Traffic network planning method and system based on multi-source information fusion

Abstract

The invention belongs to the field of traffic road network planning, and particularly relates to a traffic road network planning method and system based on multi-source information fusion, and the method comprises the steps: determining a road network planning region in a traffic key point set by taking a starting point coordinate, a path point coordinate and an end point coordinate as references; creating a traffic road network path planning fitness function in combination with each traffic key point in the road network planning area; and constructing an improved particle swarm algorithm for the traffic road network, optimizing the planned path of the traffic road network by using the constructed improved particle swarm algorithm according to the created fitness function, and obtaining and outputting the optimal planned path of the traffic road network. According to the established fitness function, the planned path of the traffic road network is optimized by using the constructed improved particle swarm algorithm, and the optimal road network planned path can be obtained in the target geographic space, so that the traffic road network planning is more targeted and scientific.

Description

Technical Field

[0001] The present invention belongs to the field of traffic network planning, and in particular relates to a traffic network planning method and system based on multi-source information fusion. Background Art

[0002] Transportation is the vein of the economy and the bond of civilization. Transportation infrastructure is a basic, leading, strategic industry and an important service industry. Roads are engineering facilities for various vehicles and pedestrians to pass through. Highways are roads that connect cities and villages and are mainly for automobiles to travel. They have certain technical conditions and facilities. Urban roads are roads with certain technical conditions and facilities for vehicles and pedestrians to pass through within the city. Urban roads and highways are generally separated by the boundaries of the city. Transportation network planning is a complex and systematic process that aims to ensure the effective layout and coordinated development of transportation facilities to meet the needs of social economy and residents' travel.

[0003] In the related technology, the commonly used road planning method is to count the peak passenger flow and road congestion of each road in real time, and conduct mining and analysis based on the peak passenger flow and road congestion to evaluate whether the current road can meet people's transportation needs, and then carry out corresponding road planning based on the analysis and evaluation results. However, road planning based on peak passenger flow and road congestion is a lagging operation, and planning and construction are often carried out after the road is congested, which is difficult to meet the actual needs of users. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a transportation network planning method and system based on multi-source information fusion, aiming to solve the technical problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions.

[0006] An embodiment of the present invention provides a traffic network planning method based on multi-source information fusion, comprising:

[0007] In response to a traffic road network path planning request for a target geographic space, the terrain data of the target geographic space and a multi-source data set that affects the road network planning are fused to obtain a set of traffic key points containing characteristic data of influencing factors;

[0008] In the set of key traffic points, the coordinates of the starting point, the coordinates of the waypoints and the coordinates of the end point are used as the basis to determine the road network planning area; combining the key traffic points in the road network planning area, a traffic network path planning fitness function is created;

[0009] An improved particle swarm algorithm for traffic network is constructed. According to the created fitness function, the constructed improved particle swarm algorithm is used to optimize the planned path of the traffic network, and the optimal traffic network planning path is obtained and output.

[0010] Furthermore, the step of fusing the terrain data of the target geographic space with the multi-source data set affecting the road network planning includes:

[0011] Based on the satellite remote sensing data of the target geographic space, the terrain data of the target geographic space is obtained;

[0012] Mark key traffic points according to the terrain data of the target geographic space to obtain multiple key traffic points;

[0013] According to each traffic point, the multi-source data set is split, and features are extracted from the split data set to obtain feature data of influencing factors of the corresponding traffic point;

[0014] Based on multiple traffic points, data matching is performed on multiple influencing factor characteristic data, and data fusion with traffic points is performed according to the data matching results to obtain a set of traffic points containing influencing factor characteristic data.

[0015] Furthermore, the coordinates (x, y) of the traffic points in the road network planning area satisfy the following formula:

[0016] min{x1,x2}-c*|x1-x2|<<x<<max{x1,x2}+c*|x1-x2|

[0017] min{y1,y2}-c*|y1-y2|<<y<<max{y1,y2}+c*|y1-y2|

[0018] Where c represents the expansion coefficient, c∈[0.35,0.5]; (x1, y1) represents the starting point coordinates; (x2, y2) represents the end point coordinates.

[0019] Furthermore, the step of obtaining the optimal traffic network planning path includes:

[0020] Initialize the parameters of the improved particle swarm algorithm, including the coordinates of key traffic points, the number of key traffic points, the population size of the particle swarm, the population learning rate and the number of iterations;

[0021] The fitness is calculated by the fitness function, and the particle with the best fitness is regarded as the global optimal point, while the particle with the second best fitness is regarded as the global suboptimal point.

[0022] The inertia weight of the particle swarm algorithm is improved by adopting the linear decreasing law change;

[0023] Generate explosion particles based on the optimal particle explosion strategy, update the speed of the optimal particles and the explosion particles, regain the positions of all particles based on the updated speeds, calculate the fitness values ​​of all particles after the update, update the global optimal point and the global suboptimal point, until the maximum number of iterations is reached, stop searching, and obtain the optimal path that traverses each traffic point.

[0024] Furthermore, in the step of improving the inertia weight of the particle swarm algorithm by adopting a linear decreasing law, the variation formula of the inertia weight is expressed as:

[0025]

[0026] Where ω represents the inertia weight; ω max Indicates the maximum weight, the value is 0.8; ω min represents the minimum weight, which is 0.5; T max represents the maximum number of iterations; t represents the current number of iterations of the particle.

[0027] Furthermore, in the step of generating explosion particles based on the optimal particle explosion strategy, the explosion particle generation method is expressed as:

[0028]

[0029] In the formula, ex nj Indicates the nth explosion particle ex generated n j-dimensional variable; Gbest j represents the optimal particle; rand represents a random number between -1 and 1; t represents the current number of iterations; b j A j-dimensional variable representing the particle's own historical optimal position.

[0030] Furthermore, in the step of updating the speeds of the optimal particles and the explosion particles:

[0031] The speed of newly generated particles is updated according to the following formula:

[0032] The traditional particle update speed strategy except for newly generated particles is expressed as:

[0033] In the formula, c2 represents the learning factor; ω represents the inertia weight; Indicates the particle speed before updating; G best represents the global optimal position; Indicates the current position of the particle; rand indicates a random number between 0 and 1; Indicates the updated speed of the newly generated particles in the explosion; Indicates the updated velocity of traditional particles.

[0034] Furthermore, the step of creating a traffic network path planning fitness function includes:

[0035] The obstacle constraint function F1 is constructed as:

[0036]

[0037] Where Q represents the number of obstacles; d n,q represents the distance from the traffic point to the qth obstacle in the nth path segment; r q represents the radius of the qth obstacle;

[0038] The smooth curvature cost function F2 is constructed as:

[0039]

[0040] In the formula, y' i Represented as y i Coordinate x i At the coordinate (x i ,y i ) under the first-order derivative, y″ i Represented as y i Coordinate x i At the coordinate (x i ,y i ) under the second-order derivative, n i Indicates the number of path points on the nth path;

[0041] The fitness function F of traffic network path planning is expressed as:

[0042] F=min(F1+F2)

[0043] Where F represents the fitness function of traffic network path planning; F1 represents the obstacle constraint function; and F2 represents the smooth curvature cost function.

[0044] Another embodiment of the present invention provides a traffic network planning system based on multi-source information fusion, including:

[0045] A data fusion module, for responding to a traffic road network path planning request for a target geographic space, fusing the terrain data of the target geographic space and a multi-source data set that affects the road network planning, to obtain a set of traffic key points containing characteristic data of influencing factors;

[0046] The model building module is used to determine the road network planning area based on the starting point coordinates, the waypoint coordinates and the end point coordinates in the traffic point set; and to create the traffic network path planning fitness function in combination with each traffic point in the road network planning area;

[0047] The road network path planning module is used to construct an improved particle swarm algorithm for the traffic road network. According to the created fitness function, the improved particle swarm algorithm is used to optimize the planned path of the traffic road network, obtain the optimal traffic road network planning path and output it.

[0048] Compared with the prior art, the traffic network planning method and system based on multi-source information fusion of the present invention has the following beneficial effects:

[0049] First, the present invention combines various traffic points in the road network planning area to create a traffic network path planning fitness function, wherein the obstacle constraint function of the fitness function can ensure that obstacles that make it impossible to build a road network are avoided during path planning, and the road network planning path is optimized; the smooth curvature cost function of the fitness function is used to ensure the smoothness of the planned path, and reduce or avoid the situation of sharp turns in the planned road network;

[0050] Second, the present invention constructs an improved particle swarm algorithm for transportation road networks, and based on the created fitness function, uses the constructed improved particle swarm algorithm to optimize the planned path of the transportation road network, and can obtain the optimal road network planning path in the target geographic space, making the transportation road network planning more targeted and scientific, and the road network planning safer, more convenient, efficient, green and economical. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0052] Figure 1 It is a flow chart of the implementation of the traffic network planning method based on multi-source information fusion of the present invention;

[0053] Figure 2 It is a sub-flow chart of the traffic network planning method based on multi-source information fusion of the present invention;

[0054] Figure 3 Another sub-flow chart of the traffic network planning method based on multi-source information fusion provided by an embodiment of the present invention;

[0055] Figure 4 It is a structural block diagram of the traffic network planning system based on multi-source information fusion of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0057] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0058] The following is a detailed description of the specific implementation of the traffic network planning method and system based on multi-source information fusion of the present invention in conjunction with specific embodiments.

[0059] Please refer to Figure 1 In a preferred embodiment of the present invention, a traffic network planning method based on multi-source information fusion is provided, comprising the following steps:

[0060] S101: In response to a traffic road network path planning request for a target geographic space, the terrain data of the target geographic space and a multi-source data set that affects the road network planning are fused to obtain a set of traffic key points containing characteristic data of influencing factors;

[0061] In an embodiment of the present invention, the terrain data of the target geographic space includes a digital elevation model (DEM), contour data, slope and aspect data, water system data, residential area and facility data, vegetation coverage data, etc.; the multi-source data set that affects road network planning includes existing traffic road network data, ecologically sensitive area data such as the distribution of historical sites and scenic spots in space, predicted traffic flow, and other data that can affect road network planning; through the fusion processing of these data, comprehensive and accurate geographic information support can be provided for traffic road network path planning, ensuring the scientific nature and feasibility of the planning.

[0062] like Figure 2 As shown, in an embodiment of the present invention, the step of fusing the terrain data of the target geographic space and the multi-source data set affecting the road network planning includes:

[0063] S201: obtaining terrain data of the target geographic space based on satellite remote sensing data of the target geographic space, marking key traffic points according to the terrain data of the target geographic space, and obtaining a plurality of key traffic points;

[0064] In the process of marking key traffic points in the embodiment of the present invention, key terrain feature points are determined, and digital elevation models (DEMs) are used to identify high points, low points, and areas with significant slope changes in the terrain. These areas are often places that require special attention in road planning, such as mountain tops, valleys, slope tops, and slope toes. Combined with the water system information in the terrain data, the locations of rivers and lakes, as well as possible bridge or tunnel crossing points are marked. These locations are crucial to ensuring the continuity of the route and reducing the impact on the natural environment; consider the distribution of residential areas and facilities: Use residential area data to determine the locations of cities, villages, and important facilities (such as schools and hospitals) so that the service scope and traffic convenience are taken into account when planning the road network.

[0065] S202: splitting the multi-source data set according to each traffic point, performing feature extraction on the split data set, and obtaining feature data of influencing factors of the corresponding traffic point;

[0066] Among them, in the embodiment of the present invention, the splitting of the multi-source data set is performed based on each traffic point. Exemplarily, there are N traffic points in total, and the multi-source data set is divided into N parts, each part is used to represent the data information of the corresponding traffic point.

[0067] S203: Based on multiple key traffic points, multiple characteristic data of influencing factors are matched, and data with key traffic points are fused according to the data matching results to obtain a set of key traffic points containing characteristic data of influencing factors; in the process of multi-source data fusion, the data marked for the key traffic points are overlaid and analyzed through GIS software to generate a comprehensive map of key traffic points, in which each key point contains rich attribute information, such as geographical location, relevant terrain features, surrounding environment, etc. Through this marking scheme that comprehensively considers multiple factors, it can be ensured that the selection of key traffic points is both scientific and practical, providing a solid foundation for subsequent road network planning.

[0068] For further information, please refer to Figure 1 In an embodiment of the present invention, the traffic network planning method based on multi-source information fusion in the embodiment of the present invention further includes the following steps:

[0069] S102: Determine the road network planning area based on the coordinates of the traffic points at the starting point and the coordinates of the traffic points at the end point in the traffic point set; create a traffic network path planning fitness function in combination with each traffic point in the road network planning area; wherein the coordinates (x, y) of the traffic points in the road network planning area satisfy the following formula:

[0070] min{x1,x2}-c*|x1-x2|<<x<<max{x1,x2}+c*|x1-x2|

[0071] min{y1,y2}-c*|y1-y2|<<y<<max{y1,y2}+c*|y1-y2|

[0072] Where c is the expansion coefficient, c∈[0.35,0.5]; (x1, y1) is the starting point coordinate; (x2, y2) is the end point coordinate. If the coefficient c is less than 0.35, there may be too little information about the key traffic points in the road network planning area. If the coefficient c is greater than 0.5, there may be too much information about the key traffic points in the road network planning area. More information will not be considered in actual path planning.

[0073] The traffic network path planning fitness function provided by the embodiment of the present invention includes an obstacle constraint function and a smooth curvature cost function, wherein the obstacle constraint refers to the presence of ecologically sensitive area data such as historical sites, national parks, nature reserves, mountains, residential buildings and other targets on the planned path that cannot be used for path planning; the present invention constructs a fitness function including an obstacle constraint function and a smooth curvature cost function, and can obtain a feasible path planning solution during the process of traffic network path optimization.

[0074] For further information, please refer to Figure 1 In an embodiment of the present invention, the traffic network planning method based on multi-source information fusion in the embodiment of the present invention further includes the following steps:

[0075] S103: constructing an improved particle swarm algorithm for the traffic network, and optimizing the planned path of the traffic network using the constructed improved particle swarm algorithm according to the created fitness function, obtaining the optimal traffic network planned path and outputting it.

[0076] Further, such as Figure 3 As shown, the step of obtaining the optimal traffic network planning path includes:

[0077] S301: Initializing the parameters of the improved particle swarm algorithm, the initialized parameters include the coordinates of key traffic points, the number of key traffic points, the population number of the particle swarm, the population learning rate and the number of iterations;

[0078] S302: Calculate the fitness through the fitness function, take the particle with the best fitness as the global optimal point, and the particle with the second best fitness as the global second best point; use the linear decreasing law to improve the inertia weight of the particle swarm algorithm;

[0079] S303: Generate explosion particles based on the optimal particle explosion strategy, update the speed of the optimal particles and the explosion particles, regain the positions of all particles based on the updated speeds, calculate the fitness values ​​of all particles after the update, update the global optimal point and the global suboptimal point, until the maximum number of iterations is reached, stop searching, and obtain the optimal path that traverses each traffic point.

[0080] Among them, in the traditional particle swarm algorithm, when the global best particle is updated according to the conventional update formula, the particle position of the next generation of population is generally worse than the particle position of the previous generation. Therefore, the present invention generates a certain number of explosion particles near the optimal particle, so that the algorithm can better jump out of the local optimum.

[0081] In addition, in the traditional particle swarm algorithm, the inertia weight is a fixed value. If the value is too large, the algorithm's search speed can be accelerated, but it is not conducive to the algorithm's small-range search for particles in the later stage; if the value is too small, although the local search capability is increased, it is not conducive to the algorithm's search speed; therefore, the present invention adopts a linear decreasing law to improve the inertia weight of the particle swarm algorithm. In the step of adopting a linear decreasing law to improve the inertia weight of the particle swarm algorithm, the variation formula of the inertia weight is expressed as:

[0082]

[0083] Where ω represents the inertia weight; ω max Indicates the maximum weight, the value is 0.8; ω min represents the minimum weight, which is 0.5; T max represents the maximum number of iterations; t represents the current number of iterations of the particle.

[0084] The embodiment of the present invention increases the global search capability and local exploration capability of the particle swarm algorithm by introducing a linear dynamic inertia weight adjustment method, thereby effectively improving the convergence speed and search accuracy of the algorithm.

[0085] Furthermore, in the step of generating explosion particles based on the optimal particle explosion strategy, the explosion particle generation method is expressed as:

[0086]

[0087] In the formula, ex nj Indicates the nth explosion particle ex generated n j-dimensional variable; Gbest j represents the optimal particle; rand represents a random number between -1 and 1; t represents the current number of iterations; b j A j-dimensional variable representing the particle's own historical optimal position.

[0088] Furthermore, in the step of updating the speeds of the optimal particles and the explosion particles:

[0089] The speed of newly generated particles is updated according to the following formula:

[0090] The traditional particle update speed strategy except for newly generated particles is expressed as:

[0091] In the formula, c2 represents the learning factor; ω represents the inertia weight; Indicates the particle speed before updating; G best represents the global optimal position; Indicates the current position of the particle; rand indicates a random number between 0 and 1; Indicates the updated speed of the newly generated particles in the explosion; Indicates the updated velocity of traditional particles.

[0092] Furthermore, the step of creating a traffic network path planning fitness function includes:

[0093] The obstacle constraint function F1 is constructed as:

[0094]

[0095] Where Q represents the number of obstacles; d n,q represents the distance from the traffic point to the qth obstacle in the nth path segment; r q represents the radius of the qth obstacle;

[0096] The smooth curvature cost function F2 is constructed as:

[0097]

[0098] In the formula, y' i Represented as y i Coordinate x i At the coordinate (x i ,y i ) under the first-order derivative, y″ i Represented as y i Coordinate x i At the coordinate (x i ,y i ) under the second-order derivative, n i Indicates the number of path points on the nth path;

[0099] The fitness function F of traffic network path planning is expressed as:

[0100] F=min(F1+F2)

[0101] Where F represents the fitness function of traffic network path planning; F1 represents the obstacle constraint function; and F2 represents the smooth curvature cost function.

[0102] The present invention constructs an improved particle swarm algorithm for traffic road networks, and optimizes the planned path of the traffic road network according to the created fitness function by using the constructed improved particle swarm algorithm, so as to obtain the optimal road network planning path in the target geographic space, making the traffic road network planning more targeted and scientific, and making the road network planning safer, more convenient, efficient, green and economical.

[0103] Further, such as Figure 4 As shown, another embodiment of the present invention provides a traffic network planning system based on multi-source information fusion, including:

[0104] The data fusion module 401 is used to respond to a traffic road network path planning request for a target geographic space, fuse the terrain data of the target geographic space and the multi-source data set that affects the road network planning, and obtain a set of traffic key points containing characteristic data of influencing factors;

[0105] The model building module 402 is used to determine the road network planning area based on the starting point coordinates, the waypoint coordinates and the end point coordinates in the traffic point set; and to create a traffic network path planning fitness function in combination with each traffic point in the road network planning area;

[0106] The road network path planning module 403 is used to construct an improved particle swarm algorithm for the traffic road network. According to the created fitness function, the constructed improved particle swarm algorithm is used to optimize the planned path of the traffic road network, and the optimal traffic road network planning path is obtained and output.

[0107] In summary, the present invention combines various traffic points in the road network planning area to create a traffic road network path planning fitness function, wherein the obstacle constraint function of the fitness function can ensure that obstacles that make road network construction impossible are avoided during path planning, thereby optimizing the road network planning path; the smooth curvature cost function of the fitness function is used to ensure the smoothness of the planned path, reducing or avoiding sharp turns in the planned road network.

[0108] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0109] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0110] Another preferred embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the transportation network planning based on multi-source information fusion as described in any one of the above embodiments is implemented.

[0111] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0112] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0113] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0114] Another preferred embodiment of the present invention provides a storage medium, which is a computer-readable storage medium. The computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented.

[0115] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0116] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A traffic network planning method based on multi-source information fusion, characterized in that: include: In response to a traffic road network path planning request for a target geographic space, the terrain data of the target geographic space and a multi-source data set that affects the road network planning are fused to obtain a set of traffic key points containing characteristic data of influencing factors; In the set of key traffic points, the coordinates of the starting point, the coordinates of the waypoints and the coordinates of the end point are used as the basis to determine the road network planning area; combining the key traffic points in the road network planning area, a traffic network path planning fitness function is created; An improved particle swarm algorithm for traffic network is constructed. According to the created fitness function, the constructed improved particle swarm algorithm is used to optimize the planned path of the traffic network, and the optimal traffic network planning path is obtained and output.

2. The method for traffic network planning based on multi-source information fusion according to claim 1 is characterized in that: The step of fusing the terrain data of the target geographic space with the multi-source data set affecting the road network planning comprises: Based on the satellite remote sensing data of the target geographic space, the terrain data of the target geographic space is obtained; Mark key traffic points according to the terrain data of the target geographic space to obtain multiple key traffic points; According to each traffic point, the multi-source data set is split, and features are extracted from the split data set to obtain feature data of influencing factors of the corresponding traffic point; Based on multiple traffic points, data matching is performed on multiple influencing factor characteristic data, and data fusion with traffic points is performed according to the data matching results to obtain a set of traffic points containing influencing factor characteristic data.

3. The method for traffic network planning based on multi-source information fusion according to claim 2 is characterized in that: The coordinates (x, y) of the traffic points in the road network planning area satisfy the following formula: min{x1,x2}-c*|x1-x2|< <x<<max{x1,x2}+c*|x1-x2| min{y1,y2}-c*|y1-y2|< <y<<max{y1,y2}+c*|y1-y2| Where c represents the expansion coefficient, c∈[0.35, 0.5]; (x1, y1) represents the starting point coordinates; (x2, y2) represents the end point coordinates.

4. The method for traffic network planning based on multi-source information fusion according to claim 3 is characterized in that: The step of obtaining the optimal traffic network planning path includes: Initialize the parameters of the improved particle swarm algorithm, including the coordinates of key traffic points, the number of key traffic points, the population size of the particle swarm, the population learning rate and the number of iterations; The fitness is calculated by the fitness function, and the particle with the best fitness is regarded as the global optimal point, while the particle with the second best fitness is regarded as the global suboptimal point. The inertia weight of the particle swarm algorithm is improved by adopting the linear decreasing law change; Generate explosion particles based on the optimal particle explosion strategy, update the speed of the optimal particles and the explosion particles, regain the positions of all particles based on the updated speeds, calculate the fitness values ​​of all particles after the update, update the global optimal point and the global suboptimal point, until the maximum number of iterations is reached, stop searching, and obtain the optimal path that traverses each traffic point.

5. The method for traffic network planning based on multi-source information fusion according to claim 4 is characterized in that: In the step of improving the inertia weight of the particle swarm algorithm by adopting a linear decreasing law, the variation formula of the inertia weight is expressed as: Where ω represents the inertia weight; ω max Indicates the maximum weight, the value is 0.8; ω min represents the minimum weight, which is 0.5; T max Indicates the maximum number of iterations; t represents the current iteration number of the particle.

6. The method for traffic network planning based on multi-source information fusion according to claim 5 is characterized in that: In the step of generating explosion particles based on the optimal particle explosion strategy, the explosion particle generation method is expressed as: In the formula, ex nj Indicates the nth explosion particle ex generated n j-dimensional variable; Gbest j represents the optimal particle; rand represents a random number between -1 and 1; t represents the current number of iterations; b j A j-dimensional variable representing the particle's own historical optimal position.

7. The method for traffic network planning based on multi-source information fusion according to claim 6 is characterized in that: In the step of updating the speeds of the optimal particles and the explosion particles: The speed of newly generated particles is updated according to the following formula: The traditional particle update speed strategy except for newly generated particles is expressed as: In the formula, c2 represents the learning factor; ω represents the inertia weight; Indicates the particle speed before updating; G best represents the global optimal position; Indicates the current position of the particle; rand indicates a random number between 0 and 1; Indicates the updated speed of the newly generated particles in the explosion; Indicates the updated velocity of traditional particles.

8. The method for traffic network planning based on multi-source information fusion according to claim 7 is characterized in that: The steps to create a traffic network path planning fitness function include: The obstacle constraint function F1 is constructed as: Where Q represents the number of obstacles; d n,q represents the distance from the traffic point to the qth obstacle in the nth path segment; r q represents the radius of the qth obstacle; The smooth curvature cost function F2 is constructed as: In the formula, y' i Represented as y i Coordinate x i At the coordinate (x i ,y i ) under the first-order derivative, y” i Represented as y i Coordinate x i At the coordinate (x i ,y i ) under the second-order derivative, n i Indicates the number of path points on the nth path; The fitness function F of traffic network path planning is expressed as: F=min(F1+F2) Where F represents the fitness function of traffic network path planning; F1 represents the obstacle constraint function; and F2 represents the smooth curvature cost function.

9. A system for implementing the traffic network planning method based on multi-source information fusion as claimed in any one of claims 1 to 8, characterized in that: The system comprises: A data fusion module, for responding to a traffic road network path planning request for a target geographic space, fusing the terrain data of the target geographic space and a multi-source data set that affects the road network planning, to obtain a set of traffic key points containing characteristic data of influencing factors; The model building module is used to determine the road network planning area based on the starting point coordinates, the waypoint coordinates and the end point coordinates in the traffic point set; and to create the traffic network path planning fitness function in combination with each traffic point in the road network planning area; The road network path planning module is used to construct an improved particle swarm algorithm for the traffic road network. According to the created fitness function, the improved particle swarm algorithm is used to optimize the planned path of the traffic road network, obtain the optimal traffic road network planning path and output it.

Images