CN115907361A - Road construction planning method, medium and electronic device for artificial intelligence big data - Google Patents
Road construction planning method, medium and electronic device for artificial intelligence big data Download PDFInfo
- Publication number
- CN115907361A CN115907361A CN202211415871.0A CN202211415871A CN115907361A CN 115907361 A CN115907361 A CN 115907361A CN 202211415871 A CN202211415871 A CN 202211415871A CN 115907361 A CN115907361 A CN 115907361A
- Authority
- CN
- China
- Prior art keywords
- road construction
- road
- image
- area
- planning
- 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
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Abstract
The application provides a road construction planning method, medium and electronic equipment of artificial intelligence big data, which are applied to the technical field of road construction, wherein the method comprises the following steps: acquiring a road construction plan and an urban road plane map to generate a planning area corresponding to the road construction plan, and performing binarization processing on the urban road plane map; modeling the road construction area image according to a spatial map neural network algorithm; performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data; determining various attributes of the planned area, and detecting the planned area according to a sparse label prediction algorithm of the urban area; comprehensively detecting data, and determining a road construction track for each subdivided region image; the purpose of consistency between road construction planning and project planning is achieved, and the collected information is effectively converted and comprehensively analyzed.
Description
Technical Field
The application relates to the technical field of road construction, in particular to a road construction planning method, medium and electronic equipment for artificial intelligence big data.
Background
With the increasing development level of cities, road construction needs to be better improved and convenient in practice, and in order to better adapt to the change trend of the big data artificial intelligence era, it is necessary to increase the technical content of road construction planning, so that the application of the road construction planning in the big data artificial intelligence era is more efficient, but the following problems exist in the existing road construction planning:
at present, in the work of road construction planning, in a basic analysis stage, data from multiple industries such as urban construction, traffic, water affairs, gardens, city management, natural resources and planning are collected, so that the collected information cannot be effectively converted, and the road construction planning and the project planning are inconsistent;
refer to patent application No. CN 202110571984.9-a highway pavement full life cycle quality tracing method based on artificial intelligence discloses: the tracing method comprises the steps of firstly establishing a database by using historical data of a plurality of roads, and then establishing a road use performance prediction neural network model by using the database and an artificial neural network. On the basis of the performance prediction model, maintenance decisions are provided for the expressway in the operation period, and construction period data of the expressway in the construction period can be planned by combining a genetic algorithm to guide construction. The invention takes various index data of the whole life cycle of the road as an investigation object, respectively processes the data according to different attributes of each index, integrates the data into a database, and realizes the whole life cycle tracing of the highway by combining an artificial neural network and a genetic algorithm.
In the prior art, maintenance decision and construction guidance of roads are optimized, but for the scheme, how to comprehensively and reasonably analyze and process road construction exists, so that the application provides a road construction planning method, medium and electronic equipment for artificial intelligent big data.
Disclosure of Invention
The application aims to provide a road construction planning method, medium and electronic equipment for artificial intelligence big data, and aims to solve the problem that collected information cannot be effectively converted, so that the road construction planning and project planning are inconsistent.
In order to achieve the above purpose, the present application provides the following technical solutions:
the application provides a road construction planning method for artificial intelligence big data, which comprises the following steps:
s1: acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
s2: modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image;
s3: performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data;
s4: determining various attributes of the planned area, and detecting the planned area according to a sparse label prediction algorithm of the urban area;
s5: and determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking the central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm.
Further, the step of modeling the road construction area image according to a spatial graph neural network algorithm to obtain information on relative distance and angle between two points in a geographic space of the road construction area image includes:
setting the input signal of the input layer of the neural network as
Which is represented as an i-th characteristic of an N-th sample in the road construction area image, and which is present in the road construction area image>
An output signal of ith characteristic of an nth sample in a road construction area image is represented, an error of a connection output layer is calculated by using an error of an input signal and an output signal, a connection weight of a network is continuously adjusted and changed through the error, and an error function is as follows:
wherein d is the feature number of the road construction area image of the input data, N is the sample number of the input data,
，/>
，/>
，/>
respectively representing the connection weight between the mapping layer and the input layer, the bottleneck layer and the mapping layer, the mapping layer and the bottleneck layer, and the output layer and the mapping layer.
Further, the step of performing region segmentation on the road construction region image, and segmenting into each subdivided region image based on road network data includes:
and performing regional segmentation on the road construction region image by using regional separation aggregation, judging image regions which do not meet the same property based on road network data, dividing the image regions into four sub-quadrant regions, and continuing dividing the image regions if the sub-quadrant regions do not meet the same property until all the sub-quadrant regions meet the same property.
Further, in the step of determining various attributes of the planning area and detecting the planning area according to the urban area sparse label prediction algorithm, the various attributes are road planning grade, road planning red line width, road planning length, conversion project type, total project investment and construction period of the calculation; and calculating the average annual investment of the project according to the total investment and the construction period of the frame calculation project.
Further, the urban area sparse tag prediction algorithm comprises:
assuming that a set W = { W1, W2, W3, \ 8943;, wi } represents non-repeating construction objects, i represents the number of construction objects, a set U = { U1, U2, U3, \ 8943;, uj } represents non-repeating roads, j represents the number of roads, an adjacent 0-1 matrix of roads and construction objects is constructed by using the construction object set and the road set as row coordinates and column coordinates of a road construction matrix, if the jth road is concerned with the behavior of the ith construction object, then (j, i) =1 in the matrix, otherwise, 0; performing characteristic decomposition, and selecting a singular value decomposition method, wherein the formula is as follows:
wherein U represents a left singular matrix; a is a singular value diagonal matrix; v represents a right singular matrix, the singular value decomposition method depends on the matrix A to shrink the range of the original matrix, and in the shrinking process, the valid and invalid matrix ranges need to be judged for dimension reduction data.
Further, the step of determining the road construction track for each subdivided region image by the data of the comprehensive detection, taking the central point in each subdivided region image as a node, selecting one of the nodes as an initial node, and determining the initial road construction track by using the initial node and the remaining nodes based on a shortest path algorithm includes:
and obtaining a road construction track for representing the road construction plan of the current project, comparing the road construction track with the predicted road construction track to obtain a compared track deviation result, and re-determining the road construction area image and updating the predicted road construction track when judging that the track deviation degree is greater than the predicted road construction track degree.
Further, the track deviation result is sent to a monitoring platform, and the monitoring platform is used for performing deviation rectification processing according to the track deviation result and providing a suggestion of the current road construction plan.
The application also provides a device for road construction planning of artificial intelligence big data, including:
an acquisition module: acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
a modeling module: modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image;
a cutting module: performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data;
a detection module: determining various attributes of the planned area, and detecting the planned area according to a sparse label prediction algorithm of the urban area;
a determination module: and determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking the central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm.
The application also provides computer equipment which comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to realize the steps of the artificial intelligence big data road construction planning method.
The present application also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the above-mentioned artificial intelligence big data road construction planning method.
The application provides a road construction planning method, medium and electronic equipment for artificial intelligence big data, and has the following beneficial effects:
(1) Converting the obtained urban road plane map into a road construction area image, and detecting according to different attributes of a planning area to lay a foundation for road construction planning;
(2) Modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image, so that the aim of keeping the road construction plan consistent with the project plan is fulfilled;
(3) The road construction track is determined for each subdivided region image of the road construction region image which is distinguished and finished by utilizing the data of comprehensive detection, a central point in each subdivided region image is taken as a node, one of the nodes is selected as an initial node, the initial node and the rest nodes are utilized, the initial road construction track is determined based on a shortest path algorithm, comparison is carried out according to the predicted road track, the road construction track is updated in real time, and the road construction planning is more convenient and flexible.
Drawings
Fig. 1 is a schematic flow chart of a road construction planning method for artificial intelligence big data according to an embodiment of the present application;
fig. 2 is a block diagram illustrating a road construction planning apparatus for artificial intelligence big data according to an embodiment of the present application;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the present application will be further described with reference to the embodiments, which are illustrated in the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
Referring to fig. 1, a schematic flow chart of a road construction planning method for artificial intelligence big data provided by the present application is shown;
the road construction planning method for the artificial intelligence big data comprises the following steps:
s1: acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
in the step, the urban road plane map acquisition method includes that an unmanned aerial vehicle carrying an RGB-D camera with a top view angle is used for carrying out image acquisition processing on a project to-be-operated area, in order to avoid the situation that a single shot image cannot cover the whole project to-be-operated area, therefore, a plurality of shot RGB-D four-channel images are subjected to feature point matching and image splicing operation to obtain a complete urban road plane map, in addition, a binary processed to-be-operated area binary image is the same as the urban road plane map in size, the pixel value of a pixel point in the to-be-planned area in the binary processed binary image is set to be 1, and the pixel value of a pixel point in a non-planned area is set to be 0.
S2: modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image; setting the input signal of the input layer of the neural network as
Which is expressed as the i-th characteristic of the nth sample in the road construction area image, is greater than or equal to>
The method comprises the steps of representing an ith characteristic output signal of an Nth sample in a road construction area image, calculating an error of a connection output layer by using an error of an input signal and the output signal, continuously adjusting and changing a connection weight of a network through the error, wherein an error function is as follows:
wherein d is the feature number of the road construction area image of the input data, N is the sample number of the input data,
，/>
，/>
，/>
respectively representing a connection weight between a mapping layer and an input layer, a bottleneck layer and the mapping layer, the mapping layer and the bottleneck layer, and an output layer and the mapping layer;
in the step, the error of the output signal and the input signal is used for calculating the error of the connection output layer, the error of the previous layer is calculated by using the error, the error values of all other layers are obtained by reversing the error values layer by layer according to the rule, and the connection weight value of the network is continuously adjusted and changed through error estimation to finish the output of the relative distance and angle information.
S3: performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data; performing regional segmentation on the road construction region image by using regional separation aggregation, judging image regions which do not meet the same property based on road network data, dividing the image regions into four sub-quadrant regions, and continuing dividing the image regions if the sub-quadrant regions do not meet the same property until all the sub-quadrant regions meet the same property;
in the step, the area separation and aggregation is to subdivide the road construction area image into disjoint areas, the subdivided area images can be aggregated or separated, the separation process firstly judges whether the current area meets the characteristic measure of the target, and if not, the current area is separated into a plurality of sub-areas for judgment; continuously and repeatedly judging and separating until the minimum region is split, wherein the segmentation result of region separation usually comprises adjacent regions with the same property, the problem can be solved by aggregation, and the aggregation is carried out only when the union of the adjacent regions meets the characteristic measure of the target; for example: separating all regions Ri that satisfy the condition Q (Ri) = False into 4 disjoint sub-regions; when further separation is impossible, all adjacent regions Rj, rk satisfying the condition Q (Rj $) = True are aggregated; when further polymerization was not possible, the operation was stopped.
S4: determining various attributes of the planned area, and detecting the planned area according to a city area sparse label prediction algorithm; determining various attributes of the planning area, and detecting the planning area according to a city area sparse tag prediction algorithm, wherein the various attributes are road planning grade, road planning red line width, road planning length, conversion project type, and calculating total project investment and construction period; wherein, the total investment and the construction period of the frame calculation project are used for calculating the average annual investment of the project; the urban area sparse label prediction algorithm comprises the following steps:
assuming that a set W = { W1, W2, W3, \ 8943;, wi } represents non-repeating construction objects, i represents the number of construction objects, a set U = { U1, U2, U3, \ 8943;, uj } represents non-repeating roads, j represents the number of roads, an adjacent 0-1 matrix of roads and construction objects is constructed by using the set of construction objects and the set of roads as row coordinates and column coordinates of a road construction matrix, and if the jth road is associated with a behavior with the ith construction object, an adjacent 0-1 matrix of roads and construction objects is constructed(j, i) =1 in the matrix, otherwise 0; performing characteristic decomposition, and selecting a singular value decomposition method, wherein the formula is as follows:
wherein U represents a left singular matrix; a is a singular value diagonal matrix; v represents a right singular matrix, the singular value decomposition method depends on the matrix A to shrink the range of an original matrix, and in the shrinking process, the valid and invalid matrix ranges need to be judged for dimension reduction data;
in the step, a 0-1 matrix of a road and a construction object is constructed, the 0-1 matrix is calculated and reconstructed by using a singular value decomposition method to obtain a road construction characteristic matrix, the bias of the construction object is emphasized, then a logistic regression model is used for training a user behavior characteristic matrix, a construction planning label corresponding to the road is predicted, an effective construction object label is predicted by using the extracted behavior characteristic value from the sparsity in the construction object, and the accurate value of the prediction label is improved, so that a certain reference basis is provided for road construction planning.
S5: determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking a central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm; acquiring a road construction track for representing the road construction plan of the current project, comparing the road construction track with the predicted road construction track to obtain a compared track deviation result, and re-determining the road construction area image and updating the predicted road construction track when judging that the track deviation degree is greater than the predicted road construction track degree; sending the track deviation result to a monitoring platform, wherein the monitoring platform is used for performing deviation rectification processing according to the track deviation result and providing a suggestion of the current road construction plan;
referring to fig. 2, the present invention further provides an apparatus for road construction planning of artificial intelligence big data, comprising:
an acquisition module: acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
a modeling module: modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image;
a cutting module: performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data;
a detection module: determining various attributes of the planned area, and detecting the planned area according to a sparse label prediction algorithm of the urban area;
a determination module: and determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking the central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for data such as road construction areas. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a road construction planning method for artificial intelligence big data.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for planning road construction by using artificial intelligence big data includes the following steps:
acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image;
performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data;
determining various attributes of the planned area, and detecting the planned area according to a city area sparse label prediction algorithm;
and determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking the central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm.
In summary, the road plane map is subjected to binarization processing through binarization processing, a space map neural network algorithm, an urban area sparse label prediction algorithm and area separation aggregation to obtain a road construction area image, and the road construction area image is subjected to modeling and area segmentation to determine a road construction track; the road construction planning method, medium and electronic equipment of artificial intelligence big data provided by the application bypass the traditional artificial analysis of the road construction planning book, reduce the time cost, achieve the aim of consistency of the road construction planning and the project planning, and effectively convert and comprehensively analyze the collected information.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, database or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of another identical element in a process, apparatus, article, or method comprising the element.
The above description is only for the preferred embodiment of the present application and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Although embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the application, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The road construction planning method for the artificial intelligence big data is characterized by comprising the following steps:
s1: acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
s2: modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image;
s3: performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data;
s4: determining various attributes of the planned area, and detecting the planned area according to a sparse label prediction algorithm of the urban area;
s5: and determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking the central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm.
2. The method for road construction planning through artificial intelligence big data according to claim 1, wherein the step of modeling the road construction area image according to a spatial map neural network algorithm to obtain the relative distance and angle information between two points in the geographic space of the road construction area image comprises:
setting the input signal of the input layer of the neural network as
Expressed as the ith property of the nth sample in the road construction area image,
the method comprises the steps of representing an ith characteristic output signal of an Nth sample in a road construction area image, calculating an error of a connection output layer by using an error of an input signal and the output signal, continuously adjusting and changing a connection weight of a network through the error, wherein an error function is as follows:
wherein d is the feature number of the road construction area image of the input data, N is the sample number of the input data,
，
，
，
respectively representing the connection weight between the mapping layer and the input layer, the bottleneck layer and the mapping layer, the mapping layer and the bottleneck layer, and the output layer and the mapping layer.
3. The method for road construction planning of artificial intelligence big data according to claim 1, wherein the step of performing region segmentation on the road construction region image, and segmenting into each subdivided region image based on road network data comprises:
and performing region segmentation on the road construction region image by using region separation aggregation, judging image regions which do not meet the same property based on road network data, dividing the image regions into four sub-quadrant regions, and continuing to divide the image regions if the sub-quadrant regions do not meet the same property until all the sub-quadrant regions meet the same property.
4. The method for road construction planning of artificial intelligence big data according to claim 1, wherein in the step of determining various attributes of the planned area and detecting the planned area according to a city area sparse label prediction algorithm, the various attributes are road planning grade, road planning red line width, road planning length, conversion project type, total investment of frame calculation project and construction period; and calculating the average annual investment of the project according to the total investment and the construction period of the project.
5. The method for road construction planning of artificial intelligence big data according to claim 4, wherein the urban area sparse label prediction algorithm comprises:
assuming that a set W = { W1, W2, W3, \ 8943;, wi } represents a non-repeating construction object, i represents the number of construction objects, a set U = { U1, U2, U3, \ 8943;, uj } represents a non-repeating road, j represents the number of roads, and the row coordinates and the column coordinates of a road construction matrix are set by the construction object set and the road set as the road construction matrixConstructing an adjacent 0-1 matrix of roads and construction objects, wherein if the jth road is concerned with the behavior of the ith construction object, the (j, i) =1 in the matrix, otherwise the matrix is 0; performing characteristic decomposition, and selecting a singular value decomposition method, wherein the formula is as follows:
wherein U represents a left singular matrix; a is a singular value diagonal matrix; v represents a right singular matrix, the singular value decomposition method depends on the matrix A to shrink the range of the original matrix, and in the shrinking process, the valid and invalid matrix ranges need to be judged for dimension reduction data.
6. The method for road construction planning of artificial intelligence big data according to claim 1, wherein the step of determining the road construction track for each subdivided region image by the data of the comprehensive detection, taking the central point in each subdivided region image as a node, selecting one of the nodes as an initial node, and determining the initial road construction track by using the initial node and the remaining nodes based on a shortest path algorithm comprises:
and obtaining a road construction track for representing the road construction plan of the current project, comparing the road construction track with the predicted road construction track to obtain a compared track deviation result, and re-determining the road construction area image and updating the predicted road construction track when judging that the track deviation degree is greater than the predicted road construction track degree.
7. The method for road construction planning of artificial intelligence big data according to claim 6, wherein the trajectory deviation result is sent to a monitoring platform, and the monitoring platform is used for performing deviation rectification processing according to the trajectory deviation result and providing a suggestion of the current road construction planning.
8. The utility model provides a road construction planning's of artificial intelligence big data device which characterized in that includes:
an acquisition module: acquiring a road construction planning book and an urban road plane map to generate a planning area corresponding to the road construction planning book, carrying out binarization processing on the urban road plane map to obtain a binary image, wherein the pixel value of a pixel point in a to-be-planned area in the binary image is a first pixel value, the pixel value of a pixel point in a non-planned area is a second pixel value, and multiplying the binary image by the pixel value of a pixel point at a position corresponding to the to-be-planned area to obtain a road construction area image;
a modeling module: modeling the road construction area image according to a spatial map neural network algorithm to obtain relative distance and angle information between two points in a geographic space of the road construction area image;
a cutting module: performing region segmentation on the road construction region image, and segmenting the road construction region image into each subdivided region image based on road network data;
a detection module: determining various attributes of the planned area, and detecting the planned area according to a city area sparse label prediction algorithm;
the determining module: and determining a road construction track for each subdivided region image by comprehensively detecting data, selecting one node as an initial node by taking the central point in each subdivided region image as a node, and determining the initial road construction track by using the initial node and the residual nodes based on a shortest path algorithm.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein the processor when executing the computer program implements the steps of the artificial intelligence big data road construction planning method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for road construction planning of artificial intelligence big data of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415871.0A CN115907361A (en) | 2022-11-11 | 2022-11-11 | Road construction planning method, medium and electronic device for artificial intelligence big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211415871.0A CN115907361A (en) | 2022-11-11 | 2022-11-11 | Road construction planning method, medium and electronic device for artificial intelligence big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115907361A true CN115907361A (en) | 2023-04-04 |
Family
ID=86475631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211415871.0A Pending CN115907361A (en) | 2022-11-11 | 2022-11-11 | Road construction planning method, medium and electronic device for artificial intelligence big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907361A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957308A (en) * | 2023-09-21 | 2023-10-27 | 武汉市规划研究院 | Urban road section planning method and system |
-
2022
- 2022-11-11 CN CN202211415871.0A patent/CN115907361A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957308A (en) * | 2023-09-21 | 2023-10-27 | 武汉市规划研究院 | Urban road section planning method and system |
| CN116957308B (en) * | 2023-09-21 | 2023-11-24 | 武汉市规划研究院 | Urban road section planning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction | |
| Safaei et al. | An automatic image processing algorithm based on crack pixel density for pavement crack detection and classification | |
| KR101638368B1 (en) | Prediction System And Method of Urban Traffic Flow Using Multifactor Pattern Recognition Model | |
| CN112419710A (en) | Traffic congestion data prediction method, traffic congestion data prediction device, computer equipment and storage medium | |
| Cao et al. | Image processing-based automatic detection of asphalt pavement rutting using a novel metaheuristic optimized machine learning approach | |
| CN111241994A (en) | Method for extracting remote sensing image rural highway desertification road section for deep learning | |
| CN115907361A (en) | Road construction planning method, medium and electronic device for artificial intelligence big data | |
| Sathya et al. | A framework for designing unsupervised pothole detection by integrating feature extraction using deep recurrent neural network | |
| CN115310532A (en) | Basin multipoint prediction early warning method based on space-time association mixed deep learning model | |
| CN111414878A (en) | Method and device for social attribute analysis and image processing of land parcel | |
| Zhou et al. | An attention-based deep learning model for citywide traffic flow forecasting | |
| Shi et al. | An improved framework for assessing the impact of different urban development strategies on land cover and ecological quality changes-A case study from Nanjing Jiangbei New Area, China | |
| Huang et al. | Traffic prediction with transfer learning: A mutual information-based approach | |
| Zhang et al. | Off-deployment traffic estimation—a traffic generative adversarial networks approach | |
| Aslan et al. | Using artifical intelligence for automating pavement condition assessment | |
| Zhai et al. | An efficiency-enhanced deep learning model for citywide crowd flows prediction | |
| Zhang et al. | Pavement crack detection based on deep learning | |
| Baduge et al. | Assessment of crack severity of asphalt pavements using deep learning algorithms and geospatial system | |
| CN115565388A (en) | Traffic light control method based on multi-channel vehicle detection and three-dimensional feature labeling | |
| CN115063684A (en) | Agricultural machinery track identification method based on remote sensing image scene division and application method thereof | |
| CN114118508A (en) | OD market aviation passenger flow prediction method based on space-time convolution network | |
| Zhao et al. | A localization method for stagnant water in city road traffic image | |
| Cao et al. | Traffic condition classification model based on traffic-net | |
| Kyriakou et al. | A low-cost pavement-rating system, based on machine learning, utilising smartphone sensors | |
| Yan et al. | City-scale taxi demand prediction using multisource urban geospatial data |
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 |