work
Data support.
In one embodiment of the invention, in Fig. 1 step S103 specific implementation flow, details are as follows:
In one embodiment, warning message is sent to pavement preservation terminal, warning message is used to indicate pavement preservation end
It is alarmed according to warning message at end.
In the present embodiment, pavement preservation terminal is placed in maintenance of surface department, maintenance of surface terminal can for computer or
Person's handheld terminal sends warning message to pavement preservation terminal, road surface when monitoring center receives road surface abnormality detection result
Maintenance terminal show road surface abnormality detection result, enable related personnel according to warning message timely road pavement abnormal position into
Row maintenance work.
In the present embodiment, when the road surface breakage type of detection damaged type more serious for destructions such as pit-holes, prison
It is nearest that warning message can also be sent to the road surface abnormal position according to the location information in pavement detection result by control center
Pavement preservation terminal makes the staff nearest apart from the position timely rush to road surface abnormal position, to avoid the breakage
The damage of the person and property is caused to pedestrian or vehicle in road surface.
In one embodiment of the invention, road surface abnormality detection result includes road surface exception type and road surface exception bits
It sets, road surface exception type includes pavement crack, and terminal device includes car-mounted terminal, road surface breakage detection method further include:
According to road surface abnormal position, pavement detection result is shown in the corresponding position of the terminal map of car-mounted terminal.
In the present embodiment, when road surface exception type is pavement crack or pit-hole, by the road surface abnormality detection result
Then label is shown, to remind vehicle driving personnel on the corresponding position of terminal map by the display screen of vehicle
In the presence of damaged road surface abnormal position.
In the present embodiment, monitoring center can also according to the road surface exception type of road surface abnormality detection result it is different into
The different processing of row.When the road surface exception type of road surface abnormality detection result is the more serious breakages such as crack or pit-hole
When, monitoring center can also send broadcast to vehicle termination, so that the vehicle near the section be enable to be subtracted according to broadcast
Speed such as is gone slowly or detours at the movement, and the risk of traffic accident occurs because of road surface breakage for the vehicular traffic for reducing the road surface.
From above-described embodiment it is found that vehicle driving can be reminded by showing road surface abnormality detection result in car-mounted terminal
Personnel avoid road surface abnormal position, to avoid traffic accident caused by due to road surface breakage.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Embodiment 2:
As shown in figure 3, a kind of road surface breakage detection device 100 of the invention, for executing in embodiment corresponding to Fig. 1
Method and step comprising:
Image capture module 110, for obtaining the collected pavement image of acquisition device；
Testing result obtains module 120, for pavement image to be inputted the first deep learning being preset in terminal device
Model obtains road surface abnormality detection result；
Testing result sending module 130, for road surface abnormality detection result to be sent to monitoring center, so that monitoring center
It is alerted according to road surface abnormality detection result.
From above-described embodiment it is found that the embodiment of the present invention obtains the collected pavement image of acquisition device first；Then will
Pavement image inputs the first deep learning model being preset in terminal device, obtains road surface abnormality detection result；Finally by road
Face abnormality detection result is sent to monitoring center, so that monitoring center is alerted according to road surface abnormality detection result.The present invention
Embodiment acquires pavement image by acquisition device, and pavement image is inputted the first deep learning by the method for image recognition
It is calculated in model, obtains road surface abnormality detection result, improve the accuracy of road surface breakage detection, meanwhile, it is deep by first
Degree learning model is preset in terminal device, can be the detection for completing pavement image in terminal device, to disperse road surface
The task of detection improves the detection efficiency of road surface breakage, further provides efficient, high-quality data branch for maintenance of surface work
It holds.
In one embodiment of the invention, road surface breakage detection device 100 further include:
Pavement image sending module, for pavement image to be sent to monitoring center, so that monitoring center is by pavement image
The second deep learning model is inputted, the second deep learning model is trained.
From above-described embodiment it is found that constantly training the second deep learning mould by the pavement image for acquiring a large amount of terminal
Type can constantly optimize the second deep learning model, improve the accuracy rate of the second deep learning model, so that it is broken to improve road surface
Damage the accuracy rate of detection.
As shown in figure 4, in one embodiment of the invention, the road surface breakage detection device 100 shown in Fig. 3 further includes using
In the structure for executing the method and step in embodiment corresponding to Fig. 2 comprising:
Accuracy rate obtains module 140, for obtaining the accuracy rate and second of the first deep learning model according to predetermined period
The accuracy rate of deep learning model；
Accuracy rate comparison module 150, for the accuracy rate and the second deep learning model to the first deep learning model
Accuracy rate is compared；
Second deep learning model receiving module 160, if the accuracy rate for the second deep learning model is greater than first deeply
The accuracy rate of learning model is spent, then obtains the second deep learning model from monitoring center；
Model modification module 170, for the first deep learning model to be replaced with the second deep learning model.
From above-described embodiment it is found that although the accuracy rate of the first deep learning model is also being mentioned by constantly training
It rises, but monitoring center is available to arrive more training samples, therefore the accuracy rate of the second deep learning model is often high
In the accuracy rate of the first deep learning model, therefore by regularly updating the first deep learning model in terminal device, energy
The accuracy for enough improving pavement detection, keeps road surface abnormality detection result more accurate.To be provided more for maintenance of surface work
Accurate data are supported.
In one embodiment of the invention, the testing result sending module 130 in embodiment corresponding to Fig. 3 is also used to
Warning message is sent to pavement preservation terminal, warning message is used to indicate pavement preservation terminal and alarms according to warning message.
In one embodiment of the invention, road surface abnormality detection result includes road surface exception type and road surface exception bits
It sets, road surface exception type includes pavement crack, and terminal device includes car-mounted terminal, road surface breakage detection device 100 further include:
According to road surface abnormal position, pavement detection result is shown in the corresponding position of the terminal map of car-mounted terminal.
From above-described embodiment it is found that vehicle driving can be reminded by showing road surface abnormality detection result in car-mounted terminal
Personnel avoid road surface abnormal position, to avoid traffic accident caused by due to road surface breakage.
In one embodiment, road surface breakage detection device 100 further includes other function module/unit, for realizing reality
Apply the method and step in example 1 in each embodiment.
Embodiment 3:
The embodiment of the invention also provides a kind of terminal devices, including memory, processor and storage are in memory
And the computer program that can be run on a processor, processor are realized when executing computer program such as each implementation in embodiment 1
Step in example, such as step S101 shown in FIG. 1 to step S103.Alternatively, processor is realized such as when executing computer program
The function of each module in each Installation practice in embodiment 2, such as the function of module 110 to 130 shown in Fig. 3.
Terminal device can be desktop PC, notebook, palm PC and cloud server etc. and calculate equipment.Terminal
Equipment may include, but be not limited only to, processor, memory.Such as terminal device can also connect including input-output equipment, network
Enter equipment, bus etc..
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
Memory can be the internal storage unit of the terminal device, such as the hard disk or memory of terminal device.It is described
Memory is also possible to the plug-in type hard disk being equipped on the External memory equipment of the terminal device, such as the terminal device,
Intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash
Card) etc..Further, the memory can also both include the internal storage unit of terminal device or set including external storage
It is standby.The memory is for other programs and data needed for storing the computer program and the terminal device.It is described
Memory can be also used for temporarily storing the data that has exported or will export.
Embodiment 4:
The embodiment of the invention also provides a kind of computer readable storage medium, computer-readable recording medium storage has meter
Calculation machine program is realized the step in each embodiment as described in example 1 above, such as is schemed when computer program is executed by processor
Step S101 shown in 1 to step S103.Alternatively, realizing when the computer program is executed by processor such as institute in embodiment 2
The function for each module in each Installation practice stated, such as the function of module 110 to 130 shown in Fig. 3.
The computer program can be stored in a computer readable storage medium, and the computer program is by processor
When execution, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the computer program includes computer program code,
The computer program code can be source code form, object identification code form, executable file or certain intermediate forms etc..Institute
State computer-readable medium may include: can carry the computer program code any entity or device, recording medium,
USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs
It is bright, the content that the computer-readable medium includes can according in jurisdiction make laws and patent practice requirement into
Row increase and decrease appropriate, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium do not include be electricity
Carrier signal and telecommunication signal.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.
Module or unit in system of the embodiment of the present invention can be combined, divided and deleted according to actual needs.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. a kind of road surface breakage detection method, which is characterized in that be applied to terminal device, comprising:
Obtain the collected pavement image of acquisition device；
The pavement image is inputted to the first deep learning model being preset in the terminal device, obtains road surface abnormality detection
As a result；
The road surface abnormality detection result is sent to monitoring center, so that the monitoring center is according to the road surface abnormality detection
As a result it is alerted.
2. a kind of road surface breakage detection method as described in claim 1, which is characterized in that acquired in the acquisition acquisition device
After the pavement image arrived, further includes:
The pavement image is sent to the monitoring center, so that the monitoring center is deep by pavement image input second
Learning model is spent, the second deep learning model is trained.
3. a kind of road surface breakage detection method as claimed in claim 2, which is characterized in that send out the pavement image described
It send to the monitoring center, further includes:
According to predetermined period obtain the first deep learning model accuracy rate and the second deep learning model it is accurate
Rate；
The accuracy rate of accuracy rate and the second deep learning model to the first deep learning model is compared；
If the accuracy rate of the second deep learning model is greater than the accuracy rate of the first deep learning model, from the prison
Control center obtains the second deep learning model；
The first deep learning model is replaced with into the second deep learning model.
4. a kind of road surface breakage detection method as described in claim 1, which is characterized in that described so that the monitoring center root
It is alerted according to the road surface abnormality detection result, comprising:
Warning message is sent to pavement preservation terminal, the warning message is used to indicate the pavement preservation terminal according to the report
Alert information is alarmed.
5. such as a kind of described in any item road surface breakage detection methods of Claims 1-4, which is characterized in that the road surface is abnormal
Testing result includes road surface exception type and road surface abnormal position, and the road surface exception type includes pavement crack, the terminal
Equipment includes car-mounted terminal, the method also includes:
According to the road surface abnormal position, the pavement detection knot is shown in the corresponding position of the terminal map of the car-mounted terminal
Fruit.
6. a kind of road surface breakage detection device characterized by comprising
Image capture module, for obtaining the collected pavement image of acquisition device；
Testing result obtains module, for the pavement image to be inputted the first deep learning being preset in the terminal device
Model obtains road surface abnormality detection result；
Testing result sending module, for the road surface abnormality detection result to be sent to monitoring center, so that in the monitoring
The heart is alerted according to the road surface abnormality detection result.
7. a kind of road surface breakage detection device as claimed in claim 6, which is characterized in that further include:
Pavement image sending module, for the pavement image to be sent to the monitoring center, so that the monitoring center will
The pavement image inputs the second deep learning model, is trained to the second deep learning model.
8. a kind of road surface breakage detection device as claimed in claim 6, which is characterized in that further include:
Accuracy rate obtains module, for obtaining the accuracy rate and described second of the first deep learning model according to predetermined period
The accuracy rate of deep learning model；
Accuracy rate comparison module, for the first deep learning model accuracy rate and the second deep learning model
Accuracy rate is compared；
Second deep learning model receiving module, if the accuracy rate for the second deep learning model is greater than described first deeply
The accuracy rate of learning model is spent, then obtains the second deep learning model from the monitoring center；
Model modification module, for the first deep learning model to be replaced with the second deep learning model.
9. a kind of terminal device, including memory, processor and storage are in the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 5 when executing the computer program
The step of any one the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810813069.4A CN109255288A (en) | 2018-07-23 | 2018-07-23 | A kind of road surface breakage detection method, device and terminal device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810813069.4A CN109255288A (en) | 2018-07-23 | 2018-07-23 | A kind of road surface breakage detection method, device and terminal device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109255288A true CN109255288A (en) | 2019-01-22 |
Family
ID=65049694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810813069.4A Pending CN109255288A (en) | 2018-07-23 | 2018-07-23 | A kind of road surface breakage detection method, device and terminal device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109255288A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188889A (en) * | 2019-04-28 | 2019-08-30 | 温州市兴海市政建设有限公司 | A kind of urban road surfaces maintenance management system based on preventative maintenance |
| CN110427911A (en) * | 2019-08-12 | 2019-11-08 | 清华大学苏州汽车研究院（吴江） | A kind of Approach for road detection, device, equipment and storage medium |
| CN111126802A (en) * | 2019-12-10 | 2020-05-08 | 福建省高速公路集团有限公司 | Highway inspection and evaluation method and system based on artificial intelligence |
| CN111223320A (en) * | 2020-02-18 | 2020-06-02 | 上汽大众汽车有限公司 | Low-adhesion road surface intelligent driving safety control method based on V2I |
| CN111553902A (en) * | 2020-04-28 | 2020-08-18 | 周欢 | Highway road surface safety monitoring system based on big data |
| CN111681420A (en) * | 2020-06-09 | 2020-09-18 | 北京百度网讯科技有限公司 | Road surface information detection method, device, equipment and storage medium |
| CN111738150A (en) * | 2020-06-22 | 2020-10-02 | 中国银行股份有限公司 | Automatic supervision method, device and system |
| CN111739308A (en) * | 2019-03-19 | 2020-10-02 | 上海大学 | Road abnormal mobile internet of things monitoring system and method for vehicle-road cooperation |
| CN112198899A (en) * | 2020-09-30 | 2021-01-08 | 安徽乐道信息科技有限公司 | Road detection method, equipment and storage medium based on unmanned aerial vehicle |
| CN112326686A (en) * | 2020-11-02 | 2021-02-05 | 坝道工程医院(平舆) | Unmanned aerial vehicle intelligent cruise pavement disease detection method, unmanned aerial vehicle and detection system |
| CN112447091A (en) * | 2019-08-27 | 2021-03-05 | 丰田自动车株式会社 | Display processing device, display processing method, and storage medium |
| CN112669453A (en) * | 2020-11-30 | 2021-04-16 | 蒋先敏 | Town road detecting system |
| CN112702568A (en) * | 2020-12-14 | 2021-04-23 | 广东荣文科技集团有限公司 | Anomaly detection method and related device |
| CN113092502A (en) * | 2021-04-14 | 2021-07-09 | 成都理工大学 | Unmanned aerial vehicle pavement damage detection method and system |
| JP2021125151A (en) * | 2020-02-07 | 2021-08-30 | ソフトバンク株式会社 | Information processing device and terminal |
| CN113670930A (en) * | 2021-07-30 | 2021-11-19 | 安徽吉厚智能科技有限公司 | Battery shell process detection system and method |
| CN113780178A (en) * | 2021-09-10 | 2021-12-10 | 北京百度网讯科技有限公司 | Road detection method, road detection device, electronic equipment and storage medium |
| WO2022083409A1 (en) * | 2020-10-24 | 2022-04-28 | 腾讯科技（深圳）有限公司 | Detection method and simulation method for abnormal road surface of road, and related apparatus |
| CN115112669A (en) * | 2022-07-05 | 2022-09-27 | 重庆大学 | Pavement nondestructive testing identification method based on small sample |
| CN115345881A (en) * | 2022-10-18 | 2022-11-15 | 上海交强国通智能科技有限公司 | Pavement disease detection method based on computer vision |
| CN116558578A (en) * | 2023-07-12 | 2023-08-08 | 中国公路工程咨询集团有限公司 | Road surface condition detection method, device and storage medium |
| US11756006B2 (en) * | 2020-05-07 | 2023-09-12 | Bye UAS LLC | Airport pavement condition assessment methods and apparatuses |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105575119A (en) * | 2015-12-29 | 2016-05-11 | 大连楼兰科技股份有限公司 | Road condition climate deep learning and recognition method and apparatus |
| CN106702870A (en) * | 2017-03-14 | 2017-05-24 | 深圳汇创联合自动化控制有限公司 | Road crack detecting system |
| CN107945153A (en) * | 2017-11-07 | 2018-04-20 | 广东广业开元科技有限公司 | A kind of road surface crack detection method based on deep learning |
-
2018
- 2018-07-23 CN CN201810813069.4A patent/CN109255288A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105575119A (en) * | 2015-12-29 | 2016-05-11 | 大连楼兰科技股份有限公司 | Road condition climate deep learning and recognition method and apparatus |
| CN106702870A (en) * | 2017-03-14 | 2017-05-24 | 深圳汇创联合自动化控制有限公司 | Road crack detecting system |
| CN107945153A (en) * | 2017-11-07 | 2018-04-20 | 广东广业开元科技有限公司 | A kind of road surface crack detection method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 左永霞: "路面破损智能检测系统的关键技术研究", 《中国博士学位论文全文数据库工程科技II辑》 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739308A (en) * | 2019-03-19 | 2020-10-02 | 上海大学 | Road abnormal mobile internet of things monitoring system and method for vehicle-road cooperation |
| CN111739308B (en) * | 2019-03-19 | 2024-01-19 | 上海大学 | Vehicle-road cooperation-oriented road abnormal movement online monitoring system and method |
| CN110188889A (en) * | 2019-04-28 | 2019-08-30 | 温州市兴海市政建设有限公司 | A kind of urban road surfaces maintenance management system based on preventative maintenance |
| CN110427911A (en) * | 2019-08-12 | 2019-11-08 | 清华大学苏州汽车研究院（吴江） | A kind of Approach for road detection, device, equipment and storage medium |
| CN110427911B (en) * | 2019-08-12 | 2023-11-28 | 清华大学苏州汽车研究院（吴江） | Road detection method, device, equipment and storage medium |
| CN112447091A (en) * | 2019-08-27 | 2021-03-05 | 丰田自动车株式会社 | Display processing device, display processing method, and storage medium |
| CN111126802A (en) * | 2019-12-10 | 2020-05-08 | 福建省高速公路集团有限公司 | Highway inspection and evaluation method and system based on artificial intelligence |
| JP2021125151A (en) * | 2020-02-07 | 2021-08-30 | ソフトバンク株式会社 | Information processing device and terminal |
| JP7009527B2 (en) | 2020-02-07 | 2022-01-25 | ソフトバンク株式会社 | Information processing equipment and terminal equipment |
| CN111223320B (en) * | 2020-02-18 | 2021-09-24 | 上汽大众汽车有限公司 | Low-adhesion road surface intelligent driving safety control method based on V2I |
| CN111223320A (en) * | 2020-02-18 | 2020-06-02 | 上汽大众汽车有限公司 | Low-adhesion road surface intelligent driving safety control method based on V2I |
| CN111553902A (en) * | 2020-04-28 | 2020-08-18 | 周欢 | Highway road surface safety monitoring system based on big data |
| US11756006B2 (en) * | 2020-05-07 | 2023-09-12 | Bye UAS LLC | Airport pavement condition assessment methods and apparatuses |
| CN111681420A (en) * | 2020-06-09 | 2020-09-18 | 北京百度网讯科技有限公司 | Road surface information detection method, device, equipment and storage medium |
| CN111738150B (en) * | 2020-06-22 | 2024-02-09 | 中国银行股份有限公司 | Automatic supervision method, device and system |
| CN111738150A (en) * | 2020-06-22 | 2020-10-02 | 中国银行股份有限公司 | Automatic supervision method, device and system |
| CN112198899A (en) * | 2020-09-30 | 2021-01-08 | 安徽乐道信息科技有限公司 | Road detection method, equipment and storage medium based on unmanned aerial vehicle |
| WO2022083409A1 (en) * | 2020-10-24 | 2022-04-28 | 腾讯科技（深圳）有限公司 | Detection method and simulation method for abnormal road surface of road, and related apparatus |
| CN112326686B (en) * | 2020-11-02 | 2024-02-02 | 坝道工程医院(平舆) | Unmanned aerial vehicle intelligent cruising pavement disease detection method, unmanned aerial vehicle and detection system |
| CN112326686A (en) * | 2020-11-02 | 2021-02-05 | 坝道工程医院(平舆) | Unmanned aerial vehicle intelligent cruise pavement disease detection method, unmanned aerial vehicle and detection system |
| CN112669453A (en) * | 2020-11-30 | 2021-04-16 | 蒋先敏 | Town road detecting system |
| CN112702568B (en) * | 2020-12-14 | 2023-11-24 | 广东荣文科技集团有限公司 | Abnormality detection method and related device |
| CN112702568A (en) * | 2020-12-14 | 2021-04-23 | 广东荣文科技集团有限公司 | Anomaly detection method and related device |
| CN113092502A (en) * | 2021-04-14 | 2021-07-09 | 成都理工大学 | Unmanned aerial vehicle pavement damage detection method and system |
| CN113670930A (en) * | 2021-07-30 | 2021-11-19 | 安徽吉厚智能科技有限公司 | Battery shell process detection system and method |
| CN113780178A (en) * | 2021-09-10 | 2021-12-10 | 北京百度网讯科技有限公司 | Road detection method, road detection device, electronic equipment and storage medium |
| CN115112669A (en) * | 2022-07-05 | 2022-09-27 | 重庆大学 | Pavement nondestructive testing identification method based on small sample |
| US11908124B2 (en) | 2022-07-05 | 2024-02-20 | Chongqing University | Pavement nondestructive detection and identification method based on small samples |
| CN115345881A (en) * | 2022-10-18 | 2022-11-15 | 上海交强国通智能科技有限公司 | Pavement disease detection method based on computer vision |
| CN116558578B (en) * | 2023-07-12 | 2023-10-17 | 中国公路工程咨询集团有限公司 | Road surface condition detection method, device and storage medium |
| CN116558578A (en) * | 2023-07-12 | 2023-08-08 | 中国公路工程咨询集团有限公司 | Road surface condition detection method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109255288A (en) | A kind of road surface breakage detection method, device and terminal device | |
| CN205920517U (en) | Intelligent movement routing inspection terminal based on thing networking | |
| CN110769195B (en) | Intelligent monitoring and recognizing system for violation of regulations on power transmission line construction site | |
| CN112863172A (en) | Highway traffic running state judgment method, early warning method, device and terminal | |
| CN110032916A (en) | A kind of method and apparatus detecting target object | |
| CN112613569B (en) | Image recognition method, training method and device for image classification model | |
| CN108053653A (en) | Vehicle behavior Forecasting Methodology and device based on LSTM | |
| CN107657390A (en) | A kind of special safety equipment hidden danger management and control big data monitoring system and monitoring method | |
| CN114140300A (en) | Method, device, storage medium and terminal for identifying vehicle stop points based on GPS data | |
| CN110263748A (en) | Method and apparatus for sending information | |
| CN112434260A (en) | Road traffic state detection method and device, storage medium and terminal | |
| CN112069894A (en) | Wire strand scattering identification method based on fast-RCNN model | |
| CN114882213A (en) | Animal weight prediction estimation system based on image recognition | |
| CN112529836A (en) | High-voltage line defect detection method and device, storage medium and electronic equipment | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN117094660A (en) | Construction monitoring method and system based on digital twin technology | |
| CN114926795B (en) | Method, device, equipment and medium for determining information relevance | |
| CN115494871A (en) | Unmanned aerial vehicle inspection method, device and system for power transmission line abnormity | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN115240101A (en) | Medical sample forwarding and monitoring system based on scene analysis | |
| CN115100546A (en) | Mobile-based small target defect identification method and system for power equipment | |
| CN114038040A (en) | Machine room inspection monitoring method, device and equipment | |
| CN113850773A (en) | Detection method, device, equipment and computer readable storage medium | |
| CN113888481A (en) | Bridge deck disease detection method, system, equipment and storage medium | |
| CN112115876A (en) | Water-soluble method experimental process identification method based on 3D convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190122 |
|
| RJ01 | Rejection of invention patent application after publication |