CN115993440A - Evolution rule analysis method for pavement pit - Google Patents
Evolution rule analysis method for pavement pit Download PDFInfo
- Publication number
- CN115993440A CN115993440A CN202211440624.6A CN202211440624A CN115993440A CN 115993440 A CN115993440 A CN 115993440A CN 202211440624 A CN202211440624 A CN 202211440624A CN 115993440 A CN115993440 A CN 115993440A
- Authority
- CN
- China
- Prior art keywords
- pit
- matrix
- dimensional
- depth
- factors
- 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
Images
Landscapes
- Road Repair (AREA)
Abstract
The invention discloses an evolution rule analysis method of a pavement pit slot, and belongs to the field of road detection. According to the invention, based on the depth information and the outline information of the pit, the pit depth distribution factors and the expansion factors are constructed and are respectively used for representing the depth distribution and the plane distribution of the pit, the change gradients of the pit depth distribution factors and the expansion factors are calculated by collecting the depth distribution factors and the expansion factors corresponding to different times, the analysis of the evolution rule of the pit in the two directions of depth and plane is realized, the development direction and the development speed of the pit can be accurately judged, the formation reason of the pit is further presumed, the pit diseases can be repaired by adopting scientific maintenance measures, the maintenance cost is reduced, and the safety of vehicle running is improved.
Description
Technical Field
The invention belongs to the field of road detection, and particularly relates to an evolution rule analysis method of a pavement pit.
Background
The road is an important infrastructure for vehicles and pedestrians to pass through, and the service state of the road influences the traveling effect of the vehicles and pedestrians. The automobile conservation amount in China breaks through 2.8 hundred million vehicles, the traditional just-needed travel mode is difficult to meet the increasing requirements of good life of people on transportation travel, and the travel quality of people is further improved from the angle of road facilities. The repair of pavement diseases is a problem which needs to be solved in order to improve the travel quality. The pit is one of common diseases on road surfaces, and has a large influence on safe running of vehicles. When the vehicle tire passes through the pit slot, jolt occurs, the driving direction is changed when serious, serious threat is caused to driving safety, and meanwhile, the reaction force born by the vehicle at the pit slot is large, so that the service life of the tire and the vehicle is reduced. Therefore, the road surface pit diseases are found in time, reasonable maintenance measures are formulated, and the influence of the pit on the traveling of people is reduced. On the other hand, the repairing effect of the pit depends on the accuracy of analysis of the pit forming reason, and the accurate disease cause analysis can ensure the rationality of the pit repairing decision, thereby achieving the purposes of reducing maintenance cost and improving road service quality.
At present, the detection of road pit diseases usually adopts a camera to shoot, and then the detection is carried out according to the two-dimensional characteristics of the pit images. Because the depth information of the pit cannot be directly obtained, the volume information is difficult to directly obtain. With the development of detection technology, the structured light scanning technology is mature, and the acquisition of three dimensional information of the road surface in the horizontal direction and the depth direction in the driving environment can be realized. On the basis, the measurement and calculation of pit volume can be realized through the processing of the acquired data, and the calculation result can be used for guiding maintenance decision and measuring and calculating the engineering quantity of the disease repair material.
However, the current research and invention has two problems in identifying and calculating three-dimensional pits: (1) In the aspect of pit identification efficiency, the three-dimensional pit contains mass data, the traditional manual identification method has low efficiency, and the intelligent identification method has high calculation power requirement on a computer and high resource consumption; (2) In the evaluation index of the evolution rule of the pit on the road surface, the change of the pit is generally reflected only by adopting a volume value, and the diversity of the evolution rule of the pit, the development direction and the development speed of the pit cannot be represented. The mastering of the development direction and development speed of the pit is the basis for accurately judging the cause of the pit, so that a maintenance strategy can be accurately formulated, and the driving safety is effectively ensured.
Aiming at the problems, the invention provides an evolution rule analysis method of a pavement pit.
Disclosure of Invention
Aiming at the defects or improvement demands of the prior art, the invention provides an evolution rule analysis method of a pavement pit, and aims to solve the technical problems that the existing method cannot characterize the diversity of the evolution rule of the pit and the development direction and development speed of the pit.
In order to achieve the above object, the present invention provides a method for analyzing evolution rules of a pavement pit, comprising:
s1, collecting three-dimensional point cloud information of a road surface, and marking a non-pit-slot area and a pit-slot area to obtain a three-dimensional matrix L; converting the three-dimensional matrix L into a two-dimensional matrix M containing pit depth information by adopting a plane projection mode;
s2, ordering the elements in the two-dimensional matrix M according to the depth, counting the element numbers corresponding to different depth values, and calculating the ratio of the element numbers corresponding to different depth values to the total element numbers;
s3, according to the difference of attention degrees of users to different pit depths, weighting is given to the corresponding duty ratio of different depth values, and pit depth distribution factors are calculated; the pit depth distribution factors represent development conditions of the pits along the depth direction;
s4, calculating the average area of the edge matrix corresponding to the whole pit slot to obtain a pit slot expansion factor; the pit expansion factors represent development conditions of the pits along the plane direction;
s5, sequentially acquiring three-dimensional point cloud information of corresponding pits at different moments, and executing steps S1-S4 on the three-dimensional point cloud information of the pits acquired at each moment to obtain pit distribution factors and pit expansion factors at corresponding times;
s6, according to the change gradient of the pit distribution factors and the change gradient of the pit expansion factors, a pit evolution rule is obtained.
Further, the pit depth distribution factor is:
nhi represents the number corresponding to different depth values, S represents the number of all elements in the two-dimensional matrix, q represents the weight, h i Representing elements corresponding to different depth values.
Further, the two-dimensional matrix M construction method is as follows:
x and y are coordinates in two directions respectively, z is the vertical axis direction of the matrix L, and the vertical downward direction is the positive direction; n is the number of pages of the three-dimensional matrix L, i is the i-th page, i=1, 2,3, …, N represents the number of pages of the three-dimensional matrix.
Further, the step S4 specifically includes:
sequentially extracting an ith page L (x, y, i) of the three-dimensional matrix L to obtain a matrix Li, and extracting an edge contour matrix Fi of the Li;
the matrix Li is respectively carried out with the matrix B and the matrix C as follows:
Li B ＝Li[x,y]*B[x,y]
Li C ＝Li[x,y]*C[x,y]
where, represents convolution operation, li B A new matrix formed by the operation of the image matrix Li and the matrix B; li (Li) C A new matrix formed by the operation of the image matrix Li and the matrix C; matrix B and matrix C represent edge operators;
calculation of Li B And Li (lithium) C Obtaining a pit edge matrix Fi by the maximum value of the same position in the matrix;
calculating the area A of pit edge matrix Fi Fi ＝∑Fi(x,y)；
Calculating the average area Z of the matrix of the corresponding edge of the whole pit to obtain the pit expansion factor
Further, before executing step S6, the method further comprises correcting the pit depth distribution factor and the expansion factor according to the system error,obtaining pit correction depth distribution factor U' q And pit correction expansion factor Z'.
Further, pit correction depth distribution factor U' q And pit correction expansion factor Z' is:
v represents the systematic error.
Further, step S1 includes:
converting the three-dimensional point cloud information of the road surface into a three-dimensional matrix H; establishing a pit edge matrix for each layer of three-dimensional point cloud information of the road surface;
cutting the three-dimensional matrix H by utilizing a matrix formed by non-zero values in the pit edge matrix to form a three-dimensional matrix J representing the external cuboid of the three-dimensional pit area;
and (3) translating a plane K parallel to the pavement from top to bottom or from bottom to top to intersect with the matrix J, and marking a non-pit area and a pit area respectively in the intersecting process to obtain a three-dimensional matrix L.
In general, the above technical solution conceived by the present invention can achieve the following advantageous effects compared to the prior art.
(1) The reasons for forming the pit grooves are various, including factors such as vehicle running speed, vehicle load, road materials, environment and the like, the development characteristics of the pit grooves formed by different factors are different, and corresponding pit groove repairing measures are also different; however, the traditional three-dimensional detection method cannot analyze the development direction of the pit, and is difficult to propose scientific maintenance measures for repairing the pit, so that the pit repairing effect is poor, diseases repeatedly appear, and the maintenance cost is increased;
according to the invention, based on the depth information and the outline information of the pit, the pit depth distribution factors and the expansion factors are constructed and are respectively used for representing the depth distribution and the plane distribution of the pit, the change gradients of the pit depth distribution factors and the expansion factors are calculated by collecting the depth distribution factors and the expansion factors corresponding to different times, the analysis of the evolution rule of the pit in the two directions of depth and plane is realized, the development direction and the development speed of the pit can be accurately judged, the formation reason of the pit is further presumed, the pit diseases can be repaired by adopting scientific maintenance measures, the maintenance cost is reduced, and the safety of vehicle running is improved.
(2) The plane projection method provided by the invention can project the position information on a plane, thereby realizing the purpose of reducing the dimension of the pit matrix, and simultaneously, the point cloud depth information is reserved on the two-dimensional plane matrix in the form of plane matrix elements, thereby realizing the efficient conversion from the three-dimensional pit matrix to the two-dimensional matrix, and solving the problems of high computational power requirement and long computation time of the three-dimensional data processing on the computer; meanwhile, under the condition of not increasing the calculation load of the system, the information of the pit depth direction is considered, and the analysis accuracy is improved.
(3) The invention adopts a mathematical statistics mode to obtain the distribution frequency and the duty ratio of different pit depth values, introduces weight parameters, and can be used for representing the weight difference of different pit depths to reflect the attention degree of maintenance management personnel to the pit depths.
(4) According to the method, when the depth distribution factor and the expansion factor are calculated, the influence of a system error is considered, and the accuracy of a calculation result is improved.
Drawings
Fig. 1 is a flowchart of an evolution law analysis method of a pavement pit.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
With reference to fig. 1, the method of the present invention comprises the steps of:
s1, collecting three-dimensional point cloud information of a road surface, and marking a non-pit-slot area and a pit-slot area to obtain a three-dimensional matrix L; converting the three-dimensional matrix L into a two-dimensional matrix M containing pit depth information by adopting a plane projection mode;
the step S1 specifically comprises the following steps:
collecting three-dimensional point cloud information of a road surface, and converting the three-dimensional point cloud information into a three-dimensional matrix H; establishing a pit edge matrix for each layer of three-dimensional point cloud information of the road surface;
cutting the three-dimensional matrix H by utilizing a matrix formed by non-zero values in the pit edge matrix to form a three-dimensional matrix J representing the external cuboid of the three-dimensional pit area; specifically, searching for non-zero values in matrix F to form a new matrix G; cutting the three-dimensional matrix H by adopting the matrix G to form a three-dimensional matrix J, wherein J is an external cuboid matrix of the three-dimensional pit slot area;
translating a plane K parallel to the pavement from top to bottom or from bottom to top to intersect with the matrix J, and marking a non-pit slot area and a pit slot area respectively in the intersecting process to obtain a three-dimensional matrix L; specifically, the translation step length is 1 pixel, in the process of intersecting the plane K and the three-dimensional matrix J, the non-pit area is 0, and the pit area is recorded as 1, so that a three-dimensional matrix L consisting of 0 and 1 can be obtained in the three-dimensional matrix J;
converting the three-dimensional matrix L into a two-dimensional matrix M containing pit depth information by adopting a plane projection mode;
the three-dimensional matrix of the pit is established in the steps, and the three-dimensional matrix calculation process has high computer power requirement, large occupied resources and high calculation cost, so the resource requirement of matrix calculation is reduced by converting the three-dimensional matrix of the pit into a two-dimensional matrix.
The existing plane projection mode mainly focuses on the projection of the point cloud position information, and after the projection is finished, the information in the depth direction of the point cloud is deleted, so that only plane information can be analyzed. For this case, the present invention improves the method of planar projection. The plane projection method provided by the invention can project the position information on a plane, thereby realizing the purpose of reducing the dimension of the pit matrix, and simultaneously, the point cloud depth information is reserved on a two-dimensional plane matrix in the form of plane matrix elements.
Based on the three-dimensional matrix L, a new two-dimensional matrix M is constructed by the following construction method:
wherein z is the vertical axis direction of the matrix L, and the vertical downward direction is the positive direction; n is the number of pages of the three-dimensional matrix L, and i is the ith page; elements in the two-dimensional matrix represent depth information of different pit positions;
s2, ordering the elements in the two-dimensional matrix M according to the depth, counting the element numbers corresponding to different depth values, and calculating the ratio of the element numbers corresponding to different depth values to the total element numbers;
specifically, in the two-dimensional matrix M, each element value represents a depth value of a corresponding position. Since the depth distribution inside the same pit of the road surface is random and disordered, the size arrangement of the elements in the two-dimensional matrix M is random. In order to analyze the depth distribution rule of pits, a mathematical statistics method is adopted, firstly, unnecessary data is required to be converted into ordered data, therefore, the elements in the two-dimensional matrix M are firstly ordered according to the depth, and are sequentially marked as h1, h2, …, hi … and hn, wherein if the values of a plurality of elements are the same in size, the elements are marked only once: and counting the number of elements corresponding to different depth values, and sequentially marking as Nh1, nh2, … and Nhn. The ratio Ti of the total number S of the numbers of different depths is calculated, and the calculation method is as follows:
where Nhi represents the number of matrix element values corresponding to a depth with a rank value of hi.
S3, according to the difference of attention degrees of users to different pit depths, weighting is given to the corresponding duty ratio of different depth values, and pit depth distribution factors are calculated; the pit depth distribution factors represent development conditions of the pits along the depth direction;
in analyzing pit depth information, different pit depths with different duty ratios may have different attentions of different researchers, for example: some people pay attention to the occurrence frequency or occupy a larger pit depth; while others may be more concerned about the overall pit depth distribution. The present invention therefore introduces the concept of a weight q in the duty cycle Ti, denoted as the conversion duty cycle Tiz,
when q is more than 1, the depth value with higher occurrence frequency in the pit is shown to have higher attention;
when q=1, it is shown that the focus on the depth values with higher frequency and lower frequency in the pit is the same;
when q <1, it is shown that the depth value with lower occurrence frequency in pit is of higher attention.
The invention gives weight to the depth value occupation ratio, which is helpful for maintenance personnel to consider the depth value occupation ratio when the maintenance personnel determine the concerned depth value; meanwhile, the occupation ratio is adopted, so that the influence of dimension can be eliminated, the calculation is simple and convenient, and the universality of the method is improved.
The invention introduces pit depth distribution factor U q The larger the value is, the deeper the overall distribution depth of the pit is; the faster the value changes, indicating faster development in the depth direction. Compared with the traditional pit characterization index (volume and depth), the index considers the difference of attention of road maintenance personnel to different pit depths, and is calculated based on all acquired data, so that the calculation result is more accurate, and the overall depth condition of the whole pit can be accurately reflected.
S4, calculating the average area of the edge matrix corresponding to the whole pit slot to obtain a pit slot expansion factor;
the expansion factor Z of the pit slot means that the pit slot develops along the plane direction, and the expansion factor becomes larger, which indicates that the faster the change speed of the expansion factor is, the faster the expansion speed of the pit slot is. The index is used for evaluating the development condition of the pit in the plane direction.
1) Sequentially extracting the ith page L (x, y, i) of the three-dimensional matrix L, and recording as a matrix Li, i=1, 2,3, …, N; the edge profile matrix Fi of Li is extracted in the following specific manner:
2) The matrices B and C are established as follows:
3) The matrix Li is respectively carried out with the matrix B and the matrix C as follows:
Li B ＝Li[x,y]*B[x,y]
Li C ＝Li[x,y]*C[x,y]
wherein x and y are coordinates in two directions respectively, li B A new matrix formed by the operation of the image matrix Li and the matrix B; li (Li) C A new matrix is formed for the image matrix Li and the matrix C operation.
4) Calculation of Li B And Li (lithium) C In the matrix, the maximum value of the same position is set up, and a pit edge matrix Fi is established, wherein the calculation process is as follows:
Fi＝Max(Li B ,Li C )
5) Calculating the area A of pit edge matrix Fi Fi ：
A Fi ＝∑Fi(x,y)
6) Calculating the average area Z of the matrix corresponding to the edge of the whole pit, wherein the index is the expansion factor of the pit:
as a preferred embodiment of the present invention, considering that the device is affected by sensor instability and the like during the process of collecting data, the system will have an error, and the system error V generally follows a gaussian distribution W, namely:
V～W(μ,σ 2 )
μ is mathematical expectation and σ is standard deviation.
Therefore, the invention adopts Gaussian distribution to respectively correct the pit depth distribution factor and the expansion factor to obtain the pit correction depth distribution factor U' q And correcting the expansion factor Z':
s5, sequentially acquiring three-dimensional point cloud information of corresponding pits at different moments, and executing steps S1-S4 on the three-dimensional point cloud information of the pits acquired at each moment to obtain pit distribution factors and pit expansion factors at corresponding times;
specifically, data of different times are collected, corresponding pit correction depth distribution factors and correction expansion factors are calculated, correction depth distribution factor change gradients and correction expansion factor change gradients are calculated, and pit size change rules are analyzed, wherein the method specifically comprises the following steps:
1) Sequentially collecting three-dimensional point cloud information of pits corresponding to the times t1, t2, … and tN, and repeating the steps S1-S6 to obtain a corrected pit distribution factor U 'corresponding to the time' q1 ,U' q2 ,…,U' qN And correcting pitExpansion factor Z' 1 ,Z' 2 ,…,Z' N The method comprises the steps of carrying out a first treatment on the surface of the The pit distribution factor variation gradient dU is established and calculated as follows:
Δt＝t i+1 -t i
wherein Deltat is the time interval, t i+1 And t i The (i+1) th time and the (i) th time, U' qi And U' q(i+1) The corrected pit distribution factors at the i-th time and the i+1-th time are respectively obtained.
The pit expansion factor change gradient dU is established and calculated as follows:
s6, according to the change gradient of the pit distribution factors and the change gradient of the pit expansion factors, a pit evolution rule is obtained.
Specifically, 1) when dZ >0, du >0, it is shown that the pit develops in both the depth direction and the planar direction;
2) When dZ >0 and du=0, the pit develops in the depth direction and does not develop in the plane direction;
3) When dZ is more than 0 and dU is less than 0, the pit groove is developed along the depth direction and contracts along the plane direction;
4) When dz=0 and du >0, the pit does not develop in the depth direction and develops in the plane direction;
5) When dz=0 and du=0, the pit does not develop in the depth direction and does not develop in the plane direction;
6) When dz=0, dU <0, the pit does not develop in the depth direction and contracts in the plane direction;
7) When dZ <0 and dU >0, the pit becomes shallow along the depth direction and develops along the plane direction;
8) When dZ <0, du=0, it indicates that the pit becomes shallow in the depth direction and does not develop in the planar direction;
9) When dZ <0, dU <0, it indicates that the pit becomes shallower in the depth direction and shrinks in the planar direction.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The evolution rule analysis method of the pavement pit slot is characterized by comprising the following steps of:
s1, collecting three-dimensional point cloud information of a road surface, and marking a non-pit-slot area and a pit-slot area to obtain a three-dimensional matrix L; converting the three-dimensional matrix L into a two-dimensional matrix M containing pit depth information by adopting a plane projection mode;
s2, ordering the elements in the two-dimensional matrix M according to the depth, counting the element numbers corresponding to different depth values, and calculating the ratio of the element numbers corresponding to different depth values to the total element numbers;
s3, according to the difference of attention degrees of users to different pit depths, weighting is given to the corresponding duty ratio of different depth values, and pit depth distribution factors are calculated; the pit depth distribution factors represent development conditions of the pits along the depth direction;
s4, calculating the average area of the edge matrix corresponding to the whole pit slot to obtain a pit slot expansion factor; the pit expansion factors represent development conditions of the pits along the plane direction;
s5, sequentially acquiring three-dimensional point cloud information of corresponding pits at different moments, and executing steps S1-S4 on the three-dimensional point cloud information of the pits acquired at each moment to obtain pit distribution factors and pit expansion factors at corresponding times;
s6, according to the change gradient of the pit distribution factors and the change gradient of the pit expansion factors, a pit evolution rule is obtained.
2. The method for analyzing evolution rules of pavement pits according to claim 1, wherein the pit depth distribution factor is:
nhi represents the number corresponding to different depth values, S represents the number of all elements in the two-dimensional matrix, q represents the weight, h i Representing elements corresponding to different depth values.
3. The evolution law analysis method of the pavement pit slot according to claim 2, wherein the two-dimensional matrix M construction method is as follows:
x and y are coordinates in two directions respectively, z is the vertical axis direction of the matrix L, and the vertical downward direction is the positive direction; n is the number of pages of the three-dimensional matrix L, i is the i-th page, i=1, 2,3, …, N represents the number of pages of the three-dimensional matrix.
4. The evolution law analysis method of a pavement pit according to claim 3, wherein the step S4 specifically includes:
sequentially extracting an ith page L (x, y, i) of the three-dimensional matrix L to obtain a matrix Li, and extracting an edge contour matrix Fi of the Li;
the matrix Li is respectively carried out with the matrix B and the matrix C as follows:
Li B ＝Li[x,y]*B[x,y]
Li C ＝Li[x,y]*C[x,y]
where, represents convolution operation, li B A new matrix formed by the operation of the image matrix Li and the matrix B; li (Li) C A new matrix formed by the operation of the image matrix Li and the matrix C; matrix B and matrix C represent edge operators;
calculation of Li B And Li (lithium) C Obtaining a pit edge matrix Fi by the maximum value of the same position in the matrix;
calculating pit edge matrix FiArea A Fi ＝∑Fi(x,y)；
Calculating the average area Z of the matrix of the corresponding edge of the whole pit to obtain the pit expansion factor
5. The method according to claim 4, further comprising correcting the pit depth distribution factor and the expansion factor according to the systematic error, respectively, to obtain a pit correction depth distribution factor U' q And pit correction expansion factor Z'.
6. The method for analyzing evolution law of pavement pit according to claim 5, wherein the pit correction depth distribution factor U' q And pit correction expansion factor Z' is:
v represents the systematic error.
7. The method for analyzing evolution law of a pavement pit according to any one of claims 1 to 6, wherein step S1 comprises:
converting the three-dimensional point cloud information of the road surface into a three-dimensional matrix H; establishing a pit edge matrix for each layer of three-dimensional point cloud information of the road surface;
cutting the three-dimensional matrix H by utilizing a matrix formed by non-zero values in the pit edge matrix to form a three-dimensional matrix J representing the external cuboid of the three-dimensional pit area;
and (3) translating a plane K parallel to the pavement from top to bottom or from bottom to top to intersect with the matrix J, and marking a non-pit area and a pit area respectively in the intersecting process to obtain a three-dimensional matrix L.
8. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the evolution law analysis method of a road surface pit according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211440624.6A CN115993440A (en) | 2022-11-17 | 2022-11-17 | Evolution rule analysis method for pavement pit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211440624.6A CN115993440A (en) | 2022-11-17 | 2022-11-17 | Evolution rule analysis method for pavement pit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115993440A true CN115993440A (en) | 2023-04-21 |
Family
ID=85991313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211440624.6A Pending CN115993440A (en) | 2022-11-17 | 2022-11-17 | Evolution rule analysis method for pavement pit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115993440A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116612400A (en) * | 2023-05-30 | 2023-08-18 | 衡水金湖交通发展集团有限公司 | Road management method and system based on road flatness |
| CN117079146A (en) * | 2023-10-17 | 2023-11-17 | 深圳市城市交通规划设计研究中心股份有限公司 | Linear crack evolution law analysis method |
-
2022
- 2022-11-17 CN CN202211440624.6A patent/CN115993440A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116612400A (en) * | 2023-05-30 | 2023-08-18 | 衡水金湖交通发展集团有限公司 | Road management method and system based on road flatness |
| CN116612400B (en) * | 2023-05-30 | 2024-03-19 | 衡水金湖交通发展集团有限公司 | Road management method and system based on road flatness |
| CN117079146A (en) * | 2023-10-17 | 2023-11-17 | 深圳市城市交通规划设计研究中心股份有限公司 | Linear crack evolution law analysis method |
| CN117079146B (en) * | 2023-10-17 | 2024-02-27 | 深圳市城市交通规划设计研究中心股份有限公司 | Linear crack evolution law analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115993440A (en) | Evolution rule analysis method for pavement pit | |
| CN102651075B (en) | Training method for vehicle identification model, and vehicle identification method and apparatus | |
| CN106228185B (en) | A kind of general image classifying and identifying system neural network based and method | |
| CN111027430B (en) | Traffic scene complexity calculation method for intelligent evaluation of unmanned vehicles | |
| CN112016605B (en) | Target detection method based on corner alignment and boundary matching of bounding box | |
| CN110544233B (en) | Depth image quality evaluation method based on face recognition application | |
| CN106600612A (en) | Damage identification and detection method for electric automobile before and after renting | |
| CN106708989A (en) | Spatial time sequence data stream application-based Skyline query method | |
| CN115205264A (en) | High-resolution remote sensing ship detection method based on improved YOLOv4 | |
| CN107564290A (en) | A kind of urban road intersection saturation volume rate computational methods | |
| CN109615627A (en) | A kind of power transmission and transformation inspection image quality evaluating method and system | |
| CN114976306A (en) | Intelligent echelon utilization method of power lithium battery based on vehicle-connected cloud | |
| CN106446538B (en) | Vehicle terminal and travel time computation method based on dynamic time warping | |
| Liu et al. | M-YOLO based detection and recognition of highway surface oil filling with unmanned aerial vehicle | |
| CN111738527B (en) | Urban traffic cell division method based on hot spot detection model | |
| Sun et al. | Decoupled feature pyramid learning for multi-scale object detection in low-altitude remote sensing images | |
| CN116052110B (en) | Intelligent positioning method and system for pavement marking defects | |
| Lu et al. | Road Condition Detection Based on Deep Learning YOLOv5 Network | |
| CN110705854A (en) | Driving level evaluation method and system | |
| CN112100731B (en) | Method and system for establishing fatigue load calculation model | |
| CN115358504A (en) | National logistics city pivotal sorting model under complex network view angle | |
| CN115100173A (en) | Highway pavement image crack geometric attribute detection and crack identification method based on deep convolutional neural network | |
| Song et al. | Fast detection of multi-direction remote sensing ship object based on scale space pyramid | |
| Lu et al. | Research on Defect Recognition of Ceramic Chips for High Temperature Fuel Cells Based on Improved Faster R-CNN | |
| Lu | Evaluation and Comparison of Deep Learning Methods for Pavement Crack Identification with Visual Images |
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 |