A method, device, and medium for pedestrian traffic allocation based on environmental dimension scoring.

Abstract

This invention discloses a pedestrian flow allocation method based on environmental dimension scoring. It characterizes the street environment of the current area by dividing it into functional categories and scores the collected features. This method can more realistically simulate pedestrian participants' path selection and ultimately obtain pedestrian flow on different road segments. Compared with traditional road allocation, it can better reflect the actual situation of the street and the distribution of pedestrian demand.

Description

Technical Field

[0001] This invention relates to the field of street planning simulation technology, and more specifically to a method for pedestrian flow allocation based on environmental dimension scoring. Background Technology

[0002] With the acceleration of urbanization, the unlimited expansion of cities and the increase in travel distance have led people to increasingly rely on cars as their primary mode of transportation. This has resulted in problems such as imbalances in urban scale, deficiencies in public functions, and unsustainable urban development. Now, the increasing exposure of urban problems is prompting a shift in planning philosophy from a "car-centric" approach to a "people-centric" one, allowing healthy modes of transportation such as walking to return to urban life and production.

[0003] The spatial distribution of pedestrian groups is influenced by a combination of factors, including the functional distribution of public spaces, environmental impacts, and travel purposes. Simultaneously, the demand for pedestrian travel affects the development and optimization of urban space. Therefore, the spatial aggregation and distribution of pedestrians, and the selection of travel routes, are crucial factors to consider in planning and layout. Currently, the spatial selection and flow distribution of pedestrian travel still follow the approach of allocating traffic flow based on motor vehicle traffic. This approach considers road capacity and the time cost of travel as the main factors for pedestrian flow allocation. However, this allocation method is from the perspective of motor vehicles, which are less affected by external environmental interference, so it focuses more on distance and time. While distance is an important factor in pedestrian allocation, the influence of the street environment on pedestrians' route selection is also significant due to their frequent contact with the external environment and street-side functions—a factor that is often overlooked. Summary of the Invention

[0004] The purpose of this invention is to provide a pedestrian flow allocation method based on environmental dimension scoring. This method characterizes the street environment of the current area and corrects walking time by assigning different weights. It can more realistically simulate pedestrian participants' route selection and finally obtain pedestrian flow on different road segments. Compared with traditional road allocation, it can better reflect the actual situation of the street and the distribution of pedestrian demand.

[0005] This invention is achieved through the following technical solution:

[0006] A pedestrian traffic allocation method based on environmental dimension scoring includes the following steps:

[0007] S1: Obtain the basic road network of the current area, import the basic road network into ArcGIS, and obtain the latitude and longitude of the starting points of multiple walking paths according to the road segment number, generate the road segment code corresponding to each walking path; and connect each road segment code to the public map path planning interface to obtain the actual walking time of each walking path, and use this time as the walking cost time.

[0008] S2: Divide the current region into functional representations to form a set of environmental parameters including the first dimension and the second dimension;

[0009] S3: Score each dimension of the environmental parameter set and combine the score results to adjust the walking cost time;

[0010] S4: Introduce the corrected walking cost time into the stochastic user model, use the probability that any user model recognizes this time as the minimum time as the base probability, label the base probability as the probability that the road segment is selected, and allocate the walking OD flow matrix to the walking network.

[0011] As an optional approach, in step S2 above,

[0012] The first dimension parameter is used to represent the distribution and quantity of living and productive service facilities on both sides of the street;

[0013] The second dimension parameter is used to represent the openness of the street space.

[0014] As an optional method, the process of obtaining the first dimension parameter also includes:

[0015] The POIs in the current area are obtained through public maps and classified into seven interest types, including business services, entertainment, leisure, education, healthcare, administration and finance.

[0016] Select any point on the walking path and construct an influence range with that point as the center and a circle of preset radius; calculate the distance from each POI within this range to that point, and determine the weight of different POIs based on the distance.

[0017] As an optional approach, different POIs are set with different attenuation coefficients based on their corresponding weights, and a distance attenuation function is generated. The distance attenuation function is used to represent the mutual attraction between the origin and destination points of a trip.

[0018] As an optional method, obtaining the second-dimensional parameters includes the following steps:

[0019] A1: The road network is topologically translated using spatial syntax to generate a topological image. The spatial components of the topological image are measured, and the network space is quantitatively characterized using integration and depth indices.

[0020] A2: Import the road network after link integration into Depthmap, create a standardized angle selectivity calculation algorithm in the line segment model for calculation, and use the calculation results to characterize the second dimension parameter;

[0021] The second dimension parameter is characterized by standardized angle selectivity and pedestrian walkway width.

[0022] A3: After normalizing the calculation results in step A2 above, score the normalized values ​​and the width of the pedestrian walkway respectively.

[0023] As an optional approach, step S2 above also includes a third dimension, which comprises multiple sets of visual conditions. Image recognition is used to fuse and calculate the feature indicators of these multiple sets of visual conditions to obtain the parameters of the third dimension, which include:

[0024] The road network generates multiple viewpoints at preset threshold intervals. Street view images are obtained by combining the viewpoints. Depth separation dilated convolution is applied to the images. The semantic segmentation of the street view images is performed based on DeepLab. After feature recognition for each type, the third-dimensional parameter information is calculated.

[0025] As an alternative approach, the first dimension parameter is used to represent the street function score, the second dimension parameter is used to represent the walkability score, and the third dimension is used to represent the environmental quality score.

[0026] As an alternative approach, the pedestrian OD flow matrix is ​​assigned to the pedestrian network before error control is performed using a Gumbel distribution.

[0027] On the other hand, the present invention also provides an electronic device including a memory and a processor, the memory storing a computer program that can run on the processor, wherein, optionally, the processor executes the computer program to implement the steps of a pedestrian traffic allocation method based on environmental dimension scoring.

[0028] On the other hand, the present invention also provides a storage medium on which a computer program is stored, wherein, optionally, when the computer program is executed by a processor, it implements steps in a pedestrian traffic allocation method based on environmental dimension scoring.

[0029] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0030] This invention, by collecting and scoring different representational functions of different environments along pedestrian routes, can better and more conveniently plan the layout of vehicular and pedestrian lanes during street design. Attached Figure Description

[0031] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be considered as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort. In the drawings:

[0032] Figure 1 This is a schematic diagram of the allocation method provided in an embodiment of the present invention. Detailed Implementation

[0033] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0034] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0035] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0036] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0037] Those skilled in the art will understand that all or part of the steps in the above facts and methods can be implemented by a program instructing related hardware. The program or the program described therein can be stored in a computer-readable storage medium. When the program is executed, it includes the following steps: at this time, the corresponding method steps are introduced. The storage medium can be ROM / RAM, magnetic disk, optical disk, etc.

[0038] Example

[0039] Please see Figure 1 This embodiment provides a pedestrian traffic allocation method based on environmental dimension scoring, including the following steps:

[0040] S1: Obtain the basic road network of the current region, import the basic road network into ArcGIS, and obtain the latitude and longitude of the starting points of multiple walking paths based on the road segment numbers to generate a road segment code corresponding to each walking path; then connect each road segment code to the public map path planning interface to obtain the actual walking time of each walking path, using this time as the initial walking cost time; specifically, select an area from OpenStreetMap to obtain the basic road network. Import the obtained road network into ArcGIS, obtain the latitude and longitude of the starting points of the road segments based on the road segment numbers to form a road segment code for each road segment. By using the road segment codes through the path planning interface provided by Baidu API, the actual walking time of walking on the road segments can be obtained in batches. To better illustrate this solution, this embodiment uses this time as the initial walking cost time T0 for the road segment.

[0041] S2: The current area is functionally divided to form an environmental parameter set including a first dimension and a second dimension. It should be noted that different dimensions can be selected as elements in the environmental parameter set for different environments and scenarios. In this embodiment, as an optional approach, the first dimension is considered as street function, and the second dimension as spatial scale. Both of these elements are positively correlated with actual walking time. In particular, this embodiment may also consider a third dimension, which is considered as the visual perception of environmental quality, and will be described below.

[0042] S3: Score each dimension of the environmental parameter set and synthesize the scores to adjust the walking cost time. By analyzing the scores of each dimension in the environmental parameter set, we can obtain its impact on walking route selection. In this embodiment, we can assign weights to the parameters in the environmental parameter set to obtain influencing factors; then, based on these influencing factors, we can form walking time correction parameters; and finally, by introducing these correction parameters, we can generate the expected walking cost time.

[0043] S4: Introduce the corrected walking cost time into the stochastic user model, use the probability that any user model recognizes this time as the minimum time as the base probability, and label the base probability as the probability that the road segment is selected, and allocate the walking OD flow matrix to the walking network.

[0044] This embodiment, based on the above method, corrects the walking cost time, which can more realistically simulate the path selection of pedestrian participants and finally obtain the pedestrian flow on different road segments. Compared with traditional road allocation, it can better reflect the actual situation of the street and the distribution of pedestrian demand.

[0045] In this embodiment, the street environment is characterized by three main dimensions: street function (Fi), pedestrian scale (Si), and visual perception (Vi). Street function (Fi) refers to the number of residential and commercial service facilities along the street; more facilities mean a more vibrant street, attracting more pedestrians. Visual perception (Vi) reflects the city's cultural atmosphere and the quality of its public spaces; these two factors significantly influence pedestrian route selection for leisure, recreation, and entertainment. Pedestrian scale (Si) is a crucial factor influencing route selection, and the two are positively correlated within a certain range.

[0046] Specifically, these three types of parameters are obtained through the following method:

[0047] Street function parameters (Fi) can be obtained and calculated by accessing the Baidu API interface. Within the research scope, relevant Points of Interest (POIs) can be obtained by category. These can be classified into seven major categories and 20 subcategories of street function elements.

[0048]

[0049] Then, select any point on the walking path and construct an influence range with that point as the center and a circle of preset radius; calculate the distance from each POI within this range to that point, and determine the weight of different POIs based on the distance.

[0050] Simultaneously considering the impact of different distances on road segments, attenuation coefficients for different Points of Interest (POIs) are set according to weights, and a distance attenuation function is established. Distance attenuation refers to the phenomenon that the mutual attraction between the origin and destination points weakens as walking distance increases. When people complete their daily travel goals by walking, the distance attenuation coefficient of the destination facilities follows the walking attenuation law. The attenuation distance of walking is divided into four parts: suitable walking distance, tolerable walking distance, resistant walking distance, and abandoned walking distance, representing the degree of attraction of POIs at different distances.

[0051] Based on the above, the street function parameters are expressed as follows:

[0052]

[0053] Among them, w i denoted by , f(j) represents the weight of the evaluation index for the i-th type of POI; f(j) represents the decay coefficient of the decay factor for the j-th type of POI; and N represents the total weight of all POIs.

[0054] The visual condition set is based on the visual perception of pedestrian participants in pedestrian street spaces, and the perceived environmental intentions are used as analytical indicators of the pedestrian street space environment. Pedestrian participants active in pedestrian street spaces can obtain more than 80% of the landscape information from the space. Street greening, small landscape features, and street-side buildings constitute a rich pedestrian street landscape. By studying the characteristics of human visual perception of street landscapes, as an optional method in this embodiment, four characteristic indicators—street sky openness, green view rate, building ratio, and motor vehicle lane ratio—can be integrated and calculated to obtain street visual perception parameters.

[0055] The road network can generate viewpoints at 50-meter intervals, and street view images can be obtained by combining the viewpoints. Depth separation dilated convolution can be applied to the images, and semantic segmentation of the street view images can be performed based on Deeplab. Feature recognition can be performed on four types of elements, and multi-scale feature information can be calculated.

[0056] Finally, the parameters of the walking scale need to be obtained. This embodiment uses the following method:

[0057] A1: A topological image is generated by performing topological translation of the road network using spatial syntax. The spatial components of the topological image are measured, and the network space is quantitatively characterized using integration degree and depth value indicators.

[0058] A2: Import the road network after link integration into Depthmap, create a standardized angle selectivity calculation algorithm in the line segment model for calculation, and use the calculation results to characterize the walking scale parameters;

[0059] The walking scale parameters include the standardized angle selectivity and the width of the walkway.

[0060] A3: After normalizing the calculation results in step A2 above, score the normalized values ​​and the width of the pedestrian walkway separately, and obtain the spatial scale index S by combining them. It can be expressed as:

[0061] S = S Nach +S width

[0062] S Nach S is used to represent the standardized angle selection score. width Used to indicate the slow lane width score. Please refer to the table below:

[0063]

[0064]

[0065] After obtaining the three types of parameters, in order to better apply this solution, this embodiment makes an example. The newly added street functions (Fi), visual perception (Vi), and walking scale (Si) of the road network are weighted by scoring to obtain the influence factor (I), and then normalized to form the walking travel time correction parameter α. When α is less than 1, the walking participants have a better evaluation of the street environment, the estimated walking travel time is less than the actual travel time, and the probability of choosing the walking route is higher. As an optional method, the correction value range is set to 0.8-1.2.

[0066] In one embodiment, the influence factor is:

[0067] I = 0.4F i +0.3V i +0.3S

[0068] Wherein, Fi represents street function parameters, Vi represents visual perception parameters, and S represents spatial scale indicators;

[0069] Therefore, the walking time correction parameter is:

[0070]

[0071]

[0072] Finally, the corrected walking cost time is introduced into the stochastic user model, and this time is considered as the probability of the minimum time, i.e., the probability of the road segment being selected, to directly allocate the walking OD flow matrix to the walking network. That is, the corrected walking cost time T α =α·T1.

[0073] Finally, before allocating the pedestrian OD traffic matrix to the pedestrian network, error control is performed using the Gumbel distribution to ensure balanced allocation of random users.

[0074] On the other hand, the present invention also provides an electronic device including a memory and a processor, the memory storing a computer program that can run on the processor, wherein, optionally, the processor executes the computer program to implement the steps of a method for allocating pedestrian traffic.

[0075] On the other hand, the present invention also provides a storage medium on which a computer program is stored, wherein, optionally, the computer program, when executed by a processor, implements the steps in the method for allocating pedestrian traffic.

[0076] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A pedestrian flow allocation method based on environmental dimension scoring, characterized in that, Including the following steps: S1: Obtain the basic road network of the current region, import the basic road network into ArcGIS, and obtain the latitude and longitude of the starting points of multiple walking paths according to the road segment number, and generate a road segment code corresponding to each walking path; Each road segment code is then connected to the public map route planning interface to obtain the actual walking time for each walking route, and this time is used as the walking cost time. S2: Divide the current region into functional representations to form a set of environmental parameters including the first dimension and the second dimension; S3: Score each dimension of the environmental parameter set, and adjust the walking cost time based on the combined score results; S4: Introduce the corrected walking cost time into the random user model, take the probability that any user model recognizes this time as the minimum time as the base probability, label the base probability as the probability that the road segment is selected, and allocate the walking OD traffic matrix to the walking network. In step S2 above, the first-dimensional parameter in the first-dimensional environmental parameter set represents the number of living and productive service facilities distributed along the streets; the second-dimensional parameter in the second-dimensional environmental parameter set represents the openness of the street space. The first-dimensional parameter representing the number of living and productive service facilities distributed along the streets is determined by obtaining regional POIs; the second-dimensional parameter representing the openness of the street space is calculated by topological representation and importing into a Depthmap. The acquisition of the second dimension parameter specifically includes the following steps: A1: Generate a topological image by performing topological translation of the road network using spatial syntax, measure the spatial constituent elements of the topological image, and quantitatively characterize the network space using integration degree and depth value indicators; A2: Import the road network after link integration into the Depthmap, create a standardized angle selectivity calculation algorithm in the line segment model for calculation, and use the calculation results to characterize the second dimension parameter; wherein, the characterization of the second dimension parameter includes standardized angle selectivity and pedestrian walkway width; A3: After normalizing the calculation results in step A2, score the normalized values ​​and pedestrian walkway width respectively.

2. The pedestrian flow allocation method based on environmental dimension scoring according to claim 1, characterized in that, Before obtaining the first dimension parameters, the following steps are also included: The POIs in the current area are obtained through public maps and classified into seven interest types, including business services, entertainment, leisure, education, healthcare, administration and finance. Select any point on the walking path and construct an influence range with that point as the center and a circle of preset radius; calculate the distance from each POI within this range to that point, and determine the weight of different POIs based on the distance.

3. The pedestrian flow allocation method based on environmental dimension scoring according to claim 2, characterized in that, Different POIs are set with corresponding weights and attenuation coefficients are generated. The distance attenuation function is used to represent the mutual attraction between the origin and destination points of a trip.

4. The pedestrian flow allocation method based on environmental dimension scoring according to claim 1, characterized in that, In step S2 above, a third dimension is also included. This third dimension comprises multiple sets of visual conditions. Image recognition is used to fuse and calculate the feature indicators of these multiple sets of visual conditions to obtain the third dimension parameters, which include: The road network generates multiple viewpoints at preset threshold intervals. Street view images are obtained by combining the viewpoints. Depth separation dilated convolution is applied to the images. The semantic segmentation of the street view images is performed based on DeepLab. After feature recognition for each type, the third-dimensional parameter information is calculated.

5. The pedestrian flow allocation method based on environmental dimension scoring according to claim 4, characterized in that, The first dimension parameter is used to represent the street function score, the second dimension parameter is used to represent the walkability score, and the third dimension is used to represent the environmental quality score.

6. The pedestrian flow allocation method based on environmental dimension scoring according to claim 5, characterized in that, Before allocating the pedestrian OD flow matrix to the pedestrian network, error control is also performed using the Gumbel distribution.

7. An electronic device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the pedestrian traffic allocation method based on environmental dimension scoring as described in any one of claims 1 to 6.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the pedestrian traffic allocation method based on environmental dimension scoring as described in any one of claims 1 to 6.

Images