CN115564174A - Method, system, computer device and medium for measuring living street space quality - Google Patents
Method, system, computer device and medium for measuring living street space quality Download PDFInfo
- Publication number
- CN115564174A CN115564174A CN202211038230.8A CN202211038230A CN115564174A CN 115564174 A CN115564174 A CN 115564174A CN 202211038230 A CN202211038230 A CN 202211038230A CN 115564174 A CN115564174 A CN 115564174A
- Authority
- CN
- China
- Prior art keywords
- street
- street view
- view image
- living
- scoring
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000011156 evaluation Methods 0.000 claims abstract description 66
- 230000008447 perception Effects 0.000 claims abstract description 32
- 238000007637 random forest analysis Methods 0.000 claims abstract description 29
- 238000010801 machine learning Methods 0.000 claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 230000000007 visual effect Effects 0.000 claims abstract description 17
- 238000003064 k means clustering Methods 0.000 claims abstract description 16
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000013135 deep learning Methods 0.000 claims abstract description 14
- 238000005070 sampling Methods 0.000 claims description 19
- 239000003086 colorant Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 description 7
- 238000012800 visualization Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000011835 investigation Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 239000013604 expression vector Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a system, computer equipment and a medium for measuring the space quality of a living street, wherein the method comprises the following steps: obtaining street view image data of a target area; establishing a street view image database according to street view image data, and scoring street view images through a random forest machine learning model to realize subjective perception of the street view images; obtaining a plurality of environment evaluation indexes of a street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network, and performing objective environment evaluation on a street view image; and calculating the measurement result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process. The method can accurately measure the space quality of the urban living streets, has the advantages of high efficiency and easy popularization and application, and can be widely applied to the field of survey measurement of the space quality of urban planning living streets.
Description
Technical Field
The invention relates to a method, a system, computer equipment and a medium for measuring the space quality of a living street, belonging to the field of urban and rural planning.
Background
The street space is the capillary vessel of the city and touches the aspects of the life of the citizen and the trip of the tourist. The living streets are generally located in residential communities and are the most common street types, the width of a roadway of the living streets is not more than that of a bidirectional four-lane street, the living streets have the functions of traffic and carrying daily life of residents, and the living streets have non-negligible importance on daily life of people and neighborhood communication. In the study of streets from human-induced perspectives, people and streets are two non-negligible subjects, and the spatial perception of people and activities in streets are two main ways in which people and streets can be connected, which is particularly important in living streets.
The existing street space quality measurement evaluation method is mainly based on field investigation data, basic geographic information data and street view picture-based measurement. However, the evaluation systems constructed by a large number of street space quality researches still focus on a single index (such as the green vision rate) or consist of a plurality of universal indexes, are not included in the color characterization indexes under specific regional environments, and lack certain locality.
Disclosure of Invention
In view of the above, the invention provides a method, a system, a computer device and a storage medium for measuring the spatial quality of an active street, which are used for selecting corresponding indexes to construct an evaluation system according to the established environment of a city, and realizing deep comprehensive evaluation of the spatial quality of the active street by combining a subjective perception and objective environment evaluation method so as to accurately measure the spatial quality of the active street in the city, have the advantages of high efficiency and easy popularization and application, and can be widely applied to the field of investigation and measurement of the spatial quality of the active street in city planning.
The first purpose of the invention is to provide a method for measuring the spatial quality of living streets
It is a second object of the present invention to provide a system for measuring the spatial quality of living streets.
It is a third object of the invention to provide a computer apparatus.
It is a fourth object of the present invention to provide a storage medium.
The first purpose of the invention can be achieved by adopting the following technical scheme:
a method of living street spatial quality metric, the method comprising:
obtaining street view image data of a target area;
establishing a street view image database according to street view image data, and scoring street view images through a trained random forest machine learning model to realize subjective perception of the street view images;
obtaining a plurality of environment evaluation indexes of a street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network, and performing objective environment evaluation on a street view image;
and calculating the measurement result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
Further, the obtaining street view image data of the target area specifically includes:
and dividing the sampling points of the streets in the target area at a preset interval, and acquiring street view images in four directions of the sampling points.
Further, establishing a street view image database according to street view image data, and scoring street view images through a random forest machine learning model to realize subjective perception of street view images, specifically comprising:
establishing a street view image database according to the street view image data;
randomly extracting street view images with preset percentage from a street view image database to serve as scoring samples, and acquiring multi-level scores of residents in the target area to the scoring samples;
performing machine deep learning on the result of the scored sample through a random forest machine learning model, and performing parameter adjustment on the random forest machine learning model to obtain a trained random forest machine learning model;
and (3) scoring the rest street view images of the street view image database by using the trained random forest machine learning model, and calculating the average value of the score of the street view images in the front, back, left and right directions of each sampling point as a scoring result.
Further, the environmental evaluation indexes comprise green vision rate, mountain vision rate, degree of girth, breadth, signboard density, sky vision rate and color entropy.
Furthermore, the green visibility, mountain visibility, degree of fitting, breadth of opening, signboard density and sky visibility are obtained as follows:
carrying out street view identification on the street view image through visual image semantic segmentation to obtain the proportion result of multiple street view elements in the street view image;
selecting the proportion results of six factors of plants, mountains, buildings, roads, signs and sky in the street view factor identification results as values of six indexes of green visibility, mountain visibility, degree of closure, breadth, sign density and sky visibility;
and calculating the average value of six indexes of green visibility, mountain visibility, degree of closure, breadth, signboard density and sky visibility in the front, back, left and right directions of each sampling point.
Further, the color entropy is obtained as follows:
removing the sky and road parts in the street view image after semantic segmentation by using a removebg algorithm, and reserving elements influencing the confusion degree of the street facade;
extracting seven main colors in the street view image with the sky and the road removed by a K-means clustering algorithm, and respectively calculating the color proportion of the seven main colors;
calculating the average value of the color entropy in the front, back, left and right directions of each sampling point, wherein the calculation formula of the color entropy is as follows:
wherein S is j Indicating the degree of colour disorder, X, of the j sample point ij The number of pixel points X representing the ith dominant color of each building element of j sampling points j The number of pixels representing architectural elements in the street view.
Further, the calculating of the measure result of the street comprehensive evaluation according to the result weights of the subjective perception and the objective environment evaluation given to the street view image by the analytic hierarchy process specifically includes:
according to an analytic hierarchy process, giving a street view image scoring evaluation result a weight of 0.5, giving a green vision rate and a color entropy weight of 0.1 respectively, giving a mountain vision rate, a degree of closure, a breadth, a signboard density and a sky vision rate weight of 0.06 respectively, and calculating a measure result of street comprehensive evaluation by fusing and normalizing the indexes.
The second purpose of the invention can be achieved by adopting the following technical scheme:
a system for measuring living street spatial quality, the system comprising:
the acquisition module is used for acquiring street view image data of a target area;
the subjective perception module is used for establishing a street view image database according to street view image data, and scoring the street view images through a random forest machine learning model to realize the subjective perception of the street view images;
the objective environment evaluation module is used for obtaining a plurality of environment evaluation indexes of the street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network and carrying out objective environment evaluation on the street view image;
and the measurement module is used for calculating the measurement result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
The third purpose of the invention can be achieved by adopting the following technical scheme:
a computer device comprising a processor and a memory for storing a program executable by the processor, wherein the processor implements the method for measuring living street space quality when executing the program stored in the memory.
The fourth purpose of the invention can be achieved by adopting the following technical scheme:
a storage medium storing a program which, when executed by a processor, implements the above living street spatial quality measuring method.
Compared with the prior art, the invention has the following beneficial effects:
the method is based on street view image data, scores street view images through a trained random forest machine learning model, achieves subjective perception of the street view images, obtains a plurality of environment evaluation indexes of streets through visual image semantic segmentation and a K-means clustering algorithm, performs objective environment evaluation on the street view images, combines the subjective perception and the objective environment indexes, accurately measures the space quality of urban living streets, has the advantages of high efficiency and easiness in popularization and application, and can be widely applied to the field of urban planning living street space quality investigation measurement.
Drawings
In order to more clearly illustrate the embodiments or technical solutions of the present invention, the drawings used in the embodiments or technical solutions of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a simplified flowchart of a method for measuring spatial quality of living streets according to embodiment 1 of the present invention.
FIG. 2 is a detailed flowchart of a method for measuring living street spatial quality according to embodiment 1 of the present invention.
FIG. 3 is a street image evaluation chart according to embodiment 1 of the present invention.
FIG. 4 is a graph of street green power in example 1 of the present invention.
FIG. 5 is a view showing a street mountain according to embodiment 1 of the present invention.
FIG. 6 is a graph of street extent according to example 1 of the present invention.
FIG. 7 is a street breadth map of example 1 of the present invention.
FIG. 8 is a graph of street sign density for example 1 of the present invention.
FIG. 9 is a view of the street sky in accordance with embodiment 1 of the present invention.
FIG. 10 is a color entropy diagram of embodiment 1 of the present invention.
Fig. 11 is a graph showing the result of the street comprehensive evaluation measure according to embodiment 1 of the present invention.
Fig. 12 is a block diagram of a system for measuring spatial quality of living streets according to embodiment 2 of the present invention.
Fig. 13 is a block diagram of a computer device according to embodiment 3 of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete, the technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention, it is obvious that the described embodiments are some, but not all, embodiments of the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the protection scope of the present invention.
Example 1:
the embodiment takes a middle mountain road area in the thought and Ming district of Xiamen city as an example, and provides a method for measuring the space quality of an living street, wherein the middle mountain road area is a typical representation of the current modern old city and landscape of Xiamen, is hopeful to separate sea from the scenic spot of the Shanghai, has rich life smell, and has characteristics and grade of the city of the Xiamen of the building, the scope of the embodiment is that the northeast of the Ximing Ming district, the west of the Xitong river, the south of the Xicheng ocean, the north of the Xicheng He district, and the area of the middle mountain road area is 0.81 square kilometer.
As shown in fig. 1 and fig. 2, the method for measuring the spatial quality of living streets of the present embodiment includes the following steps:
s201, street view image data of the target area are obtained.
This embodiment obtains network open source street view image data through batch, specifically is: compiling Python web crawlers, obtaining in batches through API (application program interface) interfaces in an Tencent map open platform, dividing streets by 50m serving as a preset interval to obtain sampling points, and obtaining street view images in four directions, namely front, rear, left and right of the sampling points, wherein the total number of the street view images is 5356; in addition, in order to display road data during visualization, road network vector data in a middle mountain road area can be obtained in batch through an API (application programming interface) of an open platform of an opentreeetmap website.
S202, establishing a street view image database according to street view image data, and scoring street view images through a trained random forest machine learning model to realize subjective perception of the street view images.
The step S202 specifically includes:
s2021, establishing a street view image database according to the street view image data.
S2022, randomly extracting street view images with preset percentages from the street view image database to serve as scoring samples, and obtaining multi-level scores of residents in the target area to the scoring samples.
The preset percentage of the embodiment is 15%, 688 street view images are randomly extracted from the street view database to serve as scoring samples, and the scoring samples are averagely distributed to eight target area locations to perform five-level scoring on the samples, wherein the scoring is from poor to good and is from 1 to 5.
S2023, performing machine deep learning on the result of the scoring sample through the random forest machine learning model, and performing parameter adjustment on the random forest machine learning model to obtain the trained random forest machine learning model.
In the embodiment, 80% of scoring samples are randomly extracted to be used as a training set, 20% of scoring samples are used as a testing set, machine deep learning is carried out on results of the scoring samples through a random forest model based on Python language, parameter adjustment is carried out on the random forest machine learning model, so that the model score of the random forest machine learning model on the testing set is higher, a more accurate machine scoring value is obtained, and the trained random forest machine learning model is finally obtained.
S2024, scoring the rest street view images of the street view image database by using the trained random forest machine learning model, and calculating the average value of the score of the street view images in the front, back, left and right directions of each sampling point as a scoring result.
In this embodiment, the average value of the street view image scores in the front, back, left, and right directions of each sampling point is calculated to obtain the scoring result in the CSV format, and the scoring result is placed in the ArcGIS for visualization, as shown in fig. 3.
S203, obtaining a plurality of environment evaluation indexes of the street through visual image semantic segmentation and a K-means clustering algorithm based on the deep learning full convolution network, and performing objective environment evaluation on the street view image.
The environmental evaluation indexes of the embodiment include green visibility, mountain visibility, degree of surrounding, breadth of opening, signboard density, sky visibility, and color entropy, wherein the green visibility, mountain visibility, degree of surrounding, breadth of opening, signboard density, and sky visibility are obtained as follows:
1) And carrying out street view identification on the street view image through visual image semantic segmentation to obtain the proportion result of the multiple street view elements in the street view image.
Specifically, street view identification is performed on the street view image obtained in step S201 through visual image semantic segmentation software, and a proportion result of 150 types of street view elements in the street view image is obtained, so as to obtain a CSV table file and a semantically segmented street view image.
The principle of semantic segmentation is based on a scene expression vector analysis framework, and the scene expression vector is composed of visual elements and used for measuring and expressing a specific urban scene. The scene semantic segmentation method based on deep learning calculates the semantic category to which each pixel point in the picture belongs, and obtains visual elements (such as buildings, vehicles, sky and the like) in the scene. A multi-dimensional vector is formed, each dimension in the vector representing the proportion of objects (e.g. buildings) of a particular class in the image.
2) And selecting the proportion results of six factors of plants, mountains, buildings, roads, signboards and sky in the street view factor recognition results as values of six indexes of green visibility rate, mountain visibility rate, degree of girdling, breadth, signboard density and sky visibility rate, wherein the green visibility rate, the mountain visibility rate, the breadth and the sky visibility rate are higher, the degree of girdling and the signboard density are lower, and the street space quality is higher.
3) Calculating the average value of six indexes of green visibility, mountain visibility, surrounding ratio, breadth, signboard density and sky visibility in four directions of the front, back, left and right of each sampling point, and placing the average value into ArcGIS for visualization, as shown in FIGS. 4 to 9.
The color entropy is obtained as follows:
1) Sky and road parts which have large influence on color clustering in the street view image after semantic segmentation are removed through a removebg algorithm based on Python, and elements which influence the confusion degree of the street facade, such as buildings, plants and the like, are reserved.
2) Seven main colors in the street view image with the sky and the road part removed are extracted through a Python-based K-means clustering algorithm, and the color proportion of the seven main colors is calculated respectively.
The principle of the K-Means clustering algorithm is that under the condition of giving K values and K initial cluster center points, each point (data record) is classified into the cluster represented by the cluster center point closest to the point, after all points are distributed, the center point of the cluster is recalculated (averaged) according to all points in the cluster, and then the points are distributed and the cluster center point is updated in an iterative mode until the change of the cluster center point is small or the specified iteration times are reached.
Assuming that a given data sample X, includes n objects X = { X1, X2, X3, \8230;, xn }, where each object has attributes of m dimensions, the goal of the K-means clustering algorithm is to cluster the n objects into a specified number K of class clusters, depending on the similarity between the objects, each object belonging to and only belonging to one of the class clusters whose distance to the center of the class cluster is the smallest.
2.1 Initialize k cluster centers C 1 ,C 2 ,C 3 ,…,C k 1 < k ≦ n, and further, by calculating the Euclidean distance of each object from the cluster center, the formula is as follows:
wherein X i Denotes that the ith object 1 ≦ i ≦ n, C j J is more than or equal to 1 and less than or equal to k and X of j-th cluster center it T-th attribute representing the ith object, t is more than or equal to 1 and less than or equal to m, C jt The t-th attribute representing the j-th cluster center.
2.2 Sequentially comparing the distance of each object from the cluster center, and assigning the objects to the cluster of the closest cluster center to obtain k clusters { S } 1 ,S 2 ,S 3 ,…,S k }。
2.3 K) the K-means cluster center is the mean of all objects in the cluster, and the calculation formula is as follows:
wherein, C l Represents the center of the first cluster, l is more than or equal to 1 and less than or equal to k, | S l I represents the number of objects in the first class cluster, X i Represents the ith object in the ith cluster, 1 is more than or equal to i is less than or equal to | S l |。
3) The average value of the color entropy in the four directions of the front, the back, the left and the right of each sampling point is calculated and is placed into ArcGIS for visualization, as shown in FIG. 10.
The calculation formula of the color entropy is as follows:
wherein S is j Indicating the degree of colour disorder, X, of the j sample point ij Various building elements for representing j sampling pointsNumber of pixel points of pixel ith dominant color, X j Expressing the number of pixel points of the building elements in the street view; the larger the color entropy value is, the less the dominant color is in the street view picture, namely, the higher the color disorder degree is, the more the street facade is disordered; the smaller the color entropy value is, the dominant color exists in the street view picture, namely the lower the color chaos is, and the street facade is neater and uniform.
S204, according to the subjective perception of the street view image and each result weight of the objective environment evaluation given by an Analytic Hierarchy Process (AHP for short), calculating the measurement result of the street comprehensive evaluation.
According to an analytic hierarchy process, giving a street view image scoring evaluation result a weight of 0.5, giving a green vision rate and a color entropy weight of 0.1 respectively, giving a mountain vision rate, a degree of closure, a breadth, a signboard density and a sky vision rate weight of 0.06 respectively, and calculating a measure result of street comprehensive evaluation by fusing and normalizing the indexes, wherein the measure result is as follows:
S=ω 1 S 1+ ω 2 (S 2 +S 3 )+ω 3 (S 4 +S 5 +S 6 +S 7 +S 8 ) (4)
wherein S is a fused street space quality measure result, S 1 Large-scale scoring of the street view image for evaluation results, S 2 Is the rate of greenness, S 3 Is the entropy of color, S 4 Is mountain rate, S 5 To a degree of closure, S 6 To an opening degree, S 7 As signboard density, S 8 Is the sky view rate, omega 1 =0.5, weight of the street view image score evaluation result, ω 2 =0.1, weight of green rate and color entropy, ω 3 =0.06, which is a weight of the mountain visibility, the degree of closeness, the breadth of opening, the signboard density, and the sky visibility.
The results of the street complex assessment measurements were placed in ArcGIS for visualization, as shown in fig. 11.
It should be noted that while the method operations of the above-described embodiments are described in a particular order, this does not require or imply that these operations must be performed in that particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the depicted steps may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
Example 2:
as shown in fig. 12, the present embodiment provides a system for measuring living street spatial quality, which includes an obtaining module 1201, a subjective perception module 1202, an objective environment evaluation module 1203, and a measuring module 1204, where specific functions of the modules are as follows:
an obtaining module 1201, configured to obtain street view image data of a target area.
The subjective perception module 1202 is configured to establish a street view image database according to street view image data, and score street view images through a random forest machine learning model to realize subjective perception of the street view images.
The objective environment evaluation module 1203 is configured to obtain multiple environment evaluation indexes of a street through a visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network, and perform objective environment evaluation on a street view image.
And the measuring module 1204 is used for calculating the measuring result of the comprehensive street evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
It should be noted that, the system provided in this embodiment is only exemplified by the division of the above functional modules, and in practical applications, the above functions may be distributed by different functional modules as needed, that is, the internal structure is divided into different functional modules to complete all or part of the above described functions.
Example 3:
the present embodiment provides a computer device, which may be a computer, as shown in fig. 13, and includes a processor 1302, a memory, an input device 1303, a display 1304, and a network interface 1305 that are connected by a system bus 1301, where the processor is configured to provide computing and controlling capabilities, the memory includes a nonvolatile storage medium 1306 and an internal memory 1307, the nonvolatile storage medium 1306 stores an operating system, a computer program, and a database, the internal memory 1307 provides an environment for the operating system and the computer program in the nonvolatile storage medium to run, and when the processor 1302 executes the computer program stored in the memory, the method for measuring living street space quality of embodiment 1 is implemented as follows:
obtaining street view image data of a target area;
establishing a street view image database according to street view image data, and scoring street view images through a trained random forest machine learning model to realize subjective perception of the street view images;
obtaining a plurality of environment evaluation indexes of a street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network, and performing objective environment evaluation on a street view image;
and calculating the measure result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
Example 4:
the present embodiment provides a storage medium, which is a computer-readable storage medium, and stores a computer program, when the computer program is executed by a processor, the method for measuring the spatial quality of living streets according to embodiment 1 is implemented as follows:
obtaining street view image data of a target area;
establishing a street view image database according to street view image data, and scoring street view images through a trained random forest machine learning model to realize subjective perception of the street view images;
obtaining a plurality of environment evaluation indexes of a street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network, and performing objective environment evaluation on a street view image;
and calculating the measurement result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
It should be noted that the computer readable storage medium of the embodiment may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this embodiment, however, a computer readable signal medium may include a propagated data signal with a computer readable program embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable storage medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program embodied on the computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable storage medium may be written with a computer program for implementing the present embodiment in one or more programming languages, including an object oriented programming language such as Java, python, C + +, and conventional procedural programming languages, such as C, or similar programming languages, or a combination thereof. The program may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
In conclusion, the street view image is scored through a trained random forest machine learning model based on street view image data, subjective perception of the street view image is achieved, a plurality of environment evaluation indexes of a street are obtained through visual image semantic segmentation and a K-means clustering algorithm, objective environment evaluation is conducted on the street view image, the subjective perception and the objective environment indexes are combined, the space quality of the urban living street is accurately measured, the method and the device have the advantages of being high in efficiency and easy to popularize and apply, and can be widely applied to the field of city planning living street space quality investigation measurement.
The above description is only for the preferred embodiments of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art can substitute or change the technical solution of the present invention and the inventive concept within the scope of the present invention, which is disclosed by the present invention, and the equivalent or change thereof belongs to the protection scope of the present invention.
Claims (10)
1. A method for measuring the spatial quality of a living street, the method comprising:
obtaining street view image data of a target area;
establishing a street view image database according to street view image data, and scoring street view images through a trained random forest machine learning model to realize subjective perception of the street view images;
obtaining a plurality of environment evaluation indexes of a street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network, and performing objective environment evaluation on a street view image;
and calculating the measure result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
2. The method for measuring the spatial quality of a living street according to claim 1, wherein the acquiring street view image data of the target area comprises:
and dividing the sampling points of the streets in the target area at a preset interval, and acquiring street view images in four directions of the sampling points.
3. The method for measuring the spatial quality of a living street according to claim 1, wherein the method for establishing a street view image database according to street view image data and scoring street view images through a random forest machine learning model to realize subjective perception of street view images comprises:
establishing a street view image database according to the street view image data;
randomly extracting street view images with preset percentage from a street view image database as scoring samples, and acquiring multi-level scores of residents in the target area on the scoring samples;
performing machine deep learning on the result of the scored sample through a random forest machine learning model, and performing parameter adjustment on the random forest machine learning model to obtain a trained random forest machine learning model;
and scoring the rest street view images of the street view image database by using the trained random forest machine learning model, and calculating the average value of the scores of the street view images in four directions, namely front, back, left and right directions of each sampling point as a scoring result.
4. The method of any one of claims 1 to 3, wherein the environmental evaluation indices include green vision rate, mountain vision rate, degree of girth, breadth, signboard density, sky vision rate, and color entropy.
5. The method of claim 4, wherein the green, mountain, surround, breadth, signboard density and sky visibility are obtained as follows:
carrying out street view identification on the street view image through visual image semantic segmentation to obtain the proportion result of multiple street view elements in the street view image;
selecting the proportion results of six factors of plants, mountains, buildings, roads, signs and sky in the street view factor identification results as values of six indexes of green visibility, mountain visibility, degree of closure, breadth, sign density and sky visibility;
and calculating the average value of six indexes of green visibility, mountain visibility, surrounding degree, breadth, signboard density and sky visibility in four directions of the front, the back, the left and the right of each sampling point.
6. The method for measuring the spatial quality of a living street as claimed in claim 4, wherein the color entropy is obtained as follows:
removing the sky and road parts in the street view image after semantic segmentation by using a removebg algorithm, and reserving elements influencing the confusion degree of the street facade;
extracting seven main colors in the street view image from which the sky and the road part are removed by a K-means clustering algorithm, and respectively calculating the color proportion of the seven main colors;
calculating the average value of the color entropy of each sampling point in the front, back, left and right directions, wherein the calculation formula of the color entropy is as follows:
wherein S is j Indicating the degree of colour disorder, X, of the j sample point ij Pixel for representing i-th dominant color of various building elements of j sampling pointNumber of dots, X j The number of pixels representing architectural elements in the street view.
7. The method for measuring the spatial quality of a living street according to claim 4, wherein the step of calculating the measurement result of the street comprehensive evaluation according to the respective result weights of subjective perception and objective environmental evaluation given to the street view image by the analytic hierarchy process comprises the following steps:
according to an analytic hierarchy process, giving a weight of 0.5 to a street view image scoring evaluation result, giving weights of 0.1 to a green vision rate and a color entropy respectively, giving weights of 0.06 to a mountain vision rate, a degree of girth, a breadth, a signboard density and a sky vision rate respectively, and calculating a measure result of street comprehensive evaluation by fusing and normalizing the indexes.
8. A system for measuring living street spatial quality, the system comprising:
the acquisition module is used for acquiring street view image data of a target area;
the subjective perception module is used for establishing a street view image database according to street view image data, and scoring the street view images through a random forest machine learning model to realize the subjective perception of the street view images;
the objective environment evaluation module is used for obtaining a plurality of environment evaluation indexes of the street through visual image semantic segmentation and a K-means clustering algorithm based on a deep learning full convolution network and carrying out objective environment evaluation on the street view image;
and the measurement module is used for calculating the measurement result of the street comprehensive evaluation according to the result weights of subjective perception and objective environment evaluation given to the street view image by the analytic hierarchy process.
9. A computer device comprising a processor and a memory for storing a program executable by the processor, wherein the processor, when executing the program stored in the memory, implements the method for measuring the spatial quality of a living street according to any one of claims 1 to 7.
10. A storage medium storing a program which, when executed by a processor, implements the method for measuring living street spatial quality according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211038230.8A CN115564174A (en) | 2022-08-29 | 2022-08-29 | Method, system, computer device and medium for measuring living street space quality |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211038230.8A CN115564174A (en) | 2022-08-29 | 2022-08-29 | Method, system, computer device and medium for measuring living street space quality |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115564174A true CN115564174A (en) | 2023-01-03 |
Family
ID=84739617
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211038230.8A Pending CN115564174A (en) | 2022-08-29 | 2022-08-29 | Method, system, computer device and medium for measuring living street space quality |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115564174A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116415499A (en) * | 2023-04-07 | 2023-07-11 | 广州市城市规划勘测设计研究院 | Community comfort simulation prediction method |
CN117875769A (en) * | 2023-12-29 | 2024-04-12 | 广州大学 | Analysis method and system for influence intensity of visual element on riding environment evaluation |
-
2022
- 2022-08-29 CN CN202211038230.8A patent/CN115564174A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116415499A (en) * | 2023-04-07 | 2023-07-11 | 广州市城市规划勘测设计研究院 | Community comfort simulation prediction method |
CN116415499B (en) * | 2023-04-07 | 2024-02-27 | 广州市城市规划勘测设计研究院 | Community comfort simulation prediction method |
CN117875769A (en) * | 2023-12-29 | 2024-04-12 | 广州大学 | Analysis method and system for influence intensity of visual element on riding environment evaluation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7351487B2 (en) | Intelligent navigation method and system based on topology map | |
CN115564174A (en) | Method, system, computer device and medium for measuring living street space quality | |
Klouček et al. | How does data accuracy influence the reliability of digital viewshed models? A case study with wind turbines | |
Zhao et al. | Mapping 3D visibility in an urban street environment from mobile LiDAR point clouds | |
EP4105600A2 (en) | Method for automatically producing map data, related apparatus and computer program product | |
CN107392252A (en) | Computer deep learning characteristics of image and the method for quantifying perceptibility | |
CN110659433B (en) | Method, device and equipment for POI value evaluation and computer storage medium | |
CN112668375B (en) | Tourist distribution analysis system and method in scenic spot | |
US20230024680A1 (en) | Method of determining regional land usage property, electronic device, and storage medium | |
Ye et al. | Urban commerce distribution analysis based on street view and deep learning | |
CN109949063A (en) | A kind of address determines method, apparatus, electronic equipment and readable storage medium storing program for executing | |
CN112883236B (en) | Map updating method and device, electronic equipment and storage medium | |
CN110060472A (en) | Road traffic accident localization method, system, readable storage medium storing program for executing and equipment | |
CN117932763A (en) | Expressway traffic model construction method based on digital twin | |
CN113420109A (en) | Method for measuring permeability of street interface, computer and storage medium | |
CN116415499B (en) | Community comfort simulation prediction method | |
CN117456342A (en) | Traffic accident risk assessment method and system based on street view image | |
CN115311867B (en) | Tunnel scene positioning method and device, computer equipment and storage medium | |
Huang et al. | Estimating urban noise along road network from street view imagery | |
CN115270904B (en) | Method and system for spatialization of proper-age permanent population in compulsory education stage | |
Feng et al. | [Retracted] Visual Evaluation of Urban Streetscape Design Supported by Multisource Data and Deep Learning | |
CN115511280A (en) | Urban flood toughness evaluation method based on multi-mode data fusion | |
CN110929618B (en) | Potential safety hazard detection and assessment method for power distribution network crossing type building | |
Wolters et al. | Classification of large-scale remote sensing images for automatic identification of health hazards: Smoke detection using an autologistic regression classifier | |
da Rocha¹ et al. | Studies of volumetric relation between vegetation and buildings using LIDAR data and NDVI to propose urban parameters |
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 |