CN115600267B - Computer vision analysis method and system for urban public space design - Google Patents
Computer vision analysis method and system for urban public space design Download PDFInfo
- Publication number
- CN115600267B CN115600267B CN202211597450.4A CN202211597450A CN115600267B CN 115600267 B CN115600267 B CN 115600267B CN 202211597450 A CN202211597450 A CN 202211597450A CN 115600267 B CN115600267 B CN 115600267B
- Authority
- CN
- China
- Prior art keywords
- space
- facility equipment
- acquiring
- preset
- facility
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to the field of space design, and discloses a computer vision analysis method and a computer vision analysis system for urban public space design.
Description
Technical Field
The invention relates to the field related to space design, in particular to a computer vision analysis method and a computer vision analysis system for urban public space design.
Background
The urban public space is an open space existing in an urban group, is mostly used for setting dependent landscapes and public convenience facilities such as parks, fitness equipment, outdoor water supply and washing facilities convenient for citizens to use and the like, and aims to better serve the public, improve the urban life quality and enhance the happiness of people.
For a large amount of public spaces, in the process of measurement design construction team, a large amount of human resources are required to be occupied, the design cost is increased, and most public facilities in the public spaces are more convenient for people and do not have more design levels, so that it is necessary to reduce the occupation of the human resources related to design to improve the facility level.
Disclosure of Invention
The present invention aims to provide a computer vision analysis method and system for urban public space design, so as to solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a computer vision analysis method for urban public space design comprises the following steps:
acquiring scanning information, namely scanning a spatial structure of a public space to be simulated through scanning acquisition equipment to acquire point cloud data and image data corresponding to the public space, wherein the point cloud data and a plurality of data points in the image data are in one-to-one correspondence in spatial distribution;
modeling and rendering the body, fitting a space body based on the point cloud data and a preset deep learning algorithm to generate a plurality of space bodies, establishing a three-dimensional space model of the public space based on the plurality of space bodies, retrieving a preset material library based on the corresponding image data, acquiring material types and color information corresponding to the space bodies, and performing material rendering and supplementing on the three-dimensional space model, wherein the three-dimensional space model comprises size information consistent with the public space;
the simulation establishment of a demand object, namely acquiring facility demands from a user side for the public space, retrieving a preset facility information base based on the facility demands, acquiring size information and state constraint conditions of a plurality of types of matched facility equipment, so as to simulate the spatial distribution of the plurality of types of facility equipment in the three-dimensional space model, and generating a plurality of groups of design schemes, wherein the state constraint conditions are used for limiting the matching constraint of the facility equipment and the three-dimensional space model;
the method comprises the steps of estimating the engineering cost, calculating the material requirements of facility equipment of different types based on the design scheme, obtaining material requirement statistical information, calculating the engineering cost based on the material requirement statistical information and a preset material supply form, and correspondingly outputting a plurality of groups of design schemes and corresponding engineering cost.
As a further scheme of the invention: each type of the facility equipment includes a plurality of kinds of size information including a non-limiting size that characterizes an arbitrary shape that the facility equipment can realize an arbitrary size by freely cutting and combining;
the state constraints include:
the attachment constraint of the facility equipment and the three-dimensional space model is used for representing the attachment relevance of the facility equipment and a wall body in a public space during assembly and the height of assembly space;
the assembly relevance between the facility equipment and the facility equipment is used for representing whether the facility equipment needs to be adjacently connected or overlapped during assembly and the spacing constraint during assembly.
As a still further scheme of the invention: the step of retrieving a preset material library based on the corresponding image data specifically includes:
acquiring feature points, acquiring a plurality of image feature points through the image data by using a preset random selection program, traversing the preset material library according to the image data of the feature points, and acquiring corresponding feature retrieval anchor points, wherein the feature retrieval anchor points are used for representing material type features with highest feature coincidence degree with the image data;
and defining a characteristic range, namely repeatedly selecting image characteristic points in multiple directions according to a radiation type rule based on the image characteristic points and a base point, judging the image characteristic points based on the characteristic retrieval anchor point, and further acquiring multiple characteristic ranges corresponding to the characteristics of different material types, wherein the different characteristic ranges are used for representing the space ranges corresponding to the different material types.
As a still further scheme of the invention: further comprising:
in the step of judging the image feature points based on the feature retrieval anchor point and further acquiring a plurality of feature ranges corresponding to different material type features, the feature ranges are defined through a minimum bisection method, when the image feature points deviate from the feature retrieval anchor point, the radiation reverse direction of the image feature points is taken as the next point taking direction, one half of the point taking distance of the image feature points is taken as the next point taking distance to select the next image feature points, if the point taking distance is smaller than a preset value, the definition of the feature ranges is stopped, and the middle point of the latest historical point taking path is taken as the boundary of the feature ranges.
As a still further scheme of the invention: further comprising the steps of:
acquiring a space deleting instruction from a user side and responding, deleting a corresponding space body part in the three-dimensional space model based on the space deleting instruction, and recording the material type and the space volume of the deleted space body;
and performing the calculation of the construction cost of the public space structure demolition part based on the removed material type and space volume of the space shape and a preset artificial charging standard.
As a further scheme of the invention: the step of calculating the material requirements of the different categories of the facility equipment comprises, for the non-limiting size of the facility equipment, the steps of:
acquiring non-limited free sizes of a plurality of corresponding plane component members, arranging the plane component members within the limit of basic size information based on the basic size information of a preset basic piece of cutting raw materials, generating material demand statistical information of the facility equipment, and outputting a cutting drawing based on the arrangement result.
The embodiment of the invention aims to provide a computer vision analysis system for urban public space design, which comprises:
the system comprises an information acquisition module, a data acquisition module and a simulation module, wherein the information acquisition module is used for acquiring scanning information and scanning a spatial structure of a public space to be simulated through scanning acquisition equipment so as to acquire point cloud data and image data corresponding to the public space, and the point cloud data and a plurality of data points in the image data are in one-to-one correspondence in spatial distribution;
the space reconstruction module is used for modeling and rendering the body, fitting the space body based on the point cloud data and a preset deep learning algorithm to generate a plurality of space bodies, establishing a three-dimensional space model of the public space based on the space bodies, retrieving a preset material library based on the corresponding image data, acquiring the material type and color information corresponding to the space bodies, and performing material rendering and supplementing on the three-dimensional space model, wherein the three-dimensional space model comprises size information consistent with the public space;
the scheme simulation module is used for simulating and establishing a demand object, acquiring facility demands from a user side to the public space, retrieving a preset facility information base based on the facility demands, acquiring size information and state constraint conditions of facility equipment with multiple matched categories, simulating spatial distribution of the facility equipment with multiple categories in the three-dimensional space model so as to generate multiple groups of design schemes, and limiting the matching constraint of the facility equipment and the three-dimensional space model by the state constraint conditions;
the construction cost estimation module is used for estimating construction cost, calculating the material requirements of the facility equipment of different types based on the design scheme, acquiring material requirement statistical information, calculating the construction cost based on the material requirement statistical information and a preset material supply form, and correspondingly outputting a plurality of groups of the design scheme and the corresponding construction cost.
As a further scheme of the invention: each type of the facility equipment includes a plurality of kinds of size information including a non-limiting size that characterizes an arbitrary shape that the facility equipment can realize an arbitrary size by freely cutting and combining;
the state constraints include:
the attachment constraint of the facility equipment and the three-dimensional space model is used for representing the attachment relevance of the facility equipment and a wall body in a public space during assembly and the height of an assembly interval;
the assembly relevance between the facility equipment and the facility equipment is used for representing whether the facility equipment needs to be adjacently connected or overlapped during assembly and the spacing constraint during assembly.
As a further scheme of the invention: the spatial reconstruction module includes a pre-rendering unit for performing the retrieval of the preset material library based on the corresponding image data, and the pre-rendering unit specifically includes:
the characteristic selection subunit is used for acquiring characteristic points, acquiring a plurality of image characteristic points through the image data by using a preset random selection program, traversing the preset material library according to the image data of the characteristic points, and acquiring corresponding characteristic retrieval anchor points, wherein the characteristic retrieval anchor points are used for representing the material type characteristics with the highest feature coincidence degree with the image data;
and the range defining subunit is used for defining a characteristic range, repeatedly selecting image characteristic points in multiple directions according to a radiation pattern rule based on the image characteristic points and the base points, judging the image characteristic points based on the characteristic retrieval anchor points, and further acquiring multiple characteristic ranges corresponding to different material type characteristics, wherein the different characteristic ranges are used for representing space ranges corresponding to different material types.
Compared with the prior art, the invention has the beneficial effects that: through the three-dimensional reconstruction technology based on point cloud data and the rendering mode based on image information content, the public space is subjected to equal-size virtualization, the facility requirements of the public space can be responded through preset size conditions and installation configuration requirements of related facility equipment, the installation distribution design of the facility equipment in the public space is simulated, generation of multiple design schemes is achieved, and learning of material requirements and engineering cost is carried out on different schemes.
Drawings
FIG. 1 is a block flow diagram of a computer vision analysis method for urban public space design.
Fig. 2 is a partial flow diagram of the rendering steps of forms in a computer vision analysis method for urban public space design.
FIG. 3 is a block diagram of a computer vision analysis system for urban public space design.
FIG. 4 is a block diagram of the components of a pre-rendering unit in a computer vision analysis system for urban public space design.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of specific embodiments of the present invention is provided in connection with specific embodiments.
As shown in fig. 1, a computer vision analysis method for urban public space design is provided for one embodiment of the present invention, and includes the following steps:
s10, acquiring scanning information, namely scanning a spatial structure of a public space to be simulated through scanning acquisition equipment to acquire point cloud data and image data corresponding to the public space, wherein the point cloud data and a plurality of data points in the image data are in one-to-one correspondence in spatial distribution.
S20, modeling and rendering the body, fitting the space body based on the point cloud data and a preset deep learning algorithm to generate a plurality of space bodies, establishing a three-dimensional space model of the public space based on the plurality of space bodies, retrieving a preset material library based on the corresponding image data, acquiring material types and color information corresponding to the space bodies, and performing material rendering and supplementing on the three-dimensional space model, wherein the three-dimensional space model comprises size information consistent with the public space.
S30, simulation establishment of a demand object, namely acquiring facility demands from a user side to the public space, retrieving a preset facility information base based on the facility demands, acquiring size information and state constraint conditions of facility equipment of multiple categories, so as to simulate spatial distribution of the facility equipment of multiple categories in the three-dimensional space model, and generating multiple groups of design schemes, wherein the state constraint conditions are used for limiting matching constraints of the facility equipment and the three-dimensional space model.
S40, estimating the construction cost, calculating the material requirements of the facility equipment of different types based on the design scheme, acquiring material requirement statistical information, calculating the construction cost based on the material requirement statistical information and a preset material supply form, and correspondingly outputting a plurality of groups of design schemes and corresponding construction costs.
In the embodiment, a computer vision analysis method for urban public space design is provided, the public space is virtualized in an equal size through a three-dimensional reconstruction technology based on point cloud data and a rendering mode based on image information content, and further the installation distribution design of facility equipment in the public space is simulated through the preset size conditions and installation configuration requirements of related facility equipment, so that generation of multiple design schemes is realized, and the material requirements and the engineering cost of different schemes are known; specifically, the scanning information segment obtaining step includes image acquisition related equipment and three-dimensional scanning equipment for scanning spatial point clouds, and meanwhile, based on the development of the current technology, obtaining point cloud data based on a plurality of groups of image data and establishing a three-dimensional model of a space can be directly realized through related software technologies (the prior art has a great deal of use, including reverse engineering, and electronic storage of historical cultural relics and buildings); after a three-dimensional space model with the same size of a public space is obtained, facility requirements (such as arrangement of a mirror face, a wash basin, a wash platform and an air dryer) of related managers for the public space are obtained, the system simulates distribution of the facility requirements in the three-dimensional space model according to preset sizes of the facility devices (based on matching constraints; for example, the wash basin is nested in the wash platform, so that the wash platform must be capable of accommodating the wash basin in size, the wash basin is in various sizes, the wash platform is in indefinite and randomly variable sizes, the devices are arranged along a wall, and the like), and then various design schemes are generated, and the requirements of materials and engineering construction cost are calculated based on the sizes of the various design schemes, and the like for reference use of related personnel.
As another preferred embodiment of the present invention, each kind of the facility equipment includes a plurality of kinds of size information including a non-limiting size which characterizes an arbitrary shape that the facility equipment can realize an arbitrary size by freely cutting and combining.
The state constraints include:
the attachment constraint of the facility equipment and the three-dimensional space model is used for representing the attachment relevance of the facility equipment and a wall body in a public space during assembly and the height of assembly space;
the assembly relevance between the facility equipment and the facility equipment is used for representing whether the facility equipment needs to be adjacently connected or overlapped during assembly and the spacing constraint during assembly.
In this embodiment, the facility equipment is further described supplementarily to achieve the definition of conditions, wherein the dimension information, for example, the wash basin may include different sizes and models, and for the non-limited dimension, the wash basin in the previous embodiment is described herein, and for different conditions, the specific dimensions of the wash basin may be set according to the requirements and the actual space environment of the public space, so that the length, width, height, and even the shape of the plane may be set freely according to non-standards, which is the content indicated by the non-limited dimension herein, and of course, when the wash basin is set, the wash basin also includes the constraint conditions, such as the requirement that the wash basin fits the wall on one side, and the requirement that the distance from the wall on the other side meets the minimum width standard, the reserved distance from the edge of the wash basin, and the like.
As shown in fig. 2, as another preferred embodiment of the present invention, the step of retrieving the preset material library based on the corresponding image data specifically includes:
s221, acquiring feature points, namely acquiring a plurality of image feature points through the image data by using a preset random selection program, traversing the preset material library according to the image data of the feature points, and acquiring corresponding feature retrieval anchor points, wherein the feature retrieval anchor points are used for representing material type features with the highest feature coincidence degree with the image data.
S222, defining a characteristic range, repeatedly selecting image characteristic points in multiple directions according to a radiation type rule based on the image characteristic points and a base point, judging the image characteristic points based on the characteristic retrieval anchor point, and further obtaining multiple characteristic ranges corresponding to different material type characteristics, wherein the different characteristic ranges are used for representing space ranges corresponding to different material types.
Further, in the step of determining the image feature points based on the feature search anchor point and further obtaining a plurality of feature ranges corresponding to different material type features, the feature ranges are defined by a minimum bisection method, when the image feature points deviate from the feature search anchor point, the radiation reverse direction of the image feature points is taken as a next point taking direction, one half of the point taking distance of the image feature points is taken as a next point taking distance, the next image feature point is selected, if the point taking distance is smaller than a preset value, the definition of the feature ranges is stopped, and the midpoint of a last historical point taking path is taken as the boundary of the feature ranges.
In this embodiment, a further description is given here, specifically, an epoch defining method and basis for defining a range of a spatial form based on image data are performed, where a coverage area of a material of the same type is determined by a radiation type expansion manner after a feature point is selected as a determination basis point, where a boundary refining manner adopted at a final intersection of adjacent materials is a bisection method, and a boundary range is narrowed by dividing twice.
As another preferred embodiment of the present invention, further comprising the steps of:
and acquiring a space deleting instruction from a user side and responding, deleting a corresponding space body part in the three-dimensional space model based on the space deleting instruction, and recording the material type and the space volume of the deleted space body.
And performing the calculation of the construction cost of the public space structure demolition part based on the removed material type and space volume of the space shape and a preset artificial charging standard.
In this embodiment, after the three-dimensional model of the public space is built, it may be necessary to remove a part of structures (for example, redundant walls or tables) in the space before the subsequent design is performed, so that after the selection of the user is obtained, the three-dimensional model is correspondingly removed, the gap after removal is supplemented, and meanwhile, the cost required for removing the relevant structures is calculated.
As another preferred embodiment of the present invention, the step of calculating the material requirements of the facility equipments of different types, particularly, for the facility equipments of the non-limited size, comprises the steps of:
acquiring non-limited free sizes of a plurality of corresponding plane component members, arranging the plane component members within the limit of basic size information based on the basic size information of a preset basic piece of cutting raw materials, generating material demand statistical information of the facility equipment, and outputting a cutting drawing based on the arrangement result.
In this embodiment, the free-size facilities are often required to be cut with standard-sized materials (e.g., the aforementioned wash basin, tiles attached to the surface thereof, etc.), so the sizes of the generated design solutions cannot be directly used for calculating the material cost, and the design solutions are required to be restored based on standard-sized standard parts, and corresponding cutting solutions are generated.
As shown in fig. 3, the present invention also provides a computer vision analysis system for urban public space design, comprising:
the information acquisition module 100 is configured to acquire scanning information, and perform spatial structure scanning on a public space to be simulated through a scanning acquisition device to acquire point cloud data and image data corresponding to the public space, where the point cloud data and a plurality of data points in the image data are in one-to-one correspondence in spatial distribution.
The space reconstruction module 200 is configured to model and render a shape, perform fitting of a space shape based on the point cloud data and a preset deep learning algorithm to generate a plurality of space shapes, establish a three-dimensional space model of the public space based on the plurality of space shapes, retrieve a preset material library based on the corresponding image data, acquire material types and color information corresponding to the space shapes, and perform material rendering and supplementation on the three-dimensional space model, where the three-dimensional space model includes size information consistent with the public space.
The plan simulation module 300 is configured to create a simulation of a demand object, acquire a facility demand for the public space from a user side, retrieve a preset facility information base based on the facility demand, acquire size information and state constraint conditions of multiple categories of matched facility devices, so as to perform a simulation of spatial distribution of the multiple categories of facility devices in the three-dimensional space model, and generate multiple sets of design plans, where the state constraint conditions are used to limit matching constraints of the facility devices and the three-dimensional space model.
The construction cost estimation module 400 is used for estimating construction cost, calculating the material requirements of the facility equipment of different types based on the design scheme, acquiring material requirement statistical information, calculating the construction cost based on the material requirement statistical information and a preset material supply form, and correspondingly outputting a plurality of groups of design schemes and corresponding construction cost.
As another preferred embodiment of the present invention, each kind of the facility equipment includes a plurality of kinds of size information including a non-limiting size which characterizes an arbitrary shape that the facility equipment can realize an arbitrary size by freely cutting and combining.
The state constraints include:
the attachment constraint of the facility equipment and the three-dimensional space model is used for representing the attachment relevance of the facility equipment and a wall body in a public space during assembly and the height of assembly space;
the assembly relevance between the facility equipment and the facility equipment is used for representing whether the facility equipment needs to be adjacently connected or overlapped during assembly and the spacing constraint during assembly.
As shown in fig. 4, as another preferred embodiment of the present invention, the spatial reconstruction module 200 includes a pre-rendering unit 220 for performing the retrieving of the preset material library based on the corresponding image data, where the pre-rendering unit 220 specifically includes:
and the feature selection subunit 221 is configured to obtain feature points, obtain a plurality of image feature points through the image data by using a preset random selection program, traverse the preset material library according to the image data of the feature points, and obtain corresponding feature retrieval anchors, where the feature retrieval anchors are used to represent material type features with the highest feature overlap ratio with the image data.
The range defining subunit 222 is configured to define a feature range, repeatedly select image feature points in multiple directions according to a radiation pattern rule based on the multiple image feature points and a base point, and determine the image feature points based on the feature search anchor point, thereby obtaining multiple feature ranges corresponding to features of different material types, where different feature ranges are used to represent spatial ranges corresponding to different material types.
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 can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (7)
1. A computer vision analysis method for urban public space design is characterized by comprising the following steps:
acquiring scanning information, namely scanning a spatial structure of a public space to be simulated through scanning acquisition equipment to acquire point cloud data and image data corresponding to the public space, wherein the point cloud data and a plurality of data points in the image data are in one-to-one correspondence in spatial distribution;
modeling and rendering the body, fitting a space body based on the point cloud data and a preset deep learning algorithm to generate a plurality of space bodies, establishing a three-dimensional space model of the public space based on the plurality of space bodies, retrieving a preset material library based on the corresponding image data, acquiring material types and color information corresponding to the space bodies, and performing material rendering and supplementing on the three-dimensional space model, wherein the three-dimensional space model comprises size information consistent with the public space;
the simulation establishment of a demand object, namely acquiring facility demands from a user side for the public space, retrieving a preset facility information base based on the facility demands, acquiring size information and state constraint conditions of multiple types of matched facility equipment, and simulating the spatial distribution of the multiple types of facility equipment in the three-dimensional space model to generate multiple sets of design schemes, wherein the state constraint conditions are used for limiting the matching constraint of the facility equipment and the three-dimensional space;
estimating the engineering cost, calculating the material requirements of the facility equipment of different types based on the design scheme to obtain material requirement statistical information, calculating the engineering cost based on the material requirement statistical information and a preset material supply table, and correspondingly outputting a plurality of groups of the design scheme and the corresponding engineering cost;
each type of the facility equipment includes a plurality of kinds of size information including a non-limited size that characterizes an arbitrary shape that the facility equipment can realize an arbitrary size by freely cutting and combining;
the state constraints include:
the attachment constraint of the facility equipment and the three-dimensional space model is used for representing the attachment relevance of the facility equipment and a wall body in a public space during assembly and the height of assembly space;
the assembly relevance between the facility equipment and the facility equipment is used for representing whether the facility equipment needs to be adjacently connected or overlapped during assembly and the spacing constraint during assembly.
2. The computer vision analysis method for urban public space design according to claim 1, wherein the step of retrieving the preset material library based on the corresponding image data specifically comprises:
acquiring feature points, acquiring a plurality of image feature points through the image data by using a preset random selection program, traversing the preset material library according to the image data of the feature points, and acquiring corresponding feature retrieval anchor points, wherein the feature retrieval anchor points are used for representing material type features with highest feature coincidence degree with the image data;
and defining a characteristic range, namely repeatedly selecting image characteristic points in multiple directions according to a radiation type rule based on the image characteristic points and a base point, judging the image characteristic points based on the characteristic retrieval anchor point, and further acquiring a plurality of characteristic ranges corresponding to different material type characteristics, wherein different characteristic ranges are used for representing space ranges corresponding to different material types.
3. The computer vision analysis method for urban public space design according to claim 2, further comprising:
in the step of judging the image feature points based on the feature retrieval anchor point and further acquiring a plurality of feature ranges corresponding to different material type features, the feature ranges are defined through a minimum bisection method, when the image feature points deviate from the feature retrieval anchor point, the radiation reverse direction of the image feature points is taken as the next point taking direction, one half of the point taking distance of the image feature points is taken as the next point taking distance to select the next image feature points, if the point taking distance is smaller than a preset value, the definition of the feature ranges is stopped, and the middle point of the latest historical point taking path is taken as the boundary of the feature ranges.
4. The computer vision analysis method for urban public space design according to claim 1, further comprising the steps of:
acquiring a space deleting instruction from a user side and responding, deleting a corresponding space body part in the three-dimensional space model based on the space deleting instruction, and recording the material type and the space volume of the deleted space body;
and performing the calculation of the construction cost of the public space structure demolition part based on the removed material type and space volume of the space shape and a preset artificial charging standard.
5. The computer vision analysis method for urban public space design according to claim 1, wherein the step of calculating the material requirements of different categories of the facility equipment comprises the steps of, for the facility equipment of the unlimited size:
acquiring non-limited free sizes of a plurality of corresponding plane component members, arranging the plane component members within the limit of basic size information based on the basic size information of a preset basic piece of cutting raw materials, generating material demand statistical information of the facility equipment, and outputting a cutting drawing based on the arrangement result.
6. A computer vision analysis system for urban public space design, comprising:
the system comprises an information acquisition module, a simulation module and a simulation module, wherein the information acquisition module is used for acquiring scanning information, and scanning a spatial structure of a public space to be simulated through scanning acquisition equipment to acquire point cloud data and image data corresponding to the public space, and the point cloud data and a plurality of data points in the image data are in one-to-one correspondence in spatial distribution;
the space reconstruction module is used for modeling and rendering the body, fitting the space body based on the point cloud data and a preset deep learning algorithm to generate a plurality of space bodies, establishing a three-dimensional space model of the public space based on the space bodies, retrieving a preset material library based on the corresponding image data, acquiring the material type and color information corresponding to the space bodies, and performing material rendering and supplementing on the three-dimensional space model, wherein the three-dimensional space model comprises size information consistent with the public space;
the scheme simulation module is used for simulating and establishing a demand object, acquiring facility demands from a user side to the public space, retrieving a preset facility information base based on the facility demands, acquiring size information and state constraint conditions of facility equipment with multiple matched categories, simulating spatial distribution of the facility equipment with multiple categories in the three-dimensional space model so as to generate multiple groups of design schemes, and limiting the matching constraint of the facility equipment and the three-dimensional space by the state constraint conditions;
the construction cost estimation module is used for estimating construction cost, calculating the material requirements of the facility equipment of different types based on the design scheme to obtain material requirement statistical information, calculating the construction cost based on the material requirement statistical information and a preset material supply form, and correspondingly outputting a plurality of groups of design schemes and the corresponding construction cost;
each type of the facility equipment includes a plurality of kinds of size information including a non-limiting size that characterizes an arbitrary shape that the facility equipment can realize an arbitrary size by freely cutting and combining;
the state constraints include:
the attachment constraint of the facility equipment and the three-dimensional space model is used for representing the attachment relevance of the facility equipment and a wall body in a public space during assembly and the height of assembly space;
the assembly relevance between the facility equipment and the facility equipment is used for representing whether the facility equipment needs to be adjacently connected or overlapped during assembly and the spacing constraint during assembly.
7. The computer vision analysis system for urban public space design according to claim 6, wherein the spatial reconstruction module comprises a prerender unit for performing the retrieval of the preset material library based on the corresponding image data, the prerender unit comprising:
the characteristic selection subunit is used for acquiring characteristic points, acquiring a plurality of image characteristic points through the image data by using a preset random selection program, traversing the preset material library according to the image data of the characteristic points, and acquiring corresponding characteristic retrieval anchor points, wherein the characteristic retrieval anchor points are used for representing material type characteristics with the highest feature coincidence degree with the image data;
and the range defining subunit is used for defining a characteristic range, repeatedly selecting image characteristic points in multiple directions according to a radiation type rule based on the image characteristic points and a base point, judging the image characteristic points based on the characteristic retrieval anchor point, and further acquiring multiple characteristic ranges corresponding to different material type characteristics, wherein the different characteristic ranges are used for representing space ranges corresponding to different material types.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211597450.4A CN115600267B (en) | 2022-12-14 | 2022-12-14 | Computer vision analysis method and system for urban public space design |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211597450.4A CN115600267B (en) | 2022-12-14 | 2022-12-14 | Computer vision analysis method and system for urban public space design |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115600267A CN115600267A (en) | 2023-01-13 |
| CN115600267B true CN115600267B (en) | 2023-04-18 |
Family
ID=84854126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211597450.4A Active CN115600267B (en) | 2022-12-14 | 2022-12-14 | Computer vision analysis method and system for urban public space design |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600267B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115359223A (en) * | 2022-08-24 | 2022-11-18 | 武汉柏汇达科技有限公司 | Real-scene three-dimensional city development display system and method |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3365874B1 (en) * | 2016-06-10 | 2022-03-16 | DIRTT Environmental Solutions, Ltd. | Mixed-reality and cad architectural design environment |
| WO2019196186A1 (en) * | 2018-04-12 | 2019-10-17 | 东南大学 | System for constructing urban design digital sandbox |
| EP3863743A4 (en) * | 2018-10-09 | 2021-12-08 | Resonai Inc. | Systems and methods for 3d scene augmentation and reconstruction |
| CN109410327B (en) * | 2018-10-09 | 2022-05-17 | 广东博智林机器人有限公司 | BIM and GIS-based three-dimensional city modeling method |
| DE102019202304B4 (en) * | 2019-02-20 | 2021-01-28 | Siemens Schweiz Ag | Method and arrangement for creating a digital building model |
| CN112507409A (en) * | 2021-02-02 | 2021-03-16 | 巧夺天宫（深圳）科技有限公司 | System and method for generating engineering quantity list by building component |
| CN112907751B (en) * | 2021-03-23 | 2023-11-24 | 中德（珠海）人工智能研究院有限公司 | Virtual decoration method, system, equipment and medium based on mixed reality |
| CN113593003A (en) * | 2021-06-10 | 2021-11-02 | 瑞祥集团(河北)科技材料有限公司 | Method and system for automatically generating decoration quotation in space design |
| CN115062366A (en) * | 2022-03-28 | 2022-09-16 | 中国地质大学（武汉） | Digital twinning design method and system for garden landscape, storage medium and terminal |
-
2022
- 2022-12-14 CN CN202211597450.4A patent/CN115600267B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115359223A (en) * | 2022-08-24 | 2022-11-18 | 武汉柏汇达科技有限公司 | Real-scene three-dimensional city development display system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115600267A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107481311B (en) | Three-dimensional city model rendering method and device | |
| CN111383303A (en) | Method and device for automatically generating plane of residential building | |
| EP0313586A4 (en) | A method for global blending of computer modeled solid objects using a convolution integral | |
| JP2023525792A (en) | Computer-aided generative design with global thickness control to facilitate manufacturing and structural performance | |
| CN111161394B (en) | Method and device for placing three-dimensional building model | |
| Fedotov et al. | Trace transform of three-dimensional objects: Recognition, analysis, and database search | |
| CN112733240A (en) | Construction progress evaluating method and device, computer equipment and storage medium | |
| CN115063557A (en) | Building intelligent extraction method and device based on tilt model | |
| CN115600267B (en) | Computer vision analysis method and system for urban public space design | |
| CN112324095A (en) | Method and system for intelligently assembling building space | |
| CN117056722A (en) | Prediction method and system for population quantity of planned land parcel | |
| CN113989680B (en) | Automatic building three-dimensional scene construction method and system | |
| Burry et al. | BIM-PIM-CIM: the challenges of modelling urban design behaviours between building and city scales | |
| CN115311396A (en) | Automatic extraction method and system for roof contour line of ultrahigh building | |
| CN110489510B (en) | Road data processing method and device, readable storage medium and computer equipment | |
| Honda et al. | Generating autonomous time-varying virtual cities | |
| CN109977600B (en) | Standardized urban three-dimensional space form compactness measuring method and system | |
| CN111311745B (en) | Model placement method and device | |
| Osipov et al. | Algorithms of automation of 3D modeling of urban environment objects using attributive information from a digital map | |
| JP3739209B2 (en) | Automatic polygon generation system from point cloud | |
| CN118051845B (en) | Geospatial full coverage data generation method and device based on space variable parameter machine learning | |
| CN117541740B (en) | River and lake region three-dimensional modeling method and system based on unmanned aerial vehicle data acquisition | |
| Ayazli | Using the Total exploratory factor analysis (T-EFA) as a calibration technique for SLEUTH model | |
| CN117876622B (en) | City map generation method and device, electronic equipment and readable medium | |
| Chao et al. | A framework for agent-based simulation in tourism planning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |