Driving path planning method, system and equipment considering urban landscape and medium

Abstract

The invention discloses a driving path planning method, system and device considering urban landscapes and a medium. The method comprises the steps that streetscape images of all roads in a city are acquired; calculating the greenness and the sky visibility of the streetscape image; calculating a road comfort index according to the greenness of the streetscape image and the sky visibility; constructing a comprehensive weight according to the road comfort index and the road length, and constructing a weighted graph structure according to the comprehensive weight; in the weighted graph structure, a Dijkstra algorithm is used for path planning, the path of the user is obtained, and the method, the system, the equipment and the medium can provide leisure travel path selection rich in visual comfort for pedestrians on the basis of meeting basic travel requirements of the pedestrians.

Description

Technical Field

[0001] The present invention belongs to the technical field of route planning, and relates to a driving route planning method, system, equipment and medium taking urban landscape into consideration. Background Art

[0002] With the accelerating urbanization process and the gradual improvement of residents' living standards, urban leisure tourism has become an important part of people's daily life. In this process, path planning technology, as a research hotspot in geographic information systems (GIS), computer science and related fields, has a large number of mature basic methods and tools. Traditional path planning technology generally aims to find the path with the shortest distance or the least driving time. Typical algorithms include Dijkstra algorithm, A* algorithm, Bellman-Ford algorithm and ant colony algorithm inspired by bionics. These algorithms have excellent performance in determinism and computational complexity, and have been widely used in many scenarios such as intelligent transportation, logistics distribution, Internet of Vehicles and public transportation scheduling.

[0003] In recent years, with the advancement of multimodal information processing and machine learning technologies, researchers have begun to try to introduce more dimensional considerations into route planning to meet the diverse travel needs of users. However, current route planning research still focuses on traditional indicators such as distance and time, and pays less attention to travelers' psychological comfort and personalized preferences in tourism and leisure scenarios.

[0004] On the other hand, street view images, as a widely covered and information-rich urban data carrier, play an increasingly important role in urban environmental evaluation and landscape analysis. Using street view images and deep learning technology to identify and quantify environmental features along roads (such as green vegetation, sky visibility, and spatial transparency) has become a new research trend. For pedestrians, the visual comfort of the road environment greatly affects the travel experience and psychological feelings. Therefore, incorporating the environmental evaluation indicators obtained from street view image analysis into the path planning objective function is expected to achieve a shift from traditional solutions that simply focus on travel time and distance to innovative path planning solutions that meet multi-perception and multi-dimensional comfort needs.

[0005] At present, the existing technology has the following defects and shortcomings:

[0006] Single evaluation index lacks multi-dimensional experience consideration: Traditional path planning methods mainly focus on single indicators such as distance and time, but lack quantitative evaluation and integration of the visual comfort of the road environment (such as greening level, sky visibility, etc.), making it difficult to meet the comprehensive needs of pedestrians for psychological, emotional and visual experience during leisure travel.

[0007] Lack of flexible integration and personalized control mechanisms: Although existing technologies can extract and analyze road environment characteristics, these results have not yet been effectively integrated into the shortest path algorithm. There is a lack of mechanisms to dynamically adjust distance and comfort weights, and it is impossible to provide more flexible and customized path planning solutions for users with different preferences and requirements. Summary of the invention

[0008] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and to provide a driving route planning method, system, device and medium that takes urban landscape into consideration. The method, system, device and medium can provide pedestrians with a leisure travel route option that is visually comfortable on the basis of meeting their basic travel requirements.

[0009] To achieve the above object, the present invention discloses a driving route planning method considering urban landscape, comprising:

[0010] Get street view images of each road in the city;

[0011] Calculating the greenness and sky visibility of the street view image;

[0012] Calculating a road comfort index based on the greenness and sky visibility of the street view image;

[0013] Constructing a comprehensive weight according to the road comfort index and the road length, and constructing a weighted graph structure according to the comprehensive weight;

[0014] In the weighted graph structure, the Dijkstra algorithm is used for path planning to obtain the user's path.

[0015] The further improvement of the driving route planning method considering urban landscape of the present invention is:

[0016] Furthermore, the process of calculating the greenness of the street view image is:

[0017] Calculate the number of green pixels NumGreen of the street view image based on the GVE algorithm;

[0018] The greenness GDgree of the street view image is calculated according to the number of green pixel points NumGreen of the street view image and the total number of pixels of the street view image.

[0019] Furthermore, the process of calculating the sky visibility of the street view image is:

[0020] Inputting the street view image into the trained PSPNet model to obtain a prediction map, wherein each pixel in the prediction map has a corresponding category label;

[0021] The number of pixels with the category label of sky in the statistical prediction map is NumSky;

[0022] The sky visibility SDgree of the street view image is calculated according to the number of pixels NumSky whose category label is sky and the total number of pixels NumSVI of the prediction image.

[0023] Furthermore, the road comfort index is calculated according to the greenness and sky visibility of the street view image, wherein the road comfort index emo is:

[0024] emo=GDgree+SDgree

[0025] Among them, GDgree is the greenness of the street view image, and SDgree is the sky visibility of the street view image.

[0026] Furthermore, a comprehensive weight is constructed according to the road comfort index and the road length, and the comprehensive weight w is:

[0027]

[0028] Among them, r1 and r2 are adjustable parameters, dist is the road length, emo is the road comfort index, and a weighted graph structure is constructed according to the comprehensive weight.

[0029] Furthermore, the method of performing path planning using the Dijkstra algorithm according to the weighted graph structure and obtaining the user's path further includes:

[0030] A visualization operation is performed on the path of the user.

[0031] The present invention discloses a driving route planning system considering urban landscape, comprising:

[0032] An acquisition module, used to acquire street view images of various roads in the city;

[0033] A first calculation module, used for calculating the greenness and sky visibility of the street view image;

[0034] A second calculation module, used for calculating a road comfort index according to the greenness and sky visibility of the street view image;

[0035] A construction module, used to construct a comprehensive weight according to the road comfort index and the road length, and to construct a weighted graph structure according to the comprehensive weight;

[0036] The planning module is used to perform path planning using the Dijkstra algorithm in a weighted graph structure to obtain the user's path.

[0037] The further improvement of the driving route planning system considering urban landscape of the present invention is:

[0038] Furthermore, the first calculation module includes:

[0039] The third calculation module is used to calculate the number of green pixels NumGreen of the street view image based on the GVE algorithm;

[0040] A fourth calculation module, used for calculating the greenness GDgree of the street view image according to the number of green pixel points NumGreen of the street view image and the total number of pixels of the street view image;

[0041] A prediction module, used for inputting the street view image into the trained PSPNet model to obtain a prediction map, in which each pixel point in the prediction map has a corresponding category label;

[0042] Statistics module, the number of pixels NumSky with the category label of sky in the user's statistical prediction graph;

[0043] The fifth calculation module is used to calculate the sky visibility SDgree of the street view image according to the number of pixels NumSky with the category label of sky and the total number of pixels NumSVI of the prediction image.

[0044] The present invention discloses a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the driving route planning method considering urban landscape are implemented.

[0045] The present invention discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the driving route planning method considering urban landscape are implemented.

[0046] The present invention has the following beneficial effects:

[0047] The driving route planning method, system, device and medium for considering urban landscape described in the present invention combine visual comfort indicators such as road greenness and sky visibility with traditional distance factors during specific operation to form a comprehensive weight, thereby achieving a shift from a single shortest distance goal to a multi-dimensional balanced optimization. Users can flexibly adjust the weight between distance and comfort, thereby obtaining a tourism and leisure route plan that meets travel efficiency and psychological and aesthetic needs.

[0048] Furthermore, with the help of the GVE algorithm and PSPNet model, the automatic extraction and quantitative evaluation of greenness and sky visibility can be achieved without manual labeling. It is suitable for urban road networks and can efficiently and standardizedly evaluate large-scale road environment quality, laying a data and technical foundation for high-precision path planning within the entire city. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 is a flow chart of the method of the present invention;

[0051] Figure 2 This is an example of a street view image of Guangzhou;

[0052] Figure 3 It is the workflow diagram of GVE algorithm;

[0053] Figure 4 This is an example of green vegetation extraction results;

[0054] Figure 5 This is an example of the predicted sky percentage result;

[0055] Figure 6 Examples of planning paths under different road combination weights. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0058] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0059] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0060] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0061] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0062] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0063] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0064] Embodiment 1

[0065] refer to Figure 1 The driving route planning method considering urban landscape of the present invention comprises the following steps:

[0066] 1) Acquire and process urban road network and street view image data;

[0067] Guangzhou City, Guangzhou Province is selected as the research area, and the target city road network information is obtained using the open source geographic data set OpenStreet Map, and the target city road network information is stored as a file in shp format, including basic attributes such as road node coordinates, road section length and road type. At the same time, the target city road network information is parsed and converted into a graph structure, wherein the node (Node) in the graph structure represents the endpoint of a road intersection or road segment, and the edge (Edge) in the graph structure represents a road section, and basic attributes such as distance are assigned to each edge for subsequent path algorithm calls. The present invention uses Python and tools such as geopandas and networkx to perform structured processing on the road network data to ensure that the weights can be quickly retrieved and updated in the subsequent algorithm.

[0068] In addition, the present invention uses Baidu Map API to obtain street view image data of selected roads in the city according to the preset spatial resolution and sampling strategy, and obtains a total of 20,159 panoramic street view images of Guangzhou City. The acquired street view images are then subjected to noise filtering, color correction and size adjustment to ensure that the image quality input into the deep learning model is stable and consistent, and the accuracy of image feature extraction is improved. Some street view images such as Figure 2 shown.

[0069] 2) Use GVE and PSPNet to calculate greenness and sky visibility respectively.

[0070] In the present invention, the quantification of road comfort is achieved based on the automatic identification and statistical calculation of key elements representing the visual quality of the environment in the street view image. To this end, the present invention uses the GVE (Green Vegetation Extraction) algorithm to extract the proportion of green vegetation pixels in the street view image obtained in step 1) to obtain the road greenness index, and uses the deep learning semantic segmentation model PSPNet (Pyramid Scene Parsing Network) to perform pixel-level semantic analysis on the street view image, identify and quantify the proportion of sky pixels, and then obtain the sky visibility index.

[0071] Specifically, the GVE algorithm separates green vegetation areas from other backgrounds by analyzing the reflectance differences of street scene images in the three RGB bands. Considering that in images at the urban street level, vegetation often has a higher reflectance in the green band (G band) and a relatively lower reflectance in the red (R band) and blue (B band) bands, GVE uses this spectral feature to classify pixels. The calculation process is as follows: Figure 3 As shown in the figure, the green vegetation extraction result is as follows Figure 4 As shown, the specific process is:

[0072] 21) Difference image construction: Two difference (Diff) images GR and GB are calculated for the preprocessed street view image, and they are multiplied to obtain a Diff image. In the Diff image, since the green channel value is significantly higher than the red and blue channels, vegetation pixels usually appear as positive values.

[0073] 22) Pixel classification and rule filtering: Based on the positive and negative values ​​of the Diff image pixel values ​​and the threshold judgment, positive pixels are judged as possible vegetation pixels, and further distinguished accurately through additional rules, for example, requiring the G channel value to be higher than the R and B channel values. Then, filtering methods (such as median filtering and morphological operations) are used to remove the spark points of the "salt and pepper" effect, that is, single abnormal pixels, to ensure that the classification results are smoother and more continuous.

[0074] 23) Greenness calculation: Divide the final number of green pixels NumGreen by the total number of pixels in the street view image NumSVI to obtain the road greenness index GDgree:

[0075]

[0076] The PSPNet model is a mature model in the field of deep learning semantic segmentation. By using a convolutional neural network based on ResNe t50 and a pyramid pooling module (PPM) to fuse multi-scale features, the PSPNet model can obtain accurate segmentation capabilities for multiple semantic categories such as the sky, roads, buildings, and vegetation in complex outdoor scenes. In the present invention, the PSPNet model is pre-trained using the public ADE20K data set, so that the model has high-precision recognition capabilities for the sky category in the urban street view parsing task, and the sky area can be accurately separated in the street view image. Specifically, the street view image that has been pre-processed (denoising, color correction, and cropping) in the early stage is input into the pre-trained PSPNet model, and no manual annotation is required. The PSPNet model automatically outputs the semantic category label of each pixel. The output result of PSPNet is a prediction map of the same size as the input image, and each pixel has a corresponding category label. The present invention focuses on the "sky" category and counts the number of pixels in this category NumSky. Finally, divide NumSky by the total number of image pixels NumSVI to get the sky visibility SDgree:

[0077]

[0078] The final prediction result is as follows Figure 5 As shown, after obtaining the greenness GDgree and the sky visibility SDgree, the greenness GDgree and the sky visibility SDgree are combined to form the road comfort index emo:

[0079] emo=GDgree+SDgree

[0080] The larger the emo value, the richer the greenery and the wider the sky in the street view dimension of the road section, which can provide pedestrians with better visual perception and psychological pleasure. By directly sending the emo value to the path planning module of the next stage. In path planning, the present invention constructs a comprehensive weight by combining emo with the road distance dist, and based on algorithms such as Dijkstra, it provides users with more personalized leisure path choices from two aspects: meeting the travel time requirements of pedestrians and improving the pleasure of the travel process.

[0081] 3) Integrate distance and comfort into weights and apply Dijkstra algorithm for planning.

[0082] By successfully extracting two key factors from road networks and street view images: road length (di stance) and road comfort (emo), the two are combined into a comprehensive weight, thereby optimizing the pedestrian leisure travel experience at the global level.

[0083] Specifically, the emo value (composed of greenness and sky visibility) reflects the visual quality of the road environment, and the distance dist represents the spatial cost of travel. The comprehensive weight function proposed in the present invention is:

[0084]

[0085] Among them, r1 and r2 are adjustable parameters. The smaller dist is, the shorter the road section is, which is conducive to reducing time cost and physical exertion and meeting basic travel efficiency requirements. The larger the emo value is, the higher the road greenness and sky visibility are, and the better the visual perception of pedestrians while walking. However, considering that the shortest path algorithm needs to find the path with the least cost, directly adding the emo value may conflict with the shortest logic. To this end, the present invention adopts the form of 1 / emo, and corresponds high-comfort roads to lower cost factors, thereby encouraging the path search process to tend to sections with high emo values. R1 and r2 are set by the user or the system according to preference. When the user prefers to arrive at the destination faster, r1 can be increased to emphasize the distance factor; when the user pays more attention to the travel experience and visual comfort, r2 can be increased to balance the path planning to lean towards high comfort. This flexible adjustment mechanism can adapt to a variety of travel preference scenarios.

[0086] According to the comprehensive weight w, the road network is constructed as a weighted graph structure (Graph), where the nodes are road intersections or segment endpoints, and the edge weights are w. As a classic single-source shortest path algorithm, the Dijkstra algorithm can guarantee the global optimal solution without additional complexity optimization in the absence of negative weight edges. The specific steps are:

[0087] 31) Starting from the starting node, initialize the starting distance to 0 and the distances of other nodes to infinity;

[0088] 32) Repeatedly select the node with the smallest current distance and unconfirmed, and update the distance record of its adjacent nodes. Since the path cost w comprehensively considers distance and comfort, the path with high emo value (corresponding to lower 1 / emo value) will appear cheaper in the search process and will be selected first;

[0089] 33) Continue iterating until the target node is reached or all nodes are processed, thus finding a path with the lowest weight at the global level.

[0090] The application of the comprehensive weight w and the Dijkstra algorithm enables the present invention to effectively improve the comfort level of the road environment while meeting the basic travel distance requirements, which has obvious value for tourism and leisure travel: pedestrians are no longer limited to choosing the shortest path, but can enjoy a better street greening environment and high-quality sky view within a reasonable range, thereby enhancing psychological pleasure and travel satisfaction.

[0091] 4) Output leisure paths that meet user needs and display them visually.

[0092] When the Dijkstra algorithm calculates the path with the minimum comprehensive weight, it outputs the path in the form of a node sequence or a linear network. The path is not only a simple geographical location sequence, but also comes with relevant environmental indicator information, including:

[0093] 41) Path length: The total distance of the entire path, so that users can evaluate the basic time cost of travel;

[0094] 42) Average or weighted comfort index: Based on the emo value of each section on the path, the average greenness of the path and the average sky visibility are output, or a comprehensive weighted summary of the road greenness and sky ratio is made, so that users can predict the visual experience quality of the entire journey.

[0095] In addition, visualization is a key means to improve user understanding and decision-making quality. The present invention marks the planned path with highlighted lines on the interactive electronic map, marking the starting point and the end point, so that users can intuitively view the spatial direction of the path, such as Figure 6 shown.

[0096] Embodiment 2

[0097] The driving route planning system considering urban landscape of the present invention comprises:

[0098] An acquisition module, used to acquire street view images of various roads in the city;

[0099] A first calculation module, used for calculating the greenness and sky visibility of the street view image;

[0100] A second calculation module, used for calculating a road comfort index according to the greenness and sky visibility of the street view image;

[0101] A construction module, used to construct a comprehensive weight according to the road comfort index and the road length, and to construct a weighted graph structure according to the comprehensive weight;

[0102] The planning module is used to perform path planning using the Dijkstra algorithm in a weighted graph structure to obtain the user's path.

[0103] In this embodiment, the first calculation module includes:

[0104] The third calculation module is used to calculate the number of green pixels NumGreen of the street view image based on the GVE algorithm;

[0105] A fourth calculation module, used for calculating the greenness GDgree of the street view image according to the number of green pixel points NumGreen of the street view image and the total number of pixels of the street view image;

[0106] A prediction module, used for inputting the street view image into the trained PSPNet model to obtain a prediction map, in which each pixel point in the prediction map has a corresponding category label;

[0107] Statistics module, the number of pixels NumSky with the category label of sky in the user's statistical prediction graph;

[0108] The fifth calculation module is used to calculate the sky visibility SDgree of the street view image according to the number of pixels NumSky with the category label of sky and the total number of pixels NumSVI of the prediction image.

[0109] The division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0110] Embodiment 3

[0111] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the driving route planning method considering the urban landscape are implemented, for example, including: obtaining street view images of each road in the city; calculating the greenness and sky visibility of the street view image; calculating the road comfort index according to the greenness and sky visibility of the street view image; constructing a comprehensive weight according to the road comfort index and the road length, and constructing a weighted graph structure according to the comprehensive weight; in the weighted graph structure, using the Dijkstra algorithm to perform route planning to obtain the user's route. The memory may include a memory, such as a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk memory, etc. The processor, the network interface, and the memory are interconnected through an internal bus, and the internal bus may be an industrial standard architecture bus, a peripheral component interconnection standard bus, an extended industrial standard architecture bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include memory and nonvolatile memory and provides instructions and data to the processor.

[0112] Embodiment 4

[0113] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the driving route planning method considering the urban landscape are implemented, for example, including: obtaining street view images of each road in the city; calculating the greenness and sky visibility of the street view image; calculating the road comfort index according to the greenness and sky visibility of the street view image; constructing a comprehensive weight according to the road comfort index and the road length, and constructing a weighted graph structure according to the comprehensive weight; in the weighted graph structure, using the Dijkstra algorithm to perform path planning to obtain the user's path. Specifically, the computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0114] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0115] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and disclosure of the invention. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the following claims.

[0119] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0120] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any simple modification, change and equivalent structural change made to the above embodiment based on the technical essence of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A driving route planning method considering urban landscape, characterized in that: include: Get street view images of each road in the city; Calculating the greenness and sky visibility of the street view image; Calculating a road comfort index based on the greenness and sky visibility of the street view image; Constructing a comprehensive weight according to the road comfort index and the road length, and constructing a weighted graph structure according to the comprehensive weight; In the weighted graph structure, the Dijkstra algorithm is used for path planning to obtain the user's path.

2. The driving route planning method considering urban landscape according to claim 1, characterized in that: The process of calculating the greenness of the street view image is as follows: Calculate the number of green pixels NumGreen of the street view image based on the GVE algorithm; The greenness GDgree of the street view image is calculated according to the number of green pixel points NumGreen of the street view image and the total number of pixels of the street view image.

3. The driving route planning method considering urban landscape according to claim 1, characterized in that: The process of calculating the sky visibility of the street view image is as follows: Inputting the street view image into the trained PSPNet model to obtain a prediction map, wherein each pixel in the prediction map has a corresponding category label; The number of pixels with the category label of sky in the statistical prediction map is NumSky; The sky visibility SDgree of the street view image is calculated according to the number of pixels NumSky whose category label is sky and the total number of pixels NumSVI of the prediction image.

4. The driving route planning method considering urban landscape according to claim 1, characterized in that: The road comfort index is calculated according to the greenness and sky visibility of the street view image, wherein the road comfort index emo is: emo=GDgree+SDgree Among them, GDgree is the greenness of the street view image, and SDgree is the sky visibility of the street view image.

5. The driving route planning method considering urban landscape according to claim 1, characterized in that: A comprehensive weight is constructed according to the road comfort index and the road length, and the comprehensive weight w is: Among them, r1 and r2 are adjustable parameters, dist is the road length, emo is the road comfort index, and a weighted graph structure is constructed according to the weights.

6. The driving route planning method considering urban landscape according to claim 1, characterized in that: After the path planning is performed using the Dijkstra algorithm according to the weighted graph structure and the user's path is obtained, the following steps are further included: A visualization operation is performed on the path of the user.

7. A driving route planning system considering urban landscape, characterized in that: include: An acquisition module, used to acquire street view images of various roads in the city; A first calculation module, used for calculating the greenness and sky visibility of the street view image; A second calculation module, used for calculating a road comfort index according to the greenness and sky visibility of the street view image; A construction module, used to construct a comprehensive weight according to the road comfort index and the road length, and to construct a weighted graph structure according to the comprehensive weight; The planning module is used to perform path planning using the Dijkstra algorithm in a weighted graph structure to obtain the user's path.

8. The driving route planning system considering urban landscape according to claim 7, characterized in that: The first calculation module includes: The third calculation module is used to calculate the number of green pixels NumGreen of the street view image based on the GVE algorithm; A fourth calculation module, used for calculating the greenness GDgree of the street view image according to the number of green pixel points NumGreen of the street view image and the total number of pixels of the street view image; A prediction module, used for inputting the street view image into the trained PSPNet model to obtain a prediction map, in which each pixel point in the prediction map has a corresponding category label; Statistics module, the number of pixels NumSky with the category label of sky in the user's statistical prediction graph; The fifth calculation module is used to calculate the sky visibility SDgree of the street view image according to the number of pixels NumSky with the category label of sky and the total number of pixels NumSVI of the prediction image.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the driving route planning method considering urban landscape as described in any one of claims 1-6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the driving route planning method considering urban landscape as described in any one of claims 1 to 6 are implemented.

Images