CN114911891A - Method, system, storage medium and device for analyzing space quality of historical street - Google Patents
Method, system, storage medium and device for analyzing space quality of historical street Download PDFInfo
- Publication number
- CN114911891A CN114911891A CN202210662348.1A CN202210662348A CN114911891A CN 114911891 A CN114911891 A CN 114911891A CN 202210662348 A CN202210662348 A CN 202210662348A CN 114911891 A CN114911891 A CN 114911891A
- Authority
- CN
- China
- Prior art keywords
- street
- quality
- view image
- index
- obtaining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/38—Outdoor scenes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method, a system, a storage medium and equipment for analyzing the space quality of a historical street, comprising the following steps: obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street identifications in the image after semantic segmentation to obtain the percentage of the elements in the street view image data; obtaining street quality indexes of different types and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value; respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and giving street attributes to the map according to the categories of the street quality indexes so as to realize street quality spatial analysis. And determining the quality of the street space according to the ratio of the elements to the total pixels of the street view image and the set weight value, and registering the quality data to a street map to obtain a visualized street space quality analysis result.
Description
Technical Field
The invention relates to the technical field of geographic image monitoring, in particular to a method, a system, a storage medium and equipment for analyzing the spatial quality of a historical street.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The street can be continuously updated and modified along with the development of a city, the experience of a user can be considered for the updating and modifying of the historical block, meanwhile, the street is a part of the urban landscape, the quality of the street space is quantitatively analyzed, and the street space layout can be improved according to the information of the traffic condition, the flow of people and traffic, the greening coverage and the like of the street, so that the updating and modifying of the street are facilitated.
In the quantitative research of streets, a geographic information system is a more classical and mature two-dimensional plane analysis platform, but the geographic information system can only analyze the constituent elements of street spaces such as street pavements, street interfaces and the like, and cannot acquire more detailed elements in the street spaces, such as plants, pedestrians and vehicles in the streets to analyze the influence of the street space quality. Although more detailed elements of street space can be obtained by identifying street scene images, such an approach relies on sophisticated computer image recognition algorithms, and it is difficult to determine the accuracy and degree of detail of image recognition from an algorithmic level.
Meanwhile, the analysis process for the street space quality at present depends on a statistical survey mode, the statistical survey mode needs a lot of time and labor cost, certain subjectivity exists, and objective quantification of the street space quality is difficult to carry out.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a method, a system, a storage medium and a device for analyzing the spatial quality of a historical street, which utilize street view image data subjected to semantic segmentation to obtain required elements, determine the quality of a street space according to the ratio of the pixels of the elements to the total pixels of the street view image and a set weight value, and register the quality data to a street map to obtain a visual analysis result of the spatial quality of the street.
In order to achieve the purpose, the invention adopts the following technical scheme:
the first aspect of the invention provides a method for analyzing the spatial quality of historical streets, which comprises the following steps:
obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street identifications in the image after semantic segmentation to obtain the percentage of the eight elements in the street view image data;
obtaining different kinds of street quality indexes and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value;
respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and giving street attributes to the map according to the categories of the street quality indexes so as to realize street quality spatial analysis.
Obtaining different types of street quality indexes according to the percentage of the elements in the street view image data and the set weight value, specifically:
obtaining a sky openness index SVI according to the ratio of the pixel of the sky in the street view image to the total pixel of the street view image;
obtaining a green vision rate index GVI according to the ratio of the pixel where the plant is located in the street view image to the total pixel of the street view image;
obtaining a space feasibility index SFI according to the ratio of the pixel of the pedestrian path in the street view image to the total pixel of the street view image occupied by the vehicle pedestrian path;
obtaining a vehicle interference index VII according to the ratio of the pixels of the vehicles and the roadways in the street view image to the total pixels of the street view image;
obtaining a traffic identification index ITI according to the ratio of the pixel of the street identification in the street view image to the total pixel of the street view image;
obtaining a facility convenience index PCI according to the ratio of the pixel of the street infrastructure in the street view image to the total pixel of the street view image;
and obtaining the crowd concentration index CCI according to the ratio of the pixel of the pedestrian in the street view image to the total pixel of the street view image.
Obtaining a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value, wherein the specific steps are as follows:
and adding the set weight values with the products of the sky openness index, the green vision rate index, the space feasibility index, the vehicle interference index, the traffic identification index, the facility convenience index and the crowd concentration index to obtain a complete street quality index.
Respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, specifically:
the street quality index and the corresponding street view image form point data and are converted into road network data;
dividing the broken line of the whole section in the road network data into a set number of sections;
and registering the road network data into the map according to the geographic position of the street view image.
A second aspect of the present invention provides a system for implementing the above method, comprising:
an image data processing module configured to: obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street marks in the image after semantic segmentation to obtain the percentage of the eight elements in the street view image data;
a quality index acquisition module configured to: obtaining street quality indexes of different types and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value;
a visualization analysis module configured to: respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and giving street attributes to the map according to the categories of the street quality indexes so as to realize street quality spatial analysis.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for historical street space quality analysis as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method for analyzing the spatial quality of the historical streets as described above when the program is executed.
Compared with the prior art, the above one or more technical schemes have the following beneficial effects:
1. the method comprises the steps of obtaining required elements by utilizing street view image data after semantic segmentation, determining quality indexes of street spaces according to the ratio of pixels where the elements are located to the pixels of the street view image and a set weight value, registering the quality indexes to a street map to obtain visual street space quality analysis results, obtaining street space constituent elements such as street pavements, street interfaces and the like by semantic segmentation, obtaining street detail elements such as street landscapes, traffic signs and the like, obtaining street quality indexes of different types by utilizing the percentage of the elements to the pixels of the street view image, analyzing the quality of the street spaces by utilizing different dimensions, and enabling the obtained results to be more visual and comprehensive.
2. When the street quality index is registered in the map, additional attributes are given to roads in the map, the qualities of different dimensions of a street space can be displayed in a more intuitive mode, the degree of association and the degree of mutual influence between each index in the street quality and the actually obtained quality index are analyzed, and guidance is provided for the improvement of street layout, vegetation coverage, traffic facilities and the like in the street updating and improving process.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a schematic flow diagram of a historical street spatial quality analysis provided by one or more embodiments of the present invention;
FIG. 2 is a schematic illustration of street view annotation provided by one or more of the present invention;
FIGS. 3(a) - (d) are schematic diagrams illustrating the loss (loss value), pa (pixel accuracy), mpa (average pixel accuracy), and miou (average cross-over ratio) of one or more street view photographs, respectively, provided by the present invention;
FIG. 4 is a graphical representation of one or more of the university road space feasibility calculations provided by the present invention and quantified values for each road segment;
FIG. 5 is a graphical representation of one or more of the university road facility convenience calculations and quantified values for various segments provided by the present invention;
FIG. 6 is a calculation of college degree of road population at universities and quantified values of each road segment provided by one or more of the present invention;
FIG. 7 is a graph of one or more of the results of the university road walk security calculations provided by the present invention and quantified values for each road segment;
FIG. 8 is a graph of the calculated university road traffic identification index and quantified values for each road segment provided by one or more of the present inventions;
FIG. 9 is a graph of a calculation of university road sky openness and quantified values for various roads in accordance with one or more aspects of the present invention;
FIGS. 10(a) - (b) are schematic and statistical diagrams after visualization of university road space feasibility data provided by one or more embodiments of the present invention;
11(a) - (b) are schematic and statistical diagrams after visualization of university road facility convenience data provided by one or more of the present inventions;
FIGS. 12(a) - (b) are schematic and statistical diagrams after visualization of college road population cluster density data provided by one or more of the present inventions;
FIGS. 13(a) - (b) are schematic and statistical diagrams after visualization of one or more university road walk safety data provided by the present invention;
14(a) - (b) are schematic and statistical diagrams of visualized university road traffic designator data provided by one or more of the present inventions;
15(a) - (b) are schematic and statistical diagrams of visualized university road sky openness data provided by one or more embodiments of the present invention;
figures 16(a) - (b) are schematic and statistical diagrams after visualization of university road spatial quality data provided by one or more of the present inventions.
Detailed Description
The present invention will be further described with reference to the following examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the quantitative research of streets, a geographic information system is a more classical and mature two-dimensional plane analysis platform. However, the important point is street space components such as street pavements and street interfaces, and the analysis of the components such as street landscapes and interface detail elements is less. The street view image data combines the application of the semantic segmentation technology to make up the blank of the detail constituent elements to a certain extent. Street view image data has the characteristics of convenience in acquisition, strong timeliness and wide coverage range, and a new thought method is provided for the measure of street space quality along with the continuous updating of semantic segmentation such as depeplab in recent years.
Therefore, the following embodiments provide a method, a system, a storage medium, and a device for analyzing quality of a historical street space, which utilize street view image data after semantic segmentation to obtain eight elements of trees, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructures, and street signs, determine quality of the street space according to a ratio of pixels between the elements and a set weight value, and register quality data to a street map to obtain a visual street space quality analysis result.
The first embodiment is as follows:
as shown in fig. 1-16, the method for analyzing the spatial quality of the historical street comprises the following steps:
obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street identifications in the image after semantic segmentation to obtain the percentage of the eight elements in the street view image data;
obtaining street quality indexes of different types and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value;
respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and giving street attributes to the map according to the categories of the street quality indexes so as to realize street quality spatial analysis.
Specifically, the method comprises the following steps:
the method for analyzing street space quality of the embodiment is divided into the following three parts:
and semantically segmenting the historical street view picture, and constructing an evaluation system and a spatial quality index. Processing photos of related streets through depllabV 3+, dividing eight parts of trees, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street signs, obtaining occupation ratios of related elements and obtaining a quantitative quality index according to the occupation ratios of the elements.
And performing visual research on the related calculation result by using the GIS, and combining related data of semantic segmentation with GIS to clearly obtain the numerical conditions of each index and the change conditions of each road section.
The SPSS analyzes the correlation analysis of the spatial quality indexes, and obtains the correlation degree and the mutual influence degree of each index by analyzing the relation between the correlation indexes and the spatial quality. And obtaining positive correlation and negative correlation according to the analysis result.
The method for analyzing the spatial quality of a street given in this embodiment is explained by taking a street named "university road" in a certain city as an example.
And acquiring spatial quality measurement data of streets of the college road.
For the quality of street space in the past, the street view picture is usually obtained by adopting a Python crawling mode. The method is suitable for large-range and wide-field research objects, such as central cities, historical blocks and the like. For the single street space quality research, the data crawling is greatly influenced by the street view map position, the street view picture data of each measuring point angle is insufficient, and the shooting place cannot always guarantee the direction along the street center line, so the manual shooting mode is selected in the embodiment. The measurement precision of Python crawl photos is improved from 30 meters to 10 meters. And street view pictures are taken every ten meters along the central line direction of the street at the height equal to the visual angle of human eyes, and the pictures taken at each measuring point are ensured to have the same angle and the same time. The method can ensure that the pictures shot in the mode can obtain data with required precision by matching with semantic segmentation, thereby reflecting the required element precision.
And constructing a historical street space quality measuring system.
The embodiment selects the road feasibility, facility convenience, walking safety, space comfort and place sociality as research objects by combining the selection of research reviews of related indexes and the characteristics of the street of a university, mainly sensing space and assisting material space, and selecting corresponding indexes to perform research measurement on the road feasibility, facility convenience, walking safety, space comfort and place sociality on the basis of indexes selected from the research on the urban street space quality measurement and influence mechanism based on street view picture data, namely, the urban area of Nanjing center, and the research on the urban area of Ming City based on multisource big data. Adopting AHP analytic hierarchy process, according to consistent matrix method to make pairwise comparison of relevant factors, so as to obtain corresponding index weight assignment, the concrete contents are shown in tables 1 and 2:
TABLE 1 street spatial quality metric index matrix
TABLE 2 street spatial quality metric index weights
As shown in fig. 1 and table 2, among the five first-level indexes in the middle layer, the spatial comfort weight is the highest, reaching 0.287; facility convenience weight was the lowest, 0.135. In the second-level index, the influence degree of the crowd concentration on the space quality of the living streets is the largest and reaches 0.221, and the positioning of the living streets is met. The traffic sign index has the lowest weight of 0.044, so the final measure calculation formula of the living street space quality (LQI) of the embodiment is as follows:
LQI＝0.133SVI+0.154GVI+0.171SFI+0.142VVI+0.044ITI+0.135PCI+0.221CCI。
wherein, each measure index is defined as follows:
SVI (sky openness index): ratio of sky to street view total pixels.
GVI (green index): ratio of total pixels of green plants to street view photos.
SFI (space feasibility index): the pixel ratio of the street and the roadway in the street view picture.
VII (vehicle disturbance index): the pixel ratio of the street view picture occupied by the motor vehicle and the motor vehicle lane.
ITI (traffic identification index): the traffic signal light and the ratio of the total pixels of the sign and the street view picture.
PCI (facility convenience index): ratio of total pixels of each facility to the street view photos.
CCI (population concentration index): the ratio of the person pixels to the total pixels of the street view photograph.
And obtaining the actual value of each measure index according to the product of the ratio of the pixels of the sky, the green plants, the pedestrian ways and the roadway, the motor vehicles and the motor vehicle lanes, the traffic signal lamps and the signs, the facilities and the characters in the total pixels of the street view image acquired from the street view image data and the weight of each measure index, and adding to obtain the final value of the street space quality (LQI).
And acquiring a spatial quality measure index of the street of the university road.
As shown in FIG. 2, the index is calculated by semantic segmentation and depending on deep-V3 +. Firstly, randomly selecting 20 street view photos, labeling the street view photos through Labelme, distinguishing eight parts of trees, sidewalks, roadways, pedestrians, vehicles, sky, street infrastructure and street signs, and training through Deeplab-V3+ after labeling.
The PyCharm deep learning library is used for training for two hundred times, and the learning rate is adjusted to be half of the previous one every 50 times. And selecting a model with the highest miou expression to predict street view photos, and performing data enhancement by five methods of random cutting, turning, USM sharpening enhancement, random noise, brightness adjustment and contrast adjustment, wherein a training iteration graph can reflect whether a training result is feasible or not, and the result is shown in fig. 3.
In fig. 3, loss, pa, mpa, miou, and total 200 trainings are indicated.
(1) In the Loss value of Loss reaction training and testing process, the deviation of the original training photo training value and the test photo test value is smaller, and the closer the training value and the test value is, the better the generalization performance of the training model is. As can be seen from the graph, the loss value decreases with the increase in the number of training times, and finally, the loss value is stably controlled to 0.05 or less.
(2) The Pa value can reflect the proportion of the photo pixels correctly classified by a machine to the total pixels of the photo, and the accuracy of the pixels reaches more than 99% after training.
(3) MPA is further calculated on the basis of Pa, various labeled elements are respectively calculated, the overall average Pa value of all photos after recognition is controlled to be about 85% after training.
(4) And the Miou average cross-over ratio reflects the training photo value and the test photo value, the ratio of the same part to the two cyan sets is the same as that of Mpa, the cross-over ratio of each element is calculated firstly, the average value is further calculated, the average cross-over ratio in the training process is finally obtained, and the average pixel accuracy average cross-over ratio reaches more than 80% along with the increase of the training times.
Through the four indexes, the result is all above the ideal value, the training result is feasible, and the semantic segmentation of the next step can be carried out. And after training is finished, importing the other street view pictures, performing semantic segmentation on the street view pictures, and obtaining the final sky openness, green-sight rate index, space feasibility index, vehicle interference index, traffic identification index, facility convenience index and crowd concentration index according to the pixel ratio of the required elements in the street view pictures after segmentation.
In this embodiment, fig. 4 to 10 respectively show the calculation results of space feasibility, facility convenience, crowd concentration, walking safety, traffic identification index and sky openness obtained after semantic segmentation of street view photographs of a college road at a plurality of intersections or a plurality of road sections.
University road street space quality index visual analysis
The method is characterized in that GIS (Geographic Information System or Geo-Information System, GIS) is combined for visual analysis, the measurement index obtained in the above steps is point data generated based on street view images, which can reflect the quality of a certain road segment or a certain number of intersections in the university road, and the street (road) is continuous and needs to be converted into a continuous line segment to show the quality of each road segment in a road or a street, and the method specifically includes the following steps:
importing point data into gis, and converting the point data into road network data by using a point turning line function in gis;
selecting the broken line of the whole section, and equally dividing the road network data into x sections by utilizing the sections in the gis editing function;
registering the road network data to a map by using a geographic registration function in gis;
respectively connecting 7 types of data (7 indexes of sky openness, green vision rate index, spatial feasibility index, vehicle interference index, traffic identification index, facility convenience index and crowd concentration index) to the road network data by using spatial connection, and giving 7 types of attributes to the road network data;
the road network data was visualized using the notation system in gis, and the data was classified into 5 classes using the natural breakpoint method (meaning 7 classes of measure indices were classified into 5 classes according to table 2), and a statistical graph was derived.
In this embodiment, fig. 11 to 15 are a statistical chart and a visualization result of spatial feasibility, facility convenience, crowd concentration, walking safety, traffic sign index, and sky openness of a college road shown at a plurality of road segments or intersections, respectively, obtained according to street view image data.
In this embodiment, fig. 16 is a visualization result and a statistical chart of spatial quality indexes displayed at a plurality of road segments or intersections of a college road obtained according to street view image data.
After the visualization result is obtained, street space quality analysis is performed on the university road as follows:
from each index, the indexes worth keeping the current situation are a road surface (space) feasibility index, a traffic identification index and a vehicle interference index; the indexes worth optimizing are facility convenience and crowd concentration; the green vision rate and the sky openness are greatly influenced by the density of seasonal leaves, so the current situation is maintained.
From the street spatial quality index. Although the spatial quality distribution of the living streets on each road section of the university road is uniform, the value of inland from the coastal region of the south to the north tends to be gradually reduced. The space quality index interval of the street of the college road life is 0.029-0.614, the average value is 0.102, and the space quality index is lower.
As can be seen from the numerical values of the road sections, the soutest section of the university road with the best quality is the Tai-Longkou road, and the numerical value is 0.107. The road section with the lowest quality is the northmost section of the university road, the Yangxian county road-the state road, and the numerical value is 0.096. The spatial quality index is mainly centered before [0.063-0.191], and has a value of 164, accounting for 60.6%. The spatial quality index is more than 0.191, is only 25, and accounts for 9.29%.
And (5) carrying out correlation analysis on the spatial quality index of the street of the university.
The indexes in the embodiment are subjected to correlation analysis by using an SPSS data analysis platform and a Pearson coefficient, so that the correlation degree and the mutual influence degree between each index and the quality are obtained. According to the analysis result, all the indexes are positively correlated with the street space quality index. Wherein [0-0.1] is weakly correlated, [0.1-0.2] is low-degree correlated, [0.2-0.4] is moderate-degree correlated, [0.4-0.5] is high-degree correlated, and [0.5-1] is significant correlated, as shown in Table 3.
TABLE 3 correlation analysis of spatial quality index and spatial quality index
In table 3, at 0.01 scale (double tail), the correlation was significant; at the 0.05 level (double tail), the correlation was significant.
Through the correlation analysis of the evaluation index and the space quality, the sky openness (SVI) is obviously related to the street space quality, and the road Surface Feasibility (SFI) and the vehicle interference index (VVI) are moderately related to the green vision rate (GVI). Wherein the vehicle interference index (VVI) is moderately correlated with the road Surface Feasibility (SFI), the Crowd Concentration (CCI) and the facility convenience (PCI). The traffic indicator index (ITI) is low correlated with road Surface Feasibility (SFI) and Crowd Concentration (CCI).
In summary of the above description of the correlation, the conclusion is as follows:
1. the sky openness, the green sight rate, the road surface feasibility, the vehicle interference index and the space quality of the street of the college road are closely related.
2. The evaluation indexes are all in positive correlation with the spatial quality index. But the traffic sign index has a lower impact on the quality of the space.
3. The crowd concentration degree and facility convenience, and the correlation degree of the vehicle interference index and the road surface feasibility are higher.
By combining the above analysis, it is clear that two indexes of college road population and facility convenience need to be improved.
In summary, the method uses the street view image data after semantic segmentation to obtain the required elements, determines the quality index of the street space according to the ratio of the pixel of the element in the street view image pixel and the set weight value, and registers the quality index into the street map to obtain the visualized quality analysis result of the street space.
When the street quality index is registered in the map, additional attributes are given to roads in the map, the qualities of different dimensions of a street space can be displayed in a more intuitive mode, the degree of association and the degree of mutual influence between each index in the street quality and the actually obtained quality index are analyzed, and guidance is provided for the improvement of street layout, vegetation coverage, traffic facilities and the like in the street updating and improving process.
Example two:
the embodiment provides a system for implementing the method, which includes:
an image data processing module configured to: obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street marks in the image after semantic segmentation to obtain the percentage of the eight elements in the street view image data;
a quality index acquisition module configured to: obtaining street quality indexes of different types and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value;
a visualization analysis module configured to: respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and giving street attributes to the map according to the categories of the street quality indexes so as to realize street quality spatial analysis.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the method for analyzing the spatial quality of the historical streets as set forth in the first embodiment.
Example four
The present embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for analyzing the spatial quality of the historical streets as set forth in the above embodiment.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program, which may be stored in a computer readable storage medium and executed by a computer to implement the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The method for analyzing the space quality of the historical streets is characterized by comprising the following steps: the method comprises the following steps:
obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street identifications in the image after semantic segmentation to obtain the percentage of the eight elements in the street view image data;
obtaining street quality indexes of different types and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value;
respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and giving street attributes to the map according to the categories of the street quality indexes so as to realize street quality spatial analysis.
2. The method of analyzing spatial quality of historical streets as recited in claim 1, wherein: obtaining different kinds of street quality indexes according to the percentage of the elements in the street view image data and the set weight value, wherein the steps of:
obtaining a sky openness index SVI according to the ratio of the pixel of the sky in the street view image to the total pixel of the street view image;
and obtaining the green vision rate index GVI according to the ratio of the pixel of the plant in the street view image to the total pixel of the street view image.
3. The method of analyzing spatial quality of historical streets as recited in claim 1, wherein: obtaining street quality indexes of different types according to the percentage of the elements in the street view image data and the set weight value, and further comprising:
and obtaining a space feasibility index SFI according to the ratio of the pixel of the pedestrian path in the street view image to the total pixel of the street view image occupied by the vehicle street path.
4. The method of analyzing spatial quality of historical streets as recited in claim 1, wherein: obtaining street quality indexes of different types according to the percentage of the elements in the street view image data and the set weight value, and further comprising:
obtaining a vehicle interference index VII according to the ratio of the pixels of the vehicles and the roadways in the street view image to the total pixels of the street view image;
and obtaining the traffic identification index ITI according to the ratio of the pixel of the street identification in the street view image to the total pixel of the street view image.
5. The method of analyzing spatial quality of historical streets as recited in claim 1, wherein: obtaining street quality indexes of different types according to the percentage of the elements in the street view image data and the set weight value, and further comprising:
obtaining a facility convenience index PCI according to the ratio of the pixel of the street infrastructure in the street view image to the total pixel of the street view image;
and obtaining the crowd concentration index CCI according to the ratio of the pixel of the pedestrian in the street view image to the total pixel of the street view image.
6. The method of analyzing spatial quality of historical streets as recited in claim 1, wherein: obtaining a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value, wherein the specific steps are as follows:
and adding the set weight values with the products of the sky openness index, the green vision rate index, the space feasibility index, the vehicle interference index, the traffic identification index, the facility convenience index and the crowd concentration index to obtain a complete street quality index.
7. The method of analyzing spatial quality of historical streets as recited in claim 1, wherein: respectively registering the street quality indexes of different types and the complete street quality index to a map of a road where the street view image is located, wherein the steps are as follows:
the street quality index and the corresponding street view image form point data and are converted into road network data;
dividing the broken line of the whole section in the road network data into a set number of sections;
and registering the road network data into the map according to the geographic position of the street view image.
8. Historical street space quality analysis system, its characterized in that: the method comprises the following steps:
an image data processing module configured to: obtaining street view image data of a required street, and obtaining plants, vehicles, pedestrians, sidewalks, roadways, sky, street infrastructure and street identifications in the image after semantic segmentation to obtain the percentage of the eight elements in the street view image data;
a quality index acquisition module configured to: obtaining street quality indexes of different types and a combined complete street quality index according to the percentage of the elements in the street view image data and a set weight value;
a visualization analysis module configured to: and respectively registering the street quality indexes of different categories and the complete street quality index to a map of a road where the street view image is located, and endowing street attributes in the map according to the categories of the street quality indexes so as to realize street quality spatial analysis.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for analyzing the spatial quality of historical streets according to any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for analyzing the spatial quality of historical streets as recited in any one of claims 1 to 7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210662348.1A CN114911891A (en) | 2022-06-13 | 2022-06-13 | Method, system, storage medium and device for analyzing space quality of historical street |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210662348.1A CN114911891A (en) | 2022-06-13 | 2022-06-13 | Method, system, storage medium and device for analyzing space quality of historical street |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114911891A true CN114911891A (en) | 2022-08-16 |
Family
ID=82769987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210662348.1A Pending CN114911891A (en) | 2022-06-13 | 2022-06-13 | Method, system, storage medium and device for analyzing space quality of historical street |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114911891A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117951239A (en) * | 2024-03-21 | 2024-04-30 | 中国电建集团西北勘测设计研究院有限公司 | Street space breaking degree determining method and device and electronic equipment |
-
2022
- 2022-06-13 CN CN202210662348.1A patent/CN114911891A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117951239A (en) * | 2024-03-21 | 2024-04-30 | 中国电建集团西北勘测设计研究院有限公司 | Street space breaking degree determining method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112418674A (en) | City multi-source data-based street space quality measure evaluation method and system | |
| CN113204718A (en) | Vehicle track destination prediction method considering space-time semantics and driving state | |
| CN107067781B (en) | GIS road black spot map generation method for advanced driving assistance system application | |
| KR102377044B1 (en) | Apparatus and method for evaluating walking safety risk, and recording media recorded program realizing the same | |
| CN109299673A (en) | The green degree spatial extraction method of group of cities and medium | |
| Ye et al. | Urban commerce distribution analysis based on street view and deep learning | |
| CN114911891A (en) | Method, system, storage medium and device for analyzing space quality of historical street | |
| CN117746221A (en) | Urban street space updating achievement evaluation method based on street view image | |
| Zhang et al. | Research on Baidu street view road crack information extraction based on deep learning method | |
| Tang et al. | Assessing the visibility of urban greenery using MLS LiDAR data | |
| Borgalli | Smart pothole detection and mapping system | |
| Boongaling et al. | Developing a street level walkability index in the Philippines using 3D photogrammetry modeling from drone surveys | |
| CN115497006A (en) | Urban remote sensing image change depth monitoring method and system based on dynamic hybrid strategy | |
| CN116092034A (en) | Lane line detection method based on improved deep V < 3+ > model | |
| CN102235868B (en) | The operated navigation systems method to provide route guiding | |
| EP4273502A1 (en) | Method, apparatus, and computer program product for map geometry generation based on data aggregation and conflation | |
| Kaviani et al. | Urban growth pattern in Tehran City: Sustainability or unsustainability | |
| CN114674338B (en) | Fine recommendation method for road drivable area based on layered input and output and double-attention jump | |
| Zachar et al. | Cenagis-Als Benchmark-New Proposal for Dense ALS Benchmark Based on the Review of Datasets and Benchmarks for 3d Point Cloud Segmentation | |
| Zarbakhsh et al. | Points-of-interest from mapillary street-level imagery: a dataset for neighborhood analytics | |
| Vernizzi et al. | The Representation of Urban Environment. From the Survey of the Built City to the Representation of the Intangible Assets | |
| US20230358566A1 (en) | Method, apparatus, and computer program product for map geometry generation based on object detection | |
| US20230358561A1 (en) | Method, apparatus, and computer program product for lane geometry generation based on graph estimation | |
| US20230358567A1 (en) | Method, apparatus, and computer program product for map geometry generation based on data aggregation and conflation with statistical analysis | |
| Liu et al. | A New Approach to Assessing Perceived Walkability: Combining Street View Imagery with Multimodal Contrastive Learning Model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |