CN115012281A - Road pavement quality detection method and device - Google Patents
Road pavement quality detection method and device Download PDFInfo
- Publication number
- CN115012281A CN115012281A CN202210600602.5A CN202210600602A CN115012281A CN 115012281 A CN115012281 A CN 115012281A CN 202210600602 A CN202210600602 A CN 202210600602A CN 115012281 A CN115012281 A CN 115012281A
- Authority
- CN
- China
- Prior art keywords
- numerical value
- preset
- inclination angle
- vertical acceleration
- road 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.)
- Granted
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
- E01C23/01—Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs
-
- G—PHYSICS
- 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
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Structural Engineering (AREA)
- Civil Engineering (AREA)
- Architecture (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method and a device for detecting road pavement quality, wherein the method comprises the following steps: acquiring a road pavement image of a detection area; inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement of the detection area and the probability lambda of the damage type; acquiring the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area; and determining the road pavement quality according to the probability lambda of the damage type of the road pavement, the inclination angle theta, the vertical acceleration alpha and respective weights thereof. The method improves the precision and efficiency of road pavement quality detection.
Description
Technical Field
The invention relates to the technical field of unmanned road pavement quality detection. In particular to a method and a device for detecting the road pavement quality.
Background
Manual detection is mostly adopted for road maintenance at the present stage. However, the construction technology adopted for maintaining and repairing roads is not advanced enough, the operation efficiency of road construction is affected due to incomplete configuration of advanced mechanical equipment, and although some road maintenance and repair units have operation equipment with high technological content, the knowledge level of related technical operators is limited, and the due efficiency of the mechanical equipment cannot be effectively exerted. The maintenance construction technology level of the road is not high due to the factors of low construction operation efficiency, old road maintenance machinery, insufficient service level of operation technicians and the like. Therefore, the difficulty in the road maintenance process is that the manual road maintenance technology is not high in level, and time and labor are wasted.
Although a multifunctional road detection vehicle has been developed in some developed areas, the multifunctional road detection vehicle still needs manual driving and manual correction of detection results, is large in size, expensive in manufacturing cost, inflexible to use, incapable of being put into use in a large area and low in use efficiency, and still cannot meet the requirement of urgent need of the society for detecting the quality of road surfaces.
Disclosure of Invention
Due to the problems of the existing method, the application provides a road pavement quality detection method and a device.
In a first aspect, the present application provides a method for detecting road surface quality, including:
acquiring a road pavement image of a detection area;
inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement of the detection area and the probability lambda of the damage type;
acquiring the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area;
and determining the road pavement quality according to the probability lambda of the damage type of the road pavement, the inclination angle theta, the vertical acceleration alpha and respective weights thereof.
In one possible implementation, the obtaining of the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area includes:
acquiring the inclination angle of the unmanned vehicle in the detection area through a camera integrated with a gyroscope;
and acquiring the vertical acceleration of the unmanned vehicle in the detection area through an inertial navigation sensor.
In one possible implementation, the road surface image recognition model is obtained by:
acquiring a road damage data set, wherein the road damage data set comprises crack data and/or depression data;
inputting the fracture class data and the hole class data into a first model, the first model being a YOLOv5 model introducing an SE attention mechanism;
extracting features of the crack type data and/or features of the hole type data;
determining the similarity between the characteristics of the crack data and/or the characteristics of the hollow data and preset characteristics, and obtaining the damage type of the road surface of the detection area and the probability lambda of the damage type;
comparing the probability lambda with a preset probability, and adjusting the parameter of the first model;
and repeating the steps until an iteration termination condition is met, and obtaining the road pavement image recognition model.
In one possible implementation, the determining the road surface quality according to the probability λ of the damage type to which the road surface belongs, the inclination angle θ, the vertical acceleration α, and the respective weights thereof includes:
if the damage type of the road pavement is a crack type, increasing a first value by 1 every time the probability lambda is increased by 0.1, wherein the first value belongs to [0, a first preset value ]; and is
When the inclination angle theta belongs to [0 DEG and a first preset inclination angle ], every time 1 DEG is added, a second numerical value increases by 1, the second numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the first preset inclination angle, the second numerical value is the second preset numerical value; and is provided with
The vertical acceleration alpha belongs to [0 ], and the first preset vertical acceleration]When the amount is increased by 1m/s 2 A third value increased by 1, said third value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a first preset vertical acceleration, the third numerical value is a third preset numerical value;
and determining the road pavement quality according to the first numerical value, the second numerical value, the third numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
In one possible implementation, the determining the road surface quality according to the probability λ of the damage type to which the road surface belongs, the inclination angle θ, the vertical acceleration α, and the respective weights thereof includes:
if the damage type of the road surface is a pothole type, increasing a fourth numerical value by 1 every time the probability lambda is increased by 0.1, wherein the fourth numerical value belongs to [0, a first preset numerical value ]; and is
When the inclination angle theta belongs to [0 DEG and a second preset inclination angle ], a fifth numerical value increases by 1 every time 2 DEG is increased, and the fifth numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the second preset inclination angle, the fifth numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the second preset vertical acceleration]When the amount is increased by 2m/s each time 2 A sixth value increased by 1, said sixth value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a second preset vertical acceleration, the sixth numerical value is a third preset numerical value;
and determining the road pavement quality according to the fourth numerical value, the fifth numerical value, the sixth numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
In a second aspect, the present application provides a road surface quality detection device, including:
the receiving and transmitting unit is used for acquiring a road pavement image of the detection area;
the processing unit is used for inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement of the detection area and the probability lambda of the damage type;
the receiving and sending unit is used for acquiring the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area;
the processing unit is used for determining the road pavement quality according to the probability lambda of the damage type of the road pavement, the inclination angle theta, the vertical acceleration alpha and respective weights thereof.
In one possible implementation, the processing unit is specifically configured to:
if the damage type of the road pavement is a crack type, increasing a first value by 1 every time the probability lambda is increased by 0.1, wherein the first value belongs to [0, a first preset value ]; and is provided with
When the inclination angle theta belongs to [0 DEG and a first preset inclination angle ], every time 1 DEG is added, a second numerical value increases by 1, the second numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the first preset inclination angle, the second numerical value is the second preset numerical value; and is provided with
The vertical acceleration alpha belongs to [0 ], and the first preset vertical acceleration]When the amount is increased by 1m/s 2 A third value increased by 1, said third value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a first preset vertical acceleration, the third numerical value is a third preset numerical value;
and determining the road surface quality according to the first numerical value, the second numerical value, the third numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
In one possible implementation, the processing unit is specifically configured to:
if the damage type of the road surface is a pothole type, increasing a fourth numerical value by 1 every time the probability lambda is increased by 0.1, wherein the fourth numerical value belongs to [0, a first preset numerical value ]; and is
When the inclination angle theta belongs to [0 DEG and a second preset inclination angle ], a fifth numerical value increases by 1 every time 2 DEG is increased, and the fifth numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the second preset inclination angle, the fifth numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the second preset vertical acceleration]When the amount is increased by 2m/s each time 2 A sixth value increased by 1, said sixth value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a second preset vertical acceleration, the sixth numerical value is a third preset numerical value;
and determining the road pavement quality according to the fourth numerical value, the fifth numerical value, the sixth numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
In a third aspect, the present application also proposes a road surface quality detection device comprising at least one processor for executing a program stored in a memory, which when executed, causes the device to perform the steps as in the first aspect and in various possible implementations.
In a fourth aspect, the present application also proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps as in the first aspect and the various possible implementations.
According to the technical scheme, the camera and the sensor carried by the unmanned vehicle are used for identifying the road surface image of the detection area and the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area. And inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement in the detection area and the probability lambda of the damage type. And determining the road pavement quality according to the probability lambda, the inclination angle theta, the vertical acceleration alpha and the respective weights of the damage types of the road pavement. The method improves the precision and efficiency of road pavement quality detection.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a road pavement quality detection method according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a road surface quality detection device provided in the embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
It should be noted that the term "and/or" in this application is only one kind of association relationship describing the associated object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. The terms "first," "second," and "third," etc. in the description and claims of the embodiments of the present application are used for distinguishing between different objects and not for describing a particular order of the objects. For example, the first preset numerical value, the second preset numerical value, the third preset numerical value, and the like are used for distinguishing different preset numerical values, and are not used for describing a specific order of the target objects. In the embodiments of the present application, words such as "exemplary," "for example," or "such as" are used to mean serving as examples, illustrations, or illustrations. Any embodiment or design described herein as "exemplary," "for example," or "such as" is not necessarily to be construed as advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion. In the description of the embodiments of the present application, the meaning of "a plurality" means two or more unless otherwise specified.
In a possible implementation, the multifunctional road pavement quality detection vehicle is manually driven, detection results are manually corrected, the efficiency is low, and the urgent road pavement quality detection requirement of the society still cannot be met.
In order to solve the technical problem, the embodiment of the application provides a road pavement quality detection method. The schematic flow diagram is shown in fig. 1, and specifically includes: S101-S104;
s101, acquiring a road pavement image of the detection area.
In the embodiment of the application, the camera is arranged on the unmanned vehicle, and the road pavement image of the detection area is obtained through the camera.
And S102, inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement of the detection area and the probability lambda of the damage type.
In the embodiment of the application, the road pavement image is input into the road pavement image recognition model, and the damage type and the probability lambda of the road pavement in the detection area are obtained.
In one example, a road pavement image is input into the road pavement image recognition model. The road pavement image recognition model extracts the characteristics of the road pavement image. The road pavement image recognition model determines the similarity between the characteristics of the road pavement image and the first preset characteristics, namely the probability lambda of the damage type of the road pavement in the detection area. And determining the damage type corresponding to the first preset feature corresponding to the maximum similarity as the damage type of the road surface of the detection area. And the road surface image identification model outputs the damage type of the road surface of the detection area and the probability lambda of the damage type.
In one possible implementation, the road surface image recognition model is obtained by:
step 1, acquiring a road damage data set, wherein the road damage data set comprises crack data and/or hollow data;
step 2, inputting crack data and hollow data into a first model, wherein the first model is a YOLOv5 model introducing an SE attention mechanism;
step 3, extracting characteristics of crack data and/or pothole data;
step 4, determining the similarity between the characteristics of the crack data and/or the characteristics of the hollow data and preset characteristics, and obtaining the damage type of the road surface of the detection area and the probability lambda of the damage type;
step 5, comparing the probability lambda with a preset probability, and adjusting the parameter of the first model;
and 6, repeating the steps until an iteration termination condition is met, and obtaining the road pavement image recognition model.
And S103, acquiring the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area.
In the embodiment of the application, the inclination angle of the unmanned vehicle in the detection area is obtained through the camera integrated with the gyroscope; and acquiring the vertical acceleration of the unmanned vehicle in the detection area through an inertial navigation sensor.
And S104, determining the road surface quality according to the probability lambda, the inclination angle theta, the vertical acceleration alpha and the respective weights of the damage types of the road surface.
In the embodiment of the application, the road surface quality is determined according to the probability lambda of the damage type to which the road surface belongs, the inclination angle theta, the vertical acceleration alpha and the respective weights thereof. The road surface quality comprises the steps of smooth road surface, uneven road surface and extremely uneven road surface.
In one example, if the damage type of the road pavement is a crack type, a first value increases by 1 every time the probability λ increases by 0.1, and the first value belongs to [0, a first preset value ]; and is
When the inclination angle theta belongs to [0 DEG and a first preset inclination angle ], every time 1 DEG is added, a second numerical value increases by 1, the second numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the first preset inclination angle, the second numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the first preset vertical acceleration]When the amount is increased by 1m/s 2 A third value increased by 1, said third value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a first preset vertical acceleration, the third numerical value is a third preset numerical value;
and determining a seventh numerical value according to the first numerical value, the second numerical value, the third numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
And determining the road surface quality according to the seventh numerical value and the first preset standard. The first preset standard is that when the seventh numerical value is larger than 0 and smaller than 1.8, the road pavement quality is that the road pavement is smooth, when the seventh numerical value is larger than 1.8 and smaller than 6.1, the road pavement quality is that the road pavement is not smooth, and when the seventh numerical value is larger than 6.1, the road pavement quality is that the road pavement is extremely rough.
In yet another example, if the damage type of the road surface is a pothole type, a fourth value increases by 1 every time the probability λ increases by 0.1, and the fourth value ∈ [0, a first preset value ]; and is provided with
When the inclination angle theta belongs to [0 DEG and a second preset inclination angle ], a fifth numerical value increases by 1 every time 2 DEG is increased, and the fifth numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the second preset inclination angle, the fifth numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the second preset vertical acceleration]When the amount is increased by 2m/s each time 2 A sixth value increased by 1, said sixth value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a second preset vertical acceleration, the sixth numerical value is a third preset numerical value;
and determining an eighth numerical value according to the fourth numerical value, the fifth numerical value, the sixth numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
And determining the road surface quality according to the eighth numerical value and a second preset standard. The second preset standard is that when the eighth numerical value is larger than 0 and smaller than 2.3, the road pavement quality is the level road, when the eighth numerical value is larger than 2.3 and smaller than 6.4, the road pavement quality is the uneven road pavement, and when the eighth numerical value is larger than 6.4, the road pavement quality is the extremely uneven road pavement.
Illustratively, if the damage type of the road pavement is crack type, the probability λ is increased by 0.1, a first value is increased by 1, and the first value is epsilon [0,10 ]]The probability λ is weighted 60%. In the embodiment of the present application, the probability λ is 70%, and then the first value is 7; and the inclination angle theta epsilon [0 DEG, 10 DEG ]]At each 1 deg. increase, a second value increases by 1, said second value ∈ [0,10 ]]Or when the inclination angle theta is larger than 10 degrees, the second numerical value is still 10, and the weight of the inclination angle theta is 10%. In the embodiment of the present application, if the inclination angle θ is 3 °, the second value is 3; and the vertical acceleration alpha epsilon [0,10m/s ] 2 ]When the amount is increased by 1m/s 2 A third value increased by 1, said third value ∈ [0,10 ]]Or the vertical acceleration alpha is more than 10m/s 2 While the third value is still 10, the vertical acceleration α is weighted 30%. In the embodiment of the present application, the vertical acceleration α is 2m/s 2 The third value is 2. The seventh value 7 + 60% +3 + 10 is determined according to the first value 7, the second value 3, the third value 2 and their corresponding weights, i.e. 60%, 10% and 30%% 2 × 30% + 5.1. According to the first preset standard, the road surface quality is uneven.
According to the scheme, the road surface image of the detection area and the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area are identified through the camera and the sensor which are carried by the unmanned vehicle. And inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement in the detection area and the probability lambda of the damage type. And determining the road pavement quality according to the probability lambda, the inclination angle theta, the vertical acceleration alpha and the respective weights of the damage types of the road pavement. The method improves the precision and efficiency of road pavement quality detection.
Fig. 2 is a schematic structural diagram of a road surface quality detection device provided in an embodiment of the present application, where the schematic structural diagram includes: a transceiving unit 201 and a processing unit 202;
the transceiver 201 is configured to obtain a road surface image of a detection area;
the processing unit 202 is configured to input the road surface image into a road surface image identification model, and obtain a damage type and a probability of the road surface of the detection area;
the transceiver unit 201 is configured to acquire an inclination angle and a vertical acceleration of the unmanned vehicle in the detection area;
the processing unit 202 is configured to determine the road pavement quality according to the probability λ of the damage type to which the road pavement belongs, the inclination angle θ, the vertical acceleration α, and their respective weights.
In a possible implementation, the processing unit 202 is specifically configured to:
if the damage type of the road pavement is a crack type, increasing a first value by 1 every time the probability lambda is increased by 0.1, wherein the first value belongs to [0, a first preset value ]; and is
When the inclination angle theta belongs to [0 DEG and a first preset inclination angle ], every time 1 DEG is added, a second numerical value increases by 1, the second numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the first preset inclination angle, the second numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the first preset vertical acceleration]When the amount is increased by 1m/s 2 A third value increased by 1, said third value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a first preset vertical acceleration, the third numerical value is a third preset numerical value;
and determining the road pavement quality according to the first numerical value, the second numerical value, the third numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
In a possible implementation, the processing unit 202 is specifically configured to:
if the damage type of the road surface is a pothole type, increasing a fourth numerical value by 1 every time the probability lambda is increased by 0.1, wherein the fourth numerical value belongs to [0, a first preset numerical value ]; and is provided with
When the inclination angle theta belongs to [0 DEG and a second preset inclination angle ], a fifth numerical value increases by 1 every time 2 DEG is increased, and the fifth numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the second preset inclination angle, the fifth numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the second preset vertical acceleration]When the amount is increased by 2m/s each time 2 A sixth value increased by 1, said sixth value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a second preset vertical acceleration, the sixth numerical value is a third preset numerical value;
and determining the road pavement quality according to the fourth numerical value, the fifth numerical value, the sixth numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
Embodiments of the present application further provide a road surface quality detection apparatus, including at least one processor, where the processor is configured to execute a program stored in a memory, and when the program is executed, the apparatus is enabled to execute the aforementioned road surface quality detection method.
An embodiment of the present application provides a non-transitory computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the foregoing road surface quality detection method.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
It should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A road surface quality detection method is characterized by comprising the following steps:
acquiring a road pavement image of a detection area;
inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement of the detection area and the probability lambda of the damage type;
acquiring the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area;
and determining the road pavement quality according to the probability lambda of the damage type of the road pavement, the inclination angle theta, the vertical acceleration alpha and respective weights thereof.
2. The method of claim 1, wherein the obtaining of the inclination angle and the vertical acceleration of the unmanned vehicle at the detection area comprises:
acquiring the inclination angle of the unmanned vehicle in the detection area through a camera integrated with a gyroscope;
and acquiring the vertical acceleration of the unmanned vehicle in the detection area through an inertial navigation sensor.
3. The method of claim 1, wherein the road pavement image recognition model is obtained by:
acquiring a road damage data set, wherein the road damage data set comprises crack data and/or depression data;
inputting the fracture class data and the hole class data into a first model, the first model being a YOLOv5 model introducing an SE attention mechanism;
extracting features of the crack type data and/or features of the hole type data;
determining the similarity between the characteristics of the crack data and/or the characteristics of the hollow data and preset characteristics, and obtaining the damage type of the road surface of the detection area and the probability lambda of the damage type;
comparing the probability lambda with a preset probability, and adjusting the parameter of the first model;
and repeating the steps until an iteration termination condition is met, and obtaining the road pavement image recognition model.
4. The method according to claim 1, wherein the determining the road pavement quality according to the probability λ of the damage type to which the road pavement belongs, the inclination angle θ, the vertical acceleration a and respective weights thereof comprises:
if the damage type of the road pavement is a crack type, increasing a first value by 1 every time the probability lambda is increased by 0.1, wherein the first value belongs to [0, a first preset value ]; and is
When the inclination angle theta belongs to [0 DEG and a first preset inclination angle ], every time 1 DEG is added, a second numerical value increases by 1, the second numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the first preset inclination angle, the second numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the first preset vertical acceleration]When the amount is increased by 1m/s 2 A third value increased by 1, said third value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a first preset vertical acceleration, the third numerical value is a third preset numerical value;
and determining the road pavement quality according to the first numerical value, the second numerical value, the third numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
5. The method according to claim 1, wherein the determining the road pavement quality according to the probability λ of the damage type to which the road pavement belongs, the inclination angle θ, the vertical acceleration a and respective weights thereof comprises:
if the damage type of the road surface is a pothole type, increasing a fourth numerical value by 1 every time the probability lambda is increased by 0.1, wherein the fourth numerical value belongs to [0, a first preset numerical value ]; and is
When the inclination angle theta belongs to [0 DEG and a second preset inclination angle ], a fifth numerical value increases by 1 every time 2 DEG is increased, and the fifth numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the second preset inclination angle, the fifth numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the second preset vertical acceleration]When the amount is increased by 2m/s each time 2 A sixth value increased by 1, said sixth value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a second preset vertical acceleration, the sixth numerical value is a third preset numerical value;
and determining the road pavement quality according to the fourth numerical value, the fifth numerical value, the sixth numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
6. The utility model provides a road surface quality detection device which characterized in that includes:
the receiving and sending unit is used for acquiring a road pavement image of the detection area;
the processing unit is used for inputting the road pavement image into a road pavement image recognition model to obtain the damage type of the road pavement of the detection area and the probability lambda of the damage type;
the receiving and sending unit is used for acquiring the inclination angle and the vertical acceleration of the unmanned vehicle in the detection area;
and the processing unit is used for determining the road pavement quality according to the probability lambda of the damage type of the road pavement, the inclination angle theta, the vertical acceleration alpha and respective weights thereof.
7. The apparatus according to claim 6, wherein the processing unit is specifically configured to:
if the damage type of the road pavement is a crack type, increasing a first value by 1 every time the probability lambda is increased by 0.1, wherein the first value belongs to [0, a first preset value ]; and is
When the inclination angle theta belongs to [0 DEG and a first preset inclination angle ], every time 1 DEG is added, a second numerical value increases by 1, the second numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the first preset inclination angle, the second numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the first preset vertical acceleration]When the amount is increased by 1m/s 2 A third value increased by 1, said third value being ∈ [0 ], a third preset value]Or when the vertical acceleration alpha is larger than a first preset vertical acceleration, the third numerical value is a third preset numerical value;
and determining the road pavement quality according to the first numerical value, the second numerical value, the third numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
8. The apparatus according to claim 6, wherein the processing unit is specifically configured to:
if the damage type of the road surface is a pothole type, increasing a fourth numerical value by 1 every time the probability lambda is increased by 0.1, wherein the fourth numerical value belongs to [0, a first preset numerical value ]; and is
When the inclination angle theta belongs to [0 DEG and a second preset inclination angle ], a fifth numerical value increases by 1 every time 2 DEG is increased, and the fifth numerical value belongs to [0 ] and a second preset numerical value, or when the inclination angle theta is larger than the second preset inclination angle, the fifth numerical value is the second preset numerical value; and is
The vertical acceleration alpha belongs to [0 ], and the second preset vertical acceleration]When the amount is increased by 2m/s each time 2 A sixth value increased by 1, the sixth value being e [0 ], a third predetermined value]Or when the vertical acceleration alpha is larger than a second preset vertical acceleration, the sixth numerical value is a third preset numerical value;
and determining the road pavement quality according to the fourth numerical value, the fifth numerical value, the sixth numerical value and the corresponding weights of the probability lambda, the inclination angle theta and the vertical acceleration alpha.
9. A road surface quality detection apparatus comprising at least one processor for executing a program stored in a memory, the program, when executed, causing the apparatus to perform:
the method of any one of claims 6-8.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 6-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210600602.5A CN115012281B (en) | 2022-05-30 | 2022-05-30 | Road surface quality detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210600602.5A CN115012281B (en) | 2022-05-30 | 2022-05-30 | Road surface quality detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115012281A true CN115012281A (en) | 2022-09-06 |
| CN115012281B CN115012281B (en) | 2023-09-05 |
Family
ID=83071799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210600602.5A Active CN115012281B (en) | 2022-05-30 | 2022-05-30 | Road surface quality detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115012281B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207091888U (en) * | 2016-12-01 | 2018-03-13 | 毛庆洲 | Road road conditions fast investigation device and test car |
| CN113191398A (en) * | 2021-04-12 | 2021-07-30 | 河海大学 | Improved Faster R-CNN-based pavement damage identification method |
| CN113537016A (en) * | 2021-07-06 | 2021-10-22 | 南昌市微轲联信息技术有限公司 | Method for automatically detecting and early warning road damage in road patrol |
| CN113609911A (en) * | 2021-07-07 | 2021-11-05 | 北京工业大学 | Pavement disease automatic detection method and system based on deep learning |
| CN113628164A (en) * | 2021-07-12 | 2021-11-09 | 北京科技大学 | Pavement crack detection method based on deep learning and web end positioning |
| CN113706472A (en) * | 2021-07-30 | 2021-11-26 | 中国公路工程咨询集团有限公司 | Method, device and equipment for detecting road surface diseases and storage medium |
| CN114066808A (en) * | 2021-10-11 | 2022-02-18 | 内蒙古科技大学 | Pavement defect detection method and system based on deep learning |
| CN114518094A (en) * | 2020-11-16 | 2022-05-20 | 阿里巴巴集团控股有限公司 | Road detection method and system |
-
2022
- 2022-05-30 CN CN202210600602.5A patent/CN115012281B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207091888U (en) * | 2016-12-01 | 2018-03-13 | 毛庆洲 | Road road conditions fast investigation device and test car |
| CN114518094A (en) * | 2020-11-16 | 2022-05-20 | 阿里巴巴集团控股有限公司 | Road detection method and system |
| CN113191398A (en) * | 2021-04-12 | 2021-07-30 | 河海大学 | Improved Faster R-CNN-based pavement damage identification method |
| CN113537016A (en) * | 2021-07-06 | 2021-10-22 | 南昌市微轲联信息技术有限公司 | Method for automatically detecting and early warning road damage in road patrol |
| CN113609911A (en) * | 2021-07-07 | 2021-11-05 | 北京工业大学 | Pavement disease automatic detection method and system based on deep learning |
| CN113628164A (en) * | 2021-07-12 | 2021-11-09 | 北京科技大学 | Pavement crack detection method based on deep learning and web end positioning |
| CN113706472A (en) * | 2021-07-30 | 2021-11-26 | 中国公路工程咨询集团有限公司 | Method, device and equipment for detecting road surface diseases and storage medium |
| CN114066808A (en) * | 2021-10-11 | 2022-02-18 | 内蒙古科技大学 | Pavement defect detection method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115012281B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11094198B2 (en) | Lane determination method, device and storage medium | |
| EP3944211A2 (en) | Traffic data analysis method and apparatus, electronic device, vehicle, storage medium and program product | |
| CN110308423B (en) | Indoor vehicle-mounted laser positioning method and system based on reflector | |
| CN108305239B (en) | Bridge crack image repairing method based on generation type countermeasure network | |
| CN110838112A (en) | Insulator defect detection method based on Hough transform and YOLOv3 network | |
| CN102385707A (en) | Digital picture recognizing method and device and crawler server | |
| CN113379712A (en) | Steel bridge bolt disease detection method and system based on computer vision | |
| CN104915678A (en) | Method and device for detecting target object in power transmission line | |
| CN110796066A (en) | Lane line group construction method and device | |
| CN111144498A (en) | Image identification method and device | |
| CN114037966A (en) | High-precision map feature extraction method, device, medium and electronic equipment | |
| CN113189989A (en) | Vehicle intention prediction method, device, equipment and storage medium | |
| CN110109165B (en) | Method and device for detecting abnormal points in driving track | |
| CN115012281A (en) | Road pavement quality detection method and device | |
| CN105657021A (en) | Method, apparatus and cloud server for processing power system defects | |
| CN117058459A (en) | Rapid pavement disease detection method and system based on YOLOV7 algorithm | |
| CN111259102A (en) | Map updating method, electronic device and storage medium | |
| CN116465316A (en) | Batch measurement method, device, equipment and medium for steel thickness | |
| CN116542998A (en) | Contour detection method, device, equipment and medium for photoetching film inductance | |
| CN112270663B (en) | Asphalt pavement sieving and repairing system based on honeycomb network environment | |
| CN113670295B (en) | Data processing method, device, electronic equipment and readable storage medium | |
| CN115731458A (en) | Processing method and device for remote sensing image and electronic equipment | |
| CN114677777A (en) | Equipment inspection method, inspection system and terminal equipment | |
| Shao et al. | Crack detection and measurement using PTZ camera–based image processing method on expressways | |
| CN111651689A (en) | Data processing method and device, readable storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |